| 1443 1439 1447 1442 1443 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/kernel/return_address.c * * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> */ #include <linux/export.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/stacktrace.h> #include <asm/stack_pointer.h> struct return_address_data { unsigned int level; void *addr; }; static bool save_return_addr(void *d, unsigned long pc) { struct return_address_data *data = d; if (!data->level) { data->addr = (void *)pc; return false; } else { --data->level; return true; } } NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { struct return_address_data data; data.level = level + 2; data.addr = NULL; arch_stack_walk(save_return_addr, &data, current, NULL); if (!data.level) return data.addr; else return NULL; } EXPORT_SYMBOL_GPL(return_address); NOKPROBE_SYMBOL(return_address); |
| 1162 1157 1159 1156 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BH_H #define _LINUX_BH_H #include <linux/instruction_pointer.h> #include <linux/preempt.h> #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); #else static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) { preempt_count_add(cnt); barrier(); } #endif static inline void local_bh_disable(void) { __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } extern void _local_bh_enable(void); extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt); static inline void local_bh_enable_ip(unsigned long ip) { __local_bh_enable_ip(ip, SOFTIRQ_DISABLE_OFFSET); } static inline void local_bh_enable(void) { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } #ifdef CONFIG_PREEMPT_RT extern bool local_bh_blocked(void); #else static inline bool local_bh_blocked(void) { return false; } #endif #endif /* _LINUX_BH_H */ |
| 5 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 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 | // SPDX-License-Identifier: GPL-2.0 /* Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #include <linux/nexthop.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/lwtunnel.h> #include <net/ndisc.h> #include <net/nexthop.h> #include <net/route.h> #include <net/sock.h> #define NH_RES_DEFAULT_IDLE_TIMER (120 * HZ) #define NH_RES_DEFAULT_UNBALANCED_TIMER 0 /* No forced rebalancing. */ static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo); #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) #define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ NHA_OP_FLAG_DUMP_HW_STATS) static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, [NHA_GROUP_TYPE] = { .type = NLA_U16 }, [NHA_BLACKHOLE] = { .type = NLA_FLAG }, [NHA_OIF] = { .type = NLA_U32 }, [NHA_GATEWAY] = { .type = NLA_BINARY }, [NHA_ENCAP_TYPE] = { .type = NLA_U16 }, [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_policy_del[] = { [NHA_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_OIF] = { .type = NLA_U32 }, [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { [NHA_RES_GROUP_BUCKETS] = { .type = NLA_U16 }, [NHA_RES_GROUP_IDLE_TIMER] = { .type = NLA_U32 }, [NHA_RES_GROUP_UNBALANCED_TIMER] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump_bucket[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_OIF] = { .type = NLA_U32 }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_RES_BUCKET] = { .type = NLA_NESTED }, }; static const struct nla_policy rtm_nh_res_bucket_policy_dump[] = { [NHA_RES_BUCKET_NH_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_get_bucket[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_RES_BUCKET] = { .type = NLA_NESTED }, }; static const struct nla_policy rtm_nh_res_bucket_policy_get[] = { [NHA_RES_BUCKET_INDEX] = { .type = NLA_U16 }, }; static bool nexthop_notifiers_is_empty(struct net *net) { return !net->nexthop.notifier_chain.head; } static void __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, const struct nh_info *nhi) { nh_info->dev = nhi->fib_nhc.nhc_dev; nh_info->gw_family = nhi->fib_nhc.nhc_gw_family; if (nh_info->gw_family == AF_INET) nh_info->ipv4 = nhi->fib_nhc.nhc_gw.ipv4; else if (nh_info->gw_family == AF_INET6) nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6; nh_info->id = nhi->nh_parent->id; nh_info->is_reject = nhi->reject_nh; nh_info->is_fdb = nhi->fdb_nh; nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate; } static int nh_notifier_single_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_info *nhi = rtnl_dereference(nh->nh_info); info->type = NH_NOTIFIER_INFO_TYPE_SINGLE; info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL); if (!info->nh) return -ENOMEM; __nh_notifier_single_info_init(info->nh, nhi); return 0; } static void nh_notifier_single_info_fini(struct nh_notifier_info *info) { kfree(info->nh); } static int nh_notifier_mpath_info_init(struct nh_notifier_info *info, struct nh_group *nhg) { u16 num_nh = nhg->num_nh; int i; info->type = NH_NOTIFIER_INFO_TYPE_GRP; info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh), GFP_KERNEL); if (!info->nh_grp) return -ENOMEM; info->nh_grp->num_nh = num_nh; info->nh_grp->is_fdb = nhg->fdb_nh; info->nh_grp->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; nhi = rtnl_dereference(nhge->nh->nh_info); info->nh_grp->nh_entries[i].weight = nhge->weight; __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, nhi); } return 0; } static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, struct nh_group *nhg) { struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); u16 num_nh_buckets = res_table->num_nh_buckets; unsigned long size; u16 i; info->type = NH_NOTIFIER_INFO_TYPE_RES_TABLE; size = struct_size(info->nh_res_table, nhs, num_nh_buckets); info->nh_res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); if (!info->nh_res_table) return -ENOMEM; info->nh_res_table->num_nh_buckets = num_nh_buckets; info->nh_res_table->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; struct nh_info *nhi; nhge = rtnl_dereference(bucket->nh_entry); nhi = rtnl_dereference(nhge->nh->nh_info); __nh_notifier_single_info_init(&info->nh_res_table->nhs[i], nhi); } return 0; } static int nh_notifier_grp_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); if (nhg->hash_threshold) return nh_notifier_mpath_info_init(info, nhg); else if (nhg->resilient) return nh_notifier_res_table_info_init(info, nhg); return -EINVAL; } static void nh_notifier_grp_info_fini(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); if (nhg->hash_threshold) kfree(info->nh_grp); else if (nhg->resilient) vfree(info->nh_res_table); } static int nh_notifier_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { info->id = nh->id; if (nh->is_group) return nh_notifier_grp_info_init(info, nh); else return nh_notifier_single_info_init(info, nh); } static void nh_notifier_info_fini(struct nh_notifier_info *info, const struct nexthop *nh) { if (nh->is_group) nh_notifier_grp_info_fini(info, nh); else nh_notifier_single_info_fini(info); } static int call_nexthop_notifiers(struct net *net, enum nexthop_event_type event_type, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, }; int err; ASSERT_RTNL(); if (nexthop_notifiers_is_empty(net)) return 0; err = nh_notifier_info_init(&info, nh); if (err) { NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); return err; } err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, event_type, &info); nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } static int nh_notifier_res_bucket_idle_timer_get(const struct nh_notifier_info *info, bool force, unsigned int *p_idle_timer_ms) { struct nh_res_table *res_table; struct nh_group *nhg; struct nexthop *nh; int err = 0; /* When 'force' is false, nexthop bucket replacement is performed * because the bucket was deemed to be idle. In this case, capable * listeners can choose to perform an atomic replacement: The bucket is * only replaced if it is inactive. However, if the idle timer interval * is smaller than the interval in which a listener is querying * buckets' activity from the device, then atomic replacement should * not be tried. Pass the idle timer value to listeners, so that they * could determine which type of replacement to perform. */ if (force) { *p_idle_timer_ms = 0; return 0; } rcu_read_lock(); nh = nexthop_find_by_id(info->net, info->id); if (!nh) { err = -EINVAL; goto out; } nhg = rcu_dereference(nh->nh_grp); res_table = rcu_dereference(nhg->res_table); *p_idle_timer_ms = jiffies_to_msecs(res_table->idle_timer); out: rcu_read_unlock(); return err; } static int nh_notifier_res_bucket_info_init(struct nh_notifier_info *info, u16 bucket_index, bool force, struct nh_info *oldi, struct nh_info *newi) { unsigned int idle_timer_ms; int err; err = nh_notifier_res_bucket_idle_timer_get(info, force, &idle_timer_ms); if (err) return err; info->type = NH_NOTIFIER_INFO_TYPE_RES_BUCKET; info->nh_res_bucket = kzalloc(sizeof(*info->nh_res_bucket), GFP_KERNEL); if (!info->nh_res_bucket) return -ENOMEM; info->nh_res_bucket->bucket_index = bucket_index; info->nh_res_bucket->idle_timer_ms = idle_timer_ms; info->nh_res_bucket->force = force; __nh_notifier_single_info_init(&info->nh_res_bucket->old_nh, oldi); __nh_notifier_single_info_init(&info->nh_res_bucket->new_nh, newi); return 0; } static void nh_notifier_res_bucket_info_fini(struct nh_notifier_info *info) { kfree(info->nh_res_bucket); } static int __call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, u16 bucket_index, bool force, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, .id = nhg_id, }; int err; if (nexthop_notifiers_is_empty(net)) return 0; err = nh_notifier_res_bucket_info_init(&info, bucket_index, force, oldi, newi); if (err) return err; err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_BUCKET_REPLACE, &info); nh_notifier_res_bucket_info_fini(&info); return notifier_to_errno(err); } /* There are three users of RES_TABLE, and NHs etc. referenced from there: * * 1) a collection of callbacks for NH maintenance. This operates under * RTNL, * 2) the delayed work that gradually balances the resilient table, * 3) and nexthop_select_path(), operating under RCU. * * Both the delayed work and the RTNL block are writers, and need to * maintain mutual exclusion. Since there are only two and well-known * writers for each table, the RTNL code can make sure it has exclusive * access thus: * * - Have the DW operate without locking; * - synchronously cancel the DW; * - do the writing; * - if the write was not actually a delete, call upkeep, which schedules * DW again if necessary. * * The functions that are always called from the RTNL context use * rtnl_dereference(). The functions that can also be called from the DW do * a raw dereference and rely on the above mutual exclusion scheme. */ #define nh_res_dereference(p) (rcu_dereference_raw(p)) static int call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, u16 bucket_index, bool force, struct nexthop *old_nh, struct nexthop *new_nh, struct netlink_ext_ack *extack) { struct nh_info *oldi = nh_res_dereference(old_nh->nh_info); struct nh_info *newi = nh_res_dereference(new_nh->nh_info); return __call_nexthop_res_bucket_notifiers(net, nhg_id, bucket_index, force, oldi, newi, extack); } static int call_nexthop_res_table_notifiers(struct net *net, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, .id = nh->id, }; struct nh_group *nhg; int err; ASSERT_RTNL(); if (nexthop_notifiers_is_empty(net)) return 0; /* At this point, the nexthop buckets are still not populated. Only * emit a notification with the logical nexthops, so that a listener * could potentially veto it in case of unsupported configuration. */ nhg = rtnl_dereference(nh->nh_grp); err = nh_notifier_mpath_info_init(&info, nhg); if (err) { NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); return err; } err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, &info); kfree(info.nh_grp); return notifier_to_errno(err); } static int call_nexthop_notifier(struct notifier_block *nb, struct net *net, enum nexthop_event_type event_type, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, }; int err; err = nh_notifier_info_init(&info, nh); if (err) return err; err = nb->notifier_call(nb, event_type, &info); nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } static unsigned int nh_dev_hashfn(unsigned int val) { unsigned int mask = NH_DEV_HASHSIZE - 1; return (val ^ (val >> NH_DEV_HASHBITS) ^ (val >> (NH_DEV_HASHBITS * 2))) & mask; } static void nexthop_devhash_add(struct net *net, struct nh_info *nhi) { struct net_device *dev = nhi->fib_nhc.nhc_dev; struct hlist_head *head; unsigned int hash; WARN_ON(!dev); hash = nh_dev_hashfn(dev->ifindex); head = &net->nexthop.devhash[hash]; hlist_add_head(&nhi->dev_hash, head); } static void nexthop_free_group(struct nexthop *nh) { struct nh_group *nhg; int i; nhg = rcu_dereference_raw(nh->nh_grp); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); free_percpu(nhge->stats); nexthop_put(nhge->nh); } WARN_ON(nhg->spare == nhg); if (nhg->resilient) vfree(rcu_dereference_raw(nhg->res_table)); kfree(nhg->spare); kfree(nhg); } static void nexthop_free_single(struct nexthop *nh) { struct nh_info *nhi; nhi = rcu_dereference_raw(nh->nh_info); switch (nhi->family) { case AF_INET: fib_nh_release(nh->net, &nhi->fib_nh); break; case AF_INET6: ipv6_stub->fib6_nh_release(&nhi->fib6_nh); break; } kfree(nhi); } void nexthop_free_rcu(struct rcu_head *head) { struct nexthop *nh = container_of(head, struct nexthop, rcu); if (nh->is_group) nexthop_free_group(nh); else nexthop_free_single(nh); kfree(nh); } EXPORT_SYMBOL_GPL(nexthop_free_rcu); static struct nexthop *nexthop_alloc(void) { struct nexthop *nh; nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL); if (nh) { INIT_LIST_HEAD(&nh->fi_list); INIT_LIST_HEAD(&nh->f6i_list); INIT_LIST_HEAD(&nh->grp_list); INIT_LIST_HEAD(&nh->fdb_list); spin_lock_init(&nh->lock); } return nh; } static struct nh_group *nexthop_grp_alloc(u16 num_nh) { struct nh_group *nhg; nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; return nhg; } static void nh_res_table_upkeep_dw(struct work_struct *work); static struct nh_res_table * nexthop_res_table_alloc(struct net *net, u32 nhg_id, struct nh_config *cfg) { const u16 num_nh_buckets = cfg->nh_grp_res_num_buckets; struct nh_res_table *res_table; unsigned long size; size = struct_size(res_table, nh_buckets, num_nh_buckets); res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); if (!res_table) return NULL; res_table->net = net; res_table->nhg_id = nhg_id; INIT_DELAYED_WORK(&res_table->upkeep_dw, &nh_res_table_upkeep_dw); INIT_LIST_HEAD(&res_table->uw_nh_entries); res_table->idle_timer = cfg->nh_grp_res_idle_timer; res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer; res_table->num_nh_buckets = num_nh_buckets; return res_table; } static void nh_base_seq_inc(struct net *net) { while (++net->nexthop.seq == 0) ; } /* no reference taken; rcu lock or rtnl must be held */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id) { struct rb_node **pp, *parent = NULL, *next; pp = &net->nexthop.rb_root.rb_node; while (1) { struct nexthop *nh; next = rcu_dereference_raw(*pp); if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (id < nh->id) pp = &next->rb_left; else if (id > nh->id) pp = &next->rb_right; else return nh; } return NULL; } EXPORT_SYMBOL_GPL(nexthop_find_by_id); /* used for auto id allocation; called with rtnl held */ static u32 nh_find_unused_id(struct net *net) { u32 id_start = net->nexthop.last_id_allocated; while (1) { net->nexthop.last_id_allocated++; if (net->nexthop.last_id_allocated == id_start) break; if (!nexthop_find_by_id(net, net->nexthop.last_id_allocated)) return net->nexthop.last_id_allocated; } return 0; } static void nh_res_time_set_deadline(unsigned long next_time, unsigned long *deadline) { if (time_before(next_time, *deadline)) *deadline = next_time; } static clock_t nh_res_table_unbalanced_time(struct nh_res_table *res_table) { if (list_empty(&res_table->uw_nh_entries)) return 0; return jiffies_delta_to_clock_t(jiffies - res_table->unbalanced_since); } static int nla_put_nh_group_res(struct sk_buff *skb, struct nh_group *nhg) { struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); struct nlattr *nest; nest = nla_nest_start(skb, NHA_RES_GROUP); if (!nest) return -EMSGSIZE; if (nla_put_u16(skb, NHA_RES_GROUP_BUCKETS, res_table->num_nh_buckets) || nla_put_u32(skb, NHA_RES_GROUP_IDLE_TIMER, jiffies_to_clock_t(res_table->idle_timer)) || nla_put_u32(skb, NHA_RES_GROUP_UNBALANCED_TIMER, jiffies_to_clock_t(res_table->unbalanced_timer)) || nla_put_u64_64bit(skb, NHA_RES_GROUP_UNBALANCED_TIME, nh_res_table_unbalanced_time(res_table), NHA_RES_GROUP_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) { struct nh_grp_entry_stats *cpu_stats; cpu_stats = get_cpu_ptr(nhge->stats); u64_stats_update_begin(&cpu_stats->syncp); u64_stats_inc(&cpu_stats->packets); u64_stats_update_end(&cpu_stats->syncp); put_cpu_ptr(cpu_stats); } static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, u64 *ret_packets) { int i; *ret_packets = 0; for_each_possible_cpu(i) { struct nh_grp_entry_stats *cpu_stats; unsigned int start; u64 packets; cpu_stats = per_cpu_ptr(nhge->stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); packets = u64_stats_read(&cpu_stats->packets); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); *ret_packets += packets; } } static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg; int i; ASSERT_RTNL(); nhg = rtnl_dereference(nh->nh_grp); info->id = nh->id; info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, stats, nhg->num_nh), GFP_KERNEL); if (!info->nh_grp_hw_stats) return -ENOMEM; info->nh_grp_hw_stats->num_nh = nhg->num_nh; for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; } return 0; } static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) { kfree(info->nh_grp_hw_stats); } void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, unsigned int nh_idx, u64 delta_packets) { info->hw_stats_used = true; info->stats[nh_idx].packets += delta_packets; } EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); static void nh_grp_hw_stats_apply_update(struct nexthop *nh, struct nh_notifier_info *info) { struct nh_group *nhg; int i; ASSERT_RTNL(); nhg = rtnl_dereference(nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; } } static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) { struct nh_notifier_info info = { .net = nh->net, }; struct net *net = nh->net; int err; if (nexthop_notifiers_is_empty(net)) { *hw_stats_used = false; return 0; } err = nh_notifier_grp_hw_stats_init(&info, nh); if (err) return err; err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, &info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ nh_grp_hw_stats_apply_update(nh, &info); *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; nh_notifier_grp_hw_stats_fini(&info); return notifier_to_errno(err); } static int nla_put_nh_group_stats_entry(struct sk_buff *skb, struct nh_grp_entry *nhge, u32 op_flags) { struct nlattr *nest; u64 packets; nh_grp_entry_stats_read(nhge, &packets); nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, packets + nhge->packets_hw)) goto nla_put_failure; if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, nhge->packets_hw)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, u32 op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nlattr *nest; bool hw_stats_used; int err; int i; if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) goto err_out; if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && nhg->hw_stats) { err = nh_grp_hw_stats_update(nh, &hw_stats_used); if (err) goto out; if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) goto err_out; } nest = nla_nest_start(skb, NHA_GROUP_STATS); if (!nest) goto err_out; for (i = 0; i < nhg->num_nh; i++) if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], op_flags)) goto cancel_out; nla_nest_end(skb, nest); return 0; cancel_out: nla_nest_cancel(skb, nest); err_out: err = -EMSGSIZE; out: return err; } static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, u32 op_flags, u32 *resp_op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; u16 group_type = 0; u16 weight; int i; *resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0; if (nhg->hash_threshold) group_type = NEXTHOP_GRP_TYPE_MPATH; else if (nhg->resilient) group_type = NEXTHOP_GRP_TYPE_RES; if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type)) goto nla_put_failure; nla = nla_reserve(skb, NHA_GROUP, len); if (!nla) goto nla_put_failure; p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { weight = nhg->nh_entries[i].weight - 1; *p++ = (struct nexthop_grp) { .id = nhg->nh_entries[i].nh->id, .weight = weight, .weight_high = weight >> 8, }; } if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; if (op_flags & NHA_OP_FLAG_DUMP_STATS && (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || nla_put_nh_group_stats(skb, nh, op_flags))) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, int event, u32 portid, u32 seq, unsigned int nlflags, u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; struct nlmsghdr *nlh; struct nh_info *nhi; struct nhmsg *nhm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); if (!nlh) return -EMSGSIZE; nhm = nlmsg_data(nlh); nhm->nh_family = AF_UNSPEC; nhm->nh_flags = nh->nh_flags; nhm->nh_protocol = nh->protocol; nhm->nh_scope = 0; nhm->resvd = 0; if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); u32 resp_op_flags = 0; if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; if (nla_put_nh_group(skb, nh, op_flags, &resp_op_flags) || nla_put_u32(skb, NHA_OP_FLAGS, resp_op_flags)) goto nla_put_failure; goto out; } nhi = rtnl_dereference(nh->nh_info); nhm->nh_family = nhi->family; if (nhi->reject_nh) { if (nla_put_flag(skb, NHA_BLACKHOLE)) goto nla_put_failure; goto out; } else if (nhi->fdb_nh) { if (nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; } else { const struct net_device *dev; dev = nhi->fib_nhc.nhc_dev; if (dev && nla_put_u32(skb, NHA_OIF, dev->ifindex)) goto nla_put_failure; } nhm->nh_scope = nhi->fib_nhc.nhc_scope; switch (nhi->family) { case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; case AF_INET6: fib6_nh = &nhi->fib6_nh; if (fib6_nh->fib_nh_gw_family && nla_put_in6_addr(skb, NHA_GATEWAY, &fib6_nh->fib_nh_gw6)) goto nla_put_failure; break; } if (lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate, NHA_ENCAP, NHA_ENCAP_TYPE) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static size_t nh_nlmsg_size_grp_res(struct nh_group *nhg) { return nla_total_size(0) + /* NHA_RES_GROUP */ nla_total_size(2) + /* NHA_RES_GROUP_BUCKETS */ nla_total_size(4) + /* NHA_RES_GROUP_IDLE_TIMER */ nla_total_size(4) + /* NHA_RES_GROUP_UNBALANCED_TIMER */ nla_total_size_64bit(8);/* NHA_RES_GROUP_UNBALANCED_TIME */ } static size_t nh_nlmsg_size_grp(struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh; size_t tot = nla_total_size(sz) + nla_total_size(2); /* NHA_GROUP_TYPE */ if (nhg->resilient) tot += nh_nlmsg_size_grp_res(nhg); return tot; } static size_t nh_nlmsg_size_single(struct nexthop *nh) { struct nh_info *nhi = rtnl_dereference(nh->nh_info); size_t sz; /* covers NHA_BLACKHOLE since NHA_OIF and BLACKHOLE * are mutually exclusive */ sz = nla_total_size(4); /* NHA_OIF */ switch (nhi->family) { case AF_INET: if (nhi->fib_nh.fib_nh_gw_family) sz += nla_total_size(4); /* NHA_GATEWAY */ break; case AF_INET6: /* NHA_GATEWAY */ if (nhi->fib6_nh.fib_nh_gw_family) sz += nla_total_size(sizeof(const struct in6_addr)); break; } if (nhi->fib_nhc.nhc_lwtstate) { sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate); sz += nla_total_size(2); /* NHA_ENCAP_TYPE */ } return sz; } static size_t nh_nlmsg_size(struct nexthop *nh) { size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg)); sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) sz += nh_nlmsg_size_grp(nh) + nla_total_size(4) + /* NHA_OP_FLAGS */ 0; else sz += nh_nlmsg_size_single(nh); return sz; } static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) { unsigned int nlflags = info->nlh ? info->nlh->nlmsg_flags : 0; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any()); if (!skb) goto errout; err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_NEXTHOP, info->nlh, gfp_any()); return; errout: rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket) { return (unsigned long)atomic_long_read(&bucket->used_time); } static unsigned long nh_res_bucket_idle_point(const struct nh_res_table *res_table, const struct nh_res_bucket *bucket, unsigned long now) { unsigned long time = nh_res_bucket_used_time(bucket); /* Bucket was not used since it was migrated. The idle time is now. */ if (time == bucket->migrated_time) return now; return time + res_table->idle_timer; } static unsigned long nh_res_table_unb_point(const struct nh_res_table *res_table) { return res_table->unbalanced_since + res_table->unbalanced_timer; } static void nh_res_bucket_set_idle(const struct nh_res_table *res_table, struct nh_res_bucket *bucket) { unsigned long now = jiffies; atomic_long_set(&bucket->used_time, (long)now); bucket->migrated_time = now; } static void nh_res_bucket_set_busy(struct nh_res_bucket *bucket) { atomic_long_set(&bucket->used_time, (long)jiffies); } static clock_t nh_res_bucket_idle_time(const struct nh_res_bucket *bucket) { unsigned long used_time = nh_res_bucket_used_time(bucket); return jiffies_delta_to_clock_t(jiffies - used_time); } static int nh_fill_res_bucket(struct sk_buff *skb, struct nexthop *nh, struct nh_res_bucket *bucket, u16 bucket_index, int event, u32 portid, u32 seq, unsigned int nlflags, struct netlink_ext_ack *extack) { struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); struct nlmsghdr *nlh; struct nlattr *nest; struct nhmsg *nhm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); if (!nlh) return -EMSGSIZE; nhm = nlmsg_data(nlh); nhm->nh_family = AF_UNSPEC; nhm->nh_flags = bucket->nh_flags; nhm->nh_protocol = nh->protocol; nhm->nh_scope = 0; nhm->resvd = 0; if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; nest = nla_nest_start(skb, NHA_RES_BUCKET); if (!nest) goto nla_put_failure; if (nla_put_u16(skb, NHA_RES_BUCKET_INDEX, bucket_index) || nla_put_u32(skb, NHA_RES_BUCKET_NH_ID, nhge->nh->id) || nla_put_u64_64bit(skb, NHA_RES_BUCKET_IDLE_TIME, nh_res_bucket_idle_time(bucket), NHA_RES_BUCKET_PAD)) goto nla_put_failure_nest; nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; nla_put_failure_nest: nla_nest_cancel(skb, nest); nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void nexthop_bucket_notify(struct nh_res_table *res_table, u16 bucket_index) { struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); struct nexthop *nh = nhge->nh_parent; struct sk_buff *skb; int err = -ENOBUFS; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto errout; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, 0, 0, NLM_F_REPLACE, NULL); if (err < 0) { kfree_skb(skb); goto errout; } rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, bool *is_fdb, struct netlink_ext_ack *extack) { if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); /* Nesting groups within groups is not supported. */ if (nhg->hash_threshold) { NL_SET_ERR_MSG(extack, "Hash-threshold group can not be a nexthop within a group"); return false; } if (nhg->resilient) { NL_SET_ERR_MSG(extack, "Resilient group can not be a nexthop within a group"); return false; } *is_fdb = nhg->fdb_nh; } else { struct nh_info *nhi = rtnl_dereference(nh->nh_info); if (nhi->reject_nh && npaths > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be used in a group with more than 1 path"); return false; } *is_fdb = nhi->fdb_nh; } return true; } static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, struct netlink_ext_ack *extack) { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (!nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "FDB nexthop group can only have fdb nexthops"); return -EINVAL; } if (*nh_family == AF_UNSPEC) { *nh_family = nhi->family; } else if (*nh_family != nhi->family) { NL_SET_ERR_MSG(extack, "FDB nexthop group cannot have mixed family nexthops"); return -EINVAL; } return 0; } static int nh_check_attr_group(struct net *net, struct nlattr *tb[], size_t tb_size, u16 nh_grp_type, struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); struct nexthop_grp *nhg; unsigned int i, j; if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; } /* convert len to number of nexthop ids */ len /= sizeof(*nhg); nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { if (nhg[i].resvd2) { NL_SET_ERR_MSG(extack, "Reserved field in nexthop_grp must be 0"); return -EINVAL; } if (nexthop_grp_weight(&nhg[i]) == 0) { /* 0xffff got passed in, representing weight of 0x10000, * which is too heavy. */ NL_SET_ERR_MSG(extack, "Invalid value for weight"); return -EINVAL; } for (j = i + 1; j < len; ++j) { if (nhg[i].id == nhg[j].id) { NL_SET_ERR_MSG(extack, "Nexthop id can not be used twice in a group"); return -EINVAL; } } } nhg = nla_data(tb[NHA_GROUP]); for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { if (!tb[i]) continue; switch (i) { case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) continue; break; } NL_SET_ERR_MSG(extack, "No other attributes can be set in nexthop groups"); return -EINVAL; } return 0; } static int nh_check_attr_group_rtnl(struct net *net, struct nlattr *tb[], struct netlink_ext_ack *extack) { u8 nh_family = AF_UNSPEC; struct nexthop_grp *nhg; unsigned int len; unsigned int i; u8 nhg_fdb; len = nla_len(tb[NHA_GROUP]) / sizeof(*nhg); nhg = nla_data(tb[NHA_GROUP]); nhg_fdb = !!tb[NHA_FDB]; for (i = 0; i < len; i++) { struct nexthop *nh; bool is_fdb_nh; nh = nexthop_find_by_id(net, nhg[i].id); if (!nh) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } if (!valid_group_nh(nh, len, &is_fdb_nh, extack)) return -EINVAL; if (nhg_fdb && nh_check_attr_fdb_group(nh, &nh_family, extack)) return -EINVAL; if (!nhg_fdb && is_fdb_nh) { NL_SET_ERR_MSG(extack, "Non FDB nexthop group cannot have fdb nexthops"); return -EINVAL; } } return 0; } static bool ipv6_good_nh(const struct fib6_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); if (n) state = READ_ONCE(n->nud_state); rcu_read_unlock(); return !!(state & NUD_VALID); } static bool ipv4_good_nh(const struct fib_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock(); n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, (__force u32)nh->fib_nh_gw4); if (n) state = READ_ONCE(n->nud_state); rcu_read_unlock(); return !!(state & NUD_VALID); } static bool nexthop_is_good_nh(const struct nexthop *nh) { struct nh_info *nhi = rcu_dereference(nh->nh_info); switch (nhi->family) { case AF_INET: return ipv4_good_nh(&nhi->fib_nh); case AF_INET6: return ipv6_good_nh(&nhi->fib6_nh); } return false; } static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) { int i; for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; nh_grp_entry_stats_inc(nhge); return nhge->nh; } WARN_ON_ONCE(1); return NULL; } static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) { struct nh_grp_entry *nhge0 = NULL; int i; if (nhg->fdb_nh) return nexthop_select_path_fdb(nhg, hash); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; /* nexthops always check if it is good and does * not rely on a sysctl for this behavior */ if (!nexthop_is_good_nh(nhge->nh)) continue; if (!nhge0) nhge0 = nhge; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; nh_grp_entry_stats_inc(nhge); return nhge->nh; } if (!nhge0) nhge0 = &nhg->nh_entries[0]; nh_grp_entry_stats_inc(nhge0); return nhge0->nh; } static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) { struct nh_res_table *res_table = rcu_dereference(nhg->res_table); u16 bucket_index = hash % res_table->num_nh_buckets; struct nh_res_bucket *bucket; struct nh_grp_entry *nhge; /* nexthop_select_path() is expected to return a non-NULL value, so * skip protocol validation and just hand out whatever there is. */ bucket = &res_table->nh_buckets[bucket_index]; nh_res_bucket_set_busy(bucket); nhge = rcu_dereference(bucket->nh_entry); nh_grp_entry_stats_inc(nhge); return nhge->nh; } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) { struct nh_group *nhg; if (!nh->is_group) return nh; nhg = rcu_dereference(nh->nh_grp); if (nhg->hash_threshold) return nexthop_select_path_hthr(nhg, hash); else if (nhg->resilient) return nexthop_select_path_res(nhg, hash); /* Unreachable. */ return NULL; } EXPORT_SYMBOL_GPL(nexthop_select_path); int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg) { struct nh_info *nhi; int err; if (nh->is_group) { struct nh_group *nhg; int i; nhg = rcu_dereference_rtnl(nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; nhi = rcu_dereference_rtnl(nhge->nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } } else { nhi = rcu_dereference_rtnl(nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(nexthop_for_each_fib6_nh); static int check_src_addr(const struct in6_addr *saddr, struct netlink_ext_ack *extack) { if (!ipv6_addr_any(saddr)) { NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects"); return -EINVAL; } return 0; } int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; bool is_fdb_nh; /* fib6_src is unique to a fib6_info and limits the ability to cache * routes in fib6_nh within a nexthop that is potentially shared * across multiple fib entries. If the config wants to use source * routing it can not use nexthop objects. mlxsw also does not allow * fib6_src on routes. */ if (cfg && check_src_addr(&cfg->fc_src, extack) < 0) return -EINVAL; if (nh->is_group) { struct nh_group *nhg; nhg = rcu_dereference_rtnl(nh->nh_grp); if (nhg->has_v4) goto no_v4_nh; is_fdb_nh = nhg->fdb_nh; } else { nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->family == AF_INET) goto no_v4_nh; is_fdb_nh = nhi->fdb_nh; } if (is_fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); return -EINVAL; } return 0; no_v4_nh: NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop"); return -EINVAL; } EXPORT_SYMBOL_GPL(fib6_check_nexthop); /* if existing nexthop has ipv6 routes linked to it, need * to verify this new spec works with ipv6 */ static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib6_info *f6i; if (list_empty(&old->f6i_list)) return 0; list_for_each_entry(f6i, &old->f6i_list, nh_list) { if (check_src_addr(&f6i->fib6_src.addr, extack) < 0) return -EINVAL; } return fib6_check_nexthop(new, NULL, extack); } static int nexthop_check_scope(struct nh_info *nhi, u8 scope, struct netlink_ext_ack *extack) { if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) { NL_SET_ERR_MSG(extack, "Route with host scope can not have a gateway"); return -EINVAL; } if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) { NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop"); return -EINVAL; } return 0; } /* Invoked by fib add code to verify nexthop by id is ok with * config for prefix; parts of fib_check_nh not done when nexthop * object is used. */ int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack) { struct nh_info *nhi; int err = 0; if (nh->is_group) { struct nh_group *nhg; nhg = rtnl_dereference(nh->nh_grp); if (nhg->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } if (scope == RT_SCOPE_HOST) { NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops"); err = -EINVAL; goto out; } /* all nexthops in a group have the same scope */ nhi = rtnl_dereference(nhg->nh_entries[0].nh->nh_info); err = nexthop_check_scope(nhi, scope, extack); } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } err = nexthop_check_scope(nhi, scope, extack); } out: return err; } static int fib_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib_info *fi; list_for_each_entry(fi, &old->fi_list, nh_list) { int err; err = fib_check_nexthop(new, fi->fib_scope, extack); if (err) return err; } return 0; } static bool nh_res_nhge_is_balanced(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets == nhge->res.wants_buckets; } static bool nh_res_nhge_is_ow(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets > nhge->res.wants_buckets; } static bool nh_res_nhge_is_uw(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets < nhge->res.wants_buckets; } static bool nh_res_table_is_balanced(const struct nh_res_table *res_table) { return list_empty(&res_table->uw_nh_entries); } static void nh_res_bucket_unset_nh(struct nh_res_bucket *bucket) { struct nh_grp_entry *nhge; if (bucket->occupied) { nhge = nh_res_dereference(bucket->nh_entry); nhge->res.count_buckets--; bucket->occupied = false; } } static void nh_res_bucket_set_nh(struct nh_res_bucket *bucket, struct nh_grp_entry *nhge) { nh_res_bucket_unset_nh(bucket); bucket->occupied = true; rcu_assign_pointer(bucket->nh_entry, nhge); nhge->res.count_buckets++; } static bool nh_res_bucket_should_migrate(struct nh_res_table *res_table, struct nh_res_bucket *bucket, unsigned long *deadline, bool *force) { unsigned long now = jiffies; struct nh_grp_entry *nhge; unsigned long idle_point; if (!bucket->occupied) { /* The bucket is not occupied, its NHGE pointer is either * NULL or obsolete. We _have to_ migrate: set force. */ *force = true; return true; } nhge = nh_res_dereference(bucket->nh_entry); /* If the bucket is populated by an underweight or balanced * nexthop, do not migrate. */ if (!nh_res_nhge_is_ow(nhge)) return false; /* At this point we know that the bucket is populated with an * overweight nexthop. It needs to be migrated to a new nexthop if * the idle timer of unbalanced timer expired. */ idle_point = nh_res_bucket_idle_point(res_table, bucket, now); if (time_after_eq(now, idle_point)) { /* The bucket is idle. We _can_ migrate: unset force. */ *force = false; return true; } /* Unbalanced timer of 0 means "never force". */ if (res_table->unbalanced_timer) { unsigned long unb_point; unb_point = nh_res_table_unb_point(res_table); if (time_after(now, unb_point)) { /* The bucket is not idle, but the unbalanced timer * expired. We _can_ migrate, but set force anyway, * so that drivers know to ignore activity reports * from the HW. */ *force = true; return true; } nh_res_time_set_deadline(unb_point, deadline); } nh_res_time_set_deadline(idle_point, deadline); return false; } static bool nh_res_bucket_migrate(struct nh_res_table *res_table, u16 bucket_index, bool notify, bool notify_nl, bool force) { struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; struct nh_grp_entry *new_nhge; struct netlink_ext_ack extack; int err; new_nhge = list_first_entry_or_null(&res_table->uw_nh_entries, struct nh_grp_entry, res.uw_nh_entry); if (WARN_ON_ONCE(!new_nhge)) /* If this function is called, "bucket" is either not * occupied, or it belongs to a next hop that is * overweight. In either case, there ought to be a * corresponding underweight next hop. */ return false; if (notify) { struct nh_grp_entry *old_nhge; old_nhge = nh_res_dereference(bucket->nh_entry); err = call_nexthop_res_bucket_notifiers(res_table->net, res_table->nhg_id, bucket_index, force, old_nhge->nh, new_nhge->nh, &extack); if (err) { pr_err_ratelimited("%s\n", extack._msg); if (!force) return false; /* It is not possible to veto a forced replacement, so * just clear the hardware flags from the nexthop * bucket to indicate to user space that this bucket is * not correctly populated in hardware. */ bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); } } nh_res_bucket_set_nh(bucket, new_nhge); nh_res_bucket_set_idle(res_table, bucket); if (notify_nl) nexthop_bucket_notify(res_table, bucket_index); if (nh_res_nhge_is_balanced(new_nhge)) list_del(&new_nhge->res.uw_nh_entry); return true; } #define NH_RES_UPKEEP_DW_MINIMUM_INTERVAL (HZ / 2) static void nh_res_table_upkeep(struct nh_res_table *res_table, bool notify, bool notify_nl) { unsigned long now = jiffies; unsigned long deadline; u16 i; /* Deadline is the next time that upkeep should be run. It is the * earliest time at which one of the buckets might be migrated. * Start at the most pessimistic estimate: either unbalanced_timer * from now, or if there is none, idle_timer from now. For each * encountered time point, call nh_res_time_set_deadline() to * refine the estimate. */ if (res_table->unbalanced_timer) deadline = now + res_table->unbalanced_timer; else deadline = now + res_table->idle_timer; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; bool force; if (nh_res_bucket_should_migrate(res_table, bucket, &deadline, &force)) { if (!nh_res_bucket_migrate(res_table, i, notify, notify_nl, force)) { unsigned long idle_point; /* A driver can override the migration * decision if the HW reports that the * bucket is actually not idle. Therefore * remark the bucket as busy again and * update the deadline. */ nh_res_bucket_set_busy(bucket); idle_point = nh_res_bucket_idle_point(res_table, bucket, now); nh_res_time_set_deadline(idle_point, &deadline); } } } /* If the group is still unbalanced, schedule the next upkeep to * either the deadline computed above, or the minimum deadline, * whichever comes later. */ if (!nh_res_table_is_balanced(res_table)) { unsigned long now = jiffies; unsigned long min_deadline; min_deadline = now + NH_RES_UPKEEP_DW_MINIMUM_INTERVAL; if (time_before(deadline, min_deadline)) deadline = min_deadline; queue_delayed_work(system_power_efficient_wq, &res_table->upkeep_dw, deadline - now); } } static void nh_res_table_upkeep_dw(struct work_struct *work) { struct delayed_work *dw = to_delayed_work(work); struct nh_res_table *res_table; res_table = container_of(dw, struct nh_res_table, upkeep_dw); nh_res_table_upkeep(res_table, true, true); } static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table) { cancel_delayed_work_sync(&res_table->upkeep_dw); } static void nh_res_group_rebalance(struct nh_group *nhg, struct nh_res_table *res_table) { u16 prev_upper_bound = 0; u32 total = 0; u32 w = 0; int i; INIT_LIST_HEAD(&res_table->uw_nh_entries); for (i = 0; i < nhg->num_nh; ++i) total += nhg->nh_entries[i].weight; for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; u16 upper_bound; u64 btw; w += nhge->weight; btw = ((u64)res_table->num_nh_buckets) * w; upper_bound = DIV_ROUND_CLOSEST_ULL(btw, total); nhge->res.wants_buckets = upper_bound - prev_upper_bound; prev_upper_bound = upper_bound; if (nh_res_nhge_is_uw(nhge)) { if (list_empty(&res_table->uw_nh_entries)) res_table->unbalanced_since = jiffies; list_add(&nhge->res.uw_nh_entry, &res_table->uw_nh_entries); } } } /* Migrate buckets in res_table so that they reference NHGE's from NHG with * the right NH ID. Set those buckets that do not have a corresponding NHGE * entry in NHG as not occupied. */ static void nh_res_table_migrate_buckets(struct nh_res_table *res_table, struct nh_group *nhg) { u16 i; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; u32 id = rtnl_dereference(bucket->nh_entry)->nh->id; bool found = false; int j; for (j = 0; j < nhg->num_nh; j++) { struct nh_grp_entry *nhge = &nhg->nh_entries[j]; if (nhge->nh->id == id) { nh_res_bucket_set_nh(bucket, nhge); found = true; break; } } if (!found) nh_res_bucket_unset_nh(bucket); } } static void replace_nexthop_grp_res(struct nh_group *oldg, struct nh_group *newg) { /* For NH group replacement, the new NHG might only have a stub * hash table with 0 buckets, because the number of buckets was not * specified. For NH removal, oldg and newg both reference the same * res_table. So in any case, in the following, we want to work * with oldg->res_table. */ struct nh_res_table *old_res_table = rtnl_dereference(oldg->res_table); unsigned long prev_unbalanced_since = old_res_table->unbalanced_since; bool prev_has_uw = !list_empty(&old_res_table->uw_nh_entries); nh_res_table_cancel_upkeep(old_res_table); nh_res_table_migrate_buckets(old_res_table, newg); nh_res_group_rebalance(newg, old_res_table); if (prev_has_uw && !list_empty(&old_res_table->uw_nh_entries)) old_res_table->unbalanced_since = prev_unbalanced_since; nh_res_table_upkeep(old_res_table, true, false); } static void nh_hthr_group_rebalance(struct nh_group *nhg) { u32 total = 0; u32 w = 0; int i; for (i = 0; i < nhg->num_nh; ++i) total += nhg->nh_entries[i].weight; for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; u32 upper_bound; w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; atomic_set(&nhge->hthr.upper_bound, upper_bound); } } static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, struct nl_info *nlinfo) { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; struct netlink_ext_ack extack; struct nexthop *nh = nhge->nh; struct nh_group *nhg, *newg; int i, j, err; WARN_ON(!nh); nhg = rtnl_dereference(nhp->nh_grp); newg = nhg->spare; /* last entry, keep it visible and remove the parent */ if (nhg->num_nh == 1) { remove_nexthop(net, nhp, nlinfo); return; } newg->has_v4 = false; newg->is_multipath = nhg->is_multipath; newg->hash_threshold = nhg->hash_threshold; newg->resilient = nhg->resilient; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; /* copy old entries to new except the one getting removed */ nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { struct nh_info *nhi; /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) newg->has_v4 = true; list_del(&nhges[i].nh_list); new_nhges[j].stats = nhges[i].stats; new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list); j++; } if (newg->hash_threshold) nh_hthr_group_rebalance(newg); else if (newg->resilient) replace_nexthop_grp_res(nhg, newg); rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); free_percpu(nhge->stats); nexthop_put(nhge->nh); /* Removal of a NH from a resilient group is notified through * bucket notifications. */ if (newg->hash_threshold) { err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack); if (err) pr_err("%s\n", extack._msg); } if (nlinfo) nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); } static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { struct nh_grp_entry *nhge, *tmp; list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) remove_nh_grp_entry(net, nhge, nlinfo); /* make sure all see the newly published array before releasing rtnl */ synchronize_net(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); struct nh_res_table *res_table; int i, num_nh = nhg->num_nh; for (i = 0; i < num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; if (WARN_ON(!nhge->nh)) continue; list_del_init(&nhge->nh_list); } if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); nh_res_table_cancel_upkeep(res_table); } } /* not called for nexthop replace */ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) { struct fib6_info *f6i; bool do_flush = false; struct fib_info *fi; list_for_each_entry(fi, &nh->fi_list, nh_list) { fi->fib_flags |= RTNH_F_DEAD; do_flush = true; } if (do_flush) fib_flush(net); spin_lock_bh(&nh->lock); nh->dead = true; while (!list_empty(&nh->f6i_list)) { f6i = list_first_entry(&nh->f6i_list, typeof(*f6i), nh_list); /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); spin_unlock_bh(&nh->lock); ipv6_stub->ip6_del_rt(net, f6i, !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)); spin_lock_bh(&nh->lock); } spin_unlock_bh(&nh->lock); } static void __remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { __remove_nexthop_fib(net, nh); if (nh->is_group) { remove_nexthop_group(nh, nlinfo); } else { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (nhi->fib_nhc.nhc_dev) hlist_del(&nhi->dev_hash); remove_nexthop_from_groups(net, nh, nlinfo); } } static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL); /* remove from the tree */ rb_erase(&nh->rb_node, &net->nexthop.rb_root); if (nlinfo) nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo); __remove_nexthop(net, nh, nlinfo); nh_base_seq_inc(net); nexthop_put(nh); } /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, struct nexthop *replaced_nh) { struct fib6_info *f6i; struct nh_group *nhg; int i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); /* if an IPv6 group was replaced, we have to release all old * dsts to make sure all refcounts are released */ if (!replaced_nh->is_group) return; nhg = rtnl_dereference(replaced_nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); if (nhi->family == AF_INET6) ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); } } static int replace_nexthop_grp(struct net *net, struct nexthop *old, struct nexthop *new, const struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nh_res_table *tmp_table = NULL; struct nh_res_table *new_res_table; struct nh_res_table *old_res_table; struct nh_group *oldg, *newg; int i, err; if (!new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop."); return -EINVAL; } oldg = rtnl_dereference(old->nh_grp); newg = rtnl_dereference(new->nh_grp); if (newg->hash_threshold != oldg->hash_threshold) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with one of a different type."); return -EINVAL; } if (newg->hash_threshold) { err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; } else if (newg->resilient) { new_res_table = rtnl_dereference(newg->res_table); old_res_table = rtnl_dereference(oldg->res_table); /* Accept if num_nh_buckets was not given, but if it was * given, demand that the value be correct. */ if (cfg->nh_grp_res_has_num_buckets && cfg->nh_grp_res_num_buckets != old_res_table->num_nh_buckets) { NL_SET_ERR_MSG(extack, "Can not change number of buckets of a resilient nexthop group."); return -EINVAL; } /* Emit a pre-replace notification so that listeners could veto * a potentially unsupported configuration. Otherwise, * individual bucket replacement notifications would need to be * vetoed, which is something that should only happen if the * bucket is currently active. */ err = call_nexthop_res_table_notifiers(net, new, extack); if (err) return err; if (cfg->nh_grp_res_has_idle_timer) old_res_table->idle_timer = cfg->nh_grp_res_idle_timer; if (cfg->nh_grp_res_has_unbalanced_timer) old_res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer; replace_nexthop_grp_res(oldg, newg); tmp_table = new_res_table; rcu_assign_pointer(newg->res_table, old_res_table); rcu_assign_pointer(newg->spare->res_table, old_res_table); } /* update parents - used by nexthop code for cleanup */ for (i = 0; i < newg->num_nh; i++) newg->nh_entries[i].nh_parent = old; rcu_assign_pointer(old->nh_grp, newg); /* Make sure concurrent readers are not using 'oldg' anymore. */ synchronize_net(); if (newg->resilient) { rcu_assign_pointer(oldg->res_table, tmp_table); rcu_assign_pointer(oldg->spare->res_table, tmp_table); } for (i = 0; i < oldg->num_nh; i++) oldg->nh_entries[i].nh_parent = new; rcu_assign_pointer(new->nh_grp, oldg); return 0; } static void nh_group_v4_update(struct nh_group *nhg) { struct nh_grp_entry *nhges; bool has_v4 = false; int i; nhges = nhg->nh_entries; for (i = 0; i < nhg->num_nh; i++) { struct nh_info *nhi; nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) has_v4 = true; } nhg->has_v4 = has_v4; } static int replace_nexthop_single_notify_res(struct net *net, struct nh_res_table *res_table, struct nexthop *old, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { u32 nhg_id = res_table->nhg_id; int err; u16 i; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; nhge = rtnl_dereference(bucket->nh_entry); if (nhge->nh == old) { err = __call_nexthop_res_bucket_notifiers(net, nhg_id, i, true, oldi, newi, extack); if (err) goto err_notify; } } return 0; err_notify: while (i-- > 0) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; nhge = rtnl_dereference(bucket->nh_entry); if (nhge->nh == old) __call_nexthop_res_bucket_notifiers(net, nhg_id, i, true, newi, oldi, extack); } return err; } static int replace_nexthop_single_notify(struct net *net, struct nexthop *group_nh, struct nexthop *old, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { struct nh_group *nhg = rtnl_dereference(group_nh->nh_grp); struct nh_res_table *res_table; if (nhg->hash_threshold) { return call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, group_nh, extack); } else if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); return replace_nexthop_single_notify_res(net, res_table, old, oldi, newi, extack); } return -EINVAL; } static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { u8 old_protocol, old_nh_flags; struct nh_info *oldi, *newi; struct nh_grp_entry *nhge; int err; if (new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group."); return -EINVAL; } err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; /* Hardware flags were set on 'old' as 'new' is not in the red-black * tree. Therefore, inherit the flags from 'old' to 'new'. */ new->nh_flags |= old->nh_flags & (RTNH_F_OFFLOAD | RTNH_F_TRAP); oldi = rtnl_dereference(old->nh_info); newi = rtnl_dereference(new->nh_info); newi->nh_parent = old; oldi->nh_parent = new; old_protocol = old->protocol; old_nh_flags = old->nh_flags; old->protocol = new->protocol; old->nh_flags = new->nh_flags; rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); /* Send a replace notification for all the groups using the nexthop. */ list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; err = replace_nexthop_single_notify(net, nhp, old, oldi, newi, extack); if (err) goto err_notify; } /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially * update IPv4 indication in all the groups using the nexthop. */ if (oldi->family == AF_INET && newi->family == AF_INET6) { list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; struct nh_group *nhg; nhg = rtnl_dereference(nhp->nh_grp); nh_group_v4_update(nhg); } } return 0; err_notify: rcu_assign_pointer(new->nh_info, newi); rcu_assign_pointer(old->nh_info, oldi); old->nh_flags = old_nh_flags; old->protocol = old_protocol; oldi->nh_parent = old; newi->nh_parent = new; list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; replace_nexthop_single_notify(net, nhp, old, newi, oldi, NULL); } call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack); return err; } static void __nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct fib6_info *f6i; if (!list_empty(&nh->fi_list)) { struct fib_info *fi; /* expectation is a few fib_info per nexthop and then * a lot of routes per fib_info. So mark the fib_info * and then walk the fib tables once */ list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = true; fib_info_notify_update(net, info); list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = false; } list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_rt_update(net, f6i, info); } /* send RTM_NEWROUTE with REPLACE flag set for all FIB entries * linked to this nexthop and for all groups that the nexthop * is a member of */ static void nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct nh_grp_entry *nhge; __nexthop_replace_notify(net, nh, info); list_for_each_entry(nhge, &nh->grp_list, nh_list) __nexthop_replace_notify(net, nhge->nh_parent, info); } static int replace_nexthop(struct net *net, struct nexthop *old, struct nexthop *new, const struct nh_config *cfg, struct netlink_ext_ack *extack) { bool new_is_reject = false; struct nh_grp_entry *nhge; int err; /* check that existing FIB entries are ok with the * new nexthop definition */ err = fib_check_nh_list(old, new, extack); if (err) return err; err = fib6_check_nh_list(old, new, extack); if (err) return err; if (!new->is_group) { struct nh_info *nhi = rtnl_dereference(new->nh_info); new_is_reject = nhi->reject_nh; } list_for_each_entry(nhge, &old->grp_list, nh_list) { /* if new nexthop is a blackhole, any groups using this * nexthop cannot have more than 1 path */ if (new_is_reject && nexthop_num_path(nhge->nh_parent) > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be a member of a group with more than one path"); return -EINVAL; } err = fib_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; err = fib6_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; } if (old->is_group) err = replace_nexthop_grp(net, old, new, cfg, extack); else err = replace_nexthop_single(net, old, new, extack); if (!err) { nh_rt_cache_flush(net, old, new); __remove_nexthop(net, new, NULL); nexthop_put(new); } return err; } /* called with rtnl_lock held */ static int insert_nexthop(struct net *net, struct nexthop *new_nh, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct rb_node **pp, *parent = NULL, *next; struct rb_root *root = &net->nexthop.rb_root; bool replace = !!(cfg->nlflags & NLM_F_REPLACE); bool create = !!(cfg->nlflags & NLM_F_CREATE); u32 new_id = new_nh->id; int replace_notify = 0; int rc = -EEXIST; pp = &root->rb_node; while (1) { struct nexthop *nh; next = *pp; if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (new_id < nh->id) { pp = &next->rb_left; } else if (new_id > nh->id) { pp = &next->rb_right; } else if (replace) { rc = replace_nexthop(net, nh, new_nh, cfg, extack); if (!rc) { new_nh = nh; /* send notification with old nh */ replace_notify = 1; } goto out; } else { /* id already exists and not a replace */ goto out; } } if (replace && !create) { NL_SET_ERR_MSG(extack, "Replace specified without create and no entry exists"); rc = -ENOENT; goto out; } if (new_nh->is_group) { struct nh_group *nhg = rtnl_dereference(new_nh->nh_grp); struct nh_res_table *res_table; if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); /* Not passing the number of buckets is OK when * replacing, but not when creating a new group. */ if (!cfg->nh_grp_res_has_num_buckets) { NL_SET_ERR_MSG(extack, "Number of buckets not specified for nexthop group insertion"); rc = -EINVAL; goto out; } nh_res_group_rebalance(nhg, res_table); /* Do not send bucket notifications, we do full * notification below. */ nh_res_table_upkeep(res_table, false, false); } } rb_link_node_rcu(&new_nh->rb_node, parent, pp); rb_insert_color(&new_nh->rb_node, root); /* The initial insertion is a full notification for hash-threshold as * well as resilient groups. */ rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack); if (rc) rb_erase(&new_nh->rb_node, &net->nexthop.rb_root); out: if (!rc) { nh_base_seq_inc(net); nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); if (replace_notify && READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)) nexthop_replace_notify(net, new_nh, &cfg->nlinfo); } return rc; } /* rtnl */ /* remove all nexthops tied to a device being deleted */ static void nexthop_flush_dev(struct net_device *dev, unsigned long event) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev != dev) continue; if (nhi->reject_nh && (event == NETDEV_DOWN || event == NETDEV_CHANGE)) continue; remove_nexthop(net, nhi->nh_parent, NULL); } } /* rtnl; called when net namespace is deleted */ static void flush_all_nexthops(struct net *net) { struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; struct nexthop *nh; while ((node = rb_first(root))) { nh = rb_entry(node, struct nexthop, rb_node); remove_nexthop(net, nh, NULL); cond_resched(); } } static struct nexthop *nexthop_create_group(struct net *net, struct nh_config *cfg) { struct nlattr *grps_attr = cfg->nh_grp; struct nexthop_grp *entry = nla_data(grps_attr); u16 num_nh = nla_len(grps_attr) / sizeof(*entry); struct nh_group *nhg; struct nexthop *nh; int err; int i; nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nh->is_group = 1; nhg = nexthop_grp_alloc(num_nh); if (!nhg) { kfree(nh); return ERR_PTR(-ENOMEM); } /* spare group used for removals */ nhg->spare = nexthop_grp_alloc(num_nh); if (!nhg->spare) { kfree(nhg); kfree(nh); return ERR_PTR(-ENOMEM); } nhg->spare->spare = nhg; for (i = 0; i < nhg->num_nh; ++i) { struct nexthop *nhe; struct nh_info *nhi; nhe = nexthop_find_by_id(net, entry[i].id); if (!nexthop_get(nhe)) { err = -ENOENT; goto out_no_nh; } nhi = rtnl_dereference(nhe->nh_info); if (nhi->family == AF_INET) nhg->has_v4 = true; nhg->nh_entries[i].stats = netdev_alloc_pcpu_stats(struct nh_grp_entry_stats); if (!nhg->nh_entries[i].stats) { err = -ENOMEM; nexthop_put(nhe); goto out_no_nh; } nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = nexthop_grp_weight(&entry[i]); list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); nhg->nh_entries[i].nh_parent = nh; } if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { nhg->hash_threshold = 1; nhg->is_multipath = true; } else if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) { struct nh_res_table *res_table; res_table = nexthop_res_table_alloc(net, cfg->nh_id, cfg); if (!res_table) { err = -ENOMEM; goto out_no_nh; } rcu_assign_pointer(nhg->spare->res_table, res_table); rcu_assign_pointer(nhg->res_table, res_table); nhg->resilient = true; nhg->is_multipath = true; } WARN_ON_ONCE(nhg->hash_threshold + nhg->resilient != 1); if (nhg->hash_threshold) nh_hthr_group_rebalance(nhg); if (cfg->nh_fdb) nhg->fdb_nh = 1; if (cfg->nh_hw_stats) nhg->hw_stats = true; rcu_assign_pointer(nh->nh_grp, nhg); return nh; out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); free_percpu(nhg->nh_entries[i].stats); nexthop_put(nhg->nh_entries[i].nh); } kfree(nhg->spare); kfree(nhg); kfree(nh); return ERR_PTR(err); } static int nh_create_ipv4(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib_nh *fib_nh = &nhi->fib_nh; struct fib_config fib_cfg = { .fc_oif = cfg->nh_ifindex, .fc_gw4 = cfg->gw.ipv4, .fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, }; u32 tb_id = (cfg->dev ? l3mdev_fib_table(cfg->dev) : RT_TABLE_MAIN); int err; err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); if (err) { fib_nh_release(net, fib_nh); goto out; } if (nhi->fdb_nh) goto out; /* sets nh_dev if successful */ err = fib_check_nh(net, fib_nh, tb_id, 0, extack); if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1); } else { fib_nh_release(net, fib_nh); } out: return err; } static int nh_create_ipv6(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib6_nh *fib6_nh = &nhi->fib6_nh; struct fib6_config fib6_cfg = { .fc_table = l3mdev_fib_table(cfg->dev), .fc_ifindex = cfg->nh_ifindex, .fc_gateway = cfg->gw.ipv6, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, .fc_is_fdb = cfg->nh_fdb, }; int err; if (!ipv6_addr_any(&cfg->gw.ipv6)) fib6_cfg.fc_flags |= RTF_GATEWAY; /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); if (err) { /* IPv6 is not enabled, don't call fib6_nh_release */ if (err == -EAFNOSUPPORT) goto out; ipv6_stub->fib6_nh_release(fib6_nh); } else { nh->nh_flags = fib6_nh->fib_nh_flags; } out: return err; } static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; struct nexthop *nh; int err = 0; nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nhi = kzalloc(sizeof(*nhi), GFP_KERNEL); if (!nhi) { kfree(nh); return ERR_PTR(-ENOMEM); } nh->nh_flags = cfg->nh_flags; nh->net = net; nhi->nh_parent = nh; nhi->family = cfg->nh_family; nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; if (cfg->nh_fdb) nhi->fdb_nh = 1; if (cfg->nh_blackhole) { nhi->reject_nh = 1; cfg->nh_ifindex = net->loopback_dev->ifindex; } switch (cfg->nh_family) { case AF_INET: err = nh_create_ipv4(net, nh, nhi, cfg, extack); break; case AF_INET6: err = nh_create_ipv6(net, nh, nhi, cfg, extack); break; } if (err) { kfree(nhi); kfree(nh); return ERR_PTR(err); } /* add the entry to the device based hash */ if (!nhi->fdb_nh) nexthop_devhash_add(net, nhi); rcu_assign_pointer(nh->nh_info, nhi); return nh; } /* called with rtnl lock held */ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nexthop *nh; int err; if (!cfg->nh_id) { cfg->nh_id = nh_find_unused_id(net); if (!cfg->nh_id) { NL_SET_ERR_MSG(extack, "No unused id"); return ERR_PTR(-EINVAL); } } if (cfg->nh_grp) nh = nexthop_create_group(net, cfg); else nh = nexthop_create(net, cfg, extack); if (IS_ERR(nh)) return nh; refcount_set(&nh->refcnt, 1); nh->id = cfg->nh_id; nh->protocol = cfg->nh_protocol; nh->net = net; err = insert_nexthop(net, nh, cfg, extack); if (err) { __remove_nexthop(net, nh, NULL); nexthop_put(nh); nh = ERR_PTR(err); } return nh; } static int rtm_nh_get_timer(struct nlattr *attr, unsigned long fallback, unsigned long *timer_p, bool *has_p, struct netlink_ext_ack *extack) { unsigned long timer; u32 value; if (!attr) { *timer_p = fallback; *has_p = false; return 0; } value = nla_get_u32(attr); timer = clock_t_to_jiffies(value); if (timer == ~0UL) { NL_SET_ERR_MSG(extack, "Timer value too large"); return -EINVAL; } *timer_p = timer; *has_p = true; return 0; } static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_policy_new)] = {}; int err; if (res) { err = nla_parse_nested(tb, ARRAY_SIZE(rtm_nh_res_policy_new) - 1, res, rtm_nh_res_policy_new, extack); if (err < 0) return err; } if (tb[NHA_RES_GROUP_BUCKETS]) { cfg->nh_grp_res_num_buckets = nla_get_u16(tb[NHA_RES_GROUP_BUCKETS]); cfg->nh_grp_res_has_num_buckets = true; if (!cfg->nh_grp_res_num_buckets) { NL_SET_ERR_MSG(extack, "Number of buckets needs to be non-0"); return -EINVAL; } } err = rtm_nh_get_timer(tb[NHA_RES_GROUP_IDLE_TIMER], NH_RES_DEFAULT_IDLE_TIMER, &cfg->nh_grp_res_idle_timer, &cfg->nh_grp_res_has_idle_timer, extack); if (err) return err; return rtm_nh_get_timer(tb[NHA_RES_GROUP_UNBALANCED_TIMER], NH_RES_DEFAULT_UNBALANCED_TIMER, &cfg->nh_grp_res_unbalanced_timer, &cfg->nh_grp_res_has_unbalanced_timer, extack); } static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **tb, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); int err; err = -EINVAL; if (nhm->resvd || nhm->nh_scope) { NL_SET_ERR_MSG(extack, "Invalid values in ancillary header"); goto out; } if (nhm->nh_flags & ~NEXTHOP_VALID_USER_FLAGS) { NL_SET_ERR_MSG(extack, "Invalid nexthop flags in ancillary header"); goto out; } switch (nhm->nh_family) { case AF_INET: case AF_INET6: break; case AF_UNSPEC: if (tb[NHA_GROUP]) break; fallthrough; default: NL_SET_ERR_MSG(extack, "Invalid address family"); goto out; } memset(cfg, 0, sizeof(*cfg)); cfg->nlflags = nlh->nlmsg_flags; cfg->nlinfo.portid = NETLINK_CB(skb).portid; cfg->nlinfo.nlh = nlh; cfg->nlinfo.nl_net = net; cfg->nh_family = nhm->nh_family; cfg->nh_protocol = nhm->nh_protocol; cfg->nh_flags = nhm->nh_flags; if (tb[NHA_ID]) cfg->nh_id = nla_get_u32(tb[NHA_ID]); if (tb[NHA_FDB]) { if (tb[NHA_OIF] || tb[NHA_BLACKHOLE] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "Fdb attribute can not be used with encap, oif or blackhole"); goto out; } if (nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Unsupported nexthop flags in ancillary header"); goto out; } cfg->nh_fdb = nla_get_flag(tb[NHA_FDB]); } if (tb[NHA_GROUP]) { if (nhm->nh_family != AF_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid family for group"); goto out; } cfg->nh_grp = tb[NHA_GROUP]; cfg->nh_grp_type = NEXTHOP_GRP_TYPE_MPATH; if (tb[NHA_GROUP_TYPE]) cfg->nh_grp_type = nla_get_u16(tb[NHA_GROUP_TYPE]); if (cfg->nh_grp_type > NEXTHOP_GRP_TYPE_MAX) { NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } err = nh_check_attr_group(net, tb, ARRAY_SIZE(rtm_nh_policy_new), cfg->nh_grp_type, extack); if (err) goto out; if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); if (tb[NHA_HW_STATS_ENABLE]) cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); /* no other attributes should be set */ goto out; } if (tb[NHA_BLACKHOLE]) { if (tb[NHA_GATEWAY] || tb[NHA_OIF] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE] || tb[NHA_FDB]) { NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway, oif, encap or fdb"); goto out; } cfg->nh_blackhole = 1; err = 0; goto out; } if (!cfg->nh_fdb && !tb[NHA_OIF]) { NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole and non-fdb nexthops"); goto out; } err = -EINVAL; if (tb[NHA_GATEWAY]) { struct nlattr *gwa = tb[NHA_GATEWAY]; switch (cfg->nh_family) { case AF_INET: if (nla_len(gwa) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv4 = nla_get_be32(gwa); break; case AF_INET6: if (nla_len(gwa) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv6 = nla_get_in6_addr(gwa); break; default: NL_SET_ERR_MSG(extack, "Unknown address family for gateway"); goto out; } } else { /* device only nexthop (no gateway) */ if (cfg->nh_flags & RTNH_F_ONLINK) { NL_SET_ERR_MSG(extack, "ONLINK flag can not be set for nexthop without a gateway"); goto out; } } if (tb[NHA_ENCAP]) { cfg->nh_encap = tb[NHA_ENCAP]; if (!tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation type is missing"); goto out; } cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack); if (err < 0) goto out; } else if (tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation attribute is missing"); goto out; } if (tb[NHA_HW_STATS_ENABLE]) { NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); goto out; } err = 0; out: return err; } static int rtm_to_nh_config_rtnl(struct net *net, struct nlattr **tb, struct nh_config *cfg, struct netlink_ext_ack *extack) { if (tb[NHA_GROUP]) return nh_check_attr_group_rtnl(net, tb, extack); if (tb[NHA_OIF]) { cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); if (cfg->nh_ifindex) cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); if (!cfg->dev) { NL_SET_ERR_MSG(extack, "Invalid device index"); return -EINVAL; } if (!(cfg->dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); return -ENETDOWN; } if (!netif_carrier_ok(cfg->dev)) { NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); return -ENETDOWN; } } return 0; } /* rtnl */ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; struct net *net = sock_net(skb->sk); struct nh_config cfg; struct nexthop *nh; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_new) - 1, rtm_nh_policy_new, extack); if (err < 0) goto out; err = rtm_to_nh_config(net, skb, nlh, tb, &cfg, extack); if (err) goto out; if (cfg.nlflags & NLM_F_REPLACE && !cfg.nh_id) { NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); err = -EINVAL; goto out; } rtnl_net_lock(net); err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack); if (err) goto unlock; nh = nexthop_add(net, &cfg, extack); if (IS_ERR(nh)) err = PTR_ERR(nh); unlock: rtnl_net_unlock(net); out: return err; } static int nh_valid_get_del_req(const struct nlmsghdr *nlh, struct nlattr **tb, u32 *id, u32 *op_flags, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header"); return -EINVAL; } if (!tb[NHA_ID]) { NL_SET_ERR_MSG(extack, "Nexthop id is missing"); return -EINVAL; } *id = nla_get_u32(tb[NHA_ID]); if (!(*id)) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } if (op_flags) *op_flags = nla_get_u32_default(tb[NHA_OP_FLAGS], 0); return 0; } /* rtnl */ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_del)]; struct net *net = sock_net(skb->sk); struct nl_info nlinfo = { .nlh = nlh, .nl_net = net, .portid = NETLINK_CB(skb).portid, }; struct nexthop *nh; int err; u32 id; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_del) - 1, rtm_nh_policy_del, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, &id, NULL, extack); if (err) return err; rtnl_net_lock(net); nh = nexthop_find_by_id(net, id); if (nh) remove_nexthop(net, nh, &nlinfo); else err = -ENOENT; rtnl_net_unlock(net); return err; } /* rtnl */ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; struct net *net = sock_net(in_skb->sk); struct sk_buff *skb = NULL; struct nexthop *nh; u32 op_flags; int err; u32 id; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_get) - 1, rtm_nh_policy_get, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; err = -ENOBUFS; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto out; err = -ENOENT; nh = nexthop_find_by_id(net, id); if (!nh) goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); out: return err; errout_free: kfree_skb(skb); goto out; } struct nh_dump_filter { u32 nh_id; int dev_idx; int master_idx; bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, struct nh_dump_filter *filter, u8 family) { const struct net_device *dev; const struct nh_info *nhi; if (filter->group_filter && !nh->is_group) return true; if (!filter->dev_idx && !filter->master_idx && !family) return false; if (nh->is_group) return true; nhi = rtnl_dereference(nh->nh_info); if (family && nhi->family != family) return true; dev = nhi->fib_nhc.nhc_dev; if (filter->dev_idx && (!dev || dev->ifindex != filter->dev_idx)) return true; if (filter->master_idx) { struct net_device *master; if (!dev) return true; master = netdev_master_upper_dev_get((struct net_device *)dev); if (!master || master->ifindex != filter->master_idx) return true; } return false; } static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, struct nh_dump_filter *filter, struct netlink_ext_ack *extack) { struct nhmsg *nhm; u32 idx; if (tb[NHA_OIF]) { idx = nla_get_u32(tb[NHA_OIF]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid device index"); return -EINVAL; } filter->dev_idx = idx; } if (tb[NHA_MASTER]) { idx = nla_get_u32(tb[NHA_MASTER]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid master device index"); return -EINVAL; } filter->master_idx = idx; } filter->group_filter = nla_get_flag(tb[NHA_GROUPS]); filter->fdb_filter = nla_get_flag(tb[NHA_FDB]); nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for nexthop dump request"); return -EINVAL; } return 0; } static int nh_valid_dump_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_dump) - 1, rtm_nh_policy_dump, cb->extack); if (err < 0) return err; filter->op_flags = nla_get_u32_default(tb[NHA_OP_FLAGS], 0); return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } struct rtm_dump_nh_ctx { u32 idx; }; static struct rtm_dump_nh_ctx * rtm_dump_nh_ctx(struct netlink_callback *cb) { struct rtm_dump_nh_ctx *ctx = (void *)cb->ctx; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); return ctx; } static int rtm_dump_walk_nexthops(struct sk_buff *skb, struct netlink_callback *cb, struct rb_root *root, struct rtm_dump_nh_ctx *ctx, int (*nh_cb)(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data), void *data) { struct rb_node *node; int s_idx; int err; s_idx = ctx->idx; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); if (nh->id < s_idx) continue; ctx->idx = nh->id; err = nh_cb(skb, cb, nh, data); if (err) return err; } return 0; } static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data) { struct nhmsg *nhm = nlmsg_data(cb->nlh); struct nh_dump_filter *filter = data; if (nh_dump_filtered(nh, filter, nhm->nh_family)) return 0; return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) { struct rtm_dump_nh_ctx *ctx = rtm_dump_nh_ctx(cb); struct net *net = sock_net(skb->sk); struct rb_root *root = &net->nexthop.rb_root; struct nh_dump_filter filter = {}; int err; err = nh_valid_dump_req(cb->nlh, &filter, cb); if (err < 0) return err; err = rtm_dump_walk_nexthops(skb, cb, root, ctx, &rtm_dump_nexthop_cb, &filter); cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } static struct nexthop * nexthop_find_group_resilient(struct net *net, u32 id, struct netlink_ext_ack *extack) { struct nh_group *nhg; struct nexthop *nh; nh = nexthop_find_by_id(net, id); if (!nh) return ERR_PTR(-ENOENT); if (!nh->is_group) { NL_SET_ERR_MSG(extack, "Not a nexthop group"); return ERR_PTR(-EINVAL); } nhg = rtnl_dereference(nh->nh_grp); if (!nhg->resilient) { NL_SET_ERR_MSG(extack, "Nexthop group not of type resilient"); return ERR_PTR(-EINVAL); } return nh; } static int nh_valid_dump_nhid(struct nlattr *attr, u32 *nh_id_p, struct netlink_ext_ack *extack) { u32 idx; if (attr) { idx = nla_get_u32(attr); if (!idx) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } *nh_id_p = idx; } else { *nh_id_p = 0; } return 0; } static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { struct nlattr *res_tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_dump)]; struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump_bucket)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_dump_bucket) - 1, rtm_nh_policy_dump_bucket, NULL); if (err < 0) return err; err = nh_valid_dump_nhid(tb[NHA_ID], &filter->nh_id, cb->extack); if (err) return err; if (tb[NHA_RES_BUCKET]) { size_t max = ARRAY_SIZE(rtm_nh_res_bucket_policy_dump) - 1; err = nla_parse_nested(res_tb, max, tb[NHA_RES_BUCKET], rtm_nh_res_bucket_policy_dump, cb->extack); if (err < 0) return err; err = nh_valid_dump_nhid(res_tb[NHA_RES_BUCKET_NH_ID], &filter->res_bucket_nh_id, cb->extack); if (err) return err; } return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } struct rtm_dump_res_bucket_ctx { struct rtm_dump_nh_ctx nh; u16 bucket_index; }; static struct rtm_dump_res_bucket_ctx * rtm_dump_res_bucket_ctx(struct netlink_callback *cb) { struct rtm_dump_res_bucket_ctx *ctx = (void *)cb->ctx; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); return ctx; } struct rtm_dump_nexthop_bucket_data { struct rtm_dump_res_bucket_ctx *ctx; struct nh_dump_filter filter; }; static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, struct rtm_dump_nexthop_bucket_data *dd) { u32 portid = NETLINK_CB(cb->skb).portid; struct nhmsg *nhm = nlmsg_data(cb->nlh); struct nh_res_table *res_table; struct nh_group *nhg; u16 bucket_index; int err; nhg = rtnl_dereference(nh->nh_grp); res_table = rtnl_dereference(nhg->res_table); for (bucket_index = dd->ctx->bucket_index; bucket_index < res_table->num_nh_buckets; bucket_index++) { struct nh_res_bucket *bucket; struct nh_grp_entry *nhge; bucket = &res_table->nh_buckets[bucket_index]; nhge = rtnl_dereference(bucket->nh_entry); if (nh_dump_filtered(nhge->nh, &dd->filter, nhm->nh_family)) continue; if (dd->filter.res_bucket_nh_id && dd->filter.res_bucket_nh_id != nhge->nh->id) continue; dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); if (err) return err; } dd->ctx->bucket_index = 0; return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data) { struct rtm_dump_nexthop_bucket_data *dd = data; struct nh_group *nhg; if (!nh->is_group) return 0; nhg = rtnl_dereference(nh->nh_grp); if (!nhg->resilient) return 0; return rtm_dump_nexthop_bucket_nh(skb, cb, nh, dd); } /* rtnl */ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, struct netlink_callback *cb) { struct rtm_dump_res_bucket_ctx *ctx = rtm_dump_res_bucket_ctx(cb); struct rtm_dump_nexthop_bucket_data dd = { .ctx = ctx }; struct net *net = sock_net(skb->sk); struct nexthop *nh; int err; err = nh_valid_dump_bucket_req(cb->nlh, &dd.filter, cb); if (err) return err; if (dd.filter.nh_id) { nh = nexthop_find_group_resilient(net, dd.filter.nh_id, cb->extack); if (IS_ERR(nh)) return PTR_ERR(nh); err = rtm_dump_nexthop_bucket_nh(skb, cb, nh, &dd); } else { struct rb_root *root = &net->nexthop.rb_root; err = rtm_dump_walk_nexthops(skb, cb, root, &ctx->nh, &rtm_dump_nexthop_bucket_cb, &dd); } cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } static int nh_valid_get_bucket_req_res_bucket(struct nlattr *res, u16 *bucket_index, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_get)]; int err; err = nla_parse_nested(tb, ARRAY_SIZE(rtm_nh_res_bucket_policy_get) - 1, res, rtm_nh_res_bucket_policy_get, extack); if (err < 0) return err; if (!tb[NHA_RES_BUCKET_INDEX]) { NL_SET_ERR_MSG(extack, "Bucket index is missing"); return -EINVAL; } *bucket_index = nla_get_u16(tb[NHA_RES_BUCKET_INDEX]); return 0; } static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, u32 *id, u16 *bucket_index, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get_bucket)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_get_bucket) - 1, rtm_nh_policy_get_bucket, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, id, NULL, extack); if (err) return err; if (!tb[NHA_RES_BUCKET]) { NL_SET_ERR_MSG(extack, "Bucket information is missing"); return -EINVAL; } err = nh_valid_get_bucket_req_res_bucket(tb[NHA_RES_BUCKET], bucket_index, extack); if (err) return err; return 0; } /* rtnl */ static int rtm_get_nexthop_bucket(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nh_res_table *res_table; struct sk_buff *skb = NULL; struct nh_group *nhg; struct nexthop *nh; u16 bucket_index; int err; u32 id; err = nh_valid_get_bucket_req(nlh, &id, &bucket_index, extack); if (err) return err; nh = nexthop_find_group_resilient(net, id, extack); if (IS_ERR(nh)) return PTR_ERR(nh); nhg = rtnl_dereference(nh->nh_grp); res_table = rtnl_dereference(nhg->res_table); if (bucket_index >= res_table->num_nh_buckets) { NL_SET_ERR_MSG(extack, "Bucket index out of bounds"); return -ENOENT; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; err = nh_fill_res_bucket(skb, nh, &res_table->nh_buckets[bucket_index], bucket_index, RTM_NEWNEXTHOPBUCKET, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, extack); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; } return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: kfree_skb(skb); return err; } static void nexthop_sync_mtu(struct net_device *dev, u32 orig_mtu) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev == dev) { if (nhi->family == AF_INET) fib_nhc_update_mtu(&nhi->fib_nhc, dev->mtu, orig_mtu); } } } /* rtnl */ static int nh_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_info_ext *info_ext; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: if (!(netif_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: info_ext = ptr; nexthop_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(dev_net(dev)); break; } return NOTIFY_DONE; } static struct notifier_block nh_netdev_notifier = { .notifier_call = nh_netdev_event, }; static int nexthops_dump(struct net *net, struct notifier_block *nb, enum nexthop_event_type event_type, struct netlink_ext_ack *extack) { struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; int err = 0; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); err = call_nexthop_notifier(nb, net, event_type, nh, extack); if (err) break; } return err; } int register_nexthop_notifier(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; rtnl_lock(); err = nexthops_dump(net, nb, NEXTHOP_EVENT_REPLACE, extack); if (err) goto unlock; err = blocking_notifier_chain_register(&net->nexthop.notifier_chain, nb); unlock: rtnl_unlock(); return err; } EXPORT_SYMBOL(register_nexthop_notifier); int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; err = blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, nb); if (!err) nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); return err; } EXPORT_SYMBOL(__unregister_nexthop_notifier); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __unregister_nexthop_notifier(net, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_nexthop_notifier); void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap) { struct nexthop *nexthop; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop) goto out; nexthop->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); if (offload) nexthop->nh_flags |= RTNH_F_OFFLOAD; if (trap) nexthop->nh_flags |= RTNH_F_TRAP; out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_set_hw_flags); void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap) { struct nh_res_table *res_table; struct nh_res_bucket *bucket; struct nexthop *nexthop; struct nh_group *nhg; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop || !nexthop->is_group) goto out; nhg = rcu_dereference(nexthop->nh_grp); if (!nhg->resilient) goto out; if (bucket_index >= nhg->res_table->num_nh_buckets) goto out; res_table = rcu_dereference(nhg->res_table); bucket = &res_table->nh_buckets[bucket_index]; bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); if (offload) bucket->nh_flags |= RTNH_F_OFFLOAD; if (trap) bucket->nh_flags |= RTNH_F_TRAP; out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_bucket_set_hw_flags); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity) { struct nh_res_table *res_table; struct nexthop *nexthop; struct nh_group *nhg; u16 i; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop || !nexthop->is_group) goto out; nhg = rcu_dereference(nexthop->nh_grp); if (!nhg->resilient) goto out; /* Instead of silently ignoring some buckets, demand that the sizes * be the same. */ res_table = rcu_dereference(nhg->res_table); if (num_buckets != res_table->num_nh_buckets) goto out; for (i = 0; i < num_buckets; i++) { if (test_bit(i, activity)) nh_res_bucket_set_busy(&res_table->nh_buckets[i]); } out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_res_grp_activity_update); static void __net_exit nexthop_net_exit_rtnl(struct net *net, struct list_head *dev_to_kill) { ASSERT_RTNL_NET(net); flush_all_nexthops(net); } static void __net_exit nexthop_net_exit(struct net *net) { kfree(net->nexthop.devhash); net->nexthop.devhash = NULL; } static int __net_init nexthop_net_init(struct net *net) { size_t sz = sizeof(struct hlist_head) * NH_DEV_HASHSIZE; net->nexthop.rb_root = RB_ROOT; net->nexthop.devhash = kzalloc(sz, GFP_KERNEL); if (!net->nexthop.devhash) return -ENOMEM; BLOCKING_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain); return 0; } static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, .exit = nexthop_net_exit, .exit_rtnl = nexthop_net_exit_rtnl, }; static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop, .dumpit = rtm_dump_nexthop}, {.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket, .dumpit = rtm_dump_nexthop_bucket}, {.protocol = PF_INET, .msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, {.protocol = PF_INET6, .msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET6, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, }; static int __init nexthop_init(void) { register_pernet_subsys(&nexthop_net_ops); register_netdevice_notifier(&nh_netdev_notifier); rtnl_register_many(nexthop_rtnl_msg_handlers); return 0; } subsys_initcall(nexthop_init); |
| 94 94 889 450 193 80 467 928 918 193 80 936 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/cmpxchg.h * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_CMPXCHG_H #define __ASM_CMPXCHG_H #include <linux/build_bug.h> #include <linux/compiler.h> #include <asm/barrier.h> #include <asm/lse.h> /* * We need separate acquire parameters for ll/sc and lse, since the full * barrier case is generated as release+dmb for the former and * acquire+release for the latter. */ #define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl) \ static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr) \ { \ u##sz ret; \ unsigned long tmp; \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr" #sfx "\t%" #w "0, %2\n" \ " st" #rel "xr" #sfx "\t%w1, %" #w "3, %2\n" \ " cbnz %w1, 1b\n" \ " " #mb, \ /* LSE atomics */ \ " swp" #acq_lse #rel #sfx "\t%" #w "3, %" #w "0, %2\n" \ __nops(3) \ " " #nop_lse) \ : "=&r" (ret), "=&r" (tmp), "+Q" (*(u##sz *)ptr) \ : "r" (x) \ : cl); \ \ return ret; \ } __XCHG_CASE(w, b, , 8, , , , , , ) __XCHG_CASE(w, h, , 16, , , , , , ) __XCHG_CASE(w, , , 32, , , , , , ) __XCHG_CASE( , , , 64, , , , , , ) __XCHG_CASE(w, b, acq_, 8, , , a, a, , "memory") __XCHG_CASE(w, h, acq_, 16, , , a, a, , "memory") __XCHG_CASE(w, , acq_, 32, , , a, a, , "memory") __XCHG_CASE( , , acq_, 64, , , a, a, , "memory") __XCHG_CASE(w, b, rel_, 8, , , , , l, "memory") __XCHG_CASE(w, h, rel_, 16, , , , , l, "memory") __XCHG_CASE(w, , rel_, 32, , , , , l, "memory") __XCHG_CASE( , , rel_, 64, , , , , l, "memory") __XCHG_CASE(w, b, mb_, 8, dmb ish, nop, , a, l, "memory") __XCHG_CASE(w, h, mb_, 16, dmb ish, nop, , a, l, "memory") __XCHG_CASE(w, , mb_, 32, dmb ish, nop, , a, l, "memory") __XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE #define __XCHG_GEN(sfx) \ static __always_inline unsigned long \ __arch_xchg##sfx(unsigned long x, volatile void *ptr, int size) \ { \ switch (size) { \ case 1: \ return __xchg_case##sfx##_8(x, ptr); \ case 2: \ return __xchg_case##sfx##_16(x, ptr); \ case 4: \ return __xchg_case##sfx##_32(x, ptr); \ case 8: \ return __xchg_case##sfx##_64(x, ptr); \ default: \ BUILD_BUG(); \ } \ \ unreachable(); \ } __XCHG_GEN() __XCHG_GEN(_acq) __XCHG_GEN(_rel) __XCHG_GEN(_mb) #undef __XCHG_GEN #define __xchg_wrapper(sfx, ptr, x) \ ({ \ __typeof__(*(ptr)) __ret; \ __ret = (__typeof__(*(ptr))) \ __arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \ __ret; \ }) /* xchg */ #define arch_xchg_relaxed(...) __xchg_wrapper( , __VA_ARGS__) #define arch_xchg_acquire(...) __xchg_wrapper(_acq, __VA_ARGS__) #define arch_xchg_release(...) __xchg_wrapper(_rel, __VA_ARGS__) #define arch_xchg(...) __xchg_wrapper( _mb, __VA_ARGS__) #define __CMPXCHG_CASE(name, sz) \ static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ u##sz old, \ u##sz new) \ { \ return __lse_ll_sc_body(_cmpxchg_case_##name##sz, \ ptr, old, new); \ } __CMPXCHG_CASE( , 8) __CMPXCHG_CASE( , 16) __CMPXCHG_CASE( , 32) __CMPXCHG_CASE( , 64) __CMPXCHG_CASE(acq_, 8) __CMPXCHG_CASE(acq_, 16) __CMPXCHG_CASE(acq_, 32) __CMPXCHG_CASE(acq_, 64) __CMPXCHG_CASE(rel_, 8) __CMPXCHG_CASE(rel_, 16) __CMPXCHG_CASE(rel_, 32) __CMPXCHG_CASE(rel_, 64) __CMPXCHG_CASE(mb_, 8) __CMPXCHG_CASE(mb_, 16) __CMPXCHG_CASE(mb_, 32) __CMPXCHG_CASE(mb_, 64) #undef __CMPXCHG_CASE #define __CMPXCHG128(name) \ static inline u128 __cmpxchg128##name(volatile u128 *ptr, \ u128 old, u128 new) \ { \ return __lse_ll_sc_body(_cmpxchg128##name, \ ptr, old, new); \ } __CMPXCHG128( ) __CMPXCHG128(_mb) #undef __CMPXCHG128 #define __CMPXCHG_GEN(sfx) \ static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ unsigned long old, \ unsigned long new, \ int size) \ { \ switch (size) { \ case 1: \ return __cmpxchg_case##sfx##_8(ptr, old, new); \ case 2: \ return __cmpxchg_case##sfx##_16(ptr, old, new); \ case 4: \ return __cmpxchg_case##sfx##_32(ptr, old, new); \ case 8: \ return __cmpxchg_case##sfx##_64(ptr, old, new); \ default: \ BUILD_BUG(); \ } \ \ unreachable(); \ } __CMPXCHG_GEN() __CMPXCHG_GEN(_acq) __CMPXCHG_GEN(_rel) __CMPXCHG_GEN(_mb) #undef __CMPXCHG_GEN #define __cmpxchg_wrapper(sfx, ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ __ret = (__typeof__(*(ptr))) \ __cmpxchg##sfx((ptr), (unsigned long)(o), \ (unsigned long)(n), sizeof(*(ptr))); \ __ret; \ }) /* cmpxchg */ #define arch_cmpxchg_relaxed(...) __cmpxchg_wrapper( , __VA_ARGS__) #define arch_cmpxchg_acquire(...) __cmpxchg_wrapper(_acq, __VA_ARGS__) #define arch_cmpxchg_release(...) __cmpxchg_wrapper(_rel, __VA_ARGS__) #define arch_cmpxchg(...) __cmpxchg_wrapper( _mb, __VA_ARGS__) #define arch_cmpxchg_local arch_cmpxchg_relaxed /* cmpxchg64 */ #define arch_cmpxchg64_relaxed arch_cmpxchg_relaxed #define arch_cmpxchg64_acquire arch_cmpxchg_acquire #define arch_cmpxchg64_release arch_cmpxchg_release #define arch_cmpxchg64 arch_cmpxchg #define arch_cmpxchg64_local arch_cmpxchg_local /* cmpxchg128 */ #define system_has_cmpxchg128() 1 #define arch_cmpxchg128(ptr, o, n) \ ({ \ __cmpxchg128_mb((ptr), (o), (n)); \ }) #define arch_cmpxchg128_local(ptr, o, n) \ ({ \ __cmpxchg128((ptr), (o), (n)); \ }) #define __CMPWAIT_CASE(w, sfx, sz) \ static inline void __cmpwait_case_##sz(volatile void *ptr, \ unsigned long val) \ { \ unsigned long tmp; \ \ asm volatile( \ " sevl\n" \ " wfe\n" \ " ldxr" #sfx "\t%" #w "[tmp], %[v]\n" \ " eor %" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ " cbnz %" #w "[tmp], 1f\n" \ " wfe\n" \ "1:" \ : [tmp] "=&r" (tmp), [v] "+Q" (*(u##sz *)ptr) \ : [val] "r" (val)); \ } __CMPWAIT_CASE(w, b, 8); __CMPWAIT_CASE(w, h, 16); __CMPWAIT_CASE(w, , 32); __CMPWAIT_CASE( , , 64); #undef __CMPWAIT_CASE #define __CMPWAIT_GEN(sfx) \ static __always_inline void __cmpwait##sfx(volatile void *ptr, \ unsigned long val, \ int size) \ { \ switch (size) { \ case 1: \ return __cmpwait_case##sfx##_8(ptr, (u8)val); \ case 2: \ return __cmpwait_case##sfx##_16(ptr, (u16)val); \ case 4: \ return __cmpwait_case##sfx##_32(ptr, val); \ case 8: \ return __cmpwait_case##sfx##_64(ptr, val); \ default: \ BUILD_BUG(); \ } \ \ unreachable(); \ } __CMPWAIT_GEN() #undef __CMPWAIT_GEN #define __cmpwait_relaxed(ptr, val) \ __cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr))) #endif /* __ASM_CMPXCHG_H */ |
| 34 1160 1157 212 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_FP_H #define __ASM_FP_H #include <asm/errno.h> #include <asm/percpu.h> #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/sigcontext.h> #include <asm/sysreg.h> #ifndef __ASSEMBLY__ #include <linux/bitmap.h> #include <linux/build_bug.h> #include <linux/bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> #include <linux/types.h> /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 /* * The VFP state has 32x64-bit registers and a single 32-bit * control/status register. */ #define VFP_STATE_SIZE ((32 * 8) + 4) static inline unsigned long cpacr_save_enable_kernel_sve(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline unsigned long cpacr_save_enable_kernel_sme(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_SMEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline void cpacr_restore(unsigned long cpacr) { write_sysreg(cpacr, cpacr_el1); isb(); } /* * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future * expansion bits in ZCR rather than those just currently defined by * the architecture. Using this length to allocate worst size buffers * results in excessively large allocations, and this effect is even * more pronounced for SME due to ZA. Define more suitable VLs for * these situations. */ #define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1) #define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1) struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); extern void fpsimd_load_state(struct user_fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); struct cpu_fp_state { struct user_fpsimd_state *st; void *sve_state; void *sme_state; u64 *svcr; u64 *fpmr; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; enum fp_type to_save; }; DECLARE_PER_CPU(struct cpu_fp_state, fpsimd_last_state); extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_current_state(void); extern void fpsimd_save_and_flush_cpu_state(void); static inline bool thread_sm_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_SM_MASK); } static inline bool thread_za_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK); } extern void task_smstop_sm(struct task_struct *task); /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 /* Offset of FFR in the SVE register dump */ static inline size_t sve_ffr_offset(int vl) { return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET; } static inline void *sve_pffr(struct thread_struct *thread) { unsigned int vl; if (system_supports_sme() && thread_sm_enabled(thread)) vl = thread_get_sme_vl(thread); else vl = thread_get_sve_vl(thread); return (char *)thread->sve_state + sve_ffr_offset(vl); } static inline void *thread_zt_state(struct thread_struct *thread) { /* The ZT register state is stored immediately after the ZA state */ unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread)); return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); extern void sve_load_state(void const *state, u32 const *pfpsr, int restore_ffr); extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); extern void sme_set_vq(unsigned long vq_minus_1); extern void sme_save_state(void *state, int zt); extern void sme_load_state(void const *state, int zt); struct arm64_cpu_capabilities; extern void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and * vice versa). This allows find_next_bit() to be used to find the * _maximum_ VQ not exceeding a certain value. */ static inline unsigned int __vq_to_bit(unsigned int vq) { return SVE_VQ_MAX - vq; } static inline unsigned int __bit_to_vq(unsigned int bit) { return SVE_VQ_MAX - bit; } struct vl_info { enum vec_type type; const char *name; /* For display purposes */ /* Minimum supported vector length across all CPUs */ int min_vl; /* Maximum supported vector length across all CPUs */ int max_vl; int max_virtualisable_vl; /* * Set of available vector lengths, * where length vq encoded as bit __vq_to_bit(vq): */ DECLARE_BITMAP(vq_map, SVE_VQ_MAX); /* Set of vector lengths present on at least one cpu: */ DECLARE_BITMAP(vq_partial_map, SVE_VQ_MAX); }; #ifdef CONFIG_ARM64_SVE extern void sve_alloc(struct task_struct *task, bool flush); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_from_effective_state(struct task_struct *task); extern void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task); extern int vec_set_vector_length(struct task_struct *task, enum vec_type type, unsigned long vl, unsigned long flags); extern int sve_set_current_vl(unsigned long arg); extern int sve_get_current_vl(void); static inline void sve_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0); } static inline void sve_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN); } #define sve_cond_update_zcr_vq(val, reg) \ do { \ u64 __zcr = read_sysreg_s((reg)); \ u64 __new = __zcr & ~ZCR_ELx_LEN_MASK; \ __new |= (val) & ZCR_ELx_LEN_MASK; \ if (__zcr != __new) \ write_sysreg_s(__new, (reg)); \ } while (0) /* * Probing and setup functions. * Calls to these functions must be serialised with one another. */ enum vec_type; extern void __init vec_init_vq_map(enum vec_type type); extern void vec_update_vq_map(enum vec_type type); extern int vec_verify_vq_map(enum vec_type type); extern void __init sve_setup(void); extern __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX]; static inline void write_vl(enum vec_type type, u64 val) { u64 tmp; switch (type) { #ifdef CONFIG_ARM64_SVE case ARM64_VEC_SVE: tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif #ifdef CONFIG_ARM64_SME case ARM64_VEC_SME: tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_SMCR_EL1); break; #endif default: WARN_ON_ONCE(1); break; } } static inline int vec_max_vl(enum vec_type type) { return vl_info[type].max_vl; } static inline int vec_max_virtualisable_vl(enum vec_type type) { return vl_info[type].max_virtualisable_vl; } static inline int sve_max_vl(void) { return vec_max_vl(ARM64_VEC_SVE); } static inline int sve_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SVE); } /* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */ static inline bool vq_available(enum vec_type type, unsigned int vq) { return test_bit(__vq_to_bit(vq), vl_info[type].vq_map); } static inline bool sve_vq_available(unsigned int vq) { return vq_available(ARM64_VEC_SVE, vq); } static inline size_t __sve_state_size(unsigned int sve_vl, unsigned int sme_vl) { unsigned int vl = max(sve_vl, sme_vl); return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)); } /* * Return how many bytes of memory are required to store the full SVE * state for task, given task's currently configured vector length. */ static inline size_t sve_state_size(struct task_struct const *task) { unsigned int sve_vl = task_get_sve_vl(task); unsigned int sme_vl = task_get_sme_vl(task); return __sve_state_size(sve_vl, sme_vl); } #else /* ! CONFIG_ARM64_SVE */ static inline void sve_alloc(struct task_struct *task, bool flush) { } static inline void fpsimd_release_task(struct task_struct *task) { } static inline void fpsimd_sync_from_effective_state(struct task_struct *task) { } static inline void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task) { } static inline int sve_max_virtualisable_vl(void) { return 0; } static inline int sve_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sve_get_current_vl(void) { return -EINVAL; } static inline int sve_max_vl(void) { return -EINVAL; } static inline bool sve_vq_available(unsigned int vq) { return false; } static inline void sve_user_disable(void) { BUILD_BUG(); } static inline void sve_user_enable(void) { BUILD_BUG(); } #define sve_cond_update_zcr_vq(val, reg) do { } while (0) static inline void vec_init_vq_map(enum vec_type t) { } static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } static inline size_t __sve_state_size(unsigned int sve_vl, unsigned int sme_vl) { return 0; } static inline size_t sve_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static inline void sme_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); } static inline void sme_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); } static inline void sme_smstart_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); } static inline void sme_smstop_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); } static inline void sme_smstop(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); } extern void __init sme_setup(void); static inline int sme_max_vl(void) { return vec_max_vl(ARM64_VEC_SME); } static inline int sme_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SME); } extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); extern void sme_suspend_exit(void); static inline size_t __sme_state_size(unsigned int sme_vl) { size_t size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(sme_vl)); if (system_supports_sme2()) size += ZT_SIG_REG_SIZE; return size; } /* * Return how many bytes of memory are required to store the full SME * specific state for task, given task's currently configured vector * length. */ static inline size_t sme_state_size(struct task_struct const *task) { return __sme_state_size(task_get_sme_vl(task)); } #else static inline void sme_user_disable(void) { BUILD_BUG(); } static inline void sme_user_enable(void) { BUILD_BUG(); } static inline void sme_smstart_sm(void) { } static inline void sme_smstop_sm(void) { } static inline void sme_smstop(void) { } static inline void sme_alloc(struct task_struct *task, bool flush) { } static inline void sme_setup(void) { } static inline unsigned int sme_get_vl(void) { return 0; } static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } static inline void sme_suspend_exit(void) { } static inline size_t __sme_state_size(unsigned int sme_vl) { return 0; } static inline size_t sme_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SME */ /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); #endif #endif |
| 2 3 46 1 43 3 9 10 1 9 2 1 1 39 39 | 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; } |
| 11 5 404 191 404 404 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Access vector cache interface for object managers. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SELINUX_AVC_H_ #define _SELINUX_AVC_H_ #include <linux/stddef.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/kdev_t.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/audit.h> #include <linux/lsm_audit.h> #include <linux/in6.h> #include "flask.h" #include "av_permissions.h" #include "security.h" /* * An entry in the AVC. */ struct avc_entry; struct task_struct; struct inode; struct sock; struct sk_buff; /* * AVC statistics */ struct avc_cache_stats { unsigned int lookups; unsigned int misses; unsigned int allocations; unsigned int reclaims; unsigned int frees; }; /* * We only need this data after we have decided to send an audit message. */ struct selinux_audit_data { u32 ssid; u32 tsid; u16 tclass; u32 requested; u32 audited; u32 denied; int result; } __randomize_layout; /* * AVC operations */ void __init avc_init(void); static inline u32 avc_audit_required(u32 requested, struct av_decision *avd, int result, u32 auditdeny, u32 *deniedp) { u32 denied, audited; if (avd->flags & AVD_FLAGS_NEVERAUDIT) return 0; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; /* * auditdeny is TRICKY! Setting a bit in * this field means that ANY denials should NOT be audited if * the policy contains an explicit dontaudit rule for that * permission. Take notice that this is unrelated to the * actual permissions that were denied. As an example lets * assume: * * denied == READ * avd.auditdeny & ACCESS == 0 (not set means explicit rule) * auditdeny & ACCESS == 1 * * We will NOT audit the denial even though the denied * permission was READ and the auditdeny checks were for * ACCESS */ if (auditdeny && !(auditdeny & avd->auditdeny)) audited = 0; } else if (result) audited = denied = requested; else audited = requested & avd->auditallow; *deniedp = denied; return audited; } int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a); /** * avc_audit - Audit the granting or denial of permissions. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions * @avd: access vector decisions * @result: result from avc_has_perm_noaudit * @a: auxiliary audit data * * Audit the granting or denial of permissions in accordance * with the policy. This function is typically called by * avc_has_perm() after a permission check, but can also be * called directly by callers who use avc_has_perm_noaudit() * in order to separate the permission check from the auditing. * For example, this separation is useful when the permission check must * be performed under a lock, to allow the lock to be released * before calling the auditing code. */ static inline int avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, int result, struct common_audit_data *a) { u32 audited, denied; audited = avc_audit_required(requested, avd, result, 0, &denied); if (likely(!audited)) return 0; return slow_avc_audit(ssid, tsid, tclass, requested, audited, denied, result, a); } #define AVC_STRICT 1 /* Ignore permissive mode. */ #define AVC_EXTENDED_PERMS 2 /* update extended permissions */ int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned int flags, struct av_decision *avd); int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); #define AVC_EXT_IOCTL (1 << 0) /* Cache entry for an ioctl extended permission */ #define AVC_EXT_NLMSG (1 << 1) /* Cache entry for an nlmsg extended permission */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 base_perm, u8 perm, struct common_audit_data *ad); u32 avc_policy_seqno(void); #define AVC_CALLBACK_GRANT 1 #define AVC_CALLBACK_TRY_REVOKE 2 #define AVC_CALLBACK_REVOKE 4 #define AVC_CALLBACK_RESET 8 #define AVC_CALLBACK_AUDITALLOW_ENABLE 16 #define AVC_CALLBACK_AUDITALLOW_DISABLE 32 #define AVC_CALLBACK_AUDITDENY_ENABLE 64 #define AVC_CALLBACK_AUDITDENY_DISABLE 128 #define AVC_CALLBACK_ADD_XPERMS 256 int avc_add_callback(int (*callback)(u32 event), u32 events); /* Exported to selinuxfs */ int avc_get_hash_stats(char *page); unsigned int avc_get_cache_threshold(void); void avc_set_cache_threshold(unsigned int cache_threshold); #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats); #endif #endif /* _SELINUX_AVC_H_ */ |
| 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM csd #if !defined(_TRACE_CSD_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CSD_H #include <linux/tracepoint.h> TRACE_EVENT(csd_queue_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, smp_call_func_t func, call_single_data_t *csd), TP_ARGS(cpu, callsite, func, csd), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, func) __field(void *, csd) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->func = func; __entry->csd = csd; ), TP_printk("cpu=%u callsite=%pS func=%ps csd=%p", __entry->cpu, __entry->callsite, __entry->func, __entry->csd) ); /* * Tracepoints for a function which is called as an effect of smp_call_function.* */ DECLARE_EVENT_CLASS(csd_function, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd), TP_STRUCT__entry( __field(void *, func) __field(void *, csd) ), TP_fast_assign( __entry->func = func; __entry->csd = csd; ), TP_printk("func=%ps, csd=%p", __entry->func, __entry->csd) ); DEFINE_EVENT(csd_function, csd_function_entry, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd) ); DEFINE_EVENT(csd_function, csd_function_exit, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd) ); #endif /* _TRACE_CSD_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM signal #if !defined(_TRACE_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SIGNAL_H #include <linux/signal.h> #include <linux/sched.h> #include <linux/tracepoint.h> #define TP_STORE_SIGINFO(__entry, info) \ do { \ if (info == SEND_SIG_NOINFO) { \ __entry->errno = 0; \ __entry->code = SI_USER; \ } else if (info == SEND_SIG_PRIV) { \ __entry->errno = 0; \ __entry->code = SI_KERNEL; \ } else { \ __entry->errno = info->si_errno; \ __entry->code = info->si_code; \ } \ } while (0) #ifndef TRACE_HEADER_MULTI_READ enum { TRACE_SIGNAL_DELIVERED, TRACE_SIGNAL_IGNORED, TRACE_SIGNAL_ALREADY_PENDING, TRACE_SIGNAL_OVERFLOW_FAIL, TRACE_SIGNAL_LOSE_INFO, }; #endif /** * signal_generate - called when a signal is generated * @sig: signal number * @info: pointer to struct siginfo * @task: pointer to struct task_struct * @group: shared or private * @result: TRACE_SIGNAL_* * * Current process sends a 'sig' signal to 'task' process with * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV, * 'info' is not a pointer and you can't access its field. Instead, * SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV * means that si_code is SI_KERNEL. */ TRACE_EVENT(signal_generate, TP_PROTO(int sig, struct kernel_siginfo *info, struct task_struct *task, int group, int result), TP_ARGS(sig, info, task, group, result), TP_STRUCT__entry( __field( int, sig ) __field( int, errno ) __field( int, code ) __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, group ) __field( int, result ) ), TP_fast_assign( __entry->sig = sig; TP_STORE_SIGINFO(__entry, info); memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->pid = task->pid; __entry->group = group; __entry->result = result; ), TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d grp=%d res=%d", __entry->sig, __entry->errno, __entry->code, __entry->comm, __entry->pid, __entry->group, __entry->result) ); /** * signal_deliver - called when a signal is delivered * @sig: signal number * @info: pointer to struct siginfo * @ka: pointer to struct k_sigaction * * A 'sig' signal is delivered to current process with 'info' siginfo, * and it will be handled by 'ka'. ka->sa.sa_handler can be SIG_IGN or * SIG_DFL. * Note that some signals reported by signal_generate tracepoint can be * lost, ignored or modified (by debugger) before hitting this tracepoint. * This means, this can show which signals are actually delivered, but * matching generated signals and delivered signals may not be correct. */ TRACE_EVENT(signal_deliver, TP_PROTO(int sig, struct kernel_siginfo *info, struct k_sigaction *ka), TP_ARGS(sig, info, ka), TP_STRUCT__entry( __field( int, sig ) __field( int, errno ) __field( int, code ) __field( unsigned long, sa_handler ) __field( unsigned long, sa_flags ) ), TP_fast_assign( __entry->sig = sig; TP_STORE_SIGINFO(__entry, info); __entry->sa_handler = (unsigned long)ka->sa.sa_handler; __entry->sa_flags = ka->sa.sa_flags; ), TP_printk("sig=%d errno=%d code=%d sa_handler=%lx sa_flags=%lx", __entry->sig, __entry->errno, __entry->code, __entry->sa_handler, __entry->sa_flags) ); #endif /* _TRACE_SIGNAL_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 6 6 93 93 333 333 331 1 1 93 258 93 93 93 28 82 93 258 258 258 258 258 94 246 94 258 18 258 333 332 1 332 333 91 246 331 97 254 93 258 333 333 333 332 333 93 246 532 532 532 533 27 532 463 332 5 5 18 18 18 18 18 18 18 18 18 18 18 18 18 18 18 18 508 3 506 3 511 511 2 2 3 489 363 133 242 363 419 420 362 507 505 507 506 506 505 505 501 507 1 446 445 245 203 291 291 13 288 293 293 294 244 15 294 289 290 290 290 290 290 290 290 290 288 290 290 290 3 290 290 290 290 289 290 290 290 290 289 290 290 290 290 290 290 290 290 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" #include <asm/runtime-const.h> /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_chilren * - childrens' d_sib and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ static int sysctl_vfs_cache_pressure __read_mostly = 100; static int sysctl_vfs_cache_pressure_denom __read_mostly = 100; unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, sysctl_vfs_cache_pressure_denom); } EXPORT_SYMBOL_GPL(vfs_pressure_ratio); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __ro_after_init; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. * * Marking the variables "used" ensures that the compiler doesn't * optimize them away completely on architectures with runtime * constant infrastructure, this allows debuggers to see their * values. But updating these values has no effect on those arches. */ static unsigned int d_hash_shift __ro_after_init __used; static struct hlist_bl_head *dentry_hashtable __ro_after_init __used; static inline struct hlist_bl_head *d_hash(unsigned long hashlen) { return runtime_const_ptr(dentry_hashtable) + runtime_const_shift_right_32(hashlen, d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); static int dentry_negative_policy; #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ static struct dentry_stat_t dentry_stat = { .age_limit = 45, }; /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, { .procname = "dentry-negative", .data = &dentry_negative_policy, .maxlen = sizeof(dentry_negative_policy), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static const struct ctl_table vm_dcache_sysctls[] = { { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "vfs_cache_pressure_denom", .data = &sysctl_vfs_cache_pressure_denom, .maxlen = sizeof(sysctl_vfs_cache_pressure_denom), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE_HUNDRED, }, }; static int __init init_fs_dcache_sysctls(void) { register_sysctl_init("vm", vm_dcache_sysctls); register_sysctl_init("fs", fs_dcache_sysctls); return 0; } fs_initcall(init_fs_dcache_sysctls); #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } /* * long names are allocated separately from dentry and never modified. * Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot() * for the reason why ->count and ->head can't be combined into a union. * dentry_string_cmp() relies upon ->name[] being word-aligned. */ struct external_name { atomic_t count; struct rcu_head head; unsigned char name[] __aligned(sizeof(unsigned long)); }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_shortname.string; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { unsigned seq; const unsigned char *s; rcu_read_lock(); retry: seq = read_seqcount_begin(&dentry->d_seq); s = READ_ONCE(dentry->d_name.name); name->name.hash_len = dentry->d_name.hash_len; name->name.name = name->inline_name.string; if (likely(s == dentry->d_shortname.string)) { name->inline_name = dentry->d_shortname; } else { struct external_name *p; p = container_of(s, struct external_name, name[0]); // get a valid reference if (unlikely(!atomic_inc_not_zero(&p->count))) goto retry; name->name.name = s; } if (read_seqcount_retry(&dentry->d_seq, seq)) { release_dentry_name_snapshot(name); goto retry; } rcu_read_unlock(); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name.string)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->count))) kfree_rcu(p, head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(hlist_unhashed(&dentry->d_sib))) return; __hlist_del(&dentry->d_sib); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_sib.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_sib.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_sib.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_sib.next) { next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_sib.next = next->d_sib.next; } } static struct dentry *__dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); cond_resched(); /* now that it's negative, ->d_parent is stable */ if (!IS_ROOT(dentry)) { parent = dentry->d_parent; spin_lock(&parent->d_lock); } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry_unlist(dentry); if (dentry->d_flags & DCACHE_SHRINK_LIST) can_free = false; spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); if (parent && --parent->d_lockref.count) { spin_unlock(&parent->d_lock); return NULL; } return parent; } /* * Lock a dentry for feeding it to __dentry_kill(). * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry is busy. Otherwise, return true and have * that dentry's inode locked. */ static bool lock_for_kill(struct dentry *dentry) { struct inode *inode = dentry->d_inode; if (unlikely(dentry->d_lockref.count)) return false; if (!inode || likely(spin_trylock(&inode->i_lock))) return true; do { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (likely(inode == dentry->d_inode)) break; spin_unlock(&inode->i_lock); inode = dentry->d_inode; } while (inode); if (likely(!dentry->d_lockref.count)) return true; if (inode) spin_unlock(&inode->i_lock); return false; } /* * Decide if dentry is worth retaining. Usually this is called with dentry * locked; if not locked, we are more limited and might not be able to tell * without a lock. False in this case means "punt to locked path and recheck". * * In case we aren't locked, these predicates are not "stable". However, it is * sufficient that at some point after we dropped the reference the dentry was * hashed and the flags had the proper value. Other dentry users may have * re-gotten a reference to the dentry and change that, but our work is done - * we can leave the dentry around with a zero refcount. */ static inline bool retain_dentry(struct dentry *dentry, bool locked) { unsigned int d_flags; smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); // Unreachable? Nobody would be able to look it up, no point retaining if (unlikely(d_unhashed(dentry))) return false; // Same if it's disconnected if (unlikely(d_flags & DCACHE_DISCONNECTED)) return false; // ->d_delete() might tell us not to bother, but that requires // ->d_lock; can't decide without it if (unlikely(d_flags & DCACHE_OP_DELETE)) { if (!locked || dentry->d_op->d_delete(dentry)) return false; } // Explicitly told not to bother if (unlikely(d_flags & DCACHE_DONTCACHE)) return false; // At this point it looks like we ought to keep it. We also might // need to do something - put it on LRU if it wasn't there already // and mark it referenced if it was on LRU, but not marked yet. // Unfortunately, both actions require ->d_lock, so in lockless // case we'd have to punt rather than doing those. if (unlikely(!(d_flags & DCACHE_LRU_LIST))) { if (!locked) return false; d_lru_add(dentry); } else if (unlikely(!(d_flags & DCACHE_REFERENCED))) { if (!locked) return false; dentry->d_flags |= DCACHE_REFERENCED; } return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * In that case refcount is guaranteed to be zero and we have already * decided that it's not worth keeping around. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; /* * try to decrement the lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Can we decide that decrement of refcount is all we needed without * taking the lock? There's a very common case when it's all we need - * dentry looks like it ought to be retained and there's nothing else * to do. */ if (retain_dentry(dentry, false)) return true; /* * Either not worth retaining or we can't tell without the lock. * Get the lock, then. We've already decremented the refcount to 0, * but we'll need to re-check the situation after getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count || retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return true; } return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { if (!dentry) return; might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } while (lock_for_kill(dentry)) { rcu_read_unlock(); dentry = __dentry_kill(dentry); if (!dentry) return; if (retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return; } rcu_read_lock(); } rcu_read_unlock(); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(dput); static void to_shrink_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); to_shrink_list(dentry, list); spin_unlock(&dentry->d_lock); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); lockref_get(&alias->d_lockref); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { LIST_HEAD(dispose); struct dentry *dentry; spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) to_shrink_list(dentry, &dispose); spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); shrink_dentry_list(&dispose); } EXPORT_SYMBOL(d_prune_aliases); static inline void shrink_kill(struct dentry *victim) { do { rcu_read_unlock(); victim = __dentry_kill(victim); rcu_read_lock(); } while (victim && lock_for_kill(victim)); rcu_read_unlock(); if (victim) spin_unlock(&victim->d_lock); } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!lock_for_kill(dentry)) { bool can_free; rcu_read_unlock(); d_shrink_del(dentry); can_free = dentry->d_flags & DCACHE_DENTRY_KILLED; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } d_shrink_del(dentry); shrink_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add_obj and list_lru_del_obj. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent, *dentry; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: dentry = d_first_child(this_parent); resume: hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { dentry = this_parent; this_parent = dentry->d_parent; spin_unlock(&dentry->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ hlist_for_each_entry_continue(dentry, d_sib) { if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { rcu_read_unlock(); goto resume; } } goto ascend; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; read_seqlock_excl(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: read_sequnlock_excl(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_children list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else if (!dentry->d_lockref.count) { to_shrink_list(dentry, &data->dispose); data->found++; } else if (dentry->d_lockref.count < 0) { data->found++; } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (!dentry->d_lockref.count) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } to_shrink_list(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { spin_lock(&data.victim->d_lock); if (!lock_for_kill(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { shrink_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!hlist_empty(&dentry->d_children)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; WARN(1, "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; rwsem_assert_held_write(&sb->s_umount); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { *victim = dget_dlock(dentry); return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_shortname.string; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->count, 1); dname = p->name; } else { dname = dentry->d_shortname.string; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_flags = 0; lockref_init(&dentry->d_lockref); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = sb->__s_d_op; dentry->d_flags = sb->s_d_flags; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_HLIST_HEAD(&dentry->d_children); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_HLIST_NODE(&dentry->d_sib); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ dentry->d_parent = dget_dlock(parent); hlist_add_head(&dentry->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) { dentry->d_flags |= DCACHE_NORCU; /* d_op_flags(&anon_ops) is 0 */ if (!dentry->d_op) dentry->d_op = &anon_ops; } return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); #define DCACHE_OP_FLAGS \ (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | \ DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_PRUNE | \ DCACHE_OP_REAL) static unsigned int d_op_flags(const struct dentry_operations *op) { unsigned int flags = 0; if (op) { if (op->d_hash) flags |= DCACHE_OP_HASH; if (op->d_compare) flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) flags |= DCACHE_OP_DELETE; if (op->d_prune) flags |= DCACHE_OP_PRUNE; if (op->d_real) flags |= DCACHE_OP_REAL; } return flags; } static void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { unsigned int flags = d_op_flags(op); WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & DCACHE_OP_FLAGS); dentry->d_op = op; if (flags) dentry->d_flags |= flags; } void set_default_d_op(struct super_block *s, const struct dentry_operations *ops) { unsigned int flags = d_op_flags(ops); s->__s_d_op = ops; s->s_d_flags = (s->s_d_flags & ~DCACHE_OP_FLAGS) | flags; } EXPORT_SYMBOL(set_default_d_op); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees the bit cleared or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct super_block *sb; struct dentry *new, *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); sb = inode->i_sb; res = d_find_any_alias(inode); /* existing alias? */ if (res) goto out; new = d_alloc_anon(sb); if (!new) { res = ERR_PTR(-ENOMEM); goto out; } security_d_instantiate(new, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); /* recheck under lock */ if (likely(!res)) { /* still no alias, attach a disconnected dentry */ unsigned add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&new->d_lock); __d_set_inode_and_type(new, inode, add_flags); hlist_add_head(&new->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&sb->s_roots); hlist_bl_add_head(&new->d_hash, &sb->s_roots); hlist_bl_unlock(&sb->s_roots); } spin_unlock(&new->d_lock); spin_unlock(&inode->i_lock); inode = NULL; /* consumed by new->d_inode */ res = new; } else { spin_unlock(&inode->i_lock); dput(new); } out: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @inode: the inode case-insensitive lookup has found * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @parent: parent dentry * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false */ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } EXPORT_SYMBOL_GPL(d_same_name); /* * This is __d_lookup_rcu() when the parent dentry has * DCACHE_OP_COMPARE, which makes things much nastier. */ static noinline struct dentry *__d_lookup_rcu_op_compare( const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { int tlen; const char *tname; unsigned seq; seqretry: seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) return __d_lookup_rcu_op_compare(parent, name, seqp); /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { if (dentry_negative_policy) __d_drop(dentry); dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned int n, wait_queue_head_t *d_wait) { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); if (wq_has_sleeper(d_wait)) wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = __d_alloc(parent->d_sb, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); new->d_flags |= DCACHE_PAR_LOOKUP; spin_lock(&parent->d_lock); new->d_parent = dget_dlock(parent); hlist_add_head(&new->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); new->d_wait = wq; hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); /* * - Unhash the dentry * - Retrieve and clear the waitqueue head in dentry * - Return the waitqueue head */ static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry) { wait_queue_head_t *d_wait; struct hlist_bl_head *b; lockdep_assert_held(&dentry->d_lock); b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); d_wait = dentry->d_wait; dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); return d_wait; } void __d_lookup_unhash_wake(struct dentry *dentry) { spin_lock(&dentry->d_lock); wake_up_all(__d_lookup_unhash(dentry)); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(__d_lookup_unhash_wake); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode, const struct dentry_operations *ops) { wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(dentry); } if (unlikely(ops)) d_set_d_op(dentry, ops); if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n, d_wait); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode, NULL); } EXPORT_SYMBOL(d_add); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ dentry->d_name.name = target->d_name.name; target->d_shortname = dentry->d_shortname; target->d_name.name = target->d_shortname.string; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ target->d_name.name = dentry->d_name.name; dentry->d_shortname = target->d_shortname; dentry->d_name.name = dentry->d_shortname.string; } else { /* * Both are internal. */ for (int i = 0; i < DNAME_INLINE_WORDS; i++) swap(dentry->d_shortname.words[i], target->d_shortname.words[i]); } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->count); dentry->d_name = target->d_name; } else { dentry->d_shortname = target->d_shortname; dentry->d_name.name = dentry->d_shortname.string; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->count))) kfree_rcu(old_name, head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative dcache * entries should not be moved in this way. Caller must hold rename_lock, the * i_rwsem of the source and target directories (exclusively), and the sb-> * s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); if (!hlist_unhashed(&target->d_sib)) __hlist_del(&target->d_sib); hlist_add_head(&target->d_sib, &target->d_parent->d_children); __d_rehash(target); fsnotify_update_flags(target); } if (!hlist_unhashed(&dentry->d_sib)) __hlist_del(&dentry->d_sib); hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n, d_wait); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_rwsem, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: if (alias->d_op && alias->d_op->d_unalias_trylock && !alias->d_op->d_unalias_trylock(alias)) goto out_err; __d_move(alias, dentry, false); if (alias->d_op && alias->d_op->d_unalias_unlock) alias->d_op->d_unalias_unlock(alias); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } struct dentry *d_splice_alias_ops(struct inode *inode, struct dentry *dentry, const struct dentry_operations *ops) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode, ops); return NULL; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { return d_splice_alias_ops(inode, dentry, NULL); } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; BUG_ON(dname_external(dentry) || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_shortname.string, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); } EXPORT_SYMBOL(d_mark_tmpfile); void d_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; inode_dec_link_count(inode); d_mark_tmpfile(file, inode); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); /* * Obtain inode number of the parent dentry. */ ino_t d_parent_ino(struct dentry *dentry) { struct dentry *parent; struct inode *iparent; unsigned seq; ino_t ret; scoped_guard(rcu) { seq = raw_seqcount_begin(&dentry->d_seq); parent = READ_ONCE(dentry->d_parent); iparent = d_inode_rcu(parent); if (likely(iparent)) { ret = iparent->i_ino; if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; } } spin_lock(&dentry->d_lock); ret = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(d_parent_ino); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_shortname.string); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __ro_after_init; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 347 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/processor.h * * Copyright (C) 1995-1999 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PROCESSOR_H #define __ASM_PROCESSOR_H /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is * no point in shifting all network buffers by 2 bytes just to make some IP * header fields appear aligned in memory, potentially sacrificing some DMA * performance on some platforms. */ #define NET_IP_ALIGN 0 #define MTE_CTRL_GCR_USER_EXCL_SHIFT 0 #define MTE_CTRL_GCR_USER_EXCL_MASK 0xffff #define MTE_CTRL_TCF_SYNC (1UL << 16) #define MTE_CTRL_TCF_ASYNC (1UL << 17) #define MTE_CTRL_TCF_ASYMM (1UL << 18) #define MTE_CTRL_STORE_ONLY (1UL << 19) #ifndef __ASSEMBLY__ #include <linux/build_bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/thread_info.h> #include <vdso/processor.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> #include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> #include <asm/ptrace.h> #include <asm/spectre.h> #include <asm/types.h> /* * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. */ #define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS_MIN) #define TASK_SIZE_64 (UL(1) << vabits_actual) #define TASK_SIZE_MAX (UL(1) << VA_BITS) #ifdef CONFIG_COMPAT #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS) /* * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied * by the compat vectors page. */ #define TASK_SIZE_32 UL(0x100000000) #else #define TASK_SIZE_32 (UL(0x100000000) - PAGE_SIZE) #endif /* CONFIG_ARM64_64K_PAGES */ #define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #define DEFAULT_MAP_WINDOW (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : DEFAULT_MAP_WINDOW_64) #else #define TASK_SIZE TASK_SIZE_64 #define DEFAULT_MAP_WINDOW DEFAULT_MAP_WINDOW_64 #endif /* CONFIG_COMPAT */ #ifdef CONFIG_ARM64_FORCE_52BIT #define STACK_TOP_MAX TASK_SIZE_64 #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 4)) #else #define STACK_TOP_MAX DEFAULT_MAP_WINDOW_64 #define TASK_UNMAPPED_BASE (PAGE_ALIGN(DEFAULT_MAP_WINDOW / 4)) #endif /* CONFIG_ARM64_FORCE_52BIT */ #ifdef CONFIG_COMPAT #define AARCH32_VECTORS_BASE 0xffff0000 #define STACK_TOP (test_thread_flag(TIF_32BIT) ? \ AARCH32_VECTORS_BASE : STACK_TOP_MAX) #else #define STACK_TOP STACK_TOP_MAX #endif /* CONFIG_COMPAT */ #ifndef CONFIG_ARM64_FORCE_52BIT #define arch_get_mmap_end(addr, len, flags) \ (((addr) > DEFAULT_MAP_WINDOW) ? TASK_SIZE : DEFAULT_MAP_WINDOW) #define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \ base + TASK_SIZE - DEFAULT_MAP_WINDOW :\ base) #endif /* CONFIG_ARM64_FORCE_52BIT */ extern phys_addr_t arm64_dma_phys_limit; #define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) struct debug_info { #ifdef CONFIG_HAVE_HW_BREAKPOINT /* Have we suspended stepping by a debugger? */ int suspended_step; /* Allow breakpoints and watchpoints to be disabled for this thread. */ int bps_disabled; int wps_disabled; /* Hardware breakpoints pinned to this task. */ struct perf_event *hbp_break[ARM_MAX_BRP]; struct perf_event *hbp_watch[ARM_MAX_WRP]; #endif }; enum vec_type { ARM64_VEC_SVE = 0, ARM64_VEC_SME, ARM64_VEC_MAX, }; enum fp_type { FP_STATE_CURRENT, /* Save based on current task state. */ FP_STATE_FPSIMD, FP_STATE_SVE, }; struct cpu_context { unsigned long x19; unsigned long x20; unsigned long x21; unsigned long x22; unsigned long x23; unsigned long x24; unsigned long x25; unsigned long x26; unsigned long x27; unsigned long x28; unsigned long fp; unsigned long sp; unsigned long pc; }; struct thread_struct { struct cpu_context cpu_context; /* cpu context */ /* * Whitelisted fields for hardened usercopy: * Maintainers must ensure manually that this contains no * implicit padding. */ struct { unsigned long tp_value; /* TLS register */ unsigned long tp2_value; u64 fpmr; unsigned long pad; struct user_fpsimd_state fpsimd_state; } uw; enum fp_type fp_type; /* registers FPSIMD or SVE? */ unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ void *sme_state; /* ZA and ZT state, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ struct user_fpsimd_state kernel_fpsimd_state; unsigned int kernel_fpsimd_cpu; #ifdef CONFIG_ARM64_PTR_AUTH struct ptrauth_keys_user keys_user; #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL struct ptrauth_keys_kernel keys_kernel; #endif #endif #ifdef CONFIG_ARM64_MTE u64 mte_ctrl; #endif u64 sctlr_user; u64 svcr; u64 tpidr2_el0; u64 por_el0; #ifdef CONFIG_ARM64_GCS unsigned int gcs_el0_mode; unsigned int gcs_el0_locked; u64 gcspr_el0; u64 gcs_base; u64 gcs_size; #endif }; static inline unsigned int thread_get_vl(struct thread_struct *thread, enum vec_type type) { return thread->vl[type]; } static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) { return thread_get_vl(thread, ARM64_VEC_SVE); } static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) { return thread_get_vl(thread, ARM64_VEC_SME); } static inline unsigned int thread_get_cur_vl(struct thread_struct *thread) { if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK)) return thread_get_sme_vl(thread); else return thread_get_sve_vl(thread); } unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); void task_set_vl_onexec(struct task_struct *task, enum vec_type type, unsigned long vl); unsigned int task_get_vl_onexec(const struct task_struct *task, enum vec_type type); static inline unsigned int task_get_sve_vl(const struct task_struct *task) { return task_get_vl(task, ARM64_VEC_SVE); } static inline unsigned int task_get_sme_vl(const struct task_struct *task) { return task_get_vl(task, ARM64_VEC_SME); } static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); } static inline unsigned int task_get_sve_vl_onexec(const struct task_struct *task) { return task_get_vl_onexec(task, ARM64_VEC_SVE); } static inline void task_set_sve_vl_onexec(struct task_struct *task, unsigned long vl) { task_set_vl_onexec(task, ARM64_VEC_SVE, vl); } #define SCTLR_USER_MASK \ (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | SCTLR_ELx_ENDA | SCTLR_ELx_ENDB | \ SCTLR_EL1_TCF0_MASK) static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Verify that there is no padding among the whitelisted fields: */ BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != sizeof_field(struct thread_struct, uw.tp_value) + sizeof_field(struct thread_struct, uw.tp2_value) + sizeof_field(struct thread_struct, uw.fpmr) + sizeof_field(struct thread_struct, uw.pad) + sizeof_field(struct thread_struct, uw.fpsimd_state)); *offset = offsetof(struct thread_struct, uw); *size = sizeof_field(struct thread_struct, uw); } #ifdef CONFIG_COMPAT #define task_user_tls(t) \ ({ \ unsigned long *__tls; \ if (is_compat_thread(task_thread_info(t))) \ __tls = &(t)->thread.uw.tp2_value; \ else \ __tls = &(t)->thread.uw.tp_value; \ __tls; \ }) #else #define task_user_tls(t) (&(t)->thread.uw.tp_value) #endif /* Sync TPIDR_EL0 back to thread_struct for current */ void tls_preserve_current_state(void); #define INIT_THREAD { \ .fpsimd_cpu = NR_CPUS, \ } static inline void start_thread_common(struct pt_regs *regs, unsigned long pc, unsigned long pstate) { /* * Ensure all GPRs are zeroed, and initialize PC + PSTATE. * The SP (or compat SP) will be initialized later. */ regs->user_regs = (struct user_pt_regs) { .pc = pc, .pstate = pstate, }; /* * To allow the syscalls:sys_exit_execve tracepoint we need to preserve * syscallno, but do not need orig_x0 or the original GPRs. */ regs->orig_x0 = 0; /* * An exec from a kernel thread won't have an existing PMR value. */ if (system_uses_irq_prio_masking()) regs->pmr = GIC_PRIO_IRQON; /* * The pt_regs::stackframe field must remain valid throughout this * function as a stacktrace can be taken at any time. Any user or * kernel task should have a valid final frame. */ WARN_ON_ONCE(regs->stackframe.record.fp != 0); WARN_ON_ONCE(regs->stackframe.record.lr != 0); WARN_ON_ONCE(regs->stackframe.type != FRAME_META_TYPE_FINAL); } static inline void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { start_thread_common(regs, pc, PSR_MODE_EL0t); spectre_v4_enable_task_mitigation(current); regs->sp = sp; } #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { unsigned long pstate = PSR_AA32_MODE_USR; if (pc & 1) pstate |= PSR_AA32_T_BIT; if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) pstate |= PSR_AA32_E_BIT; start_thread_common(regs, pc, pstate); spectre_v4_enable_task_mitigation(current); regs->compat_sp = sp; } #endif static __always_inline bool is_ttbr0_addr(unsigned long addr) { /* entry assembly clears tags for TTBR0 addrs */ return addr < TASK_SIZE; } static __always_inline bool is_ttbr1_addr(unsigned long addr) { /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; } /* Forward declaration, a strange C thing */ struct task_struct; unsigned long __get_wchan(struct task_struct *p); void update_sctlr_el1(u64 sctlr); /* Thread switching */ extern struct task_struct *cpu_switch_to(struct task_struct *prev, struct task_struct *next); #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) #define KSTK_EIP(tsk) ((unsigned long)task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) user_stack_pointer(task_pt_regs(tsk)) /* * Prefetching support */ #define ARCH_HAS_PREFETCH static inline void prefetch(const void *ptr) { asm volatile("prfm pldl1keep, %a0\n" : : "p" (ptr)); } #define ARCH_HAS_PREFETCHW static inline void prefetchw(const void *ptr) { asm volatile("prfm pstl1keep, %a0\n" : : "p" (ptr)); } extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */ extern void __init minsigstksz_setup(void); /* * Not at the top of the file due to a direct #include cycle between * <asm/fpsimd.h> and <asm/processor.h>. Deferring this #include * ensures that contents of processor.h are visible to fpsimd.h even if * processor.h is included first. * * These prctl helpers are the only things in this file that require * fpsimd.h. The core code expects them to be in this header. */ #include <asm/fpsimd.h> /* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() #define SME_SET_VL(arg) sme_set_current_vl(arg) #define SME_GET_VL() sme_get_current_vl() /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) /* PR_PAC_{SET,GET}_ENABLED_KEYS prctl */ #define PAC_SET_ENABLED_KEYS(tsk, keys, enabled) \ ptrauth_set_enabled_keys(tsk, keys, enabled) #define PAC_GET_ENABLED_KEYS(tsk) ptrauth_get_enabled_keys(tsk) #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI /* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg); long get_tagged_addr_ctrl(struct task_struct *task); #define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(current, arg) #define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current) #endif int get_tsc_mode(unsigned long adr); int set_tsc_mode(unsigned int val); #define GET_TSC_CTL(adr) get_tsc_mode((adr)) #define SET_TSC_CTL(val) set_tsc_mode((val)) #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ |
| 204 205 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork() * * Copyright (C) 2008-2009 Red Hat, Inc. * Authors: * Izik Eidus * Andrea Arcangeli * Chris Wright * Hugh Dickins */ #include <linux/errno.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/cputime.h> #include <linux/rwsem.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/spinlock.h> #include <linux/xxhash.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/memory.h> #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/ksm.h> #include <linux/hashtable.h> #include <linux/freezer.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/pagewalk.h> #include <asm/tlbflush.h> #include "internal.h" #include "mm_slot.h" #define CREATE_TRACE_POINTS #include <trace/events/ksm.h> #ifdef CONFIG_NUMA #define NUMA(x) (x) #define DO_NUMA(x) do { (x); } while (0) #else #define NUMA(x) (0) #define DO_NUMA(x) do { } while (0) #endif typedef u8 rmap_age_t; /** * DOC: Overview * * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: * * In order to reduce excessive scanning, KSM sorts the memory pages by their * contents into a data structure that holds pointers to the pages' locations. * * Since the contents of the pages may change at any moment, KSM cannot just * insert the pages into a normal sorted tree and expect it to find anything. * Therefore KSM uses two data structures - the stable and the unstable tree. * * The stable tree holds pointers to all the merged pages (ksm pages), sorted * by their contents. Because each such page is write-protected, searching on * this tree is fully assured to be working (except when pages are unmapped), * and therefore this tree is called the stable tree. * * The stable tree node includes information required for reverse * mapping from a KSM page to virtual addresses that map this page. * * In order to avoid large latencies of the rmap walks on KSM pages, * KSM maintains two types of nodes in the stable tree: * * * the regular nodes that keep the reverse mapping structures in a * linked list * * the "chains" that link nodes ("dups") that represent the same * write protected memory content, but each "dup" corresponds to a * different KSM page copy of that content * * Internally, the regular nodes, "dups" and "chains" are represented * using the same struct ksm_stable_node structure. * * In addition to the stable tree, KSM uses a second data structure called the * unstable tree: this tree holds pointers to pages which have been found to * be "unchanged for a period of time". The unstable tree sorts these pages * by their contents, but since they are not write-protected, KSM cannot rely * upon the unstable tree to work correctly - the unstable tree is liable to * be corrupted as its contents are modified, and so it is called unstable. * * KSM solves this problem by several techniques: * * 1) The unstable tree is flushed every time KSM completes scanning all * memory areas, and then the tree is rebuilt again from the beginning. * 2) KSM will only insert into the unstable tree, pages whose hash value * has not changed since the previous scan of all memory areas. * 3) The unstable tree is a RedBlack Tree - so its balancing is based on the * colors of the nodes and not on their contents, assuring that even when * the tree gets "corrupted" it won't get out of balance, so scanning time * remains the same (also, searching and inserting nodes in an rbtree uses * the same algorithm, so we have no overhead when we flush and rebuild). * 4) KSM never flushes the stable tree, which means that even if it were to * take 10 attempts to find a page in the unstable tree, once it is found, * it is secured in the stable tree. (When we scan a new page, we first * compare it against the stable tree, and then against the unstable tree.) * * If the merge_across_nodes tunable is unset, then KSM maintains multiple * stable trees and multiple unstable trees: one of each for each NUMA node. */ /** * struct ksm_mm_slot - ksm information per mm that is being scanned * @slot: hash lookup from mm to mm_slot * @rmap_list: head for this mm_slot's singly-linked list of rmap_items */ struct ksm_mm_slot { struct mm_slot slot; struct ksm_rmap_item *rmap_list; }; /** * struct ksm_scan - cursor for scanning * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * @rmap_list: link to the next rmap to be scanned in the rmap_list * @seqnr: count of completed full scans (needed when removing unstable node) * * There is only the one ksm_scan instance of this cursor structure. */ struct ksm_scan { struct ksm_mm_slot *mm_slot; unsigned long address; struct ksm_rmap_item **rmap_list; unsigned long seqnr; }; /** * struct ksm_stable_node - node of the stable rbtree * @node: rb node of this ksm page in the stable tree * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list * @hlist_dup: linked into the stable_node->hlist with a stable_node chain * @list: linked into migrate_nodes, pending placement in the proper node tree * @hlist: hlist head of rmap_items using this ksm page * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid) * @chain_prune_time: time of the last full garbage collection * @rmap_hlist_len: number of rmap_item entries in hlist or STABLE_NODE_CHAIN * @nid: NUMA node id of stable tree in which linked (may not match kpfn) */ struct ksm_stable_node { union { struct rb_node node; /* when node of stable tree */ struct { /* when listed for migration */ struct list_head *head; struct { struct hlist_node hlist_dup; struct list_head list; }; }; }; struct hlist_head hlist; union { unsigned long kpfn; unsigned long chain_prune_time; }; /* * STABLE_NODE_CHAIN can be any negative number in * rmap_hlist_len negative range, but better not -1 to be able * to reliably detect underflows. */ #define STABLE_NODE_CHAIN -1024 int rmap_hlist_len; #ifdef CONFIG_NUMA int nid; #endif }; /** * struct ksm_rmap_item - reverse mapping item for virtual addresses * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree * @nid: NUMA node id of unstable tree in which linked (may not match page) * @mm: the memory structure this rmap_item is pointing into * @address: the virtual address this rmap_item tracks (+ flags in low bits) * @oldchecksum: previous checksum of the page at that virtual address * @node: rb node of this rmap_item in the unstable tree * @head: pointer to stable_node heading this list in the stable tree * @hlist: link into hlist of rmap_items hanging off that stable_node * @age: number of scan iterations since creation * @remaining_skips: how many scans to skip */ struct ksm_rmap_item { struct ksm_rmap_item *rmap_list; union { struct anon_vma *anon_vma; /* when stable */ #ifdef CONFIG_NUMA int nid; /* when node of unstable tree */ #endif }; struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ rmap_age_t age; rmap_age_t remaining_skips; union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ struct ksm_stable_node *head; struct hlist_node hlist; }; }; }; #define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */ #define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */ #define STABLE_FLAG 0x200 /* is listed from the stable tree */ /* The stable and unstable tree heads */ static struct rb_root one_stable_tree[1] = { RB_ROOT }; static struct rb_root one_unstable_tree[1] = { RB_ROOT }; static struct rb_root *root_stable_tree = one_stable_tree; static struct rb_root *root_unstable_tree = one_unstable_tree; /* Recently migrated nodes of stable tree, pending proper placement */ static LIST_HEAD(migrate_nodes); #define STABLE_NODE_DUP_HEAD ((struct list_head *)&migrate_nodes.prev) #define MM_SLOTS_HASH_BITS 10 static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct ksm_mm_slot ksm_mm_head = { .slot.mm_node = LIST_HEAD_INIT(ksm_mm_head.slot.mm_node), }; static struct ksm_scan ksm_scan = { .mm_slot = &ksm_mm_head, }; static struct kmem_cache *rmap_item_cache; static struct kmem_cache *stable_node_cache; static struct kmem_cache *mm_slot_cache; /* Default number of pages to scan per batch */ #define DEFAULT_PAGES_TO_SCAN 100 /* The number of pages scanned */ static unsigned long ksm_pages_scanned; /* The number of nodes in the stable tree */ static unsigned long ksm_pages_shared; /* The number of page slots additionally sharing those nodes */ static unsigned long ksm_pages_sharing; /* The number of nodes in the unstable tree */ static unsigned long ksm_pages_unshared; /* The number of rmap_items in use: to calculate pages_volatile */ static unsigned long ksm_rmap_items; /* The number of stable_node chains */ static unsigned long ksm_stable_node_chains; /* The number of stable_node dups linked to the stable_node chains */ static unsigned long ksm_stable_node_dups; /* Delay in pruning stale stable_node_dups in the stable_node_chains */ static unsigned int ksm_stable_node_chains_prune_millisecs = 2000; /* Maximum number of page slots sharing a stable node */ static int ksm_max_page_sharing = 256; /* Number of pages ksmd should scan in one batch */ static unsigned int ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; /* Checksum of an empty (zeroed) page */ static unsigned int zero_checksum __read_mostly; /* Whether to merge empty (zeroed) pages with actual zero pages */ static bool ksm_use_zero_pages __read_mostly; /* Skip pages that couldn't be de-duplicated previously */ /* Default to true at least temporarily, for testing */ static bool ksm_smart_scan = true; /* The number of zero pages which is placed by KSM */ atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; /* Don't scan more than max pages per batch. */ static unsigned long ksm_advisor_max_pages_to_scan = 30000; /* Min CPU for scanning pages per scan */ #define KSM_ADVISOR_MIN_CPU 10 /* Max CPU for scanning pages per scan */ static unsigned int ksm_advisor_max_cpu = 70; /* Target scan time in seconds to analyze all KSM candidate pages. */ static unsigned long ksm_advisor_target_scan_time = 200; /* Exponentially weighted moving average. */ #define EWMA_WEIGHT 30 /** * struct advisor_ctx - metadata for KSM advisor * @start_scan: start time of the current scan * @scan_time: scan time of previous scan * @change: change in percent to pages_to_scan parameter * @cpu_time: cpu time consumed by the ksmd thread in the previous scan */ struct advisor_ctx { ktime_t start_scan; unsigned long scan_time; unsigned long change; unsigned long long cpu_time; }; static struct advisor_ctx advisor_ctx; /* Define different advisor's */ enum ksm_advisor_type { KSM_ADVISOR_NONE, KSM_ADVISOR_SCAN_TIME, }; static enum ksm_advisor_type ksm_advisor; #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ /* At least scan this many pages per batch. */ static unsigned long ksm_advisor_min_pages_to_scan = 500; static void set_advisor_defaults(void) { if (ksm_advisor == KSM_ADVISOR_NONE) { ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; } else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) { advisor_ctx = (const struct advisor_ctx){ 0 }; ksm_thread_pages_to_scan = ksm_advisor_min_pages_to_scan; } } #endif /* CONFIG_SYSFS */ static inline void advisor_start_scan(void) { if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) advisor_ctx.start_scan = ktime_get(); } /* * Use previous scan time if available, otherwise use current scan time as an * approximation for the previous scan time. */ static inline unsigned long prev_scan_time(struct advisor_ctx *ctx, unsigned long scan_time) { return ctx->scan_time ? ctx->scan_time : scan_time; } /* Calculate exponential weighted moving average */ static unsigned long ewma(unsigned long prev, unsigned long curr) { return ((100 - EWMA_WEIGHT) * prev + EWMA_WEIGHT * curr) / 100; } /* * The scan time advisor is based on the current scan rate and the target * scan rate. * * new_pages_to_scan = pages_to_scan * (scan_time / target_scan_time) * * To avoid perturbations it calculates a change factor of previous changes. * A new change factor is calculated for each iteration and it uses an * exponentially weighted moving average. The new pages_to_scan value is * multiplied with that change factor: * * new_pages_to_scan *= change facor * * The new_pages_to_scan value is limited by the cpu min and max values. It * calculates the cpu percent for the last scan and calculates the new * estimated cpu percent cost for the next scan. That value is capped by the * cpu min and max setting. * * In addition the new pages_to_scan value is capped by the max and min * limits. */ static void scan_time_advisor(void) { unsigned int cpu_percent; unsigned long cpu_time; unsigned long cpu_time_diff; unsigned long cpu_time_diff_ms; unsigned long pages; unsigned long per_page_cost; unsigned long factor; unsigned long change; unsigned long last_scan_time; unsigned long scan_time; /* Convert scan time to seconds */ scan_time = div_s64(ktime_ms_delta(ktime_get(), advisor_ctx.start_scan), MSEC_PER_SEC); scan_time = scan_time ? scan_time : 1; /* Calculate CPU consumption of ksmd background thread */ cpu_time = task_sched_runtime(current); cpu_time_diff = cpu_time - advisor_ctx.cpu_time; cpu_time_diff_ms = cpu_time_diff / 1000 / 1000; cpu_percent = (cpu_time_diff_ms * 100) / (scan_time * 1000); cpu_percent = cpu_percent ? cpu_percent : 1; last_scan_time = prev_scan_time(&advisor_ctx, scan_time); /* Calculate scan time as percentage of target scan time */ factor = ksm_advisor_target_scan_time * 100 / scan_time; factor = factor ? factor : 1; /* * Calculate scan time as percentage of last scan time and use * exponentially weighted average to smooth it */ change = scan_time * 100 / last_scan_time; change = change ? change : 1; change = ewma(advisor_ctx.change, change); /* Calculate new scan rate based on target scan rate. */ pages = ksm_thread_pages_to_scan * 100 / factor; /* Update pages_to_scan by weighted change percentage. */ pages = pages * change / 100; /* Cap new pages_to_scan value */ per_page_cost = ksm_thread_pages_to_scan / cpu_percent; per_page_cost = per_page_cost ? per_page_cost : 1; pages = min(pages, per_page_cost * ksm_advisor_max_cpu); pages = max(pages, per_page_cost * KSM_ADVISOR_MIN_CPU); pages = min(pages, ksm_advisor_max_pages_to_scan); /* Update advisor context */ advisor_ctx.change = change; advisor_ctx.scan_time = scan_time; advisor_ctx.cpu_time = cpu_time; ksm_thread_pages_to_scan = pages; trace_ksm_advisor(scan_time, pages, cpu_percent); } static void advisor_stop_scan(void) { if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) scan_time_advisor(); } #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; static int ksm_nr_node_ids = 1; #else #define ksm_merge_across_nodes 1U #define ksm_nr_node_ids 1 #endif #define KSM_RUN_STOP 0 #define KSM_RUN_MERGE 1 #define KSM_RUN_UNMERGE 2 #define KSM_RUN_OFFLINE 4 static unsigned long ksm_run = KSM_RUN_STOP; static void wait_while_offlining(void); static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait); static DECLARE_WAIT_QUEUE_HEAD(ksm_iter_wait); static DEFINE_MUTEX(ksm_thread_mutex); static DEFINE_SPINLOCK(ksm_mmlist_lock); static int __init ksm_slab_init(void) { rmap_item_cache = KMEM_CACHE(ksm_rmap_item, 0); if (!rmap_item_cache) goto out; stable_node_cache = KMEM_CACHE(ksm_stable_node, 0); if (!stable_node_cache) goto out_free1; mm_slot_cache = KMEM_CACHE(ksm_mm_slot, 0); if (!mm_slot_cache) goto out_free2; return 0; out_free2: kmem_cache_destroy(stable_node_cache); out_free1: kmem_cache_destroy(rmap_item_cache); out: return -ENOMEM; } static void __init ksm_slab_free(void) { kmem_cache_destroy(mm_slot_cache); kmem_cache_destroy(stable_node_cache); kmem_cache_destroy(rmap_item_cache); mm_slot_cache = NULL; } static __always_inline bool is_stable_node_chain(struct ksm_stable_node *chain) { return chain->rmap_hlist_len == STABLE_NODE_CHAIN; } static __always_inline bool is_stable_node_dup(struct ksm_stable_node *dup) { return dup->head == STABLE_NODE_DUP_HEAD; } static inline void stable_node_chain_add_dup(struct ksm_stable_node *dup, struct ksm_stable_node *chain) { VM_BUG_ON(is_stable_node_dup(dup)); dup->head = STABLE_NODE_DUP_HEAD; VM_BUG_ON(!is_stable_node_chain(chain)); hlist_add_head(&dup->hlist_dup, &chain->hlist); ksm_stable_node_dups++; } static inline void __stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(!is_stable_node_dup(dup)); hlist_del(&dup->hlist_dup); ksm_stable_node_dups--; } static inline void stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(is_stable_node_chain(dup)); if (is_stable_node_dup(dup)) __stable_node_dup_del(dup); else rb_erase(&dup->node, root_stable_tree + NUMA(dup->nid)); #ifdef CONFIG_DEBUG_VM dup->head = NULL; #endif } static inline struct ksm_rmap_item *alloc_rmap_item(void) { struct ksm_rmap_item *rmap_item; rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (rmap_item) ksm_rmap_items++; return rmap_item; } static inline void free_rmap_item(struct ksm_rmap_item *rmap_item) { ksm_rmap_items--; rmap_item->mm->ksm_rmap_items--; rmap_item->mm = NULL; /* debug safety */ kmem_cache_free(rmap_item_cache, rmap_item); } static inline struct ksm_stable_node *alloc_stable_node(void) { /* * The allocation can take too long with GFP_KERNEL when memory is under * pressure, which may lead to hung task warnings. Adding __GFP_HIGH * grants access to memory reserves, helping to avoid this problem. */ return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH); } static inline void free_stable_node(struct ksm_stable_node *stable_node) { VM_BUG_ON(stable_node->rmap_hlist_len && !is_stable_node_chain(stable_node)); kmem_cache_free(stable_node_cache, stable_node); } /* * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's * page tables after it has passed through ksm_exit() - which, if necessary, * takes mmap_lock briefly to serialize against them. ksm_exit() does not set * a special flag: they can just back out as soon as mm_users goes to zero. * ksm_test_exit() is used throughout to make this test for exit: in some * places for correctness, in some places just to avoid unnecessary work. */ static inline bool ksm_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } /* * We use break_ksm to break COW on a ksm page by triggering unsharing, * such that the ksm page will get replaced by an exclusive anonymous page. * * We take great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP * mmap of /dev/mem, where we would not want to touch it. * * FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce * protection keys here anyway. */ static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma) { vm_fault_t ret = 0; if (lock_vma) vma_start_write(vma); do { bool ksm_page = false; struct folio_walk fw; struct folio *folio; cond_resched(); folio = folio_walk_start(&fw, vma, addr, FW_MIGRATION | FW_ZEROPAGE); if (folio) { /* Small folio implies FW_LEVEL_PTE. */ if (!folio_test_large(folio) && (folio_test_ksm(folio) || is_ksm_zero_pte(fw.pte))) ksm_page = true; folio_walk_end(&fw, vma); } if (!ksm_page) return 0; ret = handle_mm_fault(vma, addr, FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, NULL); } while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop until we no longer find a KSM page because * handle_mm_fault() may back out if there's any difficulty e.g. if * pte accessed bit gets updated concurrently. * * VM_FAULT_SIGBUS could occur if we race with truncation of the * backing file, which also invalidates anonymous pages: that's * okay, that truncation will have unmapped the KSM page for us. * * VM_FAULT_OOM: at the time of writing (late July 2009), setting * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the * current task has TIF_MEMDIE set, and will be OOM killed on return * to user; and ksmd, having no mm, would never be chosen for that. * * But if the mm is in a limited mem_cgroup, then the fault may fail * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and * even ksmd can fail in this way - though it's usually breaking ksm * just to undo a merge it made a moment before, so unlikely to oom. * * That's a pity: we might therefore have more kernel pages allocated * than we're counting as nodes in the stable tree; but ksm_do_scan * will retry to break_cow on each pass, so should recover the page * in due course. The important thing is to not let VM_MERGEABLE * be cleared while any such pages might remain in the area. */ return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; } static bool ksm_compatible(const struct file *file, vm_flags_t vm_flags) { if (vm_flags & (VM_SHARED | VM_MAYSHARE | VM_SPECIAL | VM_HUGETLB | VM_DROPPABLE)) return false; /* just ignore the advice */ if (file_is_dax(file)) return false; #ifdef VM_SAO if (vm_flags & VM_SAO) return false; #endif #ifdef VM_SPARC_ADI if (vm_flags & VM_SPARC_ADI) return false; #endif return true; } static bool vma_ksm_compatible(struct vm_area_struct *vma) { return ksm_compatible(vma->vm_file, vma->vm_flags); } static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; if (ksm_test_exit(mm)) return NULL; vma = vma_lookup(mm, addr); if (!vma || !(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) return NULL; return vma; } static void break_cow(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; /* * It is not an accident that whenever we want to break COW * to undo, we also need to drop a reference to the anon_vma. */ put_anon_vma(rmap_item->anon_vma); mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (vma) break_ksm(vma, addr, false); mmap_read_unlock(mm); } static struct page *get_mergeable_page(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; struct page *page = NULL; struct folio_walk fw; struct folio *folio; mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (!vma) goto out; folio = folio_walk_start(&fw, vma, addr, 0); if (folio) { if (!folio_is_zone_device(folio) && folio_test_anon(folio)) { folio_get(folio); page = fw.page; } folio_walk_end(&fw, vma); } out: if (page) { flush_anon_page(vma, page, addr); flush_dcache_page(page); } mmap_read_unlock(mm); return page; } /* * This helper is used for getting right index into array of tree roots. * When merge_across_nodes knob is set to 1, there are only two rb-trees for * stable and unstable pages from all nodes with roots in index 0. Otherwise, * every node has its own stable and unstable tree. */ static inline int get_kpfn_nid(unsigned long kpfn) { return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn)); } static struct ksm_stable_node *alloc_stable_node_chain(struct ksm_stable_node *dup, struct rb_root *root) { struct ksm_stable_node *chain = alloc_stable_node(); VM_BUG_ON(is_stable_node_chain(dup)); if (likely(chain)) { INIT_HLIST_HEAD(&chain->hlist); chain->chain_prune_time = jiffies; chain->rmap_hlist_len = STABLE_NODE_CHAIN; #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA) chain->nid = NUMA_NO_NODE; /* debug */ #endif ksm_stable_node_chains++; /* * Put the stable node chain in the first dimension of * the stable tree and at the same time remove the old * stable node. */ rb_replace_node(&dup->node, &chain->node, root); /* * Move the old stable node to the second dimension * queued in the hlist_dup. The invariant is that all * dup stable_nodes in the chain->hlist point to pages * that are write protected and have the exact same * content. */ stable_node_chain_add_dup(dup, chain); } return chain; } static inline void free_stable_node_chain(struct ksm_stable_node *chain, struct rb_root *root) { rb_erase(&chain->node, root); free_stable_node(chain); ksm_stable_node_chains--; } static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node) { struct ksm_rmap_item *rmap_item; /* check it's not STABLE_NODE_CHAIN or negative */ BUG_ON(stable_node->rmap_hlist_len < 0); hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { if (rmap_item->hlist.next) { ksm_pages_sharing--; trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm); } else { ksm_pages_shared--; } rmap_item->mm->ksm_merging_pages--; VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); rmap_item->address &= PAGE_MASK; cond_resched(); } /* * We need the second aligned pointer of the migrate_nodes * list_head to stay clear from the rb_parent_color union * (aligned and different than any node) and also different * from &migrate_nodes. This will verify that future list.h changes * don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it. */ BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes); BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1); trace_ksm_remove_ksm_page(stable_node->kpfn); if (stable_node->head == &migrate_nodes) list_del(&stable_node->list); else stable_node_dup_del(stable_node); free_stable_node(stable_node); } enum ksm_get_folio_flags { KSM_GET_FOLIO_NOLOCK, KSM_GET_FOLIO_LOCK, KSM_GET_FOLIO_TRYLOCK }; /* * ksm_get_folio: checks if the page indicated by the stable node * is still its ksm page, despite having held no reference to it. * In which case we can trust the content of the page, and it * returns the gotten page; but if the page has now been zapped, * remove the stale node from the stable tree and return NULL. * But beware, the stable node's page might be being migrated. * * You would expect the stable_node to hold a reference to the ksm page. * But if it increments the page's count, swapping out has to wait for * ksmd to come around again before it can free the page, which may take * seconds or even minutes: much too unresponsive. So instead we use a * "keyhole reference": access to the ksm page from the stable node peeps * out through its keyhole to see if that page still holds the right key, * pointing back to this stable node. This relies on freeing a PageAnon * page to reset its page->mapping to NULL, and relies on no other use of * a page to put something that might look like our key in page->mapping. * is on its way to being freed; but it is an anomaly to bear in mind. */ static struct folio *ksm_get_folio(struct ksm_stable_node *stable_node, enum ksm_get_folio_flags flags) { struct folio *folio; void *expected_mapping; unsigned long kpfn; expected_mapping = (void *)((unsigned long)stable_node | FOLIO_MAPPING_KSM); again: kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ folio = pfn_folio(kpfn); if (READ_ONCE(folio->mapping) != expected_mapping) goto stale; /* * We cannot do anything with the page while its refcount is 0. * Usually 0 means free, or tail of a higher-order page: in which * case this node is no longer referenced, and should be freed; * however, it might mean that the page is under page_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; * the same is in reuse_ksm_page() case; but if page is swapcache * in folio_migrate_mapping(), it might still be our page, * in which case it's essential to keep the node. */ while (!folio_try_get(folio)) { /* * Another check for folio->mapping != expected_mapping * would work here too. We have chosen to test the * swapcache flag to optimize the common case, when the * folio is or is about to be freed: the swapcache flag * is cleared (under spin_lock_irq) in the ref_freeze * section of __remove_mapping(); but anon folio->mapping * is reset to NULL later, in free_pages_prepare(). */ if (!folio_test_swapcache(folio)) goto stale; cpu_relax(); } if (READ_ONCE(folio->mapping) != expected_mapping) { folio_put(folio); goto stale; } if (flags == KSM_GET_FOLIO_TRYLOCK) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EBUSY); } } else if (flags == KSM_GET_FOLIO_LOCK) folio_lock(folio); if (flags != KSM_GET_FOLIO_NOLOCK) { if (READ_ONCE(folio->mapping) != expected_mapping) { folio_unlock(folio); folio_put(folio); goto stale; } } return folio; stale: /* * We come here from above when folio->mapping or the swapcache flag * suggests that the node is stale; but it might be under migration. * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); if (READ_ONCE(stable_node->kpfn) != kpfn) goto again; remove_node_from_stable_tree(stable_node); return NULL; } /* * Removing rmap_item from stable or unstable tree. * This function will clean the information from the stable/unstable tree. */ static void remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item) { if (rmap_item->address & STABLE_FLAG) { struct ksm_stable_node *stable_node; struct folio *folio; stable_node = rmap_item->head; folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); if (!folio) goto out; hlist_del(&rmap_item->hlist); folio_unlock(folio); folio_put(folio); if (!hlist_empty(&stable_node->hlist)) ksm_pages_sharing--; else ksm_pages_shared--; rmap_item->mm->ksm_merging_pages--; VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); rmap_item->head = NULL; rmap_item->address &= PAGE_MASK; } else if (rmap_item->address & UNSTABLE_FLAG) { unsigned char age; /* * Usually ksmd can and must skip the rb_erase, because * root_unstable_tree was already reset to RB_ROOT. * But be careful when an mm is exiting: do the rb_erase * if this rmap_item was inserted by this scan, rather * than left over from before. */ age = (unsigned char)(ksm_scan.seqnr - rmap_item->address); BUG_ON(age > 1); if (!age) rb_erase(&rmap_item->node, root_unstable_tree + NUMA(rmap_item->nid)); ksm_pages_unshared--; rmap_item->address &= PAGE_MASK; } out: cond_resched(); /* we're called from many long loops */ } static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list) { while (*rmap_list) { struct ksm_rmap_item *rmap_item = *rmap_list; *rmap_list = rmap_item->rmap_list; remove_rmap_item_from_tree(rmap_item); free_rmap_item(rmap_item); } } /* * Though it's very tempting to unmerge rmap_items from stable tree rather * than check every pte of a given vma, the locking doesn't quite work for * that - an rmap_item is assigned to the stable tree after inserting ksm * page and upping mmap_lock. Nor does it fit with the way we skip dup'ing * rmap_items from parent to child at fork time (so as not to waste time * if exit comes before the next scan reaches it). * * Similarly, although we'd like to remove rmap_items (so updating counts * and freeing memory) when unmerging an area, it's easier to leave that * to the next pass of ksmd - consider, for example, how ksmd might be * in cmp_and_merge_page on one of the rmap_items we would be removing. */ static int unmerge_ksm_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool lock_vma) { unsigned long addr; int err = 0; for (addr = start; addr < end && !err; addr += PAGE_SIZE) { if (ksm_test_exit(vma->vm_mm)) break; if (signal_pending(current)) err = -ERESTARTSYS; else err = break_ksm(vma, addr, lock_vma); } return err; } static inline struct ksm_stable_node *folio_stable_node(const struct folio *folio) { return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL; } static inline struct ksm_stable_node *page_stable_node(struct page *page) { return folio_stable_node(page_folio(page)); } static inline void folio_set_stable_node(struct folio *folio, struct ksm_stable_node *stable_node) { VM_WARN_ON_FOLIO(folio_test_anon(folio) && PageAnonExclusive(&folio->page), folio); folio->mapping = (void *)((unsigned long)stable_node | FOLIO_MAPPING_KSM); } #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ static int remove_stable_node(struct ksm_stable_node *stable_node) { struct folio *folio; int err; folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); if (!folio) { /* * ksm_get_folio did remove_node_from_stable_tree itself. */ return 0; } /* * Page could be still mapped if this races with __mmput() running in * between ksm_exit() and exit_mmap(). Just refuse to let * merge_across_nodes/max_page_sharing be switched. */ err = -EBUSY; if (!folio_mapped(folio)) { /* * The stable node did not yet appear stale to ksm_get_folio(), * since that allows for an unmapped ksm folio to be recognized * right up until it is freed; but the node is safe to remove. * This folio might be in an LRU cache waiting to be freed, * or it might be in the swapcache (perhaps under writeback), * or it might have been removed from swapcache a moment ago. */ folio_set_stable_node(folio, NULL); remove_node_from_stable_tree(stable_node); err = 0; } folio_unlock(folio); folio_put(folio); return err; } static int remove_stable_node_chain(struct ksm_stable_node *stable_node, struct rb_root *root) { struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { VM_BUG_ON(is_stable_node_dup(stable_node)); if (remove_stable_node(stable_node)) return true; else return false; } hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { VM_BUG_ON(!is_stable_node_dup(dup)); if (remove_stable_node(dup)) return true; } BUG_ON(!hlist_empty(&stable_node->hlist)); free_stable_node_chain(stable_node, root); return false; } static int remove_all_stable_nodes(void) { struct ksm_stable_node *stable_node, *next; int nid; int err = 0; for (nid = 0; nid < ksm_nr_node_ids; nid++) { while (root_stable_tree[nid].rb_node) { stable_node = rb_entry(root_stable_tree[nid].rb_node, struct ksm_stable_node, node); if (remove_stable_node_chain(stable_node, root_stable_tree + nid)) { err = -EBUSY; break; /* proceed to next nid */ } cond_resched(); } } list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (remove_stable_node(stable_node)) err = -EBUSY; cond_resched(); } return err; } static int unmerge_and_remove_all_rmap_items(void) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int err = 0; spin_lock(&ksm_mmlist_lock); slot = list_entry(ksm_mm_head.slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); spin_unlock(&ksm_mmlist_lock); for (mm_slot = ksm_scan.mm_slot; mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) { VMA_ITERATOR(vmi, mm_slot->slot.mm, 0); mm = mm_slot->slot.mm; mmap_read_lock(mm); /* * Exit right away if mm is exiting to avoid lockdep issue in * the maple tree */ if (ksm_test_exit(mm)) goto mm_exiting; for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) continue; err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, false); if (err) goto error; } mm_exiting: remove_trailing_rmap_items(&mm_slot->rmap_list); mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_test_exit(mm)) { hash_del(&mm_slot->slot.hash); list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmdrop(mm); } else spin_unlock(&ksm_mmlist_lock); } /* Clean up stable nodes, but don't worry if some are still busy */ remove_all_stable_nodes(); ksm_scan.seqnr = 0; return 0; error: mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = &ksm_mm_head; spin_unlock(&ksm_mmlist_lock); return err; } #endif /* CONFIG_SYSFS */ static u32 calc_checksum(struct page *page) { u32 checksum; void *addr = kmap_local_page(page); checksum = xxhash(addr, PAGE_SIZE, 0); kunmap_local(addr); return checksum; } static int write_protect_page(struct vm_area_struct *vma, struct folio *folio, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, 0, 0); int swapped; int err = -EFAULT; struct mmu_notifier_range range; bool anon_exclusive; pte_t entry; if (WARN_ON_ONCE(folio_test_large(folio))) return err; pvmw.address = page_address_in_vma(folio, folio_page(folio, 0), vma); if (pvmw.address == -EFAULT) goto out; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address, pvmw.address + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); if (!page_vma_mapped_walk(&pvmw)) goto out_mn; if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) goto out_unlock; entry = ptep_get(pvmw.pte); /* * Handle PFN swap PTEs, such as device-exclusive ones, that actually * map pages: give up just like the next folio_walk would. */ if (unlikely(!pte_present(entry))) goto out_unlock; anon_exclusive = PageAnonExclusive(&folio->page); if (pte_write(entry) || pte_dirty(entry) || anon_exclusive || mm_tlb_flush_pending(mm)) { swapped = folio_test_swapcache(folio); flush_cache_page(vma, pvmw.address, folio_pfn(folio)); /* * Ok this is tricky, when get_user_pages_fast() run it doesn't * take any lock, therefore the check that we are going to make * with the pagecount against the mapcount is racy and * O_DIRECT can happen right after the check. * So we clear the pte and flush the tlb before the check * this assure us that no O_DIRECT can happen after the check * or in the middle of the check. * * No need to notify as we are downgrading page table to read * only not changing it to point to a new page. * * See Documentation/mm/mmu_notifier.rst */ entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); /* * Check that no O_DIRECT or similar I/O is in progress on the * page */ if (folio_mapcount(folio) + 1 + swapped != folio_ref_count(folio)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, &folio->page)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } if (pte_dirty(entry)) folio_mark_dirty(folio); entry = pte_mkclean(entry); if (pte_write(entry)) entry = pte_wrprotect(entry); set_pte_at(mm, pvmw.address, pvmw.pte, entry); } *orig_pte = entry; err = 0; out_unlock: page_vma_mapped_walk_done(&pvmw); out_mn: mmu_notifier_invalidate_range_end(&range); out: return err; } /** * replace_page - replace page in vma by new ksm page * @vma: vma that holds the pte pointing to page * @page: the page we are replacing by kpage * @kpage: the ksm page we replace page by * @orig_pte: the original value of the pte * * Returns 0 on success, -EFAULT on failure. */ static int replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage, pte_t orig_pte) { struct folio *kfolio = page_folio(kpage); struct mm_struct *mm = vma->vm_mm; struct folio *folio = page_folio(page); pmd_t *pmd; pmd_t pmde; pte_t *ptep; pte_t newpte; spinlock_t *ptl; unsigned long addr; int err = -EFAULT; struct mmu_notifier_range range; addr = page_address_in_vma(folio, page, vma); if (addr == -EFAULT) goto out; pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; /* * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ pmde = pmdp_get_lockless(pmd); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) goto out; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!ptep) goto out_mn; if (!pte_same(ptep_get(ptep), orig_pte)) { pte_unmap_unlock(ptep, ptl); goto out_mn; } VM_BUG_ON_PAGE(PageAnonExclusive(page), page); VM_BUG_ON_FOLIO(folio_test_anon(kfolio) && PageAnonExclusive(kpage), kfolio); /* * No need to check ksm_use_zero_pages here: we can only have a * zero_page here if ksm_use_zero_pages was enabled already. */ if (!is_zero_pfn(page_to_pfn(kpage))) { folio_get(kfolio); folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE); newpte = mk_pte(kpage, vma->vm_page_prot); } else { /* * Use pte_mkdirty to mark the zero page mapped by KSM, and then * we can easily track all KSM-placed zero pages by checking if * the dirty bit in zero page's PTE is set. */ newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); ksm_map_zero_page(mm); /* * We're replacing an anonymous page with a zero page, which is * not anonymous. We need to do proper accounting otherwise we * will get wrong values in /proc, and a BUG message in dmesg * when tearing down the mm. */ dec_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, addr, pte_pfn(ptep_get(ptep))); /* * No need to notify as we are replacing a read only page with another * read only page with the same content. * * See Documentation/mm/mmu_notifier.rst */ ptep_clear_flush(vma, addr, ptep); set_pte_at(mm, addr, ptep, newpte); folio_remove_rmap_pte(folio, page, vma); if (!folio_mapped(folio)) folio_free_swap(folio); folio_put(folio); pte_unmap_unlock(ptep, ptl); err = 0; out_mn: mmu_notifier_invalidate_range_end(&range); out: return err; } /* * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page * @page: the PageAnon page that we want to replace with kpage * @kpage: the KSM page that we want to map instead of page, * or NULL the first time when we want to use page as kpage. * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ static int try_to_merge_one_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { struct folio *folio = page_folio(page); pte_t orig_pte = __pte(0); int err = -EFAULT; if (page == kpage) /* ksm page forked */ return 0; if (!folio_test_anon(folio)) goto out; /* * We need the folio lock to read a stable swapcache flag in * write_protect_page(). We trylock because we don't want to wait * here - we prefer to continue scanning and merging different * pages, then come back to this page when it is unlocked. */ if (!folio_trylock(folio)) goto out; if (folio_test_large(folio)) { if (split_huge_page(page)) goto out_unlock; folio = page_folio(page); } /* * If this anonymous page is mapped only here, its pte may need * to be write-protected. If it's mapped elsewhere, all of its * ptes are necessarily already write-protected. But in either * case, we need to lock and check page_count is not raised. */ if (write_protect_page(vma, folio, &orig_pte) == 0) { if (!kpage) { /* * While we hold folio lock, upgrade folio from * anon to a NULL stable_node with the KSM flag set: * stable_tree_insert() will update stable_node. */ folio_set_stable_node(folio, NULL); folio_mark_accessed(folio); /* * Page reclaim just frees a clean folio with no dirty * ptes: make sure that the ksm page would be swapped. */ if (!folio_test_dirty(folio)) folio_mark_dirty(folio); err = 0; } else if (pages_identical(page, kpage)) err = replace_page(vma, page, kpage, orig_pte); } out_unlock: folio_unlock(folio); out: return err; } /* * This function returns 0 if the pages were merged or if they are * no longer merging candidates (e.g., VMA stale), -EFAULT otherwise. */ static int try_to_merge_with_zero_page(struct ksm_rmap_item *rmap_item, struct page *page) { struct mm_struct *mm = rmap_item->mm; int err = -EFAULT; /* * Same checksum as an empty page. We attempt to merge it with the * appropriate zero page if the user enabled this via sysfs. */ if (ksm_use_zero_pages && (rmap_item->oldchecksum == zero_checksum)) { struct vm_area_struct *vma; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (vma) { err = try_to_merge_one_page(vma, page, ZERO_PAGE(rmap_item->address)); trace_ksm_merge_one_page( page_to_pfn(ZERO_PAGE(rmap_item->address)), rmap_item, mm, err); } else { /* * If the vma is out of date, we do not need to * continue. */ err = 0; } mmap_read_unlock(mm); } return err; } /* * try_to_merge_with_ksm_page - like try_to_merge_two_pages, * but no new kernel page is allocated: kpage must already be a ksm page. * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item, struct page *page, struct page *kpage) { struct mm_struct *mm = rmap_item->mm; struct vm_area_struct *vma; int err = -EFAULT; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (!vma) goto out; err = try_to_merge_one_page(vma, page, kpage); if (err) goto out; /* Unstable nid is in union with stable anon_vma: remove first */ remove_rmap_item_from_tree(rmap_item); /* Must get reference to anon_vma while still holding mmap_lock */ rmap_item->anon_vma = vma->anon_vma; get_anon_vma(vma->anon_vma); out: mmap_read_unlock(mm); trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page), rmap_item, mm, err); return err; } /* * try_to_merge_two_pages - take two identical pages and prepare them * to be merged into one page. * * This function returns the kpage if we successfully merged two identical * pages into one ksm page, NULL otherwise. * * Note that this function upgrades page to ksm page: if one of the pages * is already a ksm page, try_to_merge_with_ksm_page should be used. */ static struct folio *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, struct ksm_rmap_item *tree_rmap_item, struct page *tree_page) { int err; err = try_to_merge_with_ksm_page(rmap_item, page, NULL); if (!err) { err = try_to_merge_with_ksm_page(tree_rmap_item, tree_page, page); /* * If that fails, we have a ksm page with only one pte * pointing to it: so break it. */ if (err) break_cow(rmap_item); } return err ? NULL : page_folio(page); } static __always_inline bool __is_page_sharing_candidate(struct ksm_stable_node *stable_node, int offset) { VM_BUG_ON(stable_node->rmap_hlist_len < 0); /* * Check that at least one mapping still exists, otherwise * there's no much point to merge and share with this * stable_node, as the underlying tree_page of the other * sharer is going to be freed soon. */ return stable_node->rmap_hlist_len && stable_node->rmap_hlist_len + offset < ksm_max_page_sharing; } static __always_inline bool is_page_sharing_candidate(struct ksm_stable_node *stable_node) { return __is_page_sharing_candidate(stable_node, 0); } static struct folio *stable_node_dup(struct ksm_stable_node **_stable_node_dup, struct ksm_stable_node **_stable_node, struct rb_root *root, bool prune_stale_stable_nodes) { struct ksm_stable_node *dup, *found = NULL, *stable_node = *_stable_node; struct hlist_node *hlist_safe; struct folio *folio, *tree_folio = NULL; int found_rmap_hlist_len; if (!prune_stale_stable_nodes || time_before(jiffies, stable_node->chain_prune_time + msecs_to_jiffies( ksm_stable_node_chains_prune_millisecs))) prune_stale_stable_nodes = false; else stable_node->chain_prune_time = jiffies; hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { cond_resched(); /* * We must walk all stable_node_dup to prune the stale * stable nodes during lookup. * * ksm_get_folio can drop the nodes from the * stable_node->hlist if they point to freed pages * (that's why we do a _safe walk). The "dup" * stable_node parameter itself will be freed from * under us if it returns NULL. */ folio = ksm_get_folio(dup, KSM_GET_FOLIO_NOLOCK); if (!folio) continue; /* Pick the best candidate if possible. */ if (!found || (is_page_sharing_candidate(dup) && (!is_page_sharing_candidate(found) || dup->rmap_hlist_len > found_rmap_hlist_len))) { if (found) folio_put(tree_folio); found = dup; found_rmap_hlist_len = found->rmap_hlist_len; tree_folio = folio; /* skip put_page for found candidate */ if (!prune_stale_stable_nodes && is_page_sharing_candidate(found)) break; continue; } folio_put(folio); } if (found) { if (hlist_is_singular_node(&found->hlist_dup, &stable_node->hlist)) { /* * If there's not just one entry it would * corrupt memory, better BUG_ON. In KSM * context with no lock held it's not even * fatal. */ BUG_ON(stable_node->hlist.first->next); /* * There's just one entry and it is below the * deduplication limit so drop the chain. */ rb_replace_node(&stable_node->node, &found->node, root); free_stable_node(stable_node); ksm_stable_node_chains--; ksm_stable_node_dups--; /* * NOTE: the caller depends on the stable_node * to be equal to stable_node_dup if the chain * was collapsed. */ *_stable_node = found; /* * Just for robustness, as stable_node is * otherwise left as a stable pointer, the * compiler shall optimize it away at build * time. */ stable_node = NULL; } else if (stable_node->hlist.first != &found->hlist_dup && __is_page_sharing_candidate(found, 1)) { /* * If the found stable_node dup can accept one * more future merge (in addition to the one * that is underway) and is not at the head of * the chain, put it there so next search will * be quicker in the !prune_stale_stable_nodes * case. * * NOTE: it would be inaccurate to use nr > 1 * instead of checking the hlist.first pointer * directly, because in the * prune_stale_stable_nodes case "nr" isn't * the position of the found dup in the chain, * but the total number of dups in the chain. */ hlist_del(&found->hlist_dup); hlist_add_head(&found->hlist_dup, &stable_node->hlist); } } else { /* Its hlist must be empty if no one found. */ free_stable_node_chain(stable_node, root); } *_stable_node_dup = found; return tree_folio; } /* * Like for ksm_get_folio, this function can free the *_stable_node and * *_stable_node_dup if the returned tree_page is NULL. * * It can also free and overwrite *_stable_node with the found * stable_node_dup if the chain is collapsed (in which case * *_stable_node will be equal to *_stable_node_dup like if the chain * never existed). It's up to the caller to verify tree_page is not * NULL before dereferencing *_stable_node or *_stable_node_dup. * * *_stable_node_dup is really a second output parameter of this * function and will be overwritten in all cases, the caller doesn't * need to initialize it. */ static struct folio *__stable_node_chain(struct ksm_stable_node **_stable_node_dup, struct ksm_stable_node **_stable_node, struct rb_root *root, bool prune_stale_stable_nodes) { struct ksm_stable_node *stable_node = *_stable_node; if (!is_stable_node_chain(stable_node)) { *_stable_node_dup = stable_node; return ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); } return stable_node_dup(_stable_node_dup, _stable_node, root, prune_stale_stable_nodes); } static __always_inline struct folio *chain_prune(struct ksm_stable_node **s_n_d, struct ksm_stable_node **s_n, struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, true); } static __always_inline struct folio *chain(struct ksm_stable_node **s_n_d, struct ksm_stable_node **s_n, struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, false); } /* * stable_tree_search - search for page inside the stable tree * * This function checks if there is a page inside the stable tree * with identical content to the page that we are scanning right now. * * This function returns the stable tree node of identical content if found, * -EBUSY if the stable node's page is being migrated, NULL otherwise. */ static struct folio *stable_tree_search(struct page *page) { int nid; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; struct ksm_stable_node *page_node; struct folio *folio; folio = page_folio(page); page_node = folio_stable_node(folio); if (page_node && page_node->head != &migrate_nodes) { /* ksm page forked */ folio_get(folio); return folio; } nid = get_kpfn_nid(folio_pfn(folio)); root = root_stable_tree + nid; again: new = &root->rb_node; parent = NULL; while (*new) { struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); tree_folio = chain_prune(&stable_node_dup, &stable_node, root); if (!tree_folio) { /* * If we walked over a stale stable_node, * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate * false negative insertions just because some * stable_node was stale. */ goto again; } ret = memcmp_pages(page, &tree_folio->page); folio_put(tree_folio); parent = *new; if (ret < 0) new = &parent->rb_left; else if (ret > 0) new = &parent->rb_right; else { if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); /* * If the mapcount of our migrated KSM folio is * at most 1, we can merge it with another * KSM folio where we know that we have space * for one more mapping without exceeding the * ksm_max_page_sharing limit: see * chain_prune(). This way, we can avoid adding * this stable node to the chain. */ if (folio_mapcount(folio) > 1) goto chain_append; } if (!is_page_sharing_candidate(stable_node_dup)) { /* * If the stable_node is a chain and * we got a payload match in memcmp * but we cannot merge the scanned * page in any of the existing * stable_node dups because they're * all full, we need to wait the * scanned page to find itself a match * in the unstable tree to create a * brand new KSM page to add later to * the dups of this stable_node. */ return NULL; } /* * Lock and unlock the stable_node's page (which * might already have been migrated) so that page * migration is sure to notice its raised count. * It would be more elegant to return stable_node * than kpage, but that involves more changes. */ tree_folio = ksm_get_folio(stable_node_dup, KSM_GET_FOLIO_TRYLOCK); if (PTR_ERR(tree_folio) == -EBUSY) return ERR_PTR(-EBUSY); if (unlikely(!tree_folio)) /* * The tree may have been rebalanced, * so re-evaluate parent and new. */ goto again; folio_unlock(tree_folio); if (get_kpfn_nid(stable_node_dup->kpfn) != NUMA(stable_node_dup->nid)) { folio_put(tree_folio); goto replace; } return tree_folio; } } if (!page_node) return NULL; list_del(&page_node->list); DO_NUMA(page_node->nid = nid); rb_link_node(&page_node->node, parent, new); rb_insert_color(&page_node->node, root); out: if (is_page_sharing_candidate(page_node)) { folio_get(folio); return folio; } else return NULL; replace: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { VM_BUG_ON(is_stable_node_chain(stable_node_dup)); VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* there is no chain */ if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); rb_replace_node(&stable_node_dup->node, &page_node->node, root); if (is_page_sharing_candidate(page_node)) folio_get(folio); else folio = NULL; } else { rb_erase(&stable_node_dup->node, root); folio = NULL; } } else { VM_BUG_ON(!is_stable_node_chain(stable_node)); __stable_node_dup_del(stable_node_dup); if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); if (is_page_sharing_candidate(page_node)) folio_get(folio); else folio = NULL; } else { folio = NULL; } } stable_node_dup->head = &migrate_nodes; list_add(&stable_node_dup->list, stable_node_dup->head); return folio; chain_append: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* chain is missing so create it */ stable_node = alloc_stable_node_chain(stable_node_dup, root); if (!stable_node) return NULL; } /* * Add this stable_node dup that was * migrated to the stable_node chain * of the current nid for this page * content. */ VM_BUG_ON(!is_stable_node_dup(stable_node_dup)); VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); goto out; } /* * stable_tree_insert - insert stable tree node pointing to new ksm page * into the stable tree. * * This function returns the stable tree node just allocated on success, * NULL otherwise. */ static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio) { int nid; unsigned long kpfn; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; bool need_chain = false; kpfn = folio_pfn(kfolio); nid = get_kpfn_nid(kpfn); root = root_stable_tree + nid; again: parent = NULL; new = &root->rb_node; while (*new) { struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); tree_folio = chain(&stable_node_dup, &stable_node, root); if (!tree_folio) { /* * If we walked over a stale stable_node, * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate * false negative insertions just because some * stable_node was stale. */ goto again; } ret = memcmp_pages(&kfolio->page, &tree_folio->page); folio_put(tree_folio); parent = *new; if (ret < 0) new = &parent->rb_left; else if (ret > 0) new = &parent->rb_right; else { need_chain = true; break; } } stable_node_dup = alloc_stable_node(); if (!stable_node_dup) return NULL; INIT_HLIST_HEAD(&stable_node_dup->hlist); stable_node_dup->kpfn = kpfn; stable_node_dup->rmap_hlist_len = 0; DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) { rb_link_node(&stable_node_dup->node, parent, new); rb_insert_color(&stable_node_dup->node, root); } else { if (!is_stable_node_chain(stable_node)) { struct ksm_stable_node *orig = stable_node; /* chain is missing so create it */ stable_node = alloc_stable_node_chain(orig, root); if (!stable_node) { free_stable_node(stable_node_dup); return NULL; } } stable_node_chain_add_dup(stable_node_dup, stable_node); } folio_set_stable_node(kfolio, stable_node_dup); return stable_node_dup; } /* * unstable_tree_search_insert - search for identical page, * else insert rmap_item into the unstable tree. * * This function searches for a page in the unstable tree identical to the * page currently being scanned; and if no identical page is found in the * tree, we insert rmap_item as a new object into the unstable tree. * * This function returns pointer to rmap_item found to be identical * to the currently scanned page, NULL otherwise. * * This function does both searching and inserting, because they share * the same walking algorithm in an rbtree. */ static struct ksm_rmap_item *unstable_tree_search_insert(struct ksm_rmap_item *rmap_item, struct page *page, struct page **tree_pagep) { struct rb_node **new; struct rb_root *root; struct rb_node *parent = NULL; int nid; nid = get_kpfn_nid(page_to_pfn(page)); root = root_unstable_tree + nid; new = &root->rb_node; while (*new) { struct ksm_rmap_item *tree_rmap_item; struct page *tree_page; int ret; cond_resched(); tree_rmap_item = rb_entry(*new, struct ksm_rmap_item, node); tree_page = get_mergeable_page(tree_rmap_item); if (!tree_page) return NULL; /* * Don't substitute a ksm page for a forked page. */ if (page == tree_page) { put_page(tree_page); return NULL; } ret = memcmp_pages(page, tree_page); parent = *new; if (ret < 0) { put_page(tree_page); new = &parent->rb_left; } else if (ret > 0) { put_page(tree_page); new = &parent->rb_right; } else if (!ksm_merge_across_nodes && page_to_nid(tree_page) != nid) { /* * If tree_page has been migrated to another NUMA node, * it will be flushed out and put in the right unstable * tree next time: only merge with it when across_nodes. */ put_page(tree_page); return NULL; } else { *tree_pagep = tree_page; return tree_rmap_item; } } rmap_item->address |= UNSTABLE_FLAG; rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK); DO_NUMA(rmap_item->nid = nid); rb_link_node(&rmap_item->node, parent, new); rb_insert_color(&rmap_item->node, root); ksm_pages_unshared++; return NULL; } /* * stable_tree_append - add another rmap_item to the linked list of * rmap_items hanging off a given node of the stable tree, all sharing * the same ksm page. */ static void stable_tree_append(struct ksm_rmap_item *rmap_item, struct ksm_stable_node *stable_node, bool max_page_sharing_bypass) { /* * rmap won't find this mapping if we don't insert the * rmap_item in the right stable_node * duplicate. page_migration could break later if rmap breaks, * so we can as well crash here. We really need to check for * rmap_hlist_len == STABLE_NODE_CHAIN, but we can as well check * for other negative values as an underflow if detected here * for the first time (and not when decreasing rmap_hlist_len) * would be sign of memory corruption in the stable_node. */ BUG_ON(stable_node->rmap_hlist_len < 0); stable_node->rmap_hlist_len++; if (!max_page_sharing_bypass) /* possibly non fatal but unexpected overflow, only warn */ WARN_ON_ONCE(stable_node->rmap_hlist_len > ksm_max_page_sharing); rmap_item->head = stable_node; rmap_item->address |= STABLE_FLAG; hlist_add_head(&rmap_item->hlist, &stable_node->hlist); if (rmap_item->hlist.next) ksm_pages_sharing++; else ksm_pages_shared++; rmap_item->mm->ksm_merging_pages++; } /* * cmp_and_merge_page - first see if page can be merged into the stable tree; * if not, compare checksum to previous and if it's the same, see if page can * be inserted into the unstable tree, or merged with a page already there and * both transferred to the stable tree. * * @page: the page that we are searching identical page to. * @rmap_item: the reverse mapping into the virtual address of this page */ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_item) { struct ksm_rmap_item *tree_rmap_item; struct page *tree_page = NULL; struct ksm_stable_node *stable_node; struct folio *kfolio; unsigned int checksum; int err; bool max_page_sharing_bypass = false; stable_node = page_stable_node(page); if (stable_node) { if (stable_node->head != &migrate_nodes && get_kpfn_nid(READ_ONCE(stable_node->kpfn)) != NUMA(stable_node->nid)) { stable_node_dup_del(stable_node); stable_node->head = &migrate_nodes; list_add(&stable_node->list, stable_node->head); } if (stable_node->head != &migrate_nodes && rmap_item->head == stable_node) return; /* * If it's a KSM fork, allow it to go over the sharing limit * without warnings. */ if (!is_page_sharing_candidate(stable_node)) max_page_sharing_bypass = true; } else { remove_rmap_item_from_tree(rmap_item); /* * If the hash value of the page has changed from the last time * we calculated it, this page is changing frequently: therefore we * don't want to insert it in the unstable tree, and we don't want * to waste our time searching for something identical to it there. */ checksum = calc_checksum(page); if (rmap_item->oldchecksum != checksum) { rmap_item->oldchecksum = checksum; return; } if (!try_to_merge_with_zero_page(rmap_item, page)) return; } /* Start by searching for the folio in the stable tree */ kfolio = stable_tree_search(page); if (&kfolio->page == page && rmap_item->head == stable_node) { folio_put(kfolio); return; } remove_rmap_item_from_tree(rmap_item); if (kfolio) { if (kfolio == ERR_PTR(-EBUSY)) return; err = try_to_merge_with_ksm_page(rmap_item, page, &kfolio->page); if (!err) { /* * The page was successfully merged: * add its rmap_item to the stable tree. */ folio_lock(kfolio); stable_tree_append(rmap_item, folio_stable_node(kfolio), max_page_sharing_bypass); folio_unlock(kfolio); } folio_put(kfolio); return; } tree_rmap_item = unstable_tree_search_insert(rmap_item, page, &tree_page); if (tree_rmap_item) { bool split; kfolio = try_to_merge_two_pages(rmap_item, page, tree_rmap_item, tree_page); /* * If both pages we tried to merge belong to the same compound * page, then we actually ended up increasing the reference * count of the same compound page twice, and split_huge_page * failed. * Here we set a flag if that happened, and we use it later to * try split_huge_page again. Since we call put_page right * afterwards, the reference count will be correct and * split_huge_page should succeed. */ split = PageTransCompound(page) && compound_head(page) == compound_head(tree_page); put_page(tree_page); if (kfolio) { /* * The pages were successfully merged: insert new * node in the stable tree and add both rmap_items. */ folio_lock(kfolio); stable_node = stable_tree_insert(kfolio); if (stable_node) { stable_tree_append(tree_rmap_item, stable_node, false); stable_tree_append(rmap_item, stable_node, false); } folio_unlock(kfolio); /* * If we fail to insert the page into the stable tree, * we will have 2 virtual addresses that are pointing * to a ksm page left outside the stable tree, * in which case we need to break_cow on both. */ if (!stable_node) { break_cow(tree_rmap_item); break_cow(rmap_item); } } else if (split) { /* * We are here if we tried to merge two pages and * failed because they both belonged to the same * compound page. We will split the page now, but no * merging will take place. * We do not want to add the cost of a full lock; if * the page is locked, it is better to skip it and * perhaps try again later. */ if (!trylock_page(page)) return; split_huge_page(page); unlock_page(page); } } } static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot, struct ksm_rmap_item **rmap_list, unsigned long addr) { struct ksm_rmap_item *rmap_item; while (*rmap_list) { rmap_item = *rmap_list; if ((rmap_item->address & PAGE_MASK) == addr) return rmap_item; if (rmap_item->address > addr) break; *rmap_list = rmap_item->rmap_list; remove_rmap_item_from_tree(rmap_item); free_rmap_item(rmap_item); } rmap_item = alloc_rmap_item(); if (rmap_item) { /* It has already been zeroed */ rmap_item->mm = mm_slot->slot.mm; rmap_item->mm->ksm_rmap_items++; rmap_item->address = addr; rmap_item->rmap_list = *rmap_list; *rmap_list = rmap_item; } return rmap_item; } /* * Calculate skip age for the ksm page age. The age determines how often * de-duplicating has already been tried unsuccessfully. If the age is * smaller, the scanning of this page is skipped for less scans. * * @age: rmap_item age of page */ static unsigned int skip_age(rmap_age_t age) { if (age <= 3) return 1; if (age <= 5) return 2; if (age <= 8) return 4; return 8; } /* * Determines if a page should be skipped for the current scan. * * @folio: folio containing the page to check * @rmap_item: associated rmap_item of page */ static bool should_skip_rmap_item(struct folio *folio, struct ksm_rmap_item *rmap_item) { rmap_age_t age; if (!ksm_smart_scan) return false; /* * Never skip pages that are already KSM; pages cmp_and_merge_page() * will essentially ignore them, but we still have to process them * properly. */ if (folio_test_ksm(folio)) return false; age = rmap_item->age; if (age != U8_MAX) rmap_item->age++; /* * Smaller ages are not skipped, they need to get a chance to go * through the different phases of the KSM merging. */ if (age < 3) return false; /* * Are we still allowed to skip? If not, then don't skip it * and determine how much more often we are allowed to skip next. */ if (!rmap_item->remaining_skips) { rmap_item->remaining_skips = skip_age(age); return false; } /* Skip this page */ ksm_pages_skipped++; rmap_item->remaining_skips--; remove_rmap_item_from_tree(rmap_item); return true; } static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) { struct mm_struct *mm; struct ksm_mm_slot *mm_slot; struct mm_slot *slot; struct vm_area_struct *vma; struct ksm_rmap_item *rmap_item; struct vma_iterator vmi; int nid; if (list_empty(&ksm_mm_head.slot.mm_node)) return NULL; mm_slot = ksm_scan.mm_slot; if (mm_slot == &ksm_mm_head) { advisor_start_scan(); trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items); /* * A number of pages can hang around indefinitely in per-cpu * LRU cache, raised page count preventing write_protect_page * from merging them. Though it doesn't really matter much, * it is puzzling to see some stuck in pages_volatile until * other activity jostles them out, and they also prevented * LTP's KSM test from succeeding deterministically; so drain * them here (here rather than on entry to ksm_do_scan(), * so we don't IPI too often when pages_to_scan is set low). */ lru_add_drain_all(); /* * Whereas stale stable_nodes on the stable_tree itself * get pruned in the regular course of stable_tree_search(), * those moved out to the migrate_nodes list can accumulate: * so prune them once before each full scan. */ if (!ksm_merge_across_nodes) { struct ksm_stable_node *stable_node, *next; struct folio *folio; list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); if (folio) folio_put(folio); cond_resched(); } } for (nid = 0; nid < ksm_nr_node_ids; nid++) root_unstable_tree[nid] = RB_ROOT; spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); ksm_scan.mm_slot = mm_slot; spin_unlock(&ksm_mmlist_lock); /* * Although we tested list_empty() above, a racing __ksm_exit * of the last mm on the list may have removed it since then. */ if (mm_slot == &ksm_mm_head) return NULL; next_mm: ksm_scan.address = 0; ksm_scan.rmap_list = &mm_slot->rmap_list; } slot = &mm_slot->slot; mm = slot->mm; vma_iter_init(&vmi, mm, ksm_scan.address); mmap_read_lock(mm); if (ksm_test_exit(mm)) goto no_vmas; for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE)) continue; if (ksm_scan.address < vma->vm_start) ksm_scan.address = vma->vm_start; if (!vma->anon_vma) ksm_scan.address = vma->vm_end; while (ksm_scan.address < vma->vm_end) { struct page *tmp_page = NULL; struct folio_walk fw; struct folio *folio; if (ksm_test_exit(mm)) break; folio = folio_walk_start(&fw, vma, ksm_scan.address, 0); if (folio) { if (!folio_is_zone_device(folio) && folio_test_anon(folio)) { folio_get(folio); tmp_page = fw.page; } folio_walk_end(&fw, vma); } if (tmp_page) { flush_anon_page(vma, tmp_page, ksm_scan.address); flush_dcache_page(tmp_page); rmap_item = get_next_rmap_item(mm_slot, ksm_scan.rmap_list, ksm_scan.address); if (rmap_item) { ksm_scan.rmap_list = &rmap_item->rmap_list; if (should_skip_rmap_item(folio, rmap_item)) { folio_put(folio); goto next_page; } ksm_scan.address += PAGE_SIZE; *page = tmp_page; } else { folio_put(folio); } mmap_read_unlock(mm); return rmap_item; } next_page: ksm_scan.address += PAGE_SIZE; cond_resched(); } } if (ksm_test_exit(mm)) { no_vmas: ksm_scan.address = 0; ksm_scan.rmap_list = &mm_slot->rmap_list; } /* * Nuke all the rmap_items that are above this current rmap: * because there were no VM_MERGEABLE vmas with such addresses. */ remove_trailing_rmap_items(ksm_scan.rmap_list); spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_scan.address == 0) { /* * We've completed a full scan of all vmas, holding mmap_lock * throughout, and found no VM_MERGEABLE: so do the same as * __ksm_exit does to remove this mm from all our lists now. * This applies either when cleaning up after __ksm_exit * (but beware: we can reach here even before __ksm_exit), * or when all VM_MERGEABLE areas have been unmapped (and * mmap_lock then protects against race with MADV_MERGEABLE). */ hash_del(&mm_slot->slot.hash); list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmap_read_unlock(mm); mmdrop(mm); } else { mmap_read_unlock(mm); /* * mmap_read_unlock(mm) first because after * spin_unlock(&ksm_mmlist_lock) run, the "mm" may * already have been freed under us by __ksm_exit() * because the "mm_slot" is still hashed and * ksm_scan.mm_slot doesn't point to it anymore. */ spin_unlock(&ksm_mmlist_lock); } /* Repeat until we've completed scanning the whole list */ mm_slot = ksm_scan.mm_slot; if (mm_slot != &ksm_mm_head) goto next_mm; advisor_stop_scan(); trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items); ksm_scan.seqnr++; return NULL; } /** * ksm_do_scan - the ksm scanner main worker function. * @scan_npages: number of pages we want to scan before we return. */ static void ksm_do_scan(unsigned int scan_npages) { struct ksm_rmap_item *rmap_item; struct page *page; while (scan_npages-- && likely(!freezing(current))) { cond_resched(); rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) return; cmp_and_merge_page(page, rmap_item); put_page(page); ksm_pages_scanned++; } } static int ksmd_should_run(void) { return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.slot.mm_node); } static int ksm_scan_thread(void *nothing) { unsigned int sleep_ms; set_freezable(); set_user_nice(current, 5); while (!kthread_should_stop()) { mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksmd_should_run()) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); if (ksmd_should_run()) { sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs); wait_event_freezable_timeout(ksm_iter_wait, sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), msecs_to_jiffies(sleep_ms)); } else { wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); } } return 0; } static bool __ksm_should_add_vma(const struct file *file, vm_flags_t vm_flags) { if (vm_flags & VM_MERGEABLE) return false; return ksm_compatible(file, vm_flags); } static void __ksm_add_vma(struct vm_area_struct *vma) { if (__ksm_should_add_vma(vma->vm_file, vma->vm_flags)) vm_flags_set(vma, VM_MERGEABLE); } static int __ksm_del_vma(struct vm_area_struct *vma) { int err; if (!(vma->vm_flags & VM_MERGEABLE)) return 0; if (vma->anon_vma) { err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, true); if (err) return err; } vm_flags_clear(vma, VM_MERGEABLE); return 0; } /** * ksm_vma_flags - Update VMA flags to mark as mergeable if compatible * * @mm: Proposed VMA's mm_struct * @file: Proposed VMA's file-backed mapping, if any. * @vm_flags: Proposed VMA"s flags. * * Returns: @vm_flags possibly updated to mark mergeable. */ vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file, vm_flags_t vm_flags) { if (test_bit(MMF_VM_MERGE_ANY, &mm->flags) && __ksm_should_add_vma(file, vm_flags)) vm_flags |= VM_MERGEABLE; return vm_flags; } static void ksm_add_vmas(struct mm_struct *mm) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) __ksm_add_vma(vma); } static int ksm_del_vmas(struct mm_struct *mm) { struct vm_area_struct *vma; int err; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) { err = __ksm_del_vma(vma); if (err) return err; } return 0; } /** * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all * compatible VMA's * * @mm: Pointer to mm * * Returns 0 on success, otherwise error code */ int ksm_enable_merge_any(struct mm_struct *mm) { int err; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return 0; if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { err = __ksm_enter(mm); if (err) return err; } set_bit(MMF_VM_MERGE_ANY, &mm->flags); ksm_add_vmas(mm); return 0; } /** * ksm_disable_merge_any - Disable merging on all compatible VMA's of the mm, * previously enabled via ksm_enable_merge_any(). * * Disabling merging implies unmerging any merged pages, like setting * MADV_UNMERGEABLE would. If unmerging fails, the whole operation fails and * merging on all compatible VMA's remains enabled. * * @mm: Pointer to mm * * Returns 0 on success, otherwise error code */ int ksm_disable_merge_any(struct mm_struct *mm) { int err; if (!test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return 0; err = ksm_del_vmas(mm); if (err) { ksm_add_vmas(mm); return err; } clear_bit(MMF_VM_MERGE_ANY, &mm->flags); return 0; } int ksm_disable(struct mm_struct *mm) { mmap_assert_write_locked(mm); if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) return 0; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return ksm_disable_merge_any(mm); return ksm_del_vmas(mm); } int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, vm_flags_t *vm_flags) { struct mm_struct *mm = vma->vm_mm; int err; switch (advice) { case MADV_MERGEABLE: if (vma->vm_flags & VM_MERGEABLE) return 0; if (!vma_ksm_compatible(vma)) return 0; if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { err = __ksm_enter(mm); if (err) return err; } *vm_flags |= VM_MERGEABLE; break; case MADV_UNMERGEABLE: if (!(*vm_flags & VM_MERGEABLE)) return 0; /* just ignore the advice */ if (vma->anon_vma) { err = unmerge_ksm_pages(vma, start, end, true); if (err) return err; } *vm_flags &= ~VM_MERGEABLE; break; } return 0; } EXPORT_SYMBOL_GPL(ksm_madvise); int __ksm_enter(struct mm_struct *mm) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; int needs_wakeup; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return -ENOMEM; slot = &mm_slot->slot; /* Check ksm_run too? Would need tighter locking */ needs_wakeup = list_empty(&ksm_mm_head.slot.mm_node); spin_lock(&ksm_mmlist_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * When KSM_RUN_MERGE (or KSM_RUN_STOP), * insert just behind the scanning cursor, to let the area settle * down a little; when fork is followed by immediate exec, we don't * want ksmd to waste time setting up and tearing down an rmap_list. * * But when KSM_RUN_UNMERGE, it's important to insert ahead of its * scanning cursor, otherwise KSM pages in newly forked mms will be * missed: then we might as well insert at the end of the list. */ if (ksm_run & KSM_RUN_UNMERGE) list_add_tail(&slot->mm_node, &ksm_mm_head.slot.mm_node); else list_add_tail(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); set_bit(MMF_VM_MERGEABLE, &mm->flags); mmgrab(mm); if (needs_wakeup) wake_up_interruptible(&ksm_thread_wait); trace_ksm_enter(mm); return 0; } void __ksm_exit(struct mm_struct *mm) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; int easy_to_free = 0; /* * This process is exiting: if it's straightforward (as is the * case when ksmd was never running), free mm_slot immediately. * But if it's at the cursor or has rmap_items linked to it, use * mmap_lock to synchronize with any break_cows before pagetables * are freed, and leave the mm_slot on the list for ksmd to free. * Beware: ksm may already have noticed it exiting and freed the slot. */ spin_lock(&ksm_mmlist_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (mm_slot && ksm_scan.mm_slot != mm_slot) { if (!mm_slot->rmap_list) { hash_del(&slot->hash); list_del(&slot->mm_node); easy_to_free = 1; } else { list_move(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); } } spin_unlock(&ksm_mmlist_lock); if (easy_to_free) { mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); clear_bit(MMF_VM_MERGEABLE, &mm->flags); mmdrop(mm); } else if (mm_slot) { mmap_write_lock(mm); mmap_write_unlock(mm); } trace_ksm_exit(mm); } struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { struct page *page = folio_page(folio, 0); struct anon_vma *anon_vma = folio_anon_vma(folio); struct folio *new_folio; if (folio_test_large(folio)) return folio; if (folio_test_ksm(folio)) { if (folio_stable_node(folio) && !(ksm_run & KSM_RUN_UNMERGE)) return folio; /* no need to copy it */ } else if (!anon_vma) { return folio; /* no need to copy it */ } else if (folio->index == linear_page_index(vma, addr) && anon_vma->root == vma->anon_vma->root) { return folio; /* still no need to copy it */ } if (PageHWPoison(page)) return ERR_PTR(-EHWPOISON); if (!folio_test_uptodate(folio)) return folio; /* let do_swap_page report the error */ new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); if (new_folio && mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) { folio_put(new_folio); new_folio = NULL; } if (new_folio) { if (copy_mc_user_highpage(folio_page(new_folio, 0), page, addr, vma)) { folio_put(new_folio); return ERR_PTR(-EHWPOISON); } folio_set_dirty(new_folio); __folio_mark_uptodate(new_folio); __folio_set_locked(new_folio); #ifdef CONFIG_SWAP count_vm_event(KSM_SWPIN_COPY); #endif } return new_folio; } void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { struct ksm_stable_node *stable_node; struct ksm_rmap_item *rmap_item; int search_new_forks = 0; VM_BUG_ON_FOLIO(!folio_test_ksm(folio), folio); /* * Rely on the page lock to protect against concurrent modifications * to that page's node of the stable tree. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); stable_node = folio_stable_node(folio); if (!stable_node) return; again: hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; struct anon_vma_chain *vmac; struct vm_area_struct *vma; cond_resched(); if (!anon_vma_trylock_read(anon_vma)) { if (rwc->try_lock) { rwc->contended = true; return; } anon_vma_lock_read(anon_vma); } anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, 0, ULONG_MAX) { unsigned long addr; cond_resched(); vma = vmac->vma; /* Ignore the stable/unstable/sqnr flags */ addr = rmap_item->address & PAGE_MASK; if (addr < vma->vm_start || addr >= vma->vm_end) continue; /* * Initially we examine only the vma which covers this * rmap_item; but later, if there is still work to do, * we examine covering vmas in other mms: in case they * were forked from the original since ksmd passed. */ if ((rmap_item->mm == vma->vm_mm) == search_new_forks) continue; if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, addr, rwc->arg)) { anon_vma_unlock_read(anon_vma); return; } if (rwc->done && rwc->done(folio)) { anon_vma_unlock_read(anon_vma); return; } } anon_vma_unlock_read(anon_vma); } if (!search_new_forks++) goto again; } #ifdef CONFIG_MEMORY_FAILURE /* * Collect processes when the error hit an ksm page. */ void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early) { struct ksm_stable_node *stable_node; struct ksm_rmap_item *rmap_item; struct vm_area_struct *vma; struct task_struct *tsk; stable_node = folio_stable_node(folio); if (!stable_node) return; hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *av = rmap_item->anon_vma; anon_vma_lock_read(av); rcu_read_lock(); for_each_process(tsk) { struct anon_vma_chain *vmac; unsigned long addr; struct task_struct *t = task_early_kill(tsk, force_early); if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, 0, ULONG_MAX) { vma = vmac->vma; if (vma->vm_mm == t->mm) { addr = rmap_item->address & PAGE_MASK; add_to_kill_ksm(t, page, vma, to_kill, addr); } } } rcu_read_unlock(); anon_vma_unlock_read(av); } } #endif #ifdef CONFIG_MIGRATION void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) { struct ksm_stable_node *stable_node; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio); stable_node = folio_stable_node(folio); if (stable_node) { VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio); stable_node->kpfn = folio_pfn(newfolio); /* * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible * to ksm_get_folio() before it can see that folio->mapping * has gone stale (or that the swapcache flag has been cleared). */ smp_wmb(); folio_set_stable_node(folio, NULL); } } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE static void wait_while_offlining(void) { while (ksm_run & KSM_RUN_OFFLINE) { mutex_unlock(&ksm_thread_mutex); wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), TASK_UNINTERRUPTIBLE); mutex_lock(&ksm_thread_mutex); } } static bool stable_node_dup_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) { /* * Don't ksm_get_folio, page has already gone: * which is why we keep kpfn instead of page* */ remove_node_from_stable_tree(stable_node); return true; } return false; } static bool stable_node_chain_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn, struct rb_root *root) { struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { VM_BUG_ON(is_stable_node_dup(stable_node)); return stable_node_dup_remove_range(stable_node, start_pfn, end_pfn); } hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { VM_BUG_ON(!is_stable_node_dup(dup)); stable_node_dup_remove_range(dup, start_pfn, end_pfn); } if (hlist_empty(&stable_node->hlist)) { free_stable_node_chain(stable_node, root); return true; /* notify caller that tree was rebalanced */ } else return false; } static void ksm_check_stable_tree(unsigned long start_pfn, unsigned long end_pfn) { struct ksm_stable_node *stable_node, *next; struct rb_node *node; int nid; for (nid = 0; nid < ksm_nr_node_ids; nid++) { node = rb_first(root_stable_tree + nid); while (node) { stable_node = rb_entry(node, struct ksm_stable_node, node); if (stable_node_chain_remove_range(stable_node, start_pfn, end_pfn, root_stable_tree + nid)) node = rb_first(root_stable_tree + nid); else node = rb_next(node); cond_resched(); } } list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) remove_node_from_stable_tree(stable_node); cond_resched(); } } static int ksm_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; switch (action) { case MEM_GOING_OFFLINE: /* * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items() * and remove_all_stable_nodes() while memory is going offline: * it is unsafe for them to touch the stable tree at this time. * But unmerge_ksm_pages(), rmap lookups and other entry points * which do not need the ksm_thread_mutex are all safe. */ mutex_lock(&ksm_thread_mutex); ksm_run |= KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); break; case MEM_OFFLINE: /* * Most of the work is done by page migration; but there might * be a few stable_nodes left over, still pointing to struct * pages which have been offlined: prune those from the tree, * otherwise ksm_get_folio() might later try to access a * non-existent struct page. */ ksm_check_stable_tree(mn->start_pfn, mn->start_pfn + mn->nr_pages); fallthrough; case MEM_CANCEL_OFFLINE: mutex_lock(&ksm_thread_mutex); ksm_run &= ~KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); smp_mb(); /* wake_up_bit advises this */ wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE)); break; } return NOTIFY_OK; } #else static void wait_while_offlining(void) { } #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_PROC_FS /* * The process is mergeable only if any VMA is currently * applicable to KSM. * * The mmap lock must be held in read mode. */ bool ksm_process_mergeable(struct mm_struct *mm) { struct vm_area_struct *vma; mmap_assert_locked(mm); VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) if (vma->vm_flags & VM_MERGEABLE) return true; return false; } long ksm_process_profit(struct mm_struct *mm) { return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSFS /* * This all compiles without CONFIG_SYSFS, but is a waste of space. */ #define KSM_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define KSM_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static ssize_t sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_thread_sleep_millisecs); } static ssize_t 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; ksm_thread_sleep_millisecs = msecs; wake_up_interruptible(&ksm_iter_wait); return count; } KSM_ATTR(sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_thread_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 nr_pages; int err; if (ksm_advisor != KSM_ADVISOR_NONE) return -EINVAL; err = kstrtouint(buf, 10, &nr_pages); if (err) return -EINVAL; ksm_thread_pages_to_scan = nr_pages; return count; } KSM_ATTR(pages_to_scan); static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_run); } static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int flags; int err; err = kstrtouint(buf, 10, &flags); if (err) return -EINVAL; if (flags > KSM_RUN_UNMERGE) return -EINVAL; /* * KSM_RUN_MERGE sets ksmd running, and 0 stops it running. * KSM_RUN_UNMERGE stops it running and unmerges all rmap_items, * breaking COW to free the pages_shared (but leaves mm_slots * on the list for when ksmd may be set running again). */ mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_run != flags) { ksm_run = flags; if (flags & KSM_RUN_UNMERGE) { set_current_oom_origin(); err = unmerge_and_remove_all_rmap_items(); clear_current_oom_origin(); if (err) { ksm_run = KSM_RUN_STOP; count = err; } } } mutex_unlock(&ksm_thread_mutex); if (flags & KSM_RUN_MERGE) wake_up_interruptible(&ksm_thread_wait); return count; } KSM_ATTR(run); #ifdef CONFIG_NUMA static ssize_t merge_across_nodes_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_merge_across_nodes); } static ssize_t merge_across_nodes_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long knob; err = kstrtoul(buf, 10, &knob); if (err) return err; if (knob > 1) return -EINVAL; mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_merge_across_nodes != knob) { if (ksm_pages_shared || remove_all_stable_nodes()) err = -EBUSY; else if (root_stable_tree == one_stable_tree) { struct rb_root *buf; /* * This is the first time that we switch away from the * default of merging across nodes: must now allocate * a buffer to hold as many roots as may be needed. * Allocate stable and unstable together: * MAXSMP NODES_SHIFT 10 will use 16kB. */ buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf), GFP_KERNEL); /* Let us assume that RB_ROOT is NULL is zero */ if (!buf) err = -ENOMEM; else { root_stable_tree = buf; root_unstable_tree = buf + nr_node_ids; /* Stable tree is empty but not the unstable */ root_unstable_tree[0] = one_unstable_tree[0]; } } if (!err) { ksm_merge_across_nodes = knob; ksm_nr_node_ids = knob ? 1 : nr_node_ids; } } mutex_unlock(&ksm_thread_mutex); return err ? err : count; } KSM_ATTR(merge_across_nodes); #endif static ssize_t use_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_use_zero_pages); } static ssize_t use_zero_pages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; bool value; err = kstrtobool(buf, &value); if (err) return -EINVAL; ksm_use_zero_pages = value; return count; } KSM_ATTR(use_zero_pages); static ssize_t max_page_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_max_page_sharing); } static ssize_t max_page_sharing_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; int knob; err = kstrtoint(buf, 10, &knob); if (err) return err; /* * When a KSM page is created it is shared by 2 mappings. This * being a signed comparison, it implicitly verifies it's not * negative. */ if (knob < 2) return -EINVAL; if (READ_ONCE(ksm_max_page_sharing) == knob) return count; mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_max_page_sharing != knob) { if (ksm_pages_shared || remove_all_stable_nodes()) err = -EBUSY; else ksm_max_page_sharing = knob; } mutex_unlock(&ksm_thread_mutex); return err ? err : count; } KSM_ATTR(max_page_sharing); static ssize_t pages_scanned_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_scanned); } KSM_ATTR_RO(pages_scanned); static ssize_t pages_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_shared); } KSM_ATTR_RO(pages_shared); static ssize_t pages_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_sharing); } KSM_ATTR_RO(pages_sharing); static ssize_t pages_unshared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_unshared); } KSM_ATTR_RO(pages_unshared); static ssize_t pages_volatile_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { long ksm_pages_volatile; ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared - ksm_pages_sharing - ksm_pages_unshared; /* * It was not worth any locking to calculate that statistic, * but it might therefore sometimes be negative: conceal that. */ if (ksm_pages_volatile < 0) ksm_pages_volatile = 0; return sysfs_emit(buf, "%ld\n", ksm_pages_volatile); } KSM_ATTR_RO(pages_volatile); static ssize_t pages_skipped_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_skipped); } KSM_ATTR_RO(pages_skipped); static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); } KSM_ATTR_RO(ksm_zero_pages); static ssize_t general_profit_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { long general_profit; general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - ksm_rmap_items * sizeof(struct ksm_rmap_item); return sysfs_emit(buf, "%ld\n", general_profit); } KSM_ATTR_RO(general_profit); static ssize_t stable_node_dups_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_stable_node_dups); } KSM_ATTR_RO(stable_node_dups); static ssize_t stable_node_chains_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_stable_node_chains); } KSM_ATTR_RO(stable_node_chains); static ssize_t stable_node_chains_prune_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_stable_node_chains_prune_millisecs); } static ssize_t stable_node_chains_prune_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; ksm_stable_node_chains_prune_millisecs = msecs; return count; } KSM_ATTR(stable_node_chains_prune_millisecs); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_scan.seqnr); } KSM_ATTR_RO(full_scans); static ssize_t smart_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_smart_scan); } static ssize_t smart_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; bool value; err = kstrtobool(buf, &value); if (err) return -EINVAL; ksm_smart_scan = value; return count; } KSM_ATTR(smart_scan); static ssize_t advisor_mode_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) output = "none [scan-time]"; else output = "[none] scan-time"; return sysfs_emit(buf, "%s\n", output); } static ssize_t advisor_mode_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { enum ksm_advisor_type curr_advisor = ksm_advisor; if (sysfs_streq("scan-time", buf)) ksm_advisor = KSM_ADVISOR_SCAN_TIME; else if (sysfs_streq("none", buf)) ksm_advisor = KSM_ADVISOR_NONE; else return -EINVAL; /* Set advisor default values */ if (curr_advisor != ksm_advisor) set_advisor_defaults(); return count; } KSM_ATTR(advisor_mode); static ssize_t advisor_max_cpu_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_advisor_max_cpu); } static ssize_t advisor_max_cpu_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_max_cpu = value; return count; } KSM_ATTR(advisor_max_cpu); static ssize_t advisor_min_pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_min_pages_to_scan); } static ssize_t advisor_min_pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_min_pages_to_scan = value; return count; } KSM_ATTR(advisor_min_pages_to_scan); static ssize_t advisor_max_pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_max_pages_to_scan); } static ssize_t advisor_max_pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_max_pages_to_scan = value; return count; } KSM_ATTR(advisor_max_pages_to_scan); static ssize_t advisor_target_scan_time_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_target_scan_time); } static ssize_t advisor_target_scan_time_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; if (value < 1) return -EINVAL; ksm_advisor_target_scan_time = value; return count; } KSM_ATTR(advisor_target_scan_time); static struct attribute *ksm_attrs[] = { &sleep_millisecs_attr.attr, &pages_to_scan_attr.attr, &run_attr.attr, &pages_scanned_attr.attr, &pages_shared_attr.attr, &pages_sharing_attr.attr, &pages_unshared_attr.attr, &pages_volatile_attr.attr, &pages_skipped_attr.attr, &ksm_zero_pages_attr.attr, &full_scans_attr.attr, #ifdef CONFIG_NUMA &merge_across_nodes_attr.attr, #endif &max_page_sharing_attr.attr, &stable_node_chains_attr.attr, &stable_node_dups_attr.attr, &stable_node_chains_prune_millisecs_attr.attr, &use_zero_pages_attr.attr, &general_profit_attr.attr, &smart_scan_attr.attr, &advisor_mode_attr.attr, &advisor_max_cpu_attr.attr, &advisor_min_pages_to_scan_attr.attr, &advisor_max_pages_to_scan_attr.attr, &advisor_target_scan_time_attr.attr, NULL, }; static const struct attribute_group ksm_attr_group = { .attrs = ksm_attrs, .name = "ksm", }; #endif /* CONFIG_SYSFS */ static int __init ksm_init(void) { struct task_struct *ksm_thread; int err; /* The correct value depends on page size and endianness */ zero_checksum = calc_checksum(ZERO_PAGE(0)); /* Default to false for backwards compatibility */ ksm_use_zero_pages = false; err = ksm_slab_init(); if (err) goto out; ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd"); if (IS_ERR(ksm_thread)) { pr_err("ksm: creating kthread failed\n"); err = PTR_ERR(ksm_thread); goto out_free; } #ifdef CONFIG_SYSFS err = sysfs_create_group(mm_kobj, &ksm_attr_group); if (err) { pr_err("ksm: register sysfs failed\n"); kthread_stop(ksm_thread); goto out_free; } #else ksm_run = KSM_RUN_MERGE; /* no way for user to start it */ #endif /* CONFIG_SYSFS */ #ifdef CONFIG_MEMORY_HOTREMOVE /* There is no significance to this priority 100 */ hotplug_memory_notifier(ksm_memory_callback, KSM_CALLBACK_PRI); #endif return 0; out_free: ksm_slab_free(); out: return err; } subsys_initcall(ksm_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * A policy database (policydb) specifies the * configuration data for the security 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. * * Updated: Frank Mayer <mayerf@tresys.com> and * Karl MacMillan <kmacmillan@tresys.com> * Added conditional policy language extensions * Copyright (C) 2003-2004 Tresys Technology, LLC */ #ifndef _SS_POLICYDB_H_ #define _SS_POLICYDB_H_ #include "symtab.h" #include "avtab.h" #include "sidtab.h" #include "ebitmap.h" #include "mls_types.h" #include "context.h" #include "constraint.h" /* * A datum type is defined for each kind of symbol * in the configuration data: individual permissions, * common prefixes for access vectors, classes, * users, roles, types, sensitivities, categories, etc. */ /* Permission attributes */ struct perm_datum { u32 value; /* permission bit + 1 */ }; /* Attributes of a common prefix for access vectors */ struct common_datum { u32 value; /* internal common value */ struct symtab permissions; /* common permissions */ }; /* Class attributes */ struct class_datum { u32 value; /* class value */ char *comkey; /* common name */ struct common_datum *comdatum; /* common datum */ struct symtab permissions; /* class-specific permission symbol table */ struct constraint_node *constraints; /* constraints on class perms */ struct constraint_node *validatetrans; /* special transition rules */ /* Options how a new object user, role, and type should be decided */ #define DEFAULT_SOURCE 1 #define DEFAULT_TARGET 2 char default_user; char default_role; char default_type; /* Options how a new object range should be decided */ #define DEFAULT_SOURCE_LOW 1 #define DEFAULT_SOURCE_HIGH 2 #define DEFAULT_SOURCE_LOW_HIGH 3 #define DEFAULT_TARGET_LOW 4 #define DEFAULT_TARGET_HIGH 5 #define DEFAULT_TARGET_LOW_HIGH 6 #define DEFAULT_GLBLUB 7 char default_range; }; /* Role attributes */ struct role_datum { u32 value; /* internal role value */ u32 bounds; /* boundary of role */ struct ebitmap dominates; /* set of roles dominated by this role */ struct ebitmap types; /* set of authorized types for role */ }; struct role_trans_key { u32 role; /* current role */ u32 type; /* program executable type, or new object type */ u32 tclass; /* process class, or new object class */ }; struct role_trans_datum { u32 new_role; /* new role */ }; struct filename_trans_key { u32 ttype; /* parent dir context */ u16 tclass; /* class of new object */ const char *name; /* last path component */ }; struct filename_trans_datum { struct ebitmap stypes; /* bitmap of source types for this otype */ u32 otype; /* resulting type of new object */ struct filename_trans_datum *next; /* record for next otype*/ }; struct role_allow { u32 role; /* current role */ u32 new_role; /* new role */ struct role_allow *next; }; /* Type attributes */ struct type_datum { u32 value; /* internal type value */ u32 bounds; /* boundary of type */ unsigned char primary; /* primary name? */ unsigned char attribute; /* attribute ?*/ }; /* User attributes */ struct user_datum { u32 value; /* internal user value */ u32 bounds; /* bounds of user */ struct ebitmap roles; /* set of authorized roles for user */ struct mls_range range; /* MLS range (min - max) for user */ struct mls_level dfltlevel; /* default login MLS level for user */ }; /* Sensitivity attributes */ struct level_datum { struct mls_level level; /* sensitivity and associated categories */ unsigned char isalias; /* is this sensitivity an alias for another? */ }; /* Category attributes */ struct cat_datum { u32 value; /* internal category bit + 1 */ unsigned char isalias; /* is this category an alias for another? */ }; struct range_trans { u32 source_type; u32 target_type; u32 target_class; }; /* Boolean data type */ struct cond_bool_datum { u32 value; /* internal type value */ int state; }; struct cond_node; /* * type set preserves data needed to determine constraint info from * policy source. This is not used by the kernel policy but allows * utilities such as audit2allow to determine constraint denials. */ struct type_set { struct ebitmap types; struct ebitmap negset; u32 flags; }; /* * The configuration data includes security contexts for * initial SIDs, unlabeled file systems, TCP and UDP port numbers, * network interfaces, and nodes. This structure stores the * relevant data for one such entry. Entries of the same kind * (e.g. all initial SIDs) are linked together into a list. */ struct ocontext { union { char *name; /* name of initial SID, fs, netif, fstype, path */ struct { u8 protocol; u16 low_port; u16 high_port; } port; /* TCP or UDP port information */ struct { u32 addr; u32 mask; } node; /* node information */ struct { u32 addr[4]; u32 mask[4]; } node6; /* IPv6 node information */ struct { u64 subnet_prefix; u16 low_pkey; u16 high_pkey; } ibpkey; struct { char *dev_name; u8 port; } ibendport; } u; union { u32 sclass; /* security class for genfs */ u32 behavior; /* labeling behavior for fs_use */ } v; struct context context[2]; /* security context(s) */ u32 sid[2]; /* SID(s) */ struct ocontext *next; }; struct genfs { char *fstype; struct ocontext *head; struct genfs *next; }; /* symbol table array indices */ #define SYM_COMMONS 0 #define SYM_CLASSES 1 #define SYM_ROLES 2 #define SYM_TYPES 3 #define SYM_USERS 4 #define SYM_BOOLS 5 #define SYM_LEVELS 6 #define SYM_CATS 7 #define SYM_NUM 8 /* object context array indices */ #define OCON_ISID 0 /* initial SIDs */ #define OCON_FS 1 /* unlabeled file systems (deprecated) */ #define OCON_PORT 2 /* TCP and UDP port numbers */ #define OCON_NETIF 3 /* network interfaces */ #define OCON_NODE 4 /* nodes */ #define OCON_FSUSE 5 /* fs_use */ #define OCON_NODE6 6 /* IPv6 nodes */ #define OCON_IBPKEY 7 /* Infiniband PKeys */ #define OCON_IBENDPORT 8 /* Infiniband end ports */ #define OCON_NUM 9 /* The policy database */ struct policydb { int mls_enabled; /* symbol tables */ struct symtab symtab[SYM_NUM]; #define p_commons symtab[SYM_COMMONS] #define p_classes symtab[SYM_CLASSES] #define p_roles symtab[SYM_ROLES] #define p_types symtab[SYM_TYPES] #define p_users symtab[SYM_USERS] #define p_bools symtab[SYM_BOOLS] #define p_levels symtab[SYM_LEVELS] #define p_cats symtab[SYM_CATS] /* symbol names indexed by (value - 1) */ char **sym_val_to_name[SYM_NUM]; /* class, role, and user attributes indexed by (value - 1) */ struct class_datum **class_val_to_struct; struct role_datum **role_val_to_struct; struct user_datum **user_val_to_struct; struct type_datum **type_val_to_struct; /* type enforcement access vectors and transitions */ struct avtab te_avtab; /* role transitions */ struct hashtab role_tr; /* file transitions with the last path component */ /* quickly exclude lookups when parent ttype has no rules */ struct ebitmap filename_trans_ttypes; /* actual set of filename_trans rules */ struct hashtab filename_trans; /* only used if policyvers < POLICYDB_VERSION_COMP_FTRANS */ u32 compat_filename_trans_count; /* bools indexed by (value - 1) */ struct cond_bool_datum **bool_val_to_struct; /* type enforcement conditional access vectors and transitions */ struct avtab te_cond_avtab; /* array indexing te_cond_avtab by conditional */ struct cond_node *cond_list; u32 cond_list_len; /* role allows */ struct role_allow *role_allow; /* security contexts of initial SIDs, unlabeled file systems, TCP or UDP port numbers, network interfaces and nodes */ struct ocontext *ocontexts[OCON_NUM]; /* security contexts for files in filesystems that cannot support a persistent label mapping or use another fixed labeling behavior. */ struct genfs *genfs; /* range transitions table (range_trans_key -> mls_range) */ struct hashtab range_tr; /* type -> attribute reverse mapping */ struct ebitmap *type_attr_map_array; struct ebitmap policycaps; struct ebitmap permissive_map; struct ebitmap neveraudit_map; /* length of this policy when it was loaded */ size_t len; unsigned int policyvers; unsigned int reject_unknown : 1; unsigned int allow_unknown : 1; u16 process_class; u32 process_trans_perms; } __randomize_layout; struct policy_file { char *data; size_t len; }; extern void policydb_destroy(struct policydb *p); extern int policydb_load_isids(struct policydb *p, struct sidtab *s); extern int policydb_context_isvalid(struct policydb *p, struct context *c); extern int policydb_class_isvalid(struct policydb *p, unsigned int class); extern int policydb_type_isvalid(struct policydb *p, unsigned int type); extern int policydb_role_isvalid(struct policydb *p, unsigned int role); extern int policydb_read(struct policydb *p, struct policy_file *fp); extern int policydb_write(struct policydb *p, struct policy_file *fp); extern struct filename_trans_datum * policydb_filenametr_search(struct policydb *p, struct filename_trans_key *key); extern struct mls_range *policydb_rangetr_search(struct policydb *p, struct range_trans *key); extern struct role_trans_datum * policydb_roletr_search(struct policydb *p, struct role_trans_key *key); #define POLICYDB_CONFIG_MLS 1 /* the config flags related to unknown classes/perms are bits 2 and 3 */ #define REJECT_UNKNOWN 0x00000002 #define ALLOW_UNKNOWN 0x00000004 #define OBJECT_R "object_r" #define OBJECT_R_VAL 1 #define POLICYDB_MAGIC SELINUX_MAGIC #define POLICYDB_STRING "SE Linux" struct policy_data { struct policydb *p; struct policy_file *fp; }; static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes) { if (bytes > fp->len) return -EINVAL; memcpy(buf, fp->data, bytes); fp->data += bytes; fp->len -= bytes; return 0; } static inline int put_entry(const void *buf, size_t bytes, size_t num, struct policy_file *fp) { size_t len; if (unlikely(check_mul_overflow(bytes, num, &len))) return -EINVAL; if (len > fp->len) return -EINVAL; memcpy(fp->data, buf, len); fp->data += len; fp->len -= len; return 0; } static inline char *sym_name(struct policydb *p, unsigned int sym_num, unsigned int element_nr) { return p->sym_val_to_name[sym_num][element_nr]; } extern int str_read(char **strp, gfp_t flags, struct policy_file *fp, u32 len); extern u16 string_to_security_class(struct policydb *p, const char *name); extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name); #endif /* _SS_POLICYDB_H_ */ |
| 7 7 7 7 7 7 7 16 16 16 7 7 16 16 80 34 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* File: fs/xattr.c Extended attribute handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com> Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/fs.h> #include <linux/filelock.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/xattr.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fsnotify.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <linux/posix_acl_xattr.h> #include <linux/uaccess.h> #include "internal.h" static const char * strcmp_prefix(const char *a, const char *a_prefix) { while (*a_prefix && *a == *a_prefix) { a++; a_prefix++; } return *a_prefix ? NULL : a; } /* * In order to implement different sets of xattr operations for each xattr * prefix, a filesystem should create a null-terminated array of struct * xattr_handler (one for each prefix) and hang a pointer to it off of the * s_xattr field of the superblock. */ #define for_each_xattr_handler(handlers, handler) \ if (handlers) \ for ((handler) = *(handlers)++; \ (handler) != NULL; \ (handler) = *(handlers)++) /* * Find the xattr_handler with the matching prefix. */ static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return ERR_PTR(-EIO); return ERR_PTR(-EOPNOTSUPP); } for_each_xattr_handler(handlers, handler) { const char *n; n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { if (!handler->prefix ^ !*n) { if (*n) continue; return ERR_PTR(-EINVAL); } *name = n; return handler; } } return ERR_PTR(-EOPNOTSUPP); } /** * may_write_xattr - check whether inode allows writing xattr * @idmap: idmap of the mount the inode was found from * @inode: the inode on which to set an xattr * * Check whether the inode allows writing xattrs. Specifically, we can never * set or remove an extended attribute on a read-only filesystem or on an * immutable / append-only inode. * * We also need to ensure that the inode has a mapping in the mount to * not risk writing back invalid i_{g,u}id values. * * Return: On success zero is returned. On error a negative errno is returned. */ int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode) { if (IS_IMMUTABLE(inode)) return -EPERM; if (IS_APPEND(inode)) return -EPERM; if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; return 0; } /* * Check permissions for extended attribute access. This is a bit complicated * because different namespaces have very different rules. */ static int xattr_permission(struct mnt_idmap *idmap, struct inode *inode, const char *name, int mask) { if (mask & MAY_WRITE) { int ret; ret = may_write_xattr(idmap, inode); if (ret) return ret; } /* * No restriction for security.* and system.* from the VFS. Decision * on these is left to the underlying filesystem / security module. */ if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return 0; /* * The trusted.* namespace can only be accessed by privileged users. */ if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { if (!capable(CAP_SYS_ADMIN)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; return 0; } /* * In the user.* namespace, only regular files and directories can have * extended attributes. For sticky directories, only the owner and * privileged users can write attributes. */ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && (mask & MAY_WRITE) && !inode_owner_or_capable(idmap, inode)) return -EPERM; } return inode_permission(idmap, inode, mask); } /* * Look for any handler that deals with the specified namespace. */ int xattr_supports_user_prefix(struct inode *inode) { const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return -EIO; return -EOPNOTSUPP; } for_each_xattr_handler(handlers, handler) { if (!strncmp(xattr_prefix(handler), XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) return 0; } return -EOPNOTSUPP; } EXPORT_SYMBOL(xattr_supports_user_prefix); int __vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ return handler->set(handler, idmap, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); /** * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * * @idmap: idmap of the mount the inode was found from * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * * returns the result of the internal setxattr or setsecurity operations. * * This function requires the caller to lock the inode's i_rwsem before it * is executed. It also assumes that the caller will make the appropriate * permission checks. */ int __vfs_setxattr_noperm(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { error = __vfs_setxattr(idmap, dentry, inode, name, value, size, flags); if (!error) { fsnotify_xattr(dentry); security_inode_post_setxattr(dentry, name, value, size, flags); } } else { if (unlikely(is_bad_inode(inode))) return -EIO; } if (error == -EAGAIN) { error = -EOPNOTSUPP; if (issec) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; error = security_inode_setsecurity(inode, suffix, value, size, flags); if (!error) fsnotify_xattr(dentry); } } return error; } /** * __vfs_setxattr_locked - set an extended attribute while holding the inode * lock * * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; error = security_inode_setxattr(idmap, dentry, name, value, size, flags); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_setxattr_noperm(idmap, dentry, name, value, size, flags); out: return error; } EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; const void *orig_value = value; int error; if (size && strcmp(name, XATTR_NAME_CAPS) == 0) { error = cap_convert_nscap(idmap, dentry, &value, size); if (error < 0) return error; size = error; } retry_deleg: inode_lock(inode); error = __vfs_setxattr_locked(idmap, dentry, name, value, size, flags, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } if (value != orig_value) kfree(value); return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); static ssize_t xattr_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { len = security_inode_getsecurity(idmap, inode, name, &buffer, false); goto out_noalloc; } len = security_inode_getsecurity(idmap, inode, name, &buffer, true); if (len < 0) return len; if (size < len) { len = -ERANGE; goto out; } memcpy(value, buffer, len); out: kfree(buffer); out_noalloc: return len; } /* * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr * * Allocate memory, if not already allocated, or re-allocate correct size, * before retrieving the extended attribute. The xattr value buffer should * always be freed by the caller, even on error. * * Returns the result of alloc, if failed, or the getxattr operation. */ int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t xattr_size, gfp_t flags) { const struct xattr_handler *handler; struct inode *inode = dentry->d_inode; char *value = *xattr_value; int error; error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; error = handler->get(handler, dentry, inode, name, NULL, 0); if (error < 0) return error; if (!value || (error > xattr_size)) { value = krealloc(*xattr_value, error + 1, flags); if (!value) return -ENOMEM; memset(value, 0, error + 1); } error = handler->get(handler, dentry, inode, name, value, error); *xattr_value = value; return error; } ssize_t __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; return handler->get(handler, dentry, inode, name, value, size); } EXPORT_SYMBOL(__vfs_getxattr); ssize_t vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; error = security_inode_getxattr(dentry, name); if (error) return error; if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; int ret = xattr_getsecurity(idmap, inode, suffix, value, size); /* * Only overwrite the return value if a security module * is actually active. */ if (ret == -EOPNOTSUPP) goto nolsm; return ret; } nolsm: return __vfs_getxattr(dentry, inode, name, value, size); } EXPORT_SYMBOL_GPL(vfs_getxattr); /** * vfs_listxattr - retrieve \0 separated list of xattr names * @dentry: the dentry from whose inode the xattr names are retrieved * @list: buffer to store xattr names into * @size: size of the buffer * * This function returns the names of all xattrs associated with the * inode of @dentry. * * Note, for legacy reasons the vfs_listxattr() function lists POSIX * ACLs as well. Since POSIX ACLs are decoupled from IOP_XATTR the * vfs_listxattr() function doesn't check for this flag since a * filesystem could implement POSIX ACLs without implementing any other * xattrs. * * However, since all codepaths that remove IOP_XATTR also assign of * inode operations that either don't implement or implement a stub * ->listxattr() operation. * * Return: On success, the size of the buffer that was used. On error a * negative error code. */ ssize_t vfs_listxattr(struct dentry *dentry, char *list, size_t size) { struct inode *inode = d_inode(dentry); ssize_t error; error = security_inode_listxattr(dentry); if (error) return error; if (inode->i_op->listxattr) { error = inode->i_op->listxattr(dentry, list, size); } else { error = security_inode_listsecurity(inode, list, size); if (size && error > size) error = -ERANGE; } return error; } EXPORT_SYMBOL_GPL(vfs_listxattr); int __vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = d_inode(dentry); const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; return handler->set(handler, idmap, dentry, inode, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); /** * __vfs_removexattr_locked - set an extended attribute while holding the inode * lock * * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: name of xattr to remove * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_removexattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; error = security_inode_removexattr(idmap, dentry, name); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_removexattr(idmap, dentry, name); if (error) return error; fsnotify_xattr(dentry); security_inode_post_removexattr(dentry, name); out: return error; } EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_removexattr_locked(idmap, dentry, name, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); int import_xattr_name(struct xattr_name *kname, const char __user *name) { int error = strncpy_from_user(kname->name, name, sizeof(kname->name)); if (error == 0 || error == sizeof(kname->name)) return -ERANGE; if (error < 0) return error; return 0; } /* * Extended attribute SET operations */ int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx) { int error; if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; error = import_xattr_name(ctx->kname, name); if (error) return error; if (ctx->size) { if (ctx->size > XATTR_SIZE_MAX) return -E2BIG; ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size); if (IS_ERR(ctx->kvalue)) { error = PTR_ERR(ctx->kvalue); ctx->kvalue = NULL; } } return error; } static int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct kernel_xattr_ctx *ctx) { if (is_posix_acl_xattr(ctx->kname->name)) return do_set_acl(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size); return vfs_setxattr(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size, ctx->flags); } int file_setxattr(struct file *f, struct kernel_xattr_ctx *ctx) { int error = mnt_want_write_file(f); if (!error) { audit_file(f); error = do_setxattr(file_mnt_idmap(f), f->f_path.dentry, ctx); mnt_drop_write_file(f); } return error; } /* unconditionally consumes filename */ int filename_setxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx) { struct path path; int error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = mnt_want_write(path.mnt); if (!error) { error = do_setxattr(mnt_idmap(path.mnt), path.dentry, ctx); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static int path_setxattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name, const void __user *value, size_t size, int flags) { struct xattr_name kname; struct kernel_xattr_ctx ctx = { .cvalue = value, .kvalue = NULL, .size = size, .kname = &kname, .flags = flags, }; struct filename *filename; unsigned int lookup_flags = 0; int error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags = LOOKUP_FOLLOW; error = setxattr_copy(name, &ctx); if (error) return error; filename = getname_maybe_null(pathname, at_flags); if (!filename && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) error = -EBADF; else error = file_setxattr(fd_file(f), &ctx); } else { error = filename_setxattr(dfd, filename, lookup_flags, &ctx); } kvfree(ctx.kvalue); return error; } SYSCALL_DEFINE6(setxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name, const struct xattr_args __user *, uargs, size_t, usize) { struct xattr_args args = {}; int error; BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0); BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST); if (unlikely(usize < XATTR_ARGS_SIZE_VER0)) return -EINVAL; if (usize > PAGE_SIZE) return -E2BIG; error = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (error) return error; return path_setxattrat(dfd, pathname, at_flags, name, u64_to_user_ptr(args.value), args.size, args.flags); } SYSCALL_DEFINE5(setxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattrat(AT_FDCWD, pathname, 0, name, value, size, flags); } SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name, value, size, flags); } SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { return path_setxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size, flags); } /* * Extended attribute GET operations */ static ssize_t do_getxattr(struct mnt_idmap *idmap, struct dentry *d, struct kernel_xattr_ctx *ctx) { ssize_t error; char *kname = ctx->kname->name; void *kvalue = NULL; if (ctx->size) { if (ctx->size > XATTR_SIZE_MAX) ctx->size = XATTR_SIZE_MAX; kvalue = kvzalloc(ctx->size, GFP_KERNEL); if (!kvalue) return -ENOMEM; } if (is_posix_acl_xattr(kname)) error = do_get_acl(idmap, d, kname, kvalue, ctx->size); else error = vfs_getxattr(idmap, d, kname, kvalue, ctx->size); if (error > 0) { if (ctx->size && copy_to_user(ctx->value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(kvalue); return error; } ssize_t file_getxattr(struct file *f, struct kernel_xattr_ctx *ctx) { audit_file(f); return do_getxattr(file_mnt_idmap(f), f->f_path.dentry, ctx); } /* unconditionally consumes filename */ ssize_t filename_getxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx) { struct path path; ssize_t error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = do_getxattr(mnt_idmap(path.mnt), path.dentry, ctx); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static ssize_t path_getxattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name, void __user *value, size_t size) { struct xattr_name kname; struct kernel_xattr_ctx ctx = { .value = value, .size = size, .kname = &kname, .flags = 0, }; struct filename *filename; ssize_t error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; error = import_xattr_name(&kname, name); if (error) return error; filename = getname_maybe_null(pathname, at_flags); if (!filename && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_getxattr(fd_file(f), &ctx); } else { int lookup_flags = 0; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags = LOOKUP_FOLLOW; return filename_getxattr(dfd, filename, lookup_flags, &ctx); } } SYSCALL_DEFINE6(getxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name, struct xattr_args __user *, uargs, size_t, usize) { struct xattr_args args = {}; int error; BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0); BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST); if (unlikely(usize < XATTR_ARGS_SIZE_VER0)) return -EINVAL; if (usize > PAGE_SIZE) return -E2BIG; error = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (error) return error; if (args.flags != 0) return -EINVAL; return path_getxattrat(dfd, pathname, at_flags, name, u64_to_user_ptr(args.value), args.size); } SYSCALL_DEFINE4(getxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(AT_FDCWD, pathname, 0, name, value, size); } SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name, value, size); } SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size); } /* * Extended attribute LIST operations */ static ssize_t listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kvmalloc(size, GFP_KERNEL); if (!klist) return -ENOMEM; } error = vfs_listxattr(d, klist, size); if (error > 0) { if (size && copy_to_user(list, klist, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { /* The file system tried to returned a list bigger than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(klist); return error; } static ssize_t file_listxattr(struct file *f, char __user *list, size_t size) { audit_file(f); return listxattr(f->f_path.dentry, list, size); } /* unconditionally consumes filename */ static ssize_t filename_listxattr(int dfd, struct filename *filename, unsigned int lookup_flags, char __user *list, size_t size) { struct path path; ssize_t error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = listxattr(path.dentry, list, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static ssize_t path_listxattrat(int dfd, const char __user *pathname, unsigned int at_flags, char __user *list, size_t size) { struct filename *filename; int lookup_flags; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; filename = getname_maybe_null(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_listxattr(fd_file(f), list, size); } lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; return filename_listxattr(dfd, filename, lookup_flags, list, size); } SYSCALL_DEFINE5(listxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, char __user *, list, size_t, size) { return path_listxattrat(dfd, pathname, at_flags, list, size); } SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattrat(AT_FDCWD, pathname, 0, list, size); } SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, list, size); } SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { return path_listxattrat(fd, NULL, AT_EMPTY_PATH, list, size); } /* * Extended attribute REMOVE operations */ static long removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name) { if (is_posix_acl_xattr(name)) return vfs_remove_acl(idmap, d, name); return vfs_removexattr(idmap, d, name); } static int file_removexattr(struct file *f, struct xattr_name *kname) { int error = mnt_want_write_file(f); if (!error) { audit_file(f); error = removexattr(file_mnt_idmap(f), f->f_path.dentry, kname->name); mnt_drop_write_file(f); } return error; } /* unconditionally consumes filename */ static int filename_removexattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct xattr_name *kname) { struct path path; int error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = mnt_want_write(path.mnt); if (!error) { error = removexattr(mnt_idmap(path.mnt), path.dentry, kname->name); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: putname(filename); return error; } static int path_removexattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name) { struct xattr_name kname; struct filename *filename; unsigned int lookup_flags; int error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; error = import_xattr_name(&kname, name); if (error) return error; filename = getname_maybe_null(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_removexattr(fd_file(f), &kname); } lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; return filename_removexattr(dfd, filename, lookup_flags, &kname); } SYSCALL_DEFINE4(removexattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name) { return path_removexattrat(dfd, pathname, at_flags, name); } SYSCALL_DEFINE2(removexattr, const char __user *, pathname, const char __user *, name) { return path_removexattrat(AT_FDCWD, pathname, 0, name); } SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, const char __user *, name) { return path_removexattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name); } SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { return path_removexattrat(fd, NULL, AT_EMPTY_PATH, name); } int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) { size_t len; len = strlen(name) + 1; if (*buffer) { if (*remaining_size < len) return -ERANGE; memcpy(*buffer, name, len); *buffer += len; } *remaining_size -= len; return 0; } /** * generic_listxattr - run through a dentry's xattr list() operations * @dentry: dentry to list the xattrs * @buffer: result buffer * @buffer_size: size of @buffer * * Combine the results of the list() operation from every xattr_handler in the * xattr_handler stack. * * Note that this will not include the entries for POSIX ACLs. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr; ssize_t remaining_size = buffer_size; for_each_xattr_handler(handlers, handler) { int err; if (!handler->name || (handler->list && !handler->list(dentry))) continue; err = xattr_list_one(&buffer, &remaining_size, handler->name); if (err) return err; } return buffer_size - remaining_size; } EXPORT_SYMBOL(generic_listxattr); /** * xattr_full_name - Compute full attribute name from suffix * * @handler: handler of the xattr_handler operation * @name: name passed to the xattr_handler operation * * The get and set xattr handler operations are called with the remainder of * the attribute name after skipping the handler's prefix: for example, "foo" * is passed to the get operation of a handler with prefix "user." to get * attribute "user.foo". The full name is still "there" in the name though. * * Note: the list xattr handler operation when called from the vfs is passed a * NULL name; some file systems use this operation internally, with varying * semantics. */ const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } EXPORT_SYMBOL(xattr_full_name); /** * simple_xattr_space - estimate the memory used by a simple xattr * @name: the full name of the xattr * @size: the size of its value * * This takes no account of how much larger the two slab objects actually are: * that would depend on the slab implementation, when what is required is a * deterministic number, which grows with name length and size and quantity. * * Return: The approximate number of bytes of memory used by such an xattr. */ size_t simple_xattr_space(const char *name, size_t size) { /* * Use "40" instead of sizeof(struct simple_xattr), to return the * same result on 32-bit and 64-bit, and even if simple_xattr grows. */ return 40 + size + strlen(name); } /** * simple_xattr_free - free an xattr object * @xattr: the xattr object * * Free the xattr object. Can handle @xattr being NULL. */ void simple_xattr_free(struct simple_xattr *xattr) { if (xattr) kfree(xattr->name); kvfree(xattr); } /** * simple_xattr_alloc - allocate new xattr object * @value: value of the xattr object * @size: size of @value * * Allocate a new xattr object and initialize respective members. The caller is * responsible for handling the name of the xattr. * * Return: On success a new xattr object is returned. On failure NULL is * returned. */ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) { struct simple_xattr *new_xattr; size_t len; /* wrap around? */ len = sizeof(*new_xattr) + size; if (len < sizeof(*new_xattr)) return NULL; new_xattr = kvmalloc(len, GFP_KERNEL_ACCOUNT); if (!new_xattr) return NULL; new_xattr->size = size; memcpy(new_xattr->value, value, size); return new_xattr; } /** * rbtree_simple_xattr_cmp - compare xattr name with current rbtree xattr entry * @key: xattr name * @node: current node * * Compare the xattr name with the xattr name attached to @node in the rbtree. * * Return: Negative value if continuing left, positive if continuing right, 0 * if the xattr attached to @node matches @key. */ static int rbtree_simple_xattr_cmp(const void *key, const struct rb_node *node) { const char *xattr_name = key; const struct simple_xattr *xattr; xattr = rb_entry(node, struct simple_xattr, rb_node); return strcmp(xattr->name, xattr_name); } /** * rbtree_simple_xattr_node_cmp - compare two xattr rbtree nodes * @new_node: new node * @node: current node * * Compare the xattr attached to @new_node with the xattr attached to @node. * * Return: Negative value if continuing left, positive if continuing right, 0 * if the xattr attached to @new_node matches the xattr attached to @node. */ static int rbtree_simple_xattr_node_cmp(struct rb_node *new_node, const struct rb_node *node) { struct simple_xattr *xattr; xattr = rb_entry(new_node, struct simple_xattr, rb_node); return rbtree_simple_xattr_cmp(xattr->name, node); } /** * simple_xattr_get - get an xattr object * @xattrs: the header of the xattr object * @name: the name of the xattr to retrieve * @buffer: the buffer to store the value into * @size: the size of @buffer * * Try to find and retrieve the xattr object associated with @name. * If @buffer is provided store the value of @xattr in @buffer * otherwise just return the length. The size of @buffer is limited * to XATTR_SIZE_MAX which currently is 65536. * * Return: On success the length of the xattr value is returned. On error a * negative error code is returned. */ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size) { struct simple_xattr *xattr = NULL; struct rb_node *rbp; int ret = -ENODATA; read_lock(&xattrs->lock); rbp = rb_find(name, &xattrs->rb_root, rbtree_simple_xattr_cmp); if (rbp) { xattr = rb_entry(rbp, struct simple_xattr, rb_node); ret = xattr->size; if (buffer) { if (size < xattr->size) ret = -ERANGE; else memcpy(buffer, xattr->value, xattr->size); } } read_unlock(&xattrs->lock); return ret; } /** * simple_xattr_set - set an xattr object * @xattrs: the header of the xattr object * @name: the name of the xattr to retrieve * @value: the value to store along the xattr * @size: the size of @value * @flags: the flags determining how to set the xattr * * Set a new xattr object. * If @value is passed a new xattr object will be allocated. If XATTR_REPLACE * is specified in @flags a matching xattr object for @name must already exist. * If it does it will be replaced with the new xattr object. If it doesn't we * fail. If XATTR_CREATE is specified and a matching xattr does already exist * we fail. If it doesn't we create a new xattr. If @flags is zero we simply * insert the new xattr replacing any existing one. * * If @value is empty and a matching xattr object is found we delete it if * XATTR_REPLACE is specified in @flags or @flags is zero. * * If @value is empty and no matching xattr object for @name is found we do * nothing if XATTR_CREATE is specified in @flags or @flags is zero. For * XATTR_REPLACE we fail as mentioned above. * * Return: On success, the removed or replaced xattr is returned, to be freed * by the caller; or NULL if none. On failure a negative error code is returned. */ struct simple_xattr *simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags) { struct simple_xattr *old_xattr = NULL, *new_xattr = NULL; struct rb_node *parent = NULL, **rbp; int err = 0, ret; /* value == NULL means remove */ if (value) { new_xattr = simple_xattr_alloc(value, size); if (!new_xattr) return ERR_PTR(-ENOMEM); new_xattr->name = kstrdup(name, GFP_KERNEL_ACCOUNT); if (!new_xattr->name) { simple_xattr_free(new_xattr); return ERR_PTR(-ENOMEM); } } write_lock(&xattrs->lock); rbp = &xattrs->rb_root.rb_node; while (*rbp) { parent = *rbp; ret = rbtree_simple_xattr_cmp(name, *rbp); if (ret < 0) rbp = &(*rbp)->rb_left; else if (ret > 0) rbp = &(*rbp)->rb_right; else old_xattr = rb_entry(*rbp, struct simple_xattr, rb_node); if (old_xattr) break; } if (old_xattr) { /* Fail if XATTR_CREATE is requested and the xattr exists. */ if (flags & XATTR_CREATE) { err = -EEXIST; goto out_unlock; } if (new_xattr) rb_replace_node(&old_xattr->rb_node, &new_xattr->rb_node, &xattrs->rb_root); else rb_erase(&old_xattr->rb_node, &xattrs->rb_root); } else { /* Fail if XATTR_REPLACE is requested but no xattr is found. */ if (flags & XATTR_REPLACE) { err = -ENODATA; goto out_unlock; } /* * If XATTR_CREATE or no flags are specified together with a * new value simply insert it. */ if (new_xattr) { rb_link_node(&new_xattr->rb_node, parent, rbp); rb_insert_color(&new_xattr->rb_node, &xattrs->rb_root); } /* * If XATTR_CREATE or no flags are specified and neither an * old or new xattr exist then we don't need to do anything. */ } out_unlock: write_unlock(&xattrs->lock); if (!err) return old_xattr; simple_xattr_free(new_xattr); return ERR_PTR(err); } static bool xattr_is_trusted(const char *name) { return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } static bool xattr_is_maclabel(const char *name) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; return !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && security_ismaclabel(suffix); } /** * simple_xattr_list - list all xattr objects * @inode: inode from which to get the xattrs * @xattrs: the header of the xattr object * @buffer: the buffer to store all xattrs into * @size: the size of @buffer * * List all xattrs associated with @inode. If @buffer is NULL we returned * the required size of the buffer. If @buffer is provided we store the * xattrs value into it provided it is big enough. * * Note, the number of xattr names that can be listed with listxattr(2) is * limited to XATTR_LIST_MAX aka 65536 bytes. If a larger buffer is passed * then vfs_listxattr() caps it to XATTR_LIST_MAX and if more xattr names * are found it will return -E2BIG. * * Return: On success the required size or the size of the copied xattrs is * returned. On error a negative error code is returned. */ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); struct simple_xattr *xattr; struct rb_node *rbp; ssize_t remaining_size = size; int err = 0; err = posix_acl_listxattr(inode, &buffer, &remaining_size); if (err) return err; err = security_inode_listsecurity(inode, buffer, remaining_size); if (err < 0) return err; if (buffer) { if (remaining_size < err) return -ERANGE; buffer += err; } remaining_size -= err; err = 0; read_lock(&xattrs->lock); for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) { xattr = rb_entry(rbp, struct simple_xattr, rb_node); /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; /* skip MAC labels; these are provided by LSM above */ if (xattr_is_maclabel(xattr->name)) continue; err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) break; } read_unlock(&xattrs->lock); return err ? err : size - remaining_size; } /** * rbtree_simple_xattr_less - compare two xattr rbtree nodes * @new_node: new node * @node: current node * * Compare the xattr attached to @new_node with the xattr attached to @node. * Note that this function technically tolerates duplicate entries. * * Return: True if insertion point in the rbtree is found. */ static bool rbtree_simple_xattr_less(struct rb_node *new_node, const struct rb_node *node) { return rbtree_simple_xattr_node_cmp(new_node, node) < 0; } /** * simple_xattr_add - add xattr objects * @xattrs: the header of the xattr object * @new_xattr: the xattr object to add * * Add an xattr object to @xattrs. This assumes no replacement or removal * of matching xattrs is wanted. Should only be called during inode * initialization when a few distinct initial xattrs are supposed to be set. */ void simple_xattr_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr) { write_lock(&xattrs->lock); rb_add(&new_xattr->rb_node, &xattrs->rb_root, rbtree_simple_xattr_less); write_unlock(&xattrs->lock); } /** * simple_xattrs_init - initialize new xattr header * @xattrs: header to initialize * * Initialize relevant fields of a an xattr header. */ void simple_xattrs_init(struct simple_xattrs *xattrs) { xattrs->rb_root = RB_ROOT; rwlock_init(&xattrs->lock); } /** * simple_xattrs_free - free xattrs * @xattrs: xattr header whose xattrs to destroy * @freed_space: approximate number of bytes of memory freed from @xattrs * * Destroy all xattrs in @xattr. When this is called no one can hold a * reference to any of the xattrs anymore. */ void simple_xattrs_free(struct simple_xattrs *xattrs, size_t *freed_space) { struct rb_node *rbp; if (freed_space) *freed_space = 0; rbp = rb_first(&xattrs->rb_root); while (rbp) { struct simple_xattr *xattr; struct rb_node *rbp_next; rbp_next = rb_next(rbp); xattr = rb_entry(rbp, struct simple_xattr, rb_node); rb_erase(&xattr->rb_node, &xattrs->rb_root); if (freed_space) *freed_space += simple_xattr_space(xattr->name, xattr->size); simple_xattr_free(xattr); rbp = rbp_next; } } |
| 235 234 268 266 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * Some part derived from fs/eventfd.c (anon inode setup) and * mm/ksm.c (mm hashing). */ #include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/file.h> #include <linux/bug.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/userfaultfd_k.h> #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/swapops.h> #include <linux/miscdevice.h> #include <linux/uio.h> static int sysctl_unprivileged_userfaultfd __read_mostly; #ifdef CONFIG_SYSCTL static const struct ctl_table vm_userfaultfd_table[] = { { .procname = "unprivileged_userfaultfd", .data = &sysctl_unprivileged_userfaultfd, .maxlen = sizeof(sysctl_unprivileged_userfaultfd), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; #endif static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init; struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; struct list_head list; }; struct userfaultfd_unmap_ctx { struct userfaultfd_ctx *ctx; unsigned long start; unsigned long end; struct list_head list; }; struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; struct userfaultfd_wake_range { unsigned long start; unsigned long len; }; /* internal indication that UFFD_API ioctl was successfully executed */ #define UFFD_FEATURE_INITIALIZED (1u << 31) static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) { return ctx->features & UFFD_FEATURE_INITIALIZED; } static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx) { return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC); } /* * Whether WP_UNPOPULATED is enabled on the uffd context. It is only * meaningful when userfaultfd_wp()==true on the vma and when it's * anonymous. */ bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) { struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return false; return ctx->features & UFFD_FEATURE_WP_UNPOPULATED; } static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; int ret; struct userfaultfd_wait_queue *uwq; unsigned long start, len; uwq = container_of(wq, struct userfaultfd_wait_queue, wq); ret = 0; /* len == 0 means wake all */ start = range->start; len = range->len; if (len && (start > uwq->msg.arg.pagefault.address || start + len <= uwq->msg.arg.pagefault.address)) goto out; WRITE_ONCE(uwq->waken, true); /* * The Program-Order guarantees provided by the scheduler * ensure uwq->waken is visible before the task is woken. */ ret = wake_up_state(wq->private, mode); if (ret) { /* * Wake only once, autoremove behavior. * * After the effect of list_del_init is visible to the other * CPUs, the waitqueue may disappear from under us, see the * !list_empty_careful() in handle_userfault(). * * try_to_wake_up() has an implicit smp_mb(), and the * wq->private is read before calling the extern function * "wake_up_state" (which in turns calls try_to_wake_up). */ list_del_init(&wq->entry); } out: return ret; } /** * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { refcount_inc(&ctx->refcount); } /** * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to userfaultfd context. * * The userfaultfd context reference must have been previously acquired either * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget(). */ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) { if (refcount_dec_and_test(&ctx->refcount)) { VM_WARN_ON_ONCE(spin_is_locked(&ctx->fault_pending_wqh.lock)); VM_WARN_ON_ONCE(waitqueue_active(&ctx->fault_pending_wqh)); VM_WARN_ON_ONCE(spin_is_locked(&ctx->fault_wqh.lock)); VM_WARN_ON_ONCE(waitqueue_active(&ctx->fault_wqh)); VM_WARN_ON_ONCE(spin_is_locked(&ctx->event_wqh.lock)); VM_WARN_ON_ONCE(waitqueue_active(&ctx->event_wqh)); VM_WARN_ON_ONCE(spin_is_locked(&ctx->fd_wqh.lock)); VM_WARN_ON_ONCE(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } } static inline void msg_init(struct uffd_msg *msg) { BUILD_BUG_ON(sizeof(struct uffd_msg) != 32); /* * Must use memset to zero out the paddings or kernel data is * leaked to userland. */ memset(msg, 0, sizeof(struct uffd_msg)); } static inline struct uffd_msg userfault_msg(unsigned long address, unsigned long real_address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ? real_address : address; /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. * - Neither of these flags being set indicates a MISSING fault. * * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write * fault. Otherwise, it was a read fault. */ if (flags & FAULT_FLAG_WRITE) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; if (reason & VM_UFFD_MINOR) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } #ifdef CONFIG_HUGETLB_PAGE /* * Same functionality as userfaultfd_must_wait below with modifications for * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct vm_area_struct *vma = vmf->vma; pte_t *ptep, pte; bool ret = true; assert_fault_locked(vmf); ptep = hugetlb_walk(vma, vmf->address, vma_mmu_pagesize(vma)); if (!ptep) goto out; ret = false; pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ if (huge_pte_none_mostly(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; out: return ret; } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { return false; /* should never get here */ } #endif /* CONFIG_HUGETLB_PAGE */ /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any * userfault that has already been resolved, if userfaultfd_read_iter and * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different * threads. */ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct mm_struct *mm = ctx->mm; unsigned long address = vmf->address; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; pte_t ptent; bool ret = true; assert_fault_locked(vmf); pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); again: _pmd = pmdp_get_lockless(pmd); if (pmd_none(_pmd)) goto out; ret = false; if (!pmd_present(_pmd)) goto out; if (pmd_trans_huge(_pmd)) { if (!pmd_write(_pmd) && (reason & VM_UFFD_WP)) ret = true; goto out; } pte = pte_offset_map(pmd, address); if (!pte) { ret = true; goto again; } /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ ptent = ptep_get(pte); if (pte_none_mostly(ptent)) ret = true; if (!pte_write(ptent) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); out: return ret; } static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) { if (flags & FAULT_FLAG_INTERRUPTIBLE) return TASK_INTERRUPTIBLE; if (flags & FAULT_FLAG_KILLABLE) return TASK_KILLABLE; return TASK_UNINTERRUPTIBLE; } /* * The locking rules involved in returning VM_FAULT_RETRY depending on * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and * FAULT_FLAG_KILLABLE are not straightforward. The "Caution" * recommendation in __lock_page_or_retry is not an understatement. * * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is * not set. * * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not * set, VM_FAULT_RETRY can still be returned if and only if there are * fatal_signal_pending()s, and the mmap_lock must be released before * returning it. */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; bool must_wait; unsigned int blocking_state; /* * We don't do userfault handling for the final child pid update * and when coredumping (faults triggered by get_dump_page()). */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; assert_fault_locked(vmf); ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; VM_WARN_ON_ONCE(ctx->mm != mm); /* Any unrecognized flag is a bug. */ VM_WARN_ON_ONCE(reason & ~__VM_UFFD_FLAGS); /* 0 or > 1 flags set is a bug; we expect exactly 1. */ VM_WARN_ON_ONCE(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY)) goto out; /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY * even if FAULT_FLAG_TRIED is set without leading to gup() * -EBUSY failures, if the userfaultfd is to be extended for * VM_UFFD_WP tracking and we intend to arm the userfault * without first stopping userland access to the memory. For * VM_UFFD_MISSING userfaults this is enough for now. */ if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) { /* * Validate the invariant that nowait must allow retry * to be sure not to return SIGBUS erroneously on * nowait invocations. */ VM_WARN_ON_ONCE(vmf->flags & FAULT_FLAG_RETRY_NOWAIT); #ifdef CONFIG_DEBUG_VM if (printk_ratelimit()) { pr_warn("FAULT_FLAG_ALLOW_RETRY missing %x\n", vmf->flags); dump_stack(); } #endif goto out; } /* * Handle nowait, not much to do other than tell it to retry * and wait. */ ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out; if (unlikely(READ_ONCE(ctx->released))) { /* * If a concurrent release is detected, do not return * VM_FAULT_SIGBUS or VM_FAULT_NOPAGE, but instead always * return VM_FAULT_RETRY with lock released proactively. * * If we were to return VM_FAULT_SIGBUS here, the non * cooperative manager would be instead forced to * always call UFFDIO_UNREGISTER before it can safely * close the uffd, to avoid involuntary SIGBUS triggered. * * If we were to return VM_FAULT_NOPAGE, it would work for * the fault path, in which the lock will be released * later. However for GUP, faultin_page() does nothing * special on NOPAGE, so GUP would spin retrying without * releasing the mmap read lock, causing possible livelock. * * Here only VM_FAULT_RETRY would make sure the mmap lock * be released immediately, so that the thread concurrently * releasing the userfault would always make progress. */ release_fault_lock(vmf); goto out; } /* take the reference before dropping the mmap_lock */ userfaultfd_ctx_get(ctx); init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags, reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; blocking_state = userfaultfd_get_blocking_state(vmf->flags); /* * Take the vma lock now, in order to safely call * userfaultfd_huge_must_wait() later. Since acquiring the * (sleepable) vma lock can modify the current task state, that * must be before explicitly calling set_current_state(). */ if (is_vm_hugetlb_page(vma)) hugetlb_vma_lock_read(vma); spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq); /* * The smp_mb() after __set_current_state prevents the reads * following the spin_unlock to happen before the list_add in * __add_wait_queue. */ set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); if (!is_vm_hugetlb_page(vma)) must_wait = userfaultfd_must_wait(ctx, vmf, reason); else must_wait = userfaultfd_huge_must_wait(ctx, vmf, reason); if (is_vm_hugetlb_page(vma)) hugetlb_vma_unlock_read(vma); release_fault_lock(vmf); if (likely(must_wait && !READ_ONCE(ctx->released))) { wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); } __set_current_state(TASK_RUNNING); /* * Here we race with the list_del; list_add in * userfaultfd_ctx_read(), however because we don't ever run * list_del_init() to refile across the two lists, the prev * and next pointers will never point to self. list_add also * would never let any of the two pointers to point to * self. So list_empty_careful won't risk to see both pointers * pointing to self at any time during the list refile. The * only case where list_del_init() is called is the full * removal in the wake function and there we don't re-list_add * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ if (!list_empty_careful(&uwq.wq.entry)) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ list_del(&uwq.wq.entry); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ userfaultfd_ctx_put(ctx); out: return ret; } static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { struct userfaultfd_ctx *release_new_ctx; if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); release_new_ctx = NULL; spin_lock_irq(&ctx->event_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->event_wqh, &ewq->wq); for (;;) { set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but * __remove_wait_queue ignores the head * parameter. It would be a problem if it * didn't. */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; release_new_ctx = new; } break; } spin_unlock_irq(&ctx->event_wqh.lock); wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); spin_lock_irq(&ctx->event_wqh.lock); } __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { userfaultfd_release_new(release_new_ctx); userfaultfd_ctx_put(release_new_ctx); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ out: atomic_dec(&ctx->mmap_changing); VM_WARN_ON_ONCE(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { ewq->msg.event = 0; wake_up_locked(&ctx->event_wqh); __remove_wait_queue(&ctx->event_wqh, &ewq->wq); } int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) { struct userfaultfd_ctx *ctx = NULL, *octx; struct userfaultfd_fork_ctx *fctx; octx = vma->vm_userfaultfd_ctx.ctx; if (!octx) return 0; if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) { userfaultfd_reset_ctx(vma); return 0; } list_for_each_entry(fctx, fcs, list) if (fctx->orig == octx) { ctx = fctx->new; break; } if (!ctx) { fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); if (!fctx) return -ENOMEM; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) { kfree(fctx); return -ENOMEM; } refcount_set(&ctx->refcount, 1); ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); down_write(&octx->map_changing_lock); atomic_inc(&octx->mmap_changing); up_write(&octx->map_changing_lock); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); } vma->vm_userfaultfd_ctx.ctx = ctx; return 0; } static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } } void dup_userfaultfd_fail(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; /* * An error has occurred on fork, we will tear memory down, but have * allocated memory for fctx's and raised reference counts for both the * original and child contexts (and on the mm for each as a result). * * These would ordinarily be taken care of by a user handling the event, * but we are no longer doing so, so manually clean up here. * * mm tear down will take care of cleaning up VMA contexts. */ list_for_each_entry_safe(fctx, n, fcs, list) { struct userfaultfd_ctx *octx = fctx->orig; struct userfaultfd_ctx *ctx = fctx->new; atomic_dec(&octx->mmap_changing); VM_WARN_ON_ONCE(atomic_read(&octx->mmap_changing) < 0); userfaultfd_ctx_put(octx); userfaultfd_ctx_put(ctx); list_del(&fctx->list); kfree(fctx); } } void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { struct userfaultfd_ctx *ctx; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return; if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); } else { /* Drop uffd context if remap feature not enabled */ userfaultfd_reset_ctx(vma); } } void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, unsigned long from, unsigned long to, unsigned long len) { struct userfaultfd_ctx *ctx = vm_ctx->ctx; struct userfaultfd_wait_queue ewq; if (!ctx) return; msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMAP; ewq.msg.arg.remap.from = from; ewq.msg.arg.remap.to = to; ewq.msg.arg.remap.len = len; userfaultfd_event_wait_completion(ctx, &ewq); } void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *vm_ctx) { struct userfaultfd_ctx *ctx = vm_ctx->ctx; if (!ctx) return; userfaultfd_ctx_put(ctx); } bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue ewq; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) return true; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); mmap_read_unlock(mm); msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; ewq.msg.arg.remove.start = start; ewq.msg.arg.remove.end = end; userfaultfd_event_wait_completion(ctx, &ewq); return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, unsigned long start, unsigned long end) { struct userfaultfd_unmap_ctx *unmap_ctx; list_for_each_entry(unmap_ctx, unmaps, list) if (unmap_ctx->ctx == ctx && unmap_ctx->start == start && unmap_ctx->end == end) return true; return false; } int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *unmaps) { struct userfaultfd_unmap_ctx *unmap_ctx; struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || has_unmap_ctx(ctx, unmaps, start, end)) return 0; unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); if (!unmap_ctx) return -ENOMEM; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; list_add_tail(&unmap_ctx->list, unmaps); return 0; } void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { struct userfaultfd_unmap_ctx *ctx, *n; struct userfaultfd_wait_queue ewq; list_for_each_entry_safe(ctx, n, uf, list) { msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_UNMAP; ewq.msg.arg.remove.start = ctx->start; ewq.msg.arg.remove.end = ctx->end; userfaultfd_event_wait_completion(ctx->ctx, &ewq); list_del(&ctx->list); kfree(ctx); } } static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; struct mm_struct *mm = ctx->mm; /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; WRITE_ONCE(ctx->released, true); userfaultfd_release_all(mm, ctx); /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on * the fault_*wqh. */ spin_lock_irq(&ctx->fault_pending_wqh.lock); __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); wake_up_poll(&ctx->fd_wqh, EPOLLHUP); userfaultfd_ctx_put(ctx); return 0; } /* fault_pending_wqh.lock must be hold by the caller */ static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; lockdep_assert_held(&wqh->lock); uwq = NULL; if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } static inline struct userfaultfd_wait_queue *find_userfault( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->fault_pending_wqh); } static inline struct userfaultfd_wait_queue *find_userfault_evt( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->event_wqh); } static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; __poll_t ret; poll_wait(file, &ctx->fd_wqh, wait); if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; /* * poll() never guarantees that read won't block. * userfaults can be waken before they're read(). */ if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; /* * lockless access to see if there are pending faults * __pollwait last action is the add_wait_queue but * the spin_unlock would allow the waitqueue_active to * pass above the actual list_add inside * add_wait_queue critical section. So use a full * memory barrier to serialize the list_add write of * add_wait_queue() with the waitqueue_active read * below. */ ret = 0; smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = EPOLLIN; else if (waitqueue_active(&ctx->event_wqh)) ret = EPOLLIN; return ret; } static const struct file_operations userfaultfd_fops; static int resolve_userfault_fork(struct userfaultfd_ctx *new, struct inode *inode, struct uffd_msg *msg) { int fd; fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new, O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; msg->arg.reserved.reserved1 = 0; msg->arg.fork.ufd = fd; return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, struct uffd_msg *msg, struct inode *inode) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; /* * Handling fork event requires sleeping operations, so * we drop the event_wqh lock, then do these ops, then * lock it back and wake up the waiter. While the lock is * dropped the ewq may go away so we keep track of it * carefully. */ LIST_HEAD(fork_event); struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock_irq(&ctx->fd_wqh.lock); __add_wait_queue(&ctx->fd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); spin_lock(&ctx->fault_pending_wqh.lock); uwq = find_userfault(ctx); if (uwq) { /* * Use a seqcount to repeat the lockless check * in wake_userfault() to avoid missing * wakeups because during the refile both * waitqueue could become empty if this is the * only userfault. */ write_seqcount_begin(&ctx->refile_seq); /* * The fault_pending_wqh.lock prevents the uwq * to disappear from under us. * * Refile this userfault from * fault_pending_wqh to fault_wqh, it's not * pending anymore after we read it. * * Use list_del() by hand (as * userfaultfd_wake_function also uses * list_del_init() by hand) to be sure nobody * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ list_del(&uwq->wq.entry); add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); /* careful to always initialize msg if ret == 0 */ *msg = uwq->msg; spin_unlock(&ctx->fault_pending_wqh.lock); ret = 0; break; } spin_unlock(&ctx->fault_pending_wqh.lock); spin_lock(&ctx->event_wqh.lock); uwq = find_userfault_evt(ctx); if (uwq) { *msg = uwq->msg; if (uwq->msg.event == UFFD_EVENT_FORK) { fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); /* * fork_nctx can be freed as soon as * we drop the lock, unless we take a * reference on it. */ userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } userfaultfd_event_complete(ctx, uwq); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } spin_unlock(&ctx->event_wqh.lock); if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (no_wait) { ret = -EAGAIN; break; } spin_unlock_irq(&ctx->fd_wqh.lock); schedule(); spin_lock_irq(&ctx->fd_wqh.lock); } __remove_wait_queue(&ctx->fd_wqh, &wait); __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->fd_wqh.lock); if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(fork_nctx, inode, msg); spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* * The fork thread didn't abort, so we can * drop the temporary refcount. */ userfaultfd_ctx_put(fork_nctx); uwq = list_first_entry(&fork_event, typeof(*uwq), wq.entry); /* * If fork_event list wasn't empty and in turn * the event wasn't already released by fork * (the event is allocated on fork kernel * stack), put the event back to its place in * the event_wq. fork_event head will be freed * as soon as we return so the event cannot * stay queued there no matter the current * "ret" value. */ list_del(&uwq->wq.entry); __add_wait_queue(&ctx->event_wqh, &uwq->wq); /* * Leave the event in the waitqueue and report * error to userland if we failed to resolve * the userfault fork. */ if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); } else { /* * Here the fork thread aborted and the * refcount from the fork thread on fork_nctx * has already been released. We still hold * the reference we took before releasing the * lock above. If resolve_userfault_fork * failed we've to drop it because the * fork_nctx has to be freed in such case. If * it succeeded we'll hold it because the new * uffd references it. */ if (ret) userfaultfd_ctx_put(fork_nctx); } spin_unlock_irq(&ctx->event_wqh.lock); } return ret; } static ssize_t userfaultfd_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct userfaultfd_ctx *ctx = file->private_data; ssize_t _ret, ret = 0; struct uffd_msg msg; struct inode *inode = file_inode(file); bool no_wait; if (!userfaultfd_is_initialized(ctx)) return -EINVAL; no_wait = file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT; for (;;) { if (iov_iter_count(to) < sizeof(msg)) return ret ? ret : -EINVAL; _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode); if (_ret < 0) return ret ? ret : _ret; _ret = !copy_to_iter_full(&msg, sizeof(msg), to); if (_ret) return ret ? ret : -EFAULT; ret += sizeof(msg); /* * Allow to read more than one fault at time but only * block if waiting for the very first one. */ no_wait = true; } } static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { unsigned seq; bool need_wakeup; /* * To be sure waitqueue_active() is not reordered by the CPU * before the pagetable update, use an explicit SMP memory * barrier here. PT lock release or mmap_read_unlock(mm) still * have release semantics that can allow the * waitqueue_active() to be reordered before the pte update. */ smp_mb(); /* * Use waitqueue_active because it's very frequent to * change the address space atomically even if there are no * userfaults yet. So we take the spinlock only when we're * sure we've userfaults to wake. */ do { seq = read_seqcount_begin(&ctx->refile_seq); need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) || waitqueue_active(&ctx->fault_wqh); cond_resched(); } while (read_seqcount_retry(&ctx->refile_seq, seq)); if (need_wakeup) __wake_userfault(ctx, range); } static __always_inline int validate_unaligned_range( struct mm_struct *mm, __u64 start, __u64 len) { __u64 task_size = mm->task_size; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; if (start < mmap_min_addr) return -EINVAL; if (start >= task_size) return -EINVAL; if (len > task_size - start) return -EINVAL; if (start + len <= start) return -EINVAL; return 0; } static __always_inline int validate_range(struct mm_struct *mm, __u64 start, __u64 len) { if (start & ~PAGE_MASK) return -EINVAL; return validate_unaligned_range(mm, start, len); } static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *cur; int ret; struct uffdio_register uffdio_register; struct uffdio_register __user *user_uffdio_register; vm_flags_t vm_flags; bool found; bool basic_ioctls; unsigned long start, end; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); user_uffdio_register = (struct uffdio_register __user *) arg; ret = -EFAULT; if (copy_from_user(&uffdio_register, user_uffdio_register, sizeof(uffdio_register)-sizeof(__u64))) goto out; ret = -EINVAL; if (!uffdio_register.mode) goto out; if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP goto out; #endif vm_flags |= VM_UFFD_WP; } if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; #endif vm_flags |= VM_UFFD_MINOR; } ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; start = uffdio_register.range.start; end = start + uffdio_register.range.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; ret = -EINVAL; mmap_write_lock(mm); vma_iter_init(&vmi, mm, start); vma = vma_find(&vmi, end); if (!vma) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; basic_ioctls = false; cur = vma; do { cond_resched(); VM_WARN_ON_ONCE(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; if (!vma_can_userfault(cur, vm_flags, wp_async)) goto out_unlock; /* * UFFDIO_COPY will fill file holes even without * PROT_WRITE. This check enforces that if this is a * MAP_SHARED, the process has write permission to the backing * file. If VM_MAYWRITE is set it also enforces that on a * MAP_SHARED vma: there is no F_WRITE_SEAL and no further * F_WRITE_SEAL can be taken until the vma is destroyed. */ ret = -EPERM; if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) goto out_unlock; /* * If this vma contains ending address, and huge pages * check alignment. */ if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && end > cur->vm_start) { unsigned long vma_hpagesize = vma_kernel_pagesize(cur); ret = -EINVAL; if (end & (vma_hpagesize - 1)) goto out_unlock; } if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE)) goto out_unlock; /* * Check that this vma isn't already owned by a * different userfaultfd. We can't allow more than one * userfaultfd to own a single vma simultaneously or we * wouldn't know which one to deliver the userfaults to. */ ret = -EBUSY; if (cur->vm_userfaultfd_ctx.ctx && cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; /* * Note vmas containing huge pages */ if (is_vm_hugetlb_page(cur)) basic_ioctls = true; found = true; } for_each_vma_range(vmi, cur, end); VM_WARN_ON_ONCE(!found); ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end, wp_async); out_unlock: mmap_write_unlock(mm); mmput(mm); if (!ret) { __u64 ioctls_out; ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS; /* * Declare the WP ioctl only if the WP mode is * specified and all checks passed with the range */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)) ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT); /* CONTINUE ioctl is only supported for MINOR ranges. */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR)) ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE); /* * Now that we scanned all vmas we can already tell * userland which ioctls methods are guaranteed to * succeed on this range. */ if (put_user(ioctls_out, &user_uffdio_register->ioctls)) ret = -EFAULT; } out: return ret; } static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_range uffdio_unregister; bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; start = uffdio_unregister.start; end = start + uffdio_unregister.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); ret = -EINVAL; vma_iter_init(&vmi, mm, start); vma = vma_find(&vmi, end); if (!vma) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; cur = vma; do { cond_resched(); VM_WARN_ON_ONCE(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Prevent unregistering through a different userfaultfd than * the one used for registration. */ if (cur->vm_userfaultfd_ctx.ctx && cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; /* * Check not compatible vmas, not strictly required * here as not compatible vmas cannot have an * userfaultfd_ctx registered on them, but this * provides for more strict behavior to notice * unregistration errors. */ if (!vma_can_userfault(cur, cur->vm_flags, wp_async)) goto out_unlock; found = true; } for_each_vma_range(vmi, cur, end); VM_WARN_ON_ONCE(!found); vma_iter_set(&vmi, start); prev = vma_prev(&vmi); if (vma->vm_start < start) prev = vma; ret = 0; for_each_vma_range(vmi, vma, end) { cond_resched(); /* VMA not registered with userfaultfd. */ if (!vma->vm_userfaultfd_ctx.ctx) goto skip; VM_WARN_ON_ONCE(vma->vm_userfaultfd_ctx.ctx != ctx); VM_WARN_ON_ONCE(!vma_can_userfault(vma, vma->vm_flags, wp_async)); VM_WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE)); if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); if (userfaultfd_missing(vma)) { /* * Wake any concurrent pending userfault while * we unregister, so they will not hang * permanently and it avoids userland to call * UFFDIO_WAKE explicitly. */ struct userfaultfd_wake_range range; range.start = start; range.len = vma_end - start; wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } vma = userfaultfd_clear_vma(&vmi, prev, vma, start, vma_end); if (IS_ERR(vma)) { ret = PTR_ERR(vma); break; } skip: prev = vma; start = vma->vm_end; } out_unlock: mmap_write_unlock(mm); mmput(mm); out: return ret; } /* * userfaultfd_wake may be used in combination with the * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches. */ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_range uffdio_wake; struct userfaultfd_wake_range range; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; range.start = uffdio_wake.start; range.len = uffdio_wake.len; /* * len == 0 means wake all and we don't want to wake all here, * so check it again to be sure. */ VM_WARN_ON_ONCE(!range.len); wake_userfault(ctx, &range); ret = 0; out: return ret; } static int userfaultfd_copy(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_copy uffdio_copy; struct uffdio_copy __user *user_uffdio_copy; struct userfaultfd_wake_range range; uffd_flags_t flags = 0; user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; if (unlikely(atomic_read(&ctx->mmap_changing))) { if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; goto out; } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, /* don't copy "copy" last field */ sizeof(uffdio_copy)-sizeof(__s64))) goto out; ret = validate_unaligned_range(ctx->mm, uffdio_copy.src, uffdio_copy.len); if (ret) goto out; ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; ret = -EINVAL; if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len, flags); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; if (ret < 0) goto out; VM_WARN_ON_ONCE(!ret); /* len == 0 would wake all */ range.len = ret; if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) { range.start = uffdio_copy.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_copy.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_zeropage uffdio_zeropage; struct uffdio_zeropage __user *user_uffdio_zeropage; struct userfaultfd_wake_range range; user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; if (unlikely(atomic_read(&ctx->mmap_changing))) { if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; goto out; } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, /* don't copy "zeropage" last field */ sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start, uffdio_zeropage.range.len); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ VM_WARN_ON_ONCE(!ret); range.len = ret; if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) { range.start = uffdio_zeropage.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_writeprotect uffdio_wp; struct uffdio_writeprotect __user *user_uffdio_wp; struct userfaultfd_wake_range range; bool mode_wp, mode_dontwake; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; if (copy_from_user(&uffdio_wp, user_uffdio_wp, sizeof(struct uffdio_writeprotect))) return -EFAULT; ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE | UFFDIO_WRITEPROTECT_MODE_WP)) return -EINVAL; mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP; mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE; if (mode_wp && mode_dontwake) return -EINVAL; if (mmget_not_zero(ctx->mm)) { ret = mwriteprotect_range(ctx, uffdio_wp.range.start, uffdio_wp.range.len, mode_wp); mmput(ctx->mm); } else { return -ESRCH; } if (ret) return ret; if (!mode_wp && !mode_dontwake) { range.start = uffdio_wp.range.start; range.len = uffdio_wp.range.len; wake_userfault(ctx, &range); } return ret; } static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_continue uffdio_continue; struct uffdio_continue __user *user_uffdio_continue; struct userfaultfd_wake_range range; uffd_flags_t flags = 0; user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; if (unlikely(atomic_read(&ctx->mmap_changing))) { if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) return -EFAULT; goto out; } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, /* don't copy the output fields */ sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE | UFFDIO_CONTINUE_MODE_WP)) goto out; if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_continue(ctx, uffdio_continue.range.start, uffdio_continue.range.len, flags); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ VM_WARN_ON_ONCE(!ret); range.len = ret; if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) { range.start = uffdio_continue.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN; out: return ret; } static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_poison uffdio_poison; struct uffdio_poison __user *user_uffdio_poison; struct userfaultfd_wake_range range; user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; if (unlikely(atomic_read(&ctx->mmap_changing))) { if (unlikely(put_user(ret, &user_uffdio_poison->updated))) return -EFAULT; goto out; } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, /* don't copy the output fields */ sizeof(uffdio_poison) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_poison.range.start, uffdio_poison.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_poison.mode & ~UFFDIO_POISON_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_poison(ctx, uffdio_poison.range.start, uffdio_poison.range.len, 0); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_poison->updated))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ VM_WARN_ON_ONCE(!ret); range.len = ret; if (!(uffdio_poison.mode & UFFDIO_POISON_MODE_DONTWAKE)) { range.start = uffdio_poison.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_poison.range.len ? 0 : -EAGAIN; out: return ret; } bool userfaultfd_wp_async(struct vm_area_struct *vma) { return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx); } static inline unsigned int uffd_ctx_features(__u64 user_features) { /* * For the current set of features the bits just coincide. Set * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } static int userfaultfd_move(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_move uffdio_move; struct uffdio_move __user *user_uffdio_move; struct userfaultfd_wake_range range; struct mm_struct *mm = ctx->mm; user_uffdio_move = (struct uffdio_move __user *) arg; ret = -EAGAIN; if (unlikely(atomic_read(&ctx->mmap_changing))) { if (unlikely(put_user(ret, &user_uffdio_move->move))) return -EFAULT; goto out; } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */ sizeof(uffdio_move)-sizeof(__s64))) return -EFAULT; /* Do not allow cross-mm moves. */ if (mm != current->mm) return -EINVAL; ret = validate_range(mm, uffdio_move.dst, uffdio_move.len); if (ret) return ret; ret = validate_range(mm, uffdio_move.src, uffdio_move.len); if (ret) return ret; if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES| UFFDIO_MOVE_MODE_DONTWAKE)) return -EINVAL; if (mmget_not_zero(mm)) { ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src, uffdio_move.len, uffdio_move.mode); mmput(mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_move->move))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ VM_WARN_ON(!ret); range.len = ret; if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) { range.start = uffdio_move.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_move.len ? 0 : -EAGAIN; out: return ret; } /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API * version or -EINVAL if unknown. */ static int userfaultfd_api(struct userfaultfd_ctx *ctx, unsigned long arg) { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; unsigned int ctx_features; int ret; __u64 features; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; features = uffdio_api.features; ret = -EINVAL; if (uffdio_api.api != UFFD_API) goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; /* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */ if (features & UFFD_FEATURE_WP_ASYNC) features |= UFFD_FEATURE_WP_UNPOPULATED; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR uffdio_api.features &= ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); #endif #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif #ifndef CONFIG_PTE_MARKER_UFFD_WP uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED; uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC; #endif ret = -EINVAL; if (features & ~uffdio_api.features) goto err_out; uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; /* only enable the requested features for this uffd context */ ctx_features = uffd_ctx_features(features); ret = -EINVAL; if (cmpxchg(&ctx->features, 0, ctx_features) != 0) goto err_out; ret = 0; out: return ret; err_out: memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) ret = -EFAULT; goto out; } static long userfaultfd_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { case UFFDIO_API: ret = userfaultfd_api(ctx, arg); break; case UFFDIO_REGISTER: ret = userfaultfd_register(ctx, arg); break; case UFFDIO_UNREGISTER: ret = userfaultfd_unregister(ctx, arg); break; case UFFDIO_WAKE: ret = userfaultfd_wake(ctx, arg); break; case UFFDIO_COPY: ret = userfaultfd_copy(ctx, arg); break; case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; case UFFDIO_MOVE: ret = userfaultfd_move(ctx, arg); break; case UFFDIO_WRITEPROTECT: ret = userfaultfd_writeprotect(ctx, arg); break; case UFFDIO_CONTINUE: ret = userfaultfd_continue(ctx, arg); break; case UFFDIO_POISON: ret = userfaultfd_poison(ctx, arg); break; } return ret; } #ifdef CONFIG_PROC_FS static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; wait_queue_entry_t *wq; unsigned long pending = 0, total = 0; spin_lock_irq(&ctx->fault_pending_wqh.lock); list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { pending++; total++; } list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { total++; } spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* * If more protocols will be added, there will be all shown * separated by a space. Like this: * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif static const struct file_operations userfaultfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = userfaultfd_show_fdinfo, #endif .release = userfaultfd_release, .poll = userfaultfd_poll, .read_iter = userfaultfd_read_iter, .unlocked_ioctl = userfaultfd_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static void init_once_userfaultfd_ctx(void *mem) { struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem; init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } static int new_userfaultfd(int flags) { struct userfaultfd_ctx *ctx; struct file *file; int fd; VM_WARN_ON_ONCE(!current->mm); /* Check the UFFD_* constants for consistency. */ BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS); if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY)) return -EINVAL; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) return -ENOMEM; refcount_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; fd = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS); if (fd < 0) goto err_out; /* Create a new inode so that the LSM can block the creation. */ file = anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx, O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (IS_ERR(file)) { put_unused_fd(fd); fd = PTR_ERR(file); goto err_out; } /* prevent the mm struct to be freed */ mmgrab(ctx->mm); file->f_mode |= FMODE_NOWAIT; fd_install(fd, file); return fd; err_out: kmem_cache_free(userfaultfd_ctx_cachep, ctx); return fd; } static inline bool userfaultfd_syscall_allowed(int flags) { /* Userspace-only page faults are always allowed */ if (flags & UFFD_USER_MODE_ONLY) return true; /* * The user is requesting a userfaultfd which can handle kernel faults. * Privileged users are always allowed to do this. */ if (capable(CAP_SYS_PTRACE)) return true; /* Otherwise, access to kernel fault handling is sysctl controlled. */ return sysctl_unprivileged_userfaultfd; } SYSCALL_DEFINE1(userfaultfd, int, flags) { if (!userfaultfd_syscall_allowed(flags)) return -EPERM; return new_userfaultfd(flags); } static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags) { if (cmd != USERFAULTFD_IOC_NEW) return -EINVAL; return new_userfaultfd(flags); } static const struct file_operations userfaultfd_dev_fops = { .unlocked_ioctl = userfaultfd_dev_ioctl, .compat_ioctl = userfaultfd_dev_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice userfaultfd_misc = { .minor = MISC_DYNAMIC_MINOR, .name = "userfaultfd", .fops = &userfaultfd_dev_fops }; static int __init userfaultfd_init(void) { int ret; ret = misc_register(&userfaultfd_misc); if (ret) return ret; userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache", sizeof(struct userfaultfd_ctx), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_userfaultfd_table); #endif return 0; } __initcall(userfaultfd_init); |
| 203 205 205 204 205 205 205 205 203 204 205 204 205 205 205 205 205 205 205 205 205 204 205 205 205 205 205 205 205 205 205 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2025 Google LLC * Author: Marc Zyngier <maz@kernel.org> */ #include <linux/kvm_host.h> #include <asm/sysreg.h> /* * Describes the dependencies between a set of bits (or the negation * of a set of RES0 bits) and a feature. The flags indicate how the * data is interpreted. */ struct reg_bits_to_feat_map { union { u64 bits; u64 *res0p; }; #define NEVER_FGU BIT(0) /* Can trap, but never UNDEF */ #define CALL_FUNC BIT(1) /* Needs to evaluate tons of crap */ #define FIXED_VALUE BIT(2) /* RAZ/WI or RAO/WI in KVM */ #define RES0_POINTER BIT(3) /* Pointer to RES0 value instead of bits */ unsigned long flags; union { struct { u8 regidx; u8 shift; u8 width; bool sign; s8 lo_lim; }; bool (*match)(struct kvm *); bool (*fval)(struct kvm *, u64 *); }; }; /* * Describes the dependencies for a given register: * * @feat_map describes the dependency for the whole register. If the * features the register depends on are not present, the whole * register is effectively RES0. * * @bit_feat_map describes the dependencies for a set of bits in that * register. If the features these bits depend on are not present, the * bits are effectively RES0. */ struct reg_feat_map_desc { const char *name; const struct reg_bits_to_feat_map feat_map; const struct reg_bits_to_feat_map *bit_feat_map; const unsigned int bit_feat_map_sz; }; #define __NEEDS_FEAT_3(m, f, w, id, fld, lim) \ { \ .w = (m), \ .flags = (f), \ .regidx = IDREG_IDX(SYS_ ## id), \ .shift = id ##_## fld ## _SHIFT, \ .width = id ##_## fld ## _WIDTH, \ .sign = id ##_## fld ## _SIGNED, \ .lo_lim = id ##_## fld ##_## lim \ } #define __NEEDS_FEAT_2(m, f, w, fun, dummy) \ { \ .w = (m), \ .flags = (f) | CALL_FUNC, \ .fval = (fun), \ } #define __NEEDS_FEAT_1(m, f, w, fun) \ { \ .w = (m), \ .flags = (f) | CALL_FUNC, \ .match = (fun), \ } #define __NEEDS_FEAT_FLAG(m, f, w, ...) \ CONCATENATE(__NEEDS_FEAT_, COUNT_ARGS(__VA_ARGS__))(m, f, w, __VA_ARGS__) #define NEEDS_FEAT_FLAG(m, f, ...) \ __NEEDS_FEAT_FLAG(m, f, bits, __VA_ARGS__) #define NEEDS_FEAT_FIXED(m, ...) \ __NEEDS_FEAT_FLAG(m, FIXED_VALUE, bits, __VA_ARGS__, 0) #define NEEDS_FEAT_RES0(p, ...) \ __NEEDS_FEAT_FLAG(p, RES0_POINTER, res0p, __VA_ARGS__) /* * Declare the dependency between a set of bits and a set of features, * generating a struct reg_bit_to_feat_map. */ #define NEEDS_FEAT(m, ...) NEEDS_FEAT_FLAG(m, 0, __VA_ARGS__) /* * Declare the dependency between a non-FGT register, a set of * feature, and the set of individual bits it contains. This generates * a struct reg_feat_map_desc. */ #define DECLARE_FEAT_MAP(n, r, m, f) \ struct reg_feat_map_desc n = { \ .name = #r, \ .feat_map = NEEDS_FEAT(~r##_RES0, f), \ .bit_feat_map = m, \ .bit_feat_map_sz = ARRAY_SIZE(m), \ } /* * Specialised version of the above for FGT registers that have their * RES0 masks described as struct fgt_masks. */ #define DECLARE_FEAT_MAP_FGT(n, msk, m, f) \ struct reg_feat_map_desc n = { \ .name = #msk, \ .feat_map = NEEDS_FEAT_RES0(&msk.res0, f),\ .bit_feat_map = m, \ .bit_feat_map_sz = ARRAY_SIZE(m), \ } #define FEAT_SPE ID_AA64DFR0_EL1, PMSVer, IMP #define FEAT_SPE_FnE ID_AA64DFR0_EL1, PMSVer, V1P2 #define FEAT_BRBE ID_AA64DFR0_EL1, BRBE, IMP #define FEAT_TRC_SR ID_AA64DFR0_EL1, TraceVer, IMP #define FEAT_PMUv3 ID_AA64DFR0_EL1, PMUVer, IMP #define FEAT_TRBE ID_AA64DFR0_EL1, TraceBuffer, IMP #define FEAT_TRBEv1p1 ID_AA64DFR0_EL1, TraceBuffer, TRBE_V1P1 #define FEAT_DoubleLock ID_AA64DFR0_EL1, DoubleLock, IMP #define FEAT_TRF ID_AA64DFR0_EL1, TraceFilt, IMP #define FEAT_AA32EL0 ID_AA64PFR0_EL1, EL0, AARCH32 #define FEAT_AA32EL1 ID_AA64PFR0_EL1, EL1, AARCH32 #define FEAT_AA64EL1 ID_AA64PFR0_EL1, EL1, IMP #define FEAT_AA64EL2 ID_AA64PFR0_EL1, EL2, IMP #define FEAT_AA64EL3 ID_AA64PFR0_EL1, EL3, IMP #define FEAT_AIE ID_AA64MMFR3_EL1, AIE, IMP #define FEAT_S2POE ID_AA64MMFR3_EL1, S2POE, IMP #define FEAT_S1POE ID_AA64MMFR3_EL1, S1POE, IMP #define FEAT_S1PIE ID_AA64MMFR3_EL1, S1PIE, IMP #define FEAT_THE ID_AA64PFR1_EL1, THE, IMP #define FEAT_SME ID_AA64PFR1_EL1, SME, IMP #define FEAT_GCS ID_AA64PFR1_EL1, GCS, IMP #define FEAT_LS64 ID_AA64ISAR1_EL1, LS64, LS64 #define FEAT_LS64_V ID_AA64ISAR1_EL1, LS64, LS64_V #define FEAT_LS64_ACCDATA ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA #define FEAT_RAS ID_AA64PFR0_EL1, RAS, IMP #define FEAT_RASv2 ID_AA64PFR0_EL1, RAS, V2 #define FEAT_GICv3 ID_AA64PFR0_EL1, GIC, IMP #define FEAT_LOR ID_AA64MMFR1_EL1, LO, IMP #define FEAT_SPEv1p2 ID_AA64DFR0_EL1, PMSVer, V1P2 #define FEAT_SPEv1p4 ID_AA64DFR0_EL1, PMSVer, V1P4 #define FEAT_SPEv1p5 ID_AA64DFR0_EL1, PMSVer, V1P5 #define FEAT_ATS1A ID_AA64ISAR2_EL1, ATS1A, IMP #define FEAT_SPECRES2 ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX #define FEAT_SPECRES ID_AA64ISAR1_EL1, SPECRES, IMP #define FEAT_TLBIRANGE ID_AA64ISAR0_EL1, TLB, RANGE #define FEAT_TLBIOS ID_AA64ISAR0_EL1, TLB, OS #define FEAT_PAN2 ID_AA64MMFR1_EL1, PAN, PAN2 #define FEAT_DPB2 ID_AA64ISAR1_EL1, DPB, DPB2 #define FEAT_AMUv1 ID_AA64PFR0_EL1, AMU, IMP #define FEAT_AMUv1p1 ID_AA64PFR0_EL1, AMU, V1P1 #define FEAT_CMOW ID_AA64MMFR1_EL1, CMOW, IMP #define FEAT_D128 ID_AA64MMFR3_EL1, D128, IMP #define FEAT_DoubleFault2 ID_AA64PFR1_EL1, DF2, IMP #define FEAT_FPMR ID_AA64PFR2_EL1, FPMR, IMP #define FEAT_MOPS ID_AA64ISAR2_EL1, MOPS, IMP #define FEAT_NMI ID_AA64PFR1_EL1, NMI, IMP #define FEAT_SCTLR2 ID_AA64MMFR3_EL1, SCTLRX, IMP #define FEAT_SYSREG128 ID_AA64ISAR2_EL1, SYSREG_128, IMP #define FEAT_TCR2 ID_AA64MMFR3_EL1, TCRX, IMP #define FEAT_XS ID_AA64ISAR1_EL1, XS, IMP #define FEAT_EVT ID_AA64MMFR2_EL1, EVT, IMP #define FEAT_EVT_TTLBxS ID_AA64MMFR2_EL1, EVT, TTLBxS #define FEAT_MTE2 ID_AA64PFR1_EL1, MTE, MTE2 #define FEAT_RME ID_AA64PFR0_EL1, RME, IMP #define FEAT_MPAM ID_AA64PFR0_EL1, MPAM, 1 #define FEAT_S2FWB ID_AA64MMFR2_EL1, FWB, IMP #define FEAT_TME ID_AA64ISAR0_EL1, TME, IMP #define FEAT_TWED ID_AA64MMFR1_EL1, TWED, IMP #define FEAT_E2H0 ID_AA64MMFR4_EL1, E2H0, IMP #define FEAT_SRMASK ID_AA64MMFR4_EL1, SRMASK, IMP #define FEAT_PoPS ID_AA64MMFR4_EL1, PoPS, IMP #define FEAT_PFAR ID_AA64PFR1_EL1, PFAR, IMP #define FEAT_Debugv8p9 ID_AA64DFR0_EL1, PMUVer, V3P9 #define FEAT_PMUv3_SS ID_AA64DFR0_EL1, PMSS, IMP #define FEAT_SEBEP ID_AA64DFR0_EL1, SEBEP, IMP #define FEAT_EBEP ID_AA64DFR1_EL1, EBEP, IMP #define FEAT_ITE ID_AA64DFR1_EL1, ITE, IMP #define FEAT_PMUv3_ICNTR ID_AA64DFR1_EL1, PMICNTR, IMP #define FEAT_SPMU ID_AA64DFR1_EL1, SPMU, IMP #define FEAT_SPE_nVM ID_AA64DFR2_EL1, SPE_nVM, IMP #define FEAT_STEP2 ID_AA64DFR2_EL1, STEP, IMP #define FEAT_CPA2 ID_AA64ISAR3_EL1, CPA, CPA2 #define FEAT_ASID2 ID_AA64MMFR4_EL1, ASID2, IMP #define FEAT_MEC ID_AA64MMFR3_EL1, MEC, IMP #define FEAT_HAFT ID_AA64MMFR1_EL1, HAFDBS, HAFT #define FEAT_BTI ID_AA64PFR1_EL1, BT, IMP #define FEAT_ExS ID_AA64MMFR0_EL1, EXS, IMP #define FEAT_IESB ID_AA64MMFR2_EL1, IESB, IMP #define FEAT_LSE2 ID_AA64MMFR2_EL1, AT, IMP #define FEAT_LSMAOC ID_AA64MMFR2_EL1, LSM, IMP #define FEAT_MixedEnd ID_AA64MMFR0_EL1, BIGEND, IMP #define FEAT_MixedEndEL0 ID_AA64MMFR0_EL1, BIGENDEL0, IMP #define FEAT_MTE_ASYNC ID_AA64PFR1_EL1, MTE_frac, ASYNC #define FEAT_MTE_STORE_ONLY ID_AA64PFR2_EL1, MTESTOREONLY, IMP #define FEAT_PAN ID_AA64MMFR1_EL1, PAN, IMP #define FEAT_PAN3 ID_AA64MMFR1_EL1, PAN, PAN3 #define FEAT_SSBS ID_AA64PFR1_EL1, SSBS, IMP #define FEAT_TIDCP1 ID_AA64MMFR1_EL1, TIDCP1, IMP #define FEAT_FGT ID_AA64MMFR0_EL1, FGT, IMP #define FEAT_FGT2 ID_AA64MMFR0_EL1, FGT, FGT2 #define FEAT_MTPMU ID_AA64DFR0_EL1, MTPMU, IMP #define FEAT_HCX ID_AA64MMFR1_EL1, HCX, IMP static bool not_feat_aa64el3(struct kvm *kvm) { return !kvm_has_feat(kvm, FEAT_AA64EL3); } static bool feat_nv2(struct kvm *kvm) { return ((kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY) && kvm_has_feat_enum(kvm, ID_AA64MMFR2_EL1, NV, NI)) || kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, NV2)); } static bool feat_nv2_e2h0_ni(struct kvm *kvm) { return feat_nv2(kvm) && !kvm_has_feat(kvm, FEAT_E2H0); } static bool feat_rasv1p1(struct kvm *kvm) { return (kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1) || (kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, RAS, IMP) && kvm_has_feat(kvm, ID_AA64PFR1_EL1, RAS_frac, RASv1p1))); } static bool feat_csv2_2_csv2_1p2(struct kvm *kvm) { return (kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) || (kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2) && kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, CSV2, IMP))); } static bool feat_pauth(struct kvm *kvm) { return kvm_has_pauth(kvm, PAuth); } static bool feat_pauth_lr(struct kvm *kvm) { return kvm_has_pauth(kvm, PAuth_LR); } static bool feat_aderr(struct kvm *kvm) { return (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, FEAT_ADERR) && kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SDERR, FEAT_ADERR)); } static bool feat_anerr(struct kvm *kvm) { return (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ANERR, FEAT_ANERR) && kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SNERR, FEAT_ANERR)); } static bool feat_sme_smps(struct kvm *kvm) { /* * Revists this if KVM ever supports SME -- this really should * look at the guest's view of SMIDR_EL1. Funnily enough, this * is not captured in the JSON file, but only as a note in the * ARM ARM. */ return (kvm_has_feat(kvm, FEAT_SME) && (read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS)); } static bool feat_spe_fds(struct kvm *kvm) { /* * Revists this if KVM ever supports SPE -- this really should * look at the guest's view of PMSIDR_EL1. */ return (kvm_has_feat(kvm, FEAT_SPEv1p4) && (read_sysreg_s(SYS_PMSIDR_EL1) & PMSIDR_EL1_FDS)); } static bool feat_trbe_mpam(struct kvm *kvm) { /* * Revists this if KVM ever supports both MPAM and TRBE -- * this really should look at the guest's view of TRBIDR_EL1. */ return (kvm_has_feat(kvm, FEAT_TRBE) && kvm_has_feat(kvm, FEAT_MPAM) && (read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_MPAM)); } static bool feat_asid2_e2h1(struct kvm *kvm) { return kvm_has_feat(kvm, FEAT_ASID2) && !kvm_has_feat(kvm, FEAT_E2H0); } static bool feat_d128_e2h1(struct kvm *kvm) { return kvm_has_feat(kvm, FEAT_D128) && !kvm_has_feat(kvm, FEAT_E2H0); } static bool feat_mec_e2h1(struct kvm *kvm) { return kvm_has_feat(kvm, FEAT_MEC) && !kvm_has_feat(kvm, FEAT_E2H0); } static bool feat_ebep_pmuv3_ss(struct kvm *kvm) { return kvm_has_feat(kvm, FEAT_EBEP) || kvm_has_feat(kvm, FEAT_PMUv3_SS); } static bool feat_mixedendel0(struct kvm *kvm) { return kvm_has_feat(kvm, FEAT_MixedEnd) || kvm_has_feat(kvm, FEAT_MixedEndEL0); } static bool feat_mte_async(struct kvm *kvm) { return kvm_has_feat(kvm, FEAT_MTE2) && kvm_has_feat_enum(kvm, FEAT_MTE_ASYNC); } #define check_pmu_revision(k, r) \ ({ \ (kvm_has_feat((k), ID_AA64DFR0_EL1, PMUVer, r) && \ !kvm_has_feat((k), ID_AA64DFR0_EL1, PMUVer, IMP_DEF)); \ }) static bool feat_pmuv3p1(struct kvm *kvm) { return check_pmu_revision(kvm, V3P1); } static bool feat_pmuv3p5(struct kvm *kvm) { return check_pmu_revision(kvm, V3P5); } static bool feat_pmuv3p7(struct kvm *kvm) { return check_pmu_revision(kvm, V3P7); } static bool feat_pmuv3p9(struct kvm *kvm) { return check_pmu_revision(kvm, V3P9); } static bool compute_hcr_rw(struct kvm *kvm, u64 *bits) { /* This is purely academic: AArch32 and NV are mutually exclusive */ if (bits) { if (kvm_has_feat(kvm, FEAT_AA32EL1)) *bits &= ~HCR_EL2_RW; else *bits |= HCR_EL2_RW; } return true; } static bool compute_hcr_e2h(struct kvm *kvm, u64 *bits) { if (bits) { if (kvm_has_feat(kvm, FEAT_E2H0)) *bits &= ~HCR_EL2_E2H; else *bits |= HCR_EL2_E2H; } return true; } static const struct reg_bits_to_feat_map hfgrtr_feat_map[] = { NEEDS_FEAT(HFGRTR_EL2_nAMAIR2_EL1 | HFGRTR_EL2_nMAIR2_EL1, FEAT_AIE), NEEDS_FEAT(HFGRTR_EL2_nS2POR_EL1, FEAT_S2POE), NEEDS_FEAT(HFGRTR_EL2_nPOR_EL1 | HFGRTR_EL2_nPOR_EL0, FEAT_S1POE), NEEDS_FEAT(HFGRTR_EL2_nPIR_EL1 | HFGRTR_EL2_nPIRE0_EL1, FEAT_S1PIE), NEEDS_FEAT(HFGRTR_EL2_nRCWMASK_EL1, FEAT_THE), NEEDS_FEAT(HFGRTR_EL2_nTPIDR2_EL0 | HFGRTR_EL2_nSMPRI_EL1, FEAT_SME), NEEDS_FEAT(HFGRTR_EL2_nGCS_EL1 | HFGRTR_EL2_nGCS_EL0, FEAT_GCS), NEEDS_FEAT(HFGRTR_EL2_nACCDATA_EL1, FEAT_LS64_ACCDATA), NEEDS_FEAT(HFGRTR_EL2_ERXADDR_EL1 | HFGRTR_EL2_ERXMISCn_EL1 | HFGRTR_EL2_ERXSTATUS_EL1 | HFGRTR_EL2_ERXCTLR_EL1 | HFGRTR_EL2_ERXFR_EL1 | HFGRTR_EL2_ERRSELR_EL1 | HFGRTR_EL2_ERRIDR_EL1, FEAT_RAS), NEEDS_FEAT(HFGRTR_EL2_ERXPFGCDN_EL1 | HFGRTR_EL2_ERXPFGCTL_EL1 | HFGRTR_EL2_ERXPFGF_EL1, feat_rasv1p1), NEEDS_FEAT(HFGRTR_EL2_ICC_IGRPENn_EL1, FEAT_GICv3), NEEDS_FEAT(HFGRTR_EL2_SCXTNUM_EL0 | HFGRTR_EL2_SCXTNUM_EL1, feat_csv2_2_csv2_1p2), NEEDS_FEAT(HFGRTR_EL2_LORSA_EL1 | HFGRTR_EL2_LORN_EL1 | HFGRTR_EL2_LORID_EL1 | HFGRTR_EL2_LOREA_EL1 | HFGRTR_EL2_LORC_EL1, FEAT_LOR), NEEDS_FEAT(HFGRTR_EL2_APIBKey | HFGRTR_EL2_APIAKey | HFGRTR_EL2_APGAKey | HFGRTR_EL2_APDBKey | HFGRTR_EL2_APDAKey, feat_pauth), NEEDS_FEAT_FLAG(HFGRTR_EL2_VBAR_EL1 | HFGRTR_EL2_TTBR1_EL1 | HFGRTR_EL2_TTBR0_EL1 | HFGRTR_EL2_TPIDR_EL0 | HFGRTR_EL2_TPIDRRO_EL0 | HFGRTR_EL2_TPIDR_EL1 | HFGRTR_EL2_TCR_EL1 | HFGRTR_EL2_SCTLR_EL1 | HFGRTR_EL2_REVIDR_EL1 | HFGRTR_EL2_PAR_EL1 | HFGRTR_EL2_MPIDR_EL1 | HFGRTR_EL2_MIDR_EL1 | HFGRTR_EL2_MAIR_EL1 | HFGRTR_EL2_ISR_EL1 | HFGRTR_EL2_FAR_EL1 | HFGRTR_EL2_ESR_EL1 | HFGRTR_EL2_DCZID_EL0 | HFGRTR_EL2_CTR_EL0 | HFGRTR_EL2_CSSELR_EL1 | HFGRTR_EL2_CPACR_EL1 | HFGRTR_EL2_CONTEXTIDR_EL1| HFGRTR_EL2_CLIDR_EL1 | HFGRTR_EL2_CCSIDR_EL1 | HFGRTR_EL2_AMAIR_EL1 | HFGRTR_EL2_AIDR_EL1 | HFGRTR_EL2_AFSR1_EL1 | HFGRTR_EL2_AFSR0_EL1, NEVER_FGU, FEAT_AA64EL1), }; static const DECLARE_FEAT_MAP_FGT(hfgrtr_desc, hfgrtr_masks, hfgrtr_feat_map, FEAT_FGT); static const struct reg_bits_to_feat_map hfgwtr_feat_map[] = { NEEDS_FEAT(HFGWTR_EL2_nAMAIR2_EL1 | HFGWTR_EL2_nMAIR2_EL1, FEAT_AIE), NEEDS_FEAT(HFGWTR_EL2_nS2POR_EL1, FEAT_S2POE), NEEDS_FEAT(HFGWTR_EL2_nPOR_EL1 | HFGWTR_EL2_nPOR_EL0, FEAT_S1POE), NEEDS_FEAT(HFGWTR_EL2_nPIR_EL1 | HFGWTR_EL2_nPIRE0_EL1, FEAT_S1PIE), NEEDS_FEAT(HFGWTR_EL2_nRCWMASK_EL1, FEAT_THE), NEEDS_FEAT(HFGWTR_EL2_nTPIDR2_EL0 | HFGWTR_EL2_nSMPRI_EL1, FEAT_SME), NEEDS_FEAT(HFGWTR_EL2_nGCS_EL1 | HFGWTR_EL2_nGCS_EL0, FEAT_GCS), NEEDS_FEAT(HFGWTR_EL2_nACCDATA_EL1, FEAT_LS64_ACCDATA), NEEDS_FEAT(HFGWTR_EL2_ERXADDR_EL1 | HFGWTR_EL2_ERXMISCn_EL1 | HFGWTR_EL2_ERXSTATUS_EL1 | HFGWTR_EL2_ERXCTLR_EL1 | HFGWTR_EL2_ERRSELR_EL1, FEAT_RAS), NEEDS_FEAT(HFGWTR_EL2_ERXPFGCDN_EL1 | HFGWTR_EL2_ERXPFGCTL_EL1, feat_rasv1p1), NEEDS_FEAT(HFGWTR_EL2_ICC_IGRPENn_EL1, FEAT_GICv3), NEEDS_FEAT(HFGWTR_EL2_SCXTNUM_EL0 | HFGWTR_EL2_SCXTNUM_EL1, feat_csv2_2_csv2_1p2), NEEDS_FEAT(HFGWTR_EL2_LORSA_EL1 | HFGWTR_EL2_LORN_EL1 | HFGWTR_EL2_LOREA_EL1 | HFGWTR_EL2_LORC_EL1, FEAT_LOR), NEEDS_FEAT(HFGWTR_EL2_APIBKey | HFGWTR_EL2_APIAKey | HFGWTR_EL2_APGAKey | HFGWTR_EL2_APDBKey | HFGWTR_EL2_APDAKey, feat_pauth), NEEDS_FEAT_FLAG(HFGWTR_EL2_VBAR_EL1 | HFGWTR_EL2_TTBR1_EL1 | HFGWTR_EL2_TTBR0_EL1 | HFGWTR_EL2_TPIDR_EL0 | HFGWTR_EL2_TPIDRRO_EL0 | HFGWTR_EL2_TPIDR_EL1 | HFGWTR_EL2_TCR_EL1 | HFGWTR_EL2_SCTLR_EL1 | HFGWTR_EL2_PAR_EL1 | HFGWTR_EL2_MAIR_EL1 | HFGWTR_EL2_FAR_EL1 | HFGWTR_EL2_ESR_EL1 | HFGWTR_EL2_CSSELR_EL1 | HFGWTR_EL2_CPACR_EL1 | HFGWTR_EL2_CONTEXTIDR_EL1| HFGWTR_EL2_AMAIR_EL1 | HFGWTR_EL2_AFSR1_EL1 | HFGWTR_EL2_AFSR0_EL1, NEVER_FGU, FEAT_AA64EL1), }; static const DECLARE_FEAT_MAP_FGT(hfgwtr_desc, hfgwtr_masks, hfgwtr_feat_map, FEAT_FGT); static const struct reg_bits_to_feat_map hdfgrtr_feat_map[] = { NEEDS_FEAT(HDFGRTR_EL2_PMBIDR_EL1 | HDFGRTR_EL2_PMSLATFR_EL1 | HDFGRTR_EL2_PMSIRR_EL1 | HDFGRTR_EL2_PMSIDR_EL1 | HDFGRTR_EL2_PMSICR_EL1 | HDFGRTR_EL2_PMSFCR_EL1 | HDFGRTR_EL2_PMSEVFR_EL1 | HDFGRTR_EL2_PMSCR_EL1 | HDFGRTR_EL2_PMBSR_EL1 | HDFGRTR_EL2_PMBPTR_EL1 | HDFGRTR_EL2_PMBLIMITR_EL1, FEAT_SPE), NEEDS_FEAT(HDFGRTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE), NEEDS_FEAT(HDFGRTR_EL2_nBRBDATA | HDFGRTR_EL2_nBRBCTL | HDFGRTR_EL2_nBRBIDR, FEAT_BRBE), NEEDS_FEAT(HDFGRTR_EL2_TRCVICTLR | HDFGRTR_EL2_TRCSTATR | HDFGRTR_EL2_TRCSSCSRn | HDFGRTR_EL2_TRCSEQSTR | HDFGRTR_EL2_TRCPRGCTLR | HDFGRTR_EL2_TRCOSLSR | HDFGRTR_EL2_TRCIMSPECn | HDFGRTR_EL2_TRCID | HDFGRTR_EL2_TRCCNTVRn | HDFGRTR_EL2_TRCCLAIM | HDFGRTR_EL2_TRCAUXCTLR | HDFGRTR_EL2_TRCAUTHSTATUS | HDFGRTR_EL2_TRC, FEAT_TRC_SR), NEEDS_FEAT(HDFGRTR_EL2_PMCEIDn_EL0 | HDFGRTR_EL2_PMUSERENR_EL0 | HDFGRTR_EL2_PMMIR_EL1 | HDFGRTR_EL2_PMSELR_EL0 | HDFGRTR_EL2_PMOVS | HDFGRTR_EL2_PMINTEN | HDFGRTR_EL2_PMCNTEN | HDFGRTR_EL2_PMCCNTR_EL0 | HDFGRTR_EL2_PMCCFILTR_EL0 | HDFGRTR_EL2_PMEVTYPERn_EL0 | HDFGRTR_EL2_PMEVCNTRn_EL0, FEAT_PMUv3), NEEDS_FEAT(HDFGRTR_EL2_TRBTRG_EL1 | HDFGRTR_EL2_TRBSR_EL1 | HDFGRTR_EL2_TRBPTR_EL1 | HDFGRTR_EL2_TRBMAR_EL1 | HDFGRTR_EL2_TRBLIMITR_EL1 | HDFGRTR_EL2_TRBIDR_EL1 | HDFGRTR_EL2_TRBBASER_EL1, FEAT_TRBE), NEEDS_FEAT_FLAG(HDFGRTR_EL2_OSDLR_EL1, NEVER_FGU, FEAT_DoubleLock), NEEDS_FEAT_FLAG(HDFGRTR_EL2_OSECCR_EL1 | HDFGRTR_EL2_OSLSR_EL1 | HDFGRTR_EL2_DBGPRCR_EL1 | HDFGRTR_EL2_DBGAUTHSTATUS_EL1| HDFGRTR_EL2_DBGCLAIM | HDFGRTR_EL2_MDSCR_EL1 | HDFGRTR_EL2_DBGWVRn_EL1 | HDFGRTR_EL2_DBGWCRn_EL1 | HDFGRTR_EL2_DBGBVRn_EL1 | HDFGRTR_EL2_DBGBCRn_EL1, NEVER_FGU, FEAT_AA64EL1) }; static const DECLARE_FEAT_MAP_FGT(hdfgrtr_desc, hdfgrtr_masks, hdfgrtr_feat_map, FEAT_FGT); static const struct reg_bits_to_feat_map hdfgwtr_feat_map[] = { NEEDS_FEAT(HDFGWTR_EL2_PMSLATFR_EL1 | HDFGWTR_EL2_PMSIRR_EL1 | HDFGWTR_EL2_PMSICR_EL1 | HDFGWTR_EL2_PMSFCR_EL1 | HDFGWTR_EL2_PMSEVFR_EL1 | HDFGWTR_EL2_PMSCR_EL1 | HDFGWTR_EL2_PMBSR_EL1 | HDFGWTR_EL2_PMBPTR_EL1 | HDFGWTR_EL2_PMBLIMITR_EL1, FEAT_SPE), NEEDS_FEAT(HDFGWTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE), NEEDS_FEAT(HDFGWTR_EL2_nBRBDATA | HDFGWTR_EL2_nBRBCTL, FEAT_BRBE), NEEDS_FEAT(HDFGWTR_EL2_TRCVICTLR | HDFGWTR_EL2_TRCSSCSRn | HDFGWTR_EL2_TRCSEQSTR | HDFGWTR_EL2_TRCPRGCTLR | HDFGWTR_EL2_TRCOSLAR | HDFGWTR_EL2_TRCIMSPECn | HDFGWTR_EL2_TRCCNTVRn | HDFGWTR_EL2_TRCCLAIM | HDFGWTR_EL2_TRCAUXCTLR | HDFGWTR_EL2_TRC, FEAT_TRC_SR), NEEDS_FEAT(HDFGWTR_EL2_PMUSERENR_EL0 | HDFGWTR_EL2_PMCR_EL0 | HDFGWTR_EL2_PMSWINC_EL0 | HDFGWTR_EL2_PMSELR_EL0 | HDFGWTR_EL2_PMOVS | HDFGWTR_EL2_PMINTEN | HDFGWTR_EL2_PMCNTEN | HDFGWTR_EL2_PMCCNTR_EL0 | HDFGWTR_EL2_PMCCFILTR_EL0 | HDFGWTR_EL2_PMEVTYPERn_EL0 | HDFGWTR_EL2_PMEVCNTRn_EL0, FEAT_PMUv3), NEEDS_FEAT(HDFGWTR_EL2_TRBTRG_EL1 | HDFGWTR_EL2_TRBSR_EL1 | HDFGWTR_EL2_TRBPTR_EL1 | HDFGWTR_EL2_TRBMAR_EL1 | HDFGWTR_EL2_TRBLIMITR_EL1 | HDFGWTR_EL2_TRBBASER_EL1, FEAT_TRBE), NEEDS_FEAT_FLAG(HDFGWTR_EL2_OSDLR_EL1, NEVER_FGU, FEAT_DoubleLock), NEEDS_FEAT_FLAG(HDFGWTR_EL2_OSECCR_EL1 | HDFGWTR_EL2_OSLAR_EL1 | HDFGWTR_EL2_DBGPRCR_EL1 | HDFGWTR_EL2_DBGCLAIM | HDFGWTR_EL2_MDSCR_EL1 | HDFGWTR_EL2_DBGWVRn_EL1 | HDFGWTR_EL2_DBGWCRn_EL1 | HDFGWTR_EL2_DBGBVRn_EL1 | HDFGWTR_EL2_DBGBCRn_EL1, NEVER_FGU, FEAT_AA64EL1), NEEDS_FEAT(HDFGWTR_EL2_TRFCR_EL1, FEAT_TRF), }; static const DECLARE_FEAT_MAP_FGT(hdfgwtr_desc, hdfgwtr_masks, hdfgwtr_feat_map, FEAT_FGT); static const struct reg_bits_to_feat_map hfgitr_feat_map[] = { NEEDS_FEAT(HFGITR_EL2_PSBCSYNC, FEAT_SPEv1p5), NEEDS_FEAT(HFGITR_EL2_ATS1E1A, FEAT_ATS1A), NEEDS_FEAT(HFGITR_EL2_COSPRCTX, FEAT_SPECRES2), NEEDS_FEAT(HFGITR_EL2_nGCSEPP | HFGITR_EL2_nGCSSTR_EL1 | HFGITR_EL2_nGCSPUSHM_EL1, FEAT_GCS), NEEDS_FEAT(HFGITR_EL2_nBRBIALL | HFGITR_EL2_nBRBINJ, FEAT_BRBE), NEEDS_FEAT(HFGITR_EL2_CPPRCTX | HFGITR_EL2_DVPRCTX | HFGITR_EL2_CFPRCTX, FEAT_SPECRES), NEEDS_FEAT(HFGITR_EL2_TLBIRVAALE1 | HFGITR_EL2_TLBIRVALE1 | HFGITR_EL2_TLBIRVAAE1 | HFGITR_EL2_TLBIRVAE1 | HFGITR_EL2_TLBIRVAALE1IS | HFGITR_EL2_TLBIRVALE1IS | HFGITR_EL2_TLBIRVAAE1IS | HFGITR_EL2_TLBIRVAE1IS | HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS | HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS, FEAT_TLBIRANGE), NEEDS_FEAT(HFGITR_EL2_TLBIVAALE1OS | HFGITR_EL2_TLBIVALE1OS | HFGITR_EL2_TLBIVAAE1OS | HFGITR_EL2_TLBIASIDE1OS | HFGITR_EL2_TLBIVAE1OS | HFGITR_EL2_TLBIVMALLE1OS, FEAT_TLBIOS), NEEDS_FEAT(HFGITR_EL2_ATS1E1WP | HFGITR_EL2_ATS1E1RP, FEAT_PAN2), NEEDS_FEAT(HFGITR_EL2_DCCVADP, FEAT_DPB2), NEEDS_FEAT_FLAG(HFGITR_EL2_DCCVAC | HFGITR_EL2_SVC_EL1 | HFGITR_EL2_SVC_EL0 | HFGITR_EL2_ERET | HFGITR_EL2_TLBIVAALE1 | HFGITR_EL2_TLBIVALE1 | HFGITR_EL2_TLBIVAAE1 | HFGITR_EL2_TLBIASIDE1 | HFGITR_EL2_TLBIVAE1 | HFGITR_EL2_TLBIVMALLE1 | HFGITR_EL2_TLBIVAALE1IS | HFGITR_EL2_TLBIVALE1IS | HFGITR_EL2_TLBIVAAE1IS | HFGITR_EL2_TLBIASIDE1IS | HFGITR_EL2_TLBIVAE1IS | HFGITR_EL2_TLBIVMALLE1IS| HFGITR_EL2_ATS1E0W | HFGITR_EL2_ATS1E0R | HFGITR_EL2_ATS1E1W | HFGITR_EL2_ATS1E1R | HFGITR_EL2_DCZVA | HFGITR_EL2_DCCIVAC | HFGITR_EL2_DCCVAP | HFGITR_EL2_DCCVAU | HFGITR_EL2_DCCISW | HFGITR_EL2_DCCSW | HFGITR_EL2_DCISW | HFGITR_EL2_DCIVAC | HFGITR_EL2_ICIVAU | HFGITR_EL2_ICIALLU | HFGITR_EL2_ICIALLUIS, NEVER_FGU, FEAT_AA64EL1), }; static const DECLARE_FEAT_MAP_FGT(hfgitr_desc, hfgitr_masks, hfgitr_feat_map, FEAT_FGT); static const struct reg_bits_to_feat_map hafgrtr_feat_map[] = { NEEDS_FEAT(HAFGRTR_EL2_AMEVTYPER115_EL0 | HAFGRTR_EL2_AMEVTYPER114_EL0 | HAFGRTR_EL2_AMEVTYPER113_EL0 | HAFGRTR_EL2_AMEVTYPER112_EL0 | HAFGRTR_EL2_AMEVTYPER111_EL0 | HAFGRTR_EL2_AMEVTYPER110_EL0 | HAFGRTR_EL2_AMEVTYPER19_EL0 | HAFGRTR_EL2_AMEVTYPER18_EL0 | HAFGRTR_EL2_AMEVTYPER17_EL0 | HAFGRTR_EL2_AMEVTYPER16_EL0 | HAFGRTR_EL2_AMEVTYPER15_EL0 | HAFGRTR_EL2_AMEVTYPER14_EL0 | HAFGRTR_EL2_AMEVTYPER13_EL0 | HAFGRTR_EL2_AMEVTYPER12_EL0 | HAFGRTR_EL2_AMEVTYPER11_EL0 | HAFGRTR_EL2_AMEVTYPER10_EL0 | HAFGRTR_EL2_AMEVCNTR115_EL0 | HAFGRTR_EL2_AMEVCNTR114_EL0 | HAFGRTR_EL2_AMEVCNTR113_EL0 | HAFGRTR_EL2_AMEVCNTR112_EL0 | HAFGRTR_EL2_AMEVCNTR111_EL0 | HAFGRTR_EL2_AMEVCNTR110_EL0 | HAFGRTR_EL2_AMEVCNTR19_EL0 | HAFGRTR_EL2_AMEVCNTR18_EL0 | HAFGRTR_EL2_AMEVCNTR17_EL0 | HAFGRTR_EL2_AMEVCNTR16_EL0 | HAFGRTR_EL2_AMEVCNTR15_EL0 | HAFGRTR_EL2_AMEVCNTR14_EL0 | HAFGRTR_EL2_AMEVCNTR13_EL0 | HAFGRTR_EL2_AMEVCNTR12_EL0 | HAFGRTR_EL2_AMEVCNTR11_EL0 | HAFGRTR_EL2_AMEVCNTR10_EL0 | HAFGRTR_EL2_AMCNTEN1 | HAFGRTR_EL2_AMCNTEN0 | HAFGRTR_EL2_AMEVCNTR03_EL0 | HAFGRTR_EL2_AMEVCNTR02_EL0 | HAFGRTR_EL2_AMEVCNTR01_EL0 | HAFGRTR_EL2_AMEVCNTR00_EL0, FEAT_AMUv1), }; static const DECLARE_FEAT_MAP_FGT(hafgrtr_desc, hafgrtr_masks, hafgrtr_feat_map, FEAT_FGT); static const struct reg_bits_to_feat_map hfgitr2_feat_map[] = { NEEDS_FEAT(HFGITR2_EL2_nDCCIVAPS, FEAT_PoPS), NEEDS_FEAT(HFGITR2_EL2_TSBCSYNC, FEAT_TRBEv1p1) }; static const DECLARE_FEAT_MAP_FGT(hfgitr2_desc, hfgitr2_masks, hfgitr2_feat_map, FEAT_FGT2); static const struct reg_bits_to_feat_map hfgrtr2_feat_map[] = { NEEDS_FEAT(HFGRTR2_EL2_nPFAR_EL1, FEAT_PFAR), NEEDS_FEAT(HFGRTR2_EL2_nERXGSR_EL1, FEAT_RASv2), NEEDS_FEAT(HFGRTR2_EL2_nACTLRALIAS_EL1 | HFGRTR2_EL2_nACTLRMASK_EL1 | HFGRTR2_EL2_nCPACRALIAS_EL1 | HFGRTR2_EL2_nCPACRMASK_EL1 | HFGRTR2_EL2_nSCTLR2MASK_EL1 | HFGRTR2_EL2_nSCTLRALIAS2_EL1 | HFGRTR2_EL2_nSCTLRALIAS_EL1 | HFGRTR2_EL2_nSCTLRMASK_EL1 | HFGRTR2_EL2_nTCR2ALIAS_EL1 | HFGRTR2_EL2_nTCR2MASK_EL1 | HFGRTR2_EL2_nTCRALIAS_EL1 | HFGRTR2_EL2_nTCRMASK_EL1, FEAT_SRMASK), NEEDS_FEAT(HFGRTR2_EL2_nRCWSMASK_EL1, FEAT_THE), }; static const DECLARE_FEAT_MAP_FGT(hfgrtr2_desc, hfgrtr2_masks, hfgrtr2_feat_map, FEAT_FGT2); static const struct reg_bits_to_feat_map hfgwtr2_feat_map[] = { NEEDS_FEAT(HFGWTR2_EL2_nPFAR_EL1, FEAT_PFAR), NEEDS_FEAT(HFGWTR2_EL2_nACTLRALIAS_EL1 | HFGWTR2_EL2_nACTLRMASK_EL1 | HFGWTR2_EL2_nCPACRALIAS_EL1 | HFGWTR2_EL2_nCPACRMASK_EL1 | HFGWTR2_EL2_nSCTLR2MASK_EL1 | HFGWTR2_EL2_nSCTLRALIAS2_EL1 | HFGWTR2_EL2_nSCTLRALIAS_EL1 | HFGWTR2_EL2_nSCTLRMASK_EL1 | HFGWTR2_EL2_nTCR2ALIAS_EL1 | HFGWTR2_EL2_nTCR2MASK_EL1 | HFGWTR2_EL2_nTCRALIAS_EL1 | HFGWTR2_EL2_nTCRMASK_EL1, FEAT_SRMASK), NEEDS_FEAT(HFGWTR2_EL2_nRCWSMASK_EL1, FEAT_THE), }; static const DECLARE_FEAT_MAP_FGT(hfgwtr2_desc, hfgwtr2_masks, hfgwtr2_feat_map, FEAT_FGT2); static const struct reg_bits_to_feat_map hdfgrtr2_feat_map[] = { NEEDS_FEAT(HDFGRTR2_EL2_nMDSELR_EL1, FEAT_Debugv8p9), NEEDS_FEAT(HDFGRTR2_EL2_nPMECR_EL1, feat_ebep_pmuv3_ss), NEEDS_FEAT(HDFGRTR2_EL2_nTRCITECR_EL1, FEAT_ITE), NEEDS_FEAT(HDFGRTR2_EL2_nPMICFILTR_EL0 | HDFGRTR2_EL2_nPMICNTR_EL0, FEAT_PMUv3_ICNTR), NEEDS_FEAT(HDFGRTR2_EL2_nPMUACR_EL1, feat_pmuv3p9), NEEDS_FEAT(HDFGRTR2_EL2_nPMSSCR_EL1 | HDFGRTR2_EL2_nPMSSDATA, FEAT_PMUv3_SS), NEEDS_FEAT(HDFGRTR2_EL2_nPMIAR_EL1, FEAT_SEBEP), NEEDS_FEAT(HDFGRTR2_EL2_nPMSDSFR_EL1, feat_spe_fds), NEEDS_FEAT(HDFGRTR2_EL2_nPMBMAR_EL1, FEAT_SPE_nVM), NEEDS_FEAT(HDFGRTR2_EL2_nSPMACCESSR_EL1 | HDFGRTR2_EL2_nSPMCNTEN | HDFGRTR2_EL2_nSPMCR_EL0 | HDFGRTR2_EL2_nSPMDEVAFF_EL1 | HDFGRTR2_EL2_nSPMEVCNTRn_EL0 | HDFGRTR2_EL2_nSPMEVTYPERn_EL0| HDFGRTR2_EL2_nSPMID | HDFGRTR2_EL2_nSPMINTEN | HDFGRTR2_EL2_nSPMOVS | HDFGRTR2_EL2_nSPMSCR_EL1 | HDFGRTR2_EL2_nSPMSELR_EL0, FEAT_SPMU), NEEDS_FEAT(HDFGRTR2_EL2_nMDSTEPOP_EL1, FEAT_STEP2), NEEDS_FEAT(HDFGRTR2_EL2_nTRBMPAM_EL1, feat_trbe_mpam), }; static const DECLARE_FEAT_MAP_FGT(hdfgrtr2_desc, hdfgrtr2_masks, hdfgrtr2_feat_map, FEAT_FGT2); static const struct reg_bits_to_feat_map hdfgwtr2_feat_map[] = { NEEDS_FEAT(HDFGWTR2_EL2_nMDSELR_EL1, FEAT_Debugv8p9), NEEDS_FEAT(HDFGWTR2_EL2_nPMECR_EL1, feat_ebep_pmuv3_ss), NEEDS_FEAT(HDFGWTR2_EL2_nTRCITECR_EL1, FEAT_ITE), NEEDS_FEAT(HDFGWTR2_EL2_nPMICFILTR_EL0 | HDFGWTR2_EL2_nPMICNTR_EL0, FEAT_PMUv3_ICNTR), NEEDS_FEAT(HDFGWTR2_EL2_nPMUACR_EL1 | HDFGWTR2_EL2_nPMZR_EL0, feat_pmuv3p9), NEEDS_FEAT(HDFGWTR2_EL2_nPMSSCR_EL1, FEAT_PMUv3_SS), NEEDS_FEAT(HDFGWTR2_EL2_nPMIAR_EL1, FEAT_SEBEP), NEEDS_FEAT(HDFGWTR2_EL2_nPMSDSFR_EL1, feat_spe_fds), NEEDS_FEAT(HDFGWTR2_EL2_nPMBMAR_EL1, FEAT_SPE_nVM), NEEDS_FEAT(HDFGWTR2_EL2_nSPMACCESSR_EL1 | HDFGWTR2_EL2_nSPMCNTEN | HDFGWTR2_EL2_nSPMCR_EL0 | HDFGWTR2_EL2_nSPMEVCNTRn_EL0 | HDFGWTR2_EL2_nSPMEVTYPERn_EL0| HDFGWTR2_EL2_nSPMINTEN | HDFGWTR2_EL2_nSPMOVS | HDFGWTR2_EL2_nSPMSCR_EL1 | HDFGWTR2_EL2_nSPMSELR_EL0, FEAT_SPMU), NEEDS_FEAT(HDFGWTR2_EL2_nMDSTEPOP_EL1, FEAT_STEP2), NEEDS_FEAT(HDFGWTR2_EL2_nTRBMPAM_EL1, feat_trbe_mpam), }; static const DECLARE_FEAT_MAP_FGT(hdfgwtr2_desc, hdfgwtr2_masks, hdfgwtr2_feat_map, FEAT_FGT2); static const struct reg_bits_to_feat_map hcrx_feat_map[] = { NEEDS_FEAT(HCRX_EL2_PACMEn, feat_pauth_lr), NEEDS_FEAT(HCRX_EL2_EnFPM, FEAT_FPMR), NEEDS_FEAT(HCRX_EL2_GCSEn, FEAT_GCS), NEEDS_FEAT(HCRX_EL2_EnIDCP128, FEAT_SYSREG128), NEEDS_FEAT(HCRX_EL2_EnSDERR, feat_aderr), NEEDS_FEAT(HCRX_EL2_TMEA, FEAT_DoubleFault2), NEEDS_FEAT(HCRX_EL2_EnSNERR, feat_anerr), NEEDS_FEAT(HCRX_EL2_D128En, FEAT_D128), NEEDS_FEAT(HCRX_EL2_PTTWI, FEAT_THE), NEEDS_FEAT(HCRX_EL2_SCTLR2En, FEAT_SCTLR2), NEEDS_FEAT(HCRX_EL2_TCR2En, FEAT_TCR2), NEEDS_FEAT(HCRX_EL2_MSCEn | HCRX_EL2_MCE2, FEAT_MOPS), NEEDS_FEAT(HCRX_EL2_CMOW, FEAT_CMOW), NEEDS_FEAT(HCRX_EL2_VFNMI | HCRX_EL2_VINMI | HCRX_EL2_TALLINT, FEAT_NMI), NEEDS_FEAT(HCRX_EL2_SMPME, feat_sme_smps), NEEDS_FEAT(HCRX_EL2_FGTnXS | HCRX_EL2_FnXS, FEAT_XS), NEEDS_FEAT(HCRX_EL2_EnASR, FEAT_LS64_V), NEEDS_FEAT(HCRX_EL2_EnALS, FEAT_LS64), NEEDS_FEAT(HCRX_EL2_EnAS0, FEAT_LS64_ACCDATA), }; static const DECLARE_FEAT_MAP(hcrx_desc, __HCRX_EL2, hcrx_feat_map, FEAT_HCX); static const struct reg_bits_to_feat_map hcr_feat_map[] = { NEEDS_FEAT(HCR_EL2_TID0, FEAT_AA32EL0), NEEDS_FEAT_FIXED(HCR_EL2_RW, compute_hcr_rw), NEEDS_FEAT(HCR_EL2_HCD, not_feat_aa64el3), NEEDS_FEAT(HCR_EL2_AMO | HCR_EL2_BSU | HCR_EL2_CD | HCR_EL2_DC | HCR_EL2_FB | HCR_EL2_FMO | HCR_EL2_ID | HCR_EL2_IMO | HCR_EL2_MIOCNCE | HCR_EL2_PTW | HCR_EL2_SWIO | HCR_EL2_TACR | HCR_EL2_TDZ | HCR_EL2_TGE | HCR_EL2_TID1 | HCR_EL2_TID2 | HCR_EL2_TID3 | HCR_EL2_TIDCP | HCR_EL2_TPCP | HCR_EL2_TPU | HCR_EL2_TRVM | HCR_EL2_TSC | HCR_EL2_TSW | HCR_EL2_TTLB | HCR_EL2_TVM | HCR_EL2_TWE | HCR_EL2_TWI | HCR_EL2_VF | HCR_EL2_VI | HCR_EL2_VM | HCR_EL2_VSE, FEAT_AA64EL1), NEEDS_FEAT(HCR_EL2_AMVOFFEN, FEAT_AMUv1p1), NEEDS_FEAT(HCR_EL2_EnSCXT, feat_csv2_2_csv2_1p2), NEEDS_FEAT(HCR_EL2_TICAB | HCR_EL2_TID4 | HCR_EL2_TOCU, FEAT_EVT), NEEDS_FEAT(HCR_EL2_TTLBIS | HCR_EL2_TTLBOS, FEAT_EVT_TTLBxS), NEEDS_FEAT(HCR_EL2_TLOR, FEAT_LOR), NEEDS_FEAT(HCR_EL2_ATA | HCR_EL2_DCT | HCR_EL2_TID5, FEAT_MTE2), NEEDS_FEAT(HCR_EL2_AT | /* Ignore the original FEAT_NV */ HCR_EL2_NV2 | HCR_EL2_NV, feat_nv2), NEEDS_FEAT(HCR_EL2_NV1, feat_nv2_e2h0_ni), /* Missing from JSON */ NEEDS_FEAT(HCR_EL2_API | HCR_EL2_APK, feat_pauth), NEEDS_FEAT(HCR_EL2_TEA | HCR_EL2_TERR, FEAT_RAS), NEEDS_FEAT(HCR_EL2_FIEN, feat_rasv1p1), NEEDS_FEAT(HCR_EL2_GPF, FEAT_RME), NEEDS_FEAT(HCR_EL2_FWB, FEAT_S2FWB), NEEDS_FEAT(HCR_EL2_TME, FEAT_TME), NEEDS_FEAT(HCR_EL2_TWEDEL | HCR_EL2_TWEDEn, FEAT_TWED), NEEDS_FEAT_FIXED(HCR_EL2_E2H, compute_hcr_e2h), }; static const DECLARE_FEAT_MAP(hcr_desc, HCR_EL2, hcr_feat_map, FEAT_AA64EL2); static const struct reg_bits_to_feat_map sctlr2_feat_map[] = { NEEDS_FEAT(SCTLR2_EL1_NMEA | SCTLR2_EL1_EASE, FEAT_DoubleFault2), NEEDS_FEAT(SCTLR2_EL1_EnADERR, feat_aderr), NEEDS_FEAT(SCTLR2_EL1_EnANERR, feat_anerr), NEEDS_FEAT(SCTLR2_EL1_EnIDCP128, FEAT_SYSREG128), NEEDS_FEAT(SCTLR2_EL1_EnPACM | SCTLR2_EL1_EnPACM0, feat_pauth_lr), NEEDS_FEAT(SCTLR2_EL1_CPTA | SCTLR2_EL1_CPTA0 | SCTLR2_EL1_CPTM | SCTLR2_EL1_CPTM0, FEAT_CPA2), }; static const DECLARE_FEAT_MAP(sctlr2_desc, SCTLR2_EL1, sctlr2_feat_map, FEAT_SCTLR2); static const struct reg_bits_to_feat_map tcr2_el2_feat_map[] = { NEEDS_FEAT(TCR2_EL2_FNG1 | TCR2_EL2_FNG0 | TCR2_EL2_A2, feat_asid2_e2h1), NEEDS_FEAT(TCR2_EL2_DisCH1 | TCR2_EL2_DisCH0 | TCR2_EL2_D128, feat_d128_e2h1), NEEDS_FEAT(TCR2_EL2_AMEC1, feat_mec_e2h1), NEEDS_FEAT(TCR2_EL2_AMEC0, FEAT_MEC), NEEDS_FEAT(TCR2_EL2_HAFT, FEAT_HAFT), NEEDS_FEAT(TCR2_EL2_PTTWI | TCR2_EL2_PnCH, FEAT_THE), NEEDS_FEAT(TCR2_EL2_AIE, FEAT_AIE), NEEDS_FEAT(TCR2_EL2_POE | TCR2_EL2_E0POE, FEAT_S1POE), NEEDS_FEAT(TCR2_EL2_PIE, FEAT_S1PIE), }; static const DECLARE_FEAT_MAP(tcr2_el2_desc, TCR2_EL2, tcr2_el2_feat_map, FEAT_TCR2); static const struct reg_bits_to_feat_map sctlr_el1_feat_map[] = { NEEDS_FEAT(SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD | SCTLR_EL1_SED, FEAT_AA32EL0), NEEDS_FEAT(SCTLR_EL1_BT0 | SCTLR_EL1_BT1, FEAT_BTI), NEEDS_FEAT(SCTLR_EL1_CMOW, FEAT_CMOW), NEEDS_FEAT(SCTLR_EL1_TSCXT, feat_csv2_2_csv2_1p2), NEEDS_FEAT(SCTLR_EL1_EIS | SCTLR_EL1_EOS, FEAT_ExS), NEEDS_FEAT(SCTLR_EL1_EnFPM, FEAT_FPMR), NEEDS_FEAT(SCTLR_EL1_IESB, FEAT_IESB), NEEDS_FEAT(SCTLR_EL1_EnALS, FEAT_LS64), NEEDS_FEAT(SCTLR_EL1_EnAS0, FEAT_LS64_ACCDATA), NEEDS_FEAT(SCTLR_EL1_EnASR, FEAT_LS64_V), NEEDS_FEAT(SCTLR_EL1_nAA, FEAT_LSE2), NEEDS_FEAT(SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD, FEAT_LSMAOC), NEEDS_FEAT(SCTLR_EL1_EE, FEAT_MixedEnd), NEEDS_FEAT(SCTLR_EL1_E0E, feat_mixedendel0), NEEDS_FEAT(SCTLR_EL1_MSCEn, FEAT_MOPS), NEEDS_FEAT(SCTLR_EL1_ATA0 | SCTLR_EL1_ATA | SCTLR_EL1_TCF0 | SCTLR_EL1_TCF, FEAT_MTE2), NEEDS_FEAT(SCTLR_EL1_ITFSB, feat_mte_async), NEEDS_FEAT(SCTLR_EL1_TCSO0 | SCTLR_EL1_TCSO, FEAT_MTE_STORE_ONLY), NEEDS_FEAT(SCTLR_EL1_NMI | SCTLR_EL1_SPINTMASK, FEAT_NMI), NEEDS_FEAT(SCTLR_EL1_SPAN, FEAT_PAN), NEEDS_FEAT(SCTLR_EL1_EPAN, FEAT_PAN3), NEEDS_FEAT(SCTLR_EL1_EnDA | SCTLR_EL1_EnDB | SCTLR_EL1_EnIA | SCTLR_EL1_EnIB, feat_pauth), NEEDS_FEAT(SCTLR_EL1_EnTP2, FEAT_SME), NEEDS_FEAT(SCTLR_EL1_EnRCTX, FEAT_SPECRES), NEEDS_FEAT(SCTLR_EL1_DSSBS, FEAT_SSBS), NEEDS_FEAT(SCTLR_EL1_TIDCP, FEAT_TIDCP1), NEEDS_FEAT(SCTLR_EL1_TME0 | SCTLR_EL1_TME | SCTLR_EL1_TMT0 | SCTLR_EL1_TMT, FEAT_TME), NEEDS_FEAT(SCTLR_EL1_TWEDEL | SCTLR_EL1_TWEDEn, FEAT_TWED), NEEDS_FEAT(SCTLR_EL1_UCI | SCTLR_EL1_EE | SCTLR_EL1_E0E | SCTLR_EL1_WXN | SCTLR_EL1_nTWE | SCTLR_EL1_nTWI | SCTLR_EL1_UCT | SCTLR_EL1_DZE | SCTLR_EL1_I | SCTLR_EL1_UMA | SCTLR_EL1_SA0 | SCTLR_EL1_SA | SCTLR_EL1_C | SCTLR_EL1_A | SCTLR_EL1_M, FEAT_AA64EL1), }; static const DECLARE_FEAT_MAP(sctlr_el1_desc, SCTLR_EL1, sctlr_el1_feat_map, FEAT_AA64EL1); static const struct reg_bits_to_feat_map mdcr_el2_feat_map[] = { NEEDS_FEAT(MDCR_EL2_EBWE, FEAT_Debugv8p9), NEEDS_FEAT(MDCR_EL2_TDOSA, FEAT_DoubleLock), NEEDS_FEAT(MDCR_EL2_PMEE, FEAT_EBEP), NEEDS_FEAT(MDCR_EL2_TDCC, FEAT_FGT), NEEDS_FEAT(MDCR_EL2_MTPME, FEAT_MTPMU), NEEDS_FEAT(MDCR_EL2_HPME | MDCR_EL2_HPMN | MDCR_EL2_TPMCR | MDCR_EL2_TPM, FEAT_PMUv3), NEEDS_FEAT(MDCR_EL2_HPMD, feat_pmuv3p1), NEEDS_FEAT(MDCR_EL2_HCCD | MDCR_EL2_HLP, feat_pmuv3p5), NEEDS_FEAT(MDCR_EL2_HPMFZO, feat_pmuv3p7), NEEDS_FEAT(MDCR_EL2_PMSSE, FEAT_PMUv3_SS), NEEDS_FEAT(MDCR_EL2_E2PB | MDCR_EL2_TPMS, FEAT_SPE), NEEDS_FEAT(MDCR_EL2_HPMFZS, FEAT_SPEv1p2), NEEDS_FEAT(MDCR_EL2_EnSPM, FEAT_SPMU), NEEDS_FEAT(MDCR_EL2_EnSTEPOP, FEAT_STEP2), NEEDS_FEAT(MDCR_EL2_E2TB, FEAT_TRBE), NEEDS_FEAT(MDCR_EL2_TTRF, FEAT_TRF), NEEDS_FEAT(MDCR_EL2_TDA | MDCR_EL2_TDE | MDCR_EL2_TDRA, FEAT_AA64EL1), }; static const DECLARE_FEAT_MAP(mdcr_el2_desc, MDCR_EL2, mdcr_el2_feat_map, FEAT_AA64EL2); static void __init check_feat_map(const struct reg_bits_to_feat_map *map, int map_size, u64 res0, const char *str) { u64 mask = 0; for (int i = 0; i < map_size; i++) mask |= map[i].bits; if (mask != ~res0) kvm_err("Undefined %s behaviour, bits %016llx\n", str, mask ^ ~res0); } static u64 reg_feat_map_bits(const struct reg_bits_to_feat_map *map) { return map->flags & RES0_POINTER ? ~(*map->res0p) : map->bits; } static void __init check_reg_desc(const struct reg_feat_map_desc *r) { check_feat_map(r->bit_feat_map, r->bit_feat_map_sz, ~reg_feat_map_bits(&r->feat_map), r->name); } void __init check_feature_map(void) { check_reg_desc(&hfgrtr_desc); check_reg_desc(&hfgwtr_desc); check_reg_desc(&hfgitr_desc); check_reg_desc(&hdfgrtr_desc); check_reg_desc(&hdfgwtr_desc); check_reg_desc(&hafgrtr_desc); check_reg_desc(&hfgrtr2_desc); check_reg_desc(&hfgwtr2_desc); check_reg_desc(&hfgitr2_desc); check_reg_desc(&hdfgrtr2_desc); check_reg_desc(&hdfgwtr2_desc); check_reg_desc(&hcrx_desc); check_reg_desc(&hcr_desc); check_reg_desc(&sctlr2_desc); check_reg_desc(&tcr2_el2_desc); check_reg_desc(&sctlr_el1_desc); check_reg_desc(&mdcr_el2_desc); } static bool idreg_feat_match(struct kvm *kvm, const struct reg_bits_to_feat_map *map) { u64 regval = kvm->arch.id_regs[map->regidx]; u64 regfld = (regval >> map->shift) & GENMASK(map->width - 1, 0); if (map->sign) { s64 sfld = sign_extend64(regfld, map->width - 1); s64 slim = sign_extend64(map->lo_lim, map->width - 1); return sfld >= slim; } else { return regfld >= map->lo_lim; } } static u64 __compute_fixed_bits(struct kvm *kvm, const struct reg_bits_to_feat_map *map, int map_size, u64 *fixed_bits, unsigned long require, unsigned long exclude) { u64 val = 0; for (int i = 0; i < map_size; i++) { bool match; if ((map[i].flags & require) != require) continue; if (map[i].flags & exclude) continue; if (map[i].flags & CALL_FUNC) match = (map[i].flags & FIXED_VALUE) ? map[i].fval(kvm, fixed_bits) : map[i].match(kvm); else match = idreg_feat_match(kvm, &map[i]); if (!match || (map[i].flags & FIXED_VALUE)) val |= reg_feat_map_bits(&map[i]); } return val; } static u64 compute_res0_bits(struct kvm *kvm, const struct reg_bits_to_feat_map *map, int map_size, unsigned long require, unsigned long exclude) { return __compute_fixed_bits(kvm, map, map_size, NULL, require, exclude | FIXED_VALUE); } static u64 compute_reg_res0_bits(struct kvm *kvm, const struct reg_feat_map_desc *r, unsigned long require, unsigned long exclude) { u64 res0; res0 = compute_res0_bits(kvm, r->bit_feat_map, r->bit_feat_map_sz, require, exclude); /* * If computing FGUs, don't take RES0 or register existence * into account -- we're not computing bits for the register * itself. */ if (!(exclude & NEVER_FGU)) { res0 |= compute_res0_bits(kvm, &r->feat_map, 1, require, exclude); res0 |= ~reg_feat_map_bits(&r->feat_map); } return res0; } static u64 compute_reg_fixed_bits(struct kvm *kvm, const struct reg_feat_map_desc *r, u64 *fixed_bits, unsigned long require, unsigned long exclude) { return __compute_fixed_bits(kvm, r->bit_feat_map, r->bit_feat_map_sz, fixed_bits, require | FIXED_VALUE, exclude); } void compute_fgu(struct kvm *kvm, enum fgt_group_id fgt) { u64 val = 0; switch (fgt) { case HFGRTR_GROUP: val |= compute_reg_res0_bits(kvm, &hfgrtr_desc, 0, NEVER_FGU); val |= compute_reg_res0_bits(kvm, &hfgwtr_desc, 0, NEVER_FGU); break; case HFGITR_GROUP: val |= compute_reg_res0_bits(kvm, &hfgitr_desc, 0, NEVER_FGU); break; case HDFGRTR_GROUP: val |= compute_reg_res0_bits(kvm, &hdfgrtr_desc, 0, NEVER_FGU); val |= compute_reg_res0_bits(kvm, &hdfgwtr_desc, 0, NEVER_FGU); break; case HAFGRTR_GROUP: val |= compute_reg_res0_bits(kvm, &hafgrtr_desc, 0, NEVER_FGU); break; case HFGRTR2_GROUP: val |= compute_reg_res0_bits(kvm, &hfgrtr2_desc, 0, NEVER_FGU); val |= compute_reg_res0_bits(kvm, &hfgwtr2_desc, 0, NEVER_FGU); break; case HFGITR2_GROUP: val |= compute_reg_res0_bits(kvm, &hfgitr2_desc, 0, NEVER_FGU); break; case HDFGRTR2_GROUP: val |= compute_reg_res0_bits(kvm, &hdfgrtr2_desc, 0, NEVER_FGU); val |= compute_reg_res0_bits(kvm, &hdfgwtr2_desc, 0, NEVER_FGU); break; default: BUG(); } kvm->arch.fgu[fgt] = val; } void get_reg_fixed_bits(struct kvm *kvm, enum vcpu_sysreg reg, u64 *res0, u64 *res1) { u64 fixed = 0, mask; switch (reg) { case HFGRTR_EL2: *res0 = compute_reg_res0_bits(kvm, &hfgrtr_desc, 0, 0); *res1 = HFGRTR_EL2_RES1; break; case HFGWTR_EL2: *res0 = compute_reg_res0_bits(kvm, &hfgwtr_desc, 0, 0); *res1 = HFGWTR_EL2_RES1; break; case HFGITR_EL2: *res0 = compute_reg_res0_bits(kvm, &hfgitr_desc, 0, 0); *res1 = HFGITR_EL2_RES1; break; case HDFGRTR_EL2: *res0 = compute_reg_res0_bits(kvm, &hdfgrtr_desc, 0, 0); *res1 = HDFGRTR_EL2_RES1; break; case HDFGWTR_EL2: *res0 = compute_reg_res0_bits(kvm, &hdfgwtr_desc, 0, 0); *res1 = HDFGWTR_EL2_RES1; break; case HAFGRTR_EL2: *res0 = compute_reg_res0_bits(kvm, &hafgrtr_desc, 0, 0); *res1 = HAFGRTR_EL2_RES1; break; case HFGRTR2_EL2: *res0 = compute_reg_res0_bits(kvm, &hfgrtr2_desc, 0, 0); *res1 = HFGRTR2_EL2_RES1; break; case HFGWTR2_EL2: *res0 = compute_reg_res0_bits(kvm, &hfgwtr2_desc, 0, 0); *res1 = HFGWTR2_EL2_RES1; break; case HFGITR2_EL2: *res0 = compute_reg_res0_bits(kvm, &hfgitr2_desc, 0, 0); *res1 = HFGITR2_EL2_RES1; break; case HDFGRTR2_EL2: *res0 = compute_reg_res0_bits(kvm, &hdfgrtr2_desc, 0, 0); *res1 = HDFGRTR2_EL2_RES1; break; case HDFGWTR2_EL2: *res0 = compute_reg_res0_bits(kvm, &hdfgwtr2_desc, 0, 0); *res1 = HDFGWTR2_EL2_RES1; break; case HCRX_EL2: *res0 = compute_reg_res0_bits(kvm, &hcrx_desc, 0, 0); *res1 = __HCRX_EL2_RES1; break; case HCR_EL2: mask = compute_reg_fixed_bits(kvm, &hcr_desc, &fixed, 0, 0); *res0 = compute_reg_res0_bits(kvm, &hcr_desc, 0, 0); *res0 |= (mask & ~fixed); *res1 = HCR_EL2_RES1 | (mask & fixed); break; case SCTLR2_EL1: case SCTLR2_EL2: *res0 = compute_reg_res0_bits(kvm, &sctlr2_desc, 0, 0); *res1 = SCTLR2_EL1_RES1; break; case TCR2_EL2: *res0 = compute_reg_res0_bits(kvm, &tcr2_el2_desc, 0, 0); *res1 = TCR2_EL2_RES1; break; case SCTLR_EL1: *res0 = compute_reg_res0_bits(kvm, &sctlr_el1_desc, 0, 0); *res1 = SCTLR_EL1_RES1; break; case MDCR_EL2: *res0 = compute_reg_res0_bits(kvm, &mdcr_el2_desc, 0, 0); *res1 = MDCR_EL2_RES1; break; default: WARN_ON_ONCE(1); *res0 = *res1 = 0; break; } } |
| 175 173 175 174 | 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 | // 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/dax.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, vm_flags_t *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, vm_flags_t 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 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_maybe_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 (folio_expected_ref_count(folio) != folio_ref_count(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, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(folio, 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) { unsigned long end = address + HPAGE_PMD_SIZE; struct folio *src, *tmp; pte_t pteval; pte_t *_pte; unsigned int nr_ptes; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte += nr_ptes, address += nr_ptes * PAGE_SIZE) { nr_ptes = 1; 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)) { unsigned int max_nr_ptes = (end - address) >> PAGE_SHIFT; nr_ptes = folio_pte_batch(src, _pte, pteval, max_nr_ptes); } else { 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); clear_ptes(vma->vm_mm, address, _pte, nr_ptes); folio_remove_rmap_ptes(src, src_page, nr_ptes, vma); spin_unlock(ptl); free_swap_cache(src); folio_put_refs(src, nr_ptes); } } 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 inline int check_pmd_state(pmd_t *pmd) { pmd_t pmde = pmdp_get_lockless(pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; /* * The folio may be under migration when khugepaged is trying to * collapse it. Migration success or failure will eventually end * up with a present PMD mapping a folio again. */ if (is_pmd_migration_entry(pmde)) return SCAN_PMD_MAPPED; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; return check_pmd_state(*pmd); } 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 */ vma_start_write(vma); result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; 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 = folio_mk_pmd(folio, 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. */ if (folio_maybe_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 (folio_expected_ref_count(folio) != folio_ref_count(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, 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); } } /* folio 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 folio *folio, struct page *page) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, folio, page)) return SCAN_FAIL; folio_get(folio); 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) { int nr_mapped_ptes = 0, result = SCAN_FAIL; unsigned int nr_batch_ptes; struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; unsigned long end = haddr + HPAGE_PMD_SIZE; 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 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 += nr_batch_ptes, addr += nr_batch_ptes * PAGE_SIZE, pte += nr_batch_ptes) { unsigned int max_nr_batch_ptes = (end - addr) >> PAGE_SHIFT; struct page *page; pte_t ptent = ptep_get(pte); nr_batch_ptes = 1; 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; nr_batch_ptes = folio_pte_batch(folio, pte, ptent, max_nr_batch_ptes); /* * 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. */ clear_ptes(mm, addr, pte, nr_batch_ptes); folio_remove_rmap_ptes(folio, page, nr_batch_ptes, vma); nr_mapped_ptes += nr_batch_ptes; } if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_mapped_ptes) { folio_ref_sub(folio, nr_mapped_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_mapped_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, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_mapped_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_mapped_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_mapped_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 success = 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); /* * The lock of new_folio is still held, we will be blocked in * the page fault path, which prevents the pte entries from * being set again. So even though the old empty PTE page may be * concurrently freed and a new PTE page is filled into the pmd * entry, it is still empty and can be removed. * * So here we only need to recheck if the state of pmd entry * still meets our requirements, rather than checking pmd_same() * like elsewhere. */ if (check_pmd_state(pmd) != SCAN_SUCCEED) goto drop_pml; 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 (likely(!vma->anon_vma && !userfaultfd_wp(vma))) { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); success = true; } if (ptl != pml) spin_unlock(ptl); drop_pml: spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (success) { 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; mapping_set_update(&xas, mapping); __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_try_get(folio)) { xas_reset(&xas); continue; } if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); xas_reset(&xas); 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. */ folio_put(folio); break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; folio_put(folio); break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; folio_put(folio); break; } if (folio_expected_ref_count(folio) + 1 != folio_ref_count(folio)) { result = SCAN_PAGE_COUNT; folio_put(folio); 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); folio_put(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; } 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 (!vma_is_anonymous(vma)) { 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, unsigned long start, unsigned long end, bool *lock_dropped) { 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); 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 (!vma_is_anonymous(vma)) { 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) *lock_dropped = true; handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); 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); } |
| 1 5 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_device.c - IPsec device offloading code. * * Copyright (c) 2015 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/errno.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/gso.h> #include <net/xfrm.h> #include <linux/notifier.h> #ifdef CONFIG_XFRM_OFFLOAD static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); pskb_pull(skb, skb->mac_len + x->props.header_len - x->props.enc_hdr_len); } static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); int phlen = 0; if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); if (x->sel.family != AF_INET6) { phlen = IPV4_BEET_PHMAXLEN; if (x->outer_mode.family == AF_INET6) phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr); } pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen)); } /* Adjust pointers into the packet when IPsec is done at layer2 */ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) { switch (x->outer_mode.encap) { case XFRM_MODE_IPTFS: case XFRM_MODE_TUNNEL: if (x->outer_mode.family == AF_INET) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_TRANSPORT: if (x->outer_mode.family == AF_INET) return __xfrm_transport_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_transport_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_BEET: if (x->outer_mode.family == AF_INET) return __xfrm_mode_beet_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_beet_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: break; } } static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) { struct xfrm_offload *xo = xfrm_offload(skb); __u32 seq = xo->seq.low; seq += skb_shinfo(skb)->gso_segs; if (unlikely(seq < xo->seq.low)) return true; return false; } struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; unsigned long flags; struct xfrm_state *x; struct softnet_data *sd; struct sk_buff *skb2, *nskb, *pskb = NULL; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct net_device *dev = skb->dev; struct sec_path *sp; if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN) return skb; /* The packet was sent to HW IPsec packet offload engine, * but to wrong device. Drop the packet, so it won't skip * XFRM stack. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); err = !skb_queue_empty(&sd->xfrm_backlog); local_irq_restore(flags); if (err) { *again = true; return skb; } if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP); segs = skb_gso_segment(skb, esp_features); if (IS_ERR(segs)) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } else { consume_skb(skb); skb = segs; } } if (!skb->next) { esp_features |= skb->dev->gso_partial_features; xfrm_outer_mode_prep(x, skb); xo->flags |= XFRM_DEV_RESUME; err = x->type_offload->xmit(x, skb, esp_features); if (err) { if (err == -EINPROGRESS) return NULL; XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); return NULL; } skb_push(skb, skb->data - skb_mac_header(skb)); return skb; } skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; xfrm_outer_mode_prep(x, skb2); err = x->type_offload->xmit(x, skb2, esp_features); if (!err) { skb2->next = nskb; } else if (err != -EINPROGRESS) { XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); skb2->next = nskb; kfree_skb_list(skb2); return NULL; } else { if (skb == skb2) skb = nskb; else pskb->next = nskb; continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); pskb = skb2; } return skb; } EXPORT_SYMBOL_GPL(validate_xmit_xfrm); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { int err; struct dst_entry *dst; struct net_device *dev; struct xfrm_dev_offload *xso = &x->xso; xfrm_address_t *saddr; xfrm_address_t *daddr; bool is_packet_offload; if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) { NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); return -EINVAL; } if (xuo->flags & XFRM_OFFLOAD_INBOUND && x->if_id) { NL_SET_ERR_MSG(extack, "XFRM if_id is not supported in RX path"); return -EINVAL; } is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support TFC padding. */ if (x->tfcpad) { NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { struct xfrm_dst_lookup_params params; if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { saddr = &x->props.saddr; daddr = &x->id.daddr; } else { saddr = &x->id.daddr; daddr = &x->props.saddr; } memset(¶ms, 0, sizeof(params)); params.net = net; params.saddr = saddr; params.daddr = daddr; params.mark = xfrm_smark_get(0, x); dst = __xfrm_dst_lookup(x->props.family, ¶ms); if (IS_ERR(dst)) return (is_packet_offload) ? -EINVAL : 0; dev = dst->dev; dev_hold(dev); dst_release(dst); } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { xso->dev = NULL; dev_put(dev); return (is_packet_offload) ? -EINVAL : 0; } if (!is_packet_offload && x->props.flags & XFRM_STATE_ESN && !dev->xfrmdev_ops->xdo_dev_state_advance_esn) { NL_SET_ERR_MSG(extack, "Device doesn't support offload with ESN"); xso->dev = NULL; dev_put(dev); return -EINVAL; } if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); dev_put(dev); return -EINVAL; } xso->dev = dev; netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); if (xuo->flags & XFRM_OFFLOAD_INBOUND) xso->dir = XFRM_DEV_OFFLOAD_IN; else xso->dir = XFRM_DEV_OFFLOAD_OUT; if (is_packet_offload) xso->type = XFRM_DEV_OFFLOAD_PACKET; else xso->type = XFRM_DEV_OFFLOAD_CRYPTO; err = dev->xfrmdev_ops->xdo_dev_state_add(dev, x, extack); if (err) { xso->dev = NULL; xso->dir = 0; netdev_put(dev, &xso->dev_tracker); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xfrm_unset_type_offload(x); /* User explicitly requested packet offload mode and configured * policy in addition to the XFRM state. So be civil to users, * and return an error instead of taking fallback path. */ if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; } } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_state_add); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { struct xfrm_dev_offload *xdo = &xp->xdo; struct net_device *dev; int err; if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) { /* We support only packet offload mode and it means * that user must set XFRM_OFFLOAD_PACKET bit. */ NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) return -EINVAL; if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) { xdo->dev = NULL; dev_put(dev); NL_SET_ERR_MSG(extack, "Policy offload is not supported"); return -EINVAL; } xdo->dev = dev; netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); xdo->type = XFRM_DEV_OFFLOAD_PACKET; switch (dir) { case XFRM_POLICY_IN: xdo->dir = XFRM_DEV_OFFLOAD_IN; break; case XFRM_POLICY_OUT: xdo->dir = XFRM_DEV_OFFLOAD_OUT; break; case XFRM_POLICY_FWD: xdo->dir = XFRM_DEV_OFFLOAD_FWD; break; default: xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack); if (err) { xdo->dev = NULL; xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy"); return err; } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_policy_add); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { int mtu; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; bool check_tunnel_size; if (!x->type_offload || (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if ((!dev || dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } return false; ok: if (!dev) return true; check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; switch (x->props.family) { case AF_INET: /* Check for IPv4 options */ if (ip_hdr(skb)->ihl != 5) return false; if (check_tunnel_size && xfrm4_tunnel_check_size(skb)) return false; break; case AF_INET6: /* Check for IPv6 extensions */ if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) return false; if (check_tunnel_size && xfrm6_tunnel_check_size(skb)) return false; break; default: break; } if (dev->xfrmdev_ops->xdo_dev_offload_ok) return dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x); return true; } EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); void xfrm_dev_resume(struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret = NETDEV_TX_BUSY; struct netdev_queue *txq; struct softnet_data *sd; unsigned long flags; rcu_read_lock(); txq = netdev_core_pick_tx(dev, skb, NULL); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); if (!dev_xmit_complete(ret)) { local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); skb_queue_tail(&sd->xfrm_backlog, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(xfrm_dev_resume); void xfrm_dev_backlog(struct softnet_data *sd) { struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog; struct sk_buff_head list; struct sk_buff *skb; if (skb_queue_empty(xfrm_backlog)) return; __skb_queue_head_init(&list); spin_lock(&xfrm_backlog->lock); skb_queue_splice_init(xfrm_backlog, &list); spin_unlock(&xfrm_backlog->lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); xfrm_dev_resume(skb); } } #endif static int xfrm_api_check(struct net_device *dev) { #ifdef CONFIG_XFRM_OFFLOAD if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && !(dev->features & NETIF_F_HW_ESP)) return NOTIFY_BAD; if ((dev->features & NETIF_F_HW_ESP) && (!(dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_add && dev->xfrmdev_ops->xdo_dev_state_delete))) return NOTIFY_BAD; #else if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM)) return NOTIFY_BAD; #endif return NOTIFY_DONE; } static int xfrm_dev_down(struct net_device *dev) { if (dev->features & NETIF_F_HW_ESP) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); } return NOTIFY_DONE; } static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: return xfrm_api_check(dev); case NETDEV_FEAT_CHANGE: return xfrm_api_check(dev); case NETDEV_DOWN: case NETDEV_UNREGISTER: return xfrm_dev_down(dev); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { .notifier_call = xfrm_dev_event, }; void __init xfrm_dev_init(void) { register_netdevice_notifier(&xfrm_dev_notifier); } |
| 459 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_setup_per_zone_wmarks, TP_PROTO(struct zone *zone), TP_ARGS(zone), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __field(unsigned long, watermark_min) __field(unsigned long, watermark_low) __field(unsigned long, watermark_high) __field(unsigned long, watermark_promo) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __entry->watermark_min = zone->_watermark[WMARK_MIN]; __entry->watermark_low = zone->_watermark[WMARK_LOW]; __entry->watermark_high = zone->_watermark[WMARK_HIGH]; __entry->watermark_promo = zone->_watermark[WMARK_PROMO]; ), TP_printk("node_id=%d zone name=%s watermark min=%lu low=%lu high=%lu promo=%lu", __entry->node_id, __get_str(name), __entry->watermark_min, __entry->watermark_low, __entry->watermark_high, __entry->watermark_promo) ); TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), TP_ARGS(zone, upper_zone, lowmem_reserve), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __string(upper_name, upper_zone->name) __field(long, lowmem_reserve) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __assign_str(upper_name); __entry->lowmem_reserve = lowmem_reserve; ), TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", __entry->node_id, __get_str(name), __get_str(upper_name), __entry->lowmem_reserve) ); TRACE_EVENT(mm_calculate_totalreserve_pages, TP_PROTO(unsigned long totalreserve_pages), TP_ARGS(totalreserve_pages), TP_STRUCT__entry( __field(unsigned long, totalreserve_pages) ), TP_fast_assign( __entry->totalreserve_pages = totalreserve_pages; ), TP_printk("totalreserve_pages=%lu", __entry->totalreserve_pages) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 99 99 242 244 234 129 101 53 100 53 193 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Integrity Measurement Architecture * * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Reiner Sailer <sailer@watson.ibm.com> * Serge Hallyn <serue@us.ibm.com> * Kylene Hall <kylene@us.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_main.c * implements the IMA hooks: ima_bprm_check, ima_file_mmap, * and ima_file_check. */ #include <linux/module.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/kernel_read_file.h> #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/ima.h> #include <linux/fs.h> #include <linux/iversion.h> #include <linux/evm.h> #include <linux/crash_dump.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE int ima_appraise = IMA_APPRAISE_ENFORCE; #else int ima_appraise; #endif int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static int ima_disabled __ro_after_init; static struct notifier_block ima_lsm_policy_notifier = { .notifier_call = ima_lsm_policy_change, }; static int __init ima_setup(char *str) { if (!is_kdump_kernel()) { pr_info("Warning: ima setup option only permitted in kdump"); return 1; } if (strncmp(str, "off", 3) == 0) ima_disabled = 1; else if (strncmp(str, "on", 2) == 0) ima_disabled = 0; else pr_err("Invalid ima setup option: \"%s\" , please specify ima=on|off.", str); return 1; } __setup("ima=", ima_setup); static int __init hash_setup(char *str) { struct ima_template_desc *template_desc = ima_template_desc_current(); int i; if (hash_setup_done) return 1; if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) { if (strncmp(str, "sha1", 4) == 0) { ima_hash_algo = HASH_ALGO_SHA1; } else if (strncmp(str, "md5", 3) == 0) { ima_hash_algo = HASH_ALGO_MD5; } else { pr_err("invalid hash algorithm \"%s\" for template \"%s\"", str, IMA_TEMPLATE_IMA_NAME); return 1; } goto out; } i = match_string(hash_algo_name, HASH_ALGO__LAST, str); if (i < 0) { pr_err("invalid hash algorithm \"%s\"", str); return 1; } ima_hash_algo = i; out: hash_setup_done = 1; return 1; } __setup("ima_hash=", hash_setup); enum hash_algo ima_get_current_hash_algo(void) { return ima_hash_algo; } /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, char *filename) { struct inode *inode; int rc = 0; if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && mapping_writably_mapped(file->f_mapping)) { rc = -ETXTBSY; inode = file_inode(file); if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */ *pathname = ima_d_path(&file->f_path, pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname, "mmap_file", "mmapped_writers", rc, 0); } return rc; } /* * ima_rdwr_violation_check * * Only invalidate the PCR for measured files: * - Opening a file for write when already open for read, * results in a time of measure, time of use (ToMToU) error. * - Opening a file for read when already open for write, * could result in a file measurement error. * */ static void ima_rdwr_violation_check(struct file *file, struct ima_iint_cache *iint, int must_measure, char **pathbuf, const char **pathname, char *filename) { struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; bool send_tomtou = false, send_writers = false; if (mode & FMODE_WRITE) { if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = ima_iint_find(inode); /* IMA_MEASURE is set from reader side */ if (iint && test_and_clear_bit(IMA_MAY_EMIT_TOMTOU, &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) set_bit(IMA_MAY_EMIT_TOMTOU, &iint->atomic_flags); /* Limit number of open_writers violations */ if (inode_is_open_for_write(inode) && must_measure) { if (!test_and_set_bit(IMA_EMITTED_OPENWRITERS, &iint->atomic_flags)) send_writers = true; } } if (!send_tomtou && !send_writers) return; *pathname = ima_d_path(&file->f_path, pathbuf, filename); if (send_tomtou) ima_add_violation(file, *pathname, iint, "invalid_pcr", "ToMToU"); if (send_writers) ima_add_violation(file, *pathname, iint, "invalid_pcr", "open_writers"); } static void ima_check_last_writer(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { fmode_t mode = file->f_mode; bool update; if (!(mode & FMODE_WRITE)) return; mutex_lock(&iint->mutex); if (atomic_read(&inode->i_writecount) == 1) { struct kstat stat; clear_bit(IMA_EMITTED_OPENWRITERS, &iint->atomic_flags); update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if ((iint->flags & IMA_NEW_FILE) || vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT) || !(stat.result_mask & STATX_CHANGE_COOKIE) || stat.change_cookie != iint->real_inode.version) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; if (update) ima_update_xattr(iint, file); } } mutex_unlock(&iint->mutex); } /** * ima_file_free - called on __fput() * @file: pointer to file structure being freed * * Flag files that changed, based on i_version */ static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct ima_iint_cache *iint; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; ima_check_last_writer(iint, inode, file); } static int process_measurement(struct file *file, const struct cred *cred, struct lsm_prop *prop, char *buf, loff_t size, int mask, enum ima_hooks func) { struct inode *real_inode, *inode = file_inode(file); struct ima_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; struct inode *metadata_inode; char *pathbuf = NULL; char filename[NAME_MAX]; const char *pathname = NULL; int rc = 0, action, must_appraise = 0; int pcr = CONFIG_IMA_MEASURE_PCR_IDX; struct evm_ima_xattr_data *xattr_value = NULL; struct modsig *modsig = NULL; int xattr_len = 0; bool violation_check; enum hash_algo hash_algo; unsigned int allowed_algos = 0; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return 0; /* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ action = ima_get_action(file_mnt_idmap(file), inode, cred, prop, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && (ima_policy_flag & IMA_MEASURE) && ((action & IMA_MEASURE) || (file->f_mode & FMODE_WRITE))); if (!action && !violation_check) return 0; must_appraise = action & IMA_APPRAISE; /* Is the appraise rule hook specific? */ if (action & IMA_FILE_APPRAISE) func = FILE_CHECK; inode_lock(inode); if (action) { iint = ima_inode_get(inode); if (!iint) rc = -ENOMEM; } if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE, &pathbuf, &pathname, filename); inode_unlock(inode); if (rc) goto out; if (!action) goto out; mutex_lock(&iint->mutex); if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags)) /* * Reset appraisal flags (action and non-action rule-specific) * if ima_inode_post_setattr was called. */ iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED | IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK | IMA_NONACTION_RULE_FLAGS); /* * Re-evaulate the file if either the xattr has changed or the * kernel has no way of detecting file change on the filesystem. * (Limited to privileged mounted filesystems.) */ if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) && !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * On stacked filesystems, detect and re-evaluate file data and * metadata changes. */ real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) || integrity_inode_attrs_changed(&iint->real_inode, real_inode)) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * Reset the EVM status when metadata changed. */ metadata_inode = d_inode(d_real(file_dentry(file), D_REAL_METADATA)); if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED | IMA_APPRAISED_SUBMASK); } /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) */ iint->flags |= action; action &= IMA_DO_MASK; action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1); /* If target pcr is already measured, unset IMA_MEASURE action */ if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr))) action ^= IMA_MEASURE; /* HASH sets the digital signature and update flags, nothing else */ if ((action & IMA_HASH) && !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) { xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); if ((xattr_value && xattr_len > 2) && (xattr_value->type == EVM_IMA_XATTR_DIGSIG)) set_bit(IMA_DIGSIG, &iint->atomic_flags); iint->flags |= IMA_HASHED; action ^= IMA_HASH; set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } /* Nothing to do, just return existing appraised status */ if (!action) { if (must_appraise) { rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); if (!rc) rc = ima_get_cache_status(iint, func); } goto out_locked; } if ((action & IMA_APPRAISE_SUBMASK) || strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) { /* read 'security.ima' */ xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); /* * Read the appended modsig if allowed by the policy, and allow * an additional measurement list entry, if needed, based on the * template format and whether the file was already measured. */ if (iint->flags & IMA_MODSIG_ALLOWED) { rc = ima_read_modsig(func, buf, size, &modsig); if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED) action |= IMA_MEASURE; } } hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); if (rc != 0 && rc != -EBADF && rc != -EINVAL) goto out_locked; if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname, xattr_value, xattr_len, modsig, pcr, template_desc); if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { rc = ima_check_blacklist(iint, modsig, pcr); if (rc != -EPERM) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, xattr_value, xattr_len, modsig); inode_unlock(inode); } if (!rc) rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); } if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO)) rc = 0; /* Ensure the digest was generated using an allowed algorithm */ if (rc == 0 && must_appraise && allowed_algos != 0 && (allowed_algos & (1U << hash_algo)) == 0) { rc = -EACCES; integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file), pathname, "collect_data", "denied-hash-algorithm", rc, 0); } out_locked: if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE)) rc = -EACCES; mutex_unlock(&iint->mutex); kfree(xattr_value); ima_free_modsig(modsig); out: if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE)) return -EACCES; if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } return 0; } /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { struct lsm_prop prop; int ret; if (!file) return 0; security_current_getlsmprop_subj(&prop); if (reqprot & PROT_EXEC) { ret = process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT); if (ret) return ret; } if (prot & PROT_EXEC) return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK); return 0; } /** * ima_file_mprotect - based on policy, limit mprotect change * @vma: vm_area_struct protection is set to * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * * Files can be mmap'ed read/write and later changed to execute to circumvent * IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore * would be taken before i_mutex), files can not be measured or appraised at * this point. Eliminate this integrity gap by denying the mprotect * PROT_EXECUTE change, if an mmap appraise policy rule exists. * * On mprotect change success, return 0. On failure, return -EACESS. */ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; struct lsm_prop prop; int result = 0; int action; int pcr; /* Is mprotect making an mmap'ed file executable? */ if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file || !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; security_current_getlsmprop_subj(&prop); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) return 0; if (action & IMA_APPRAISE_SUBMASK) result = -EPERM; file = vma->vm_file; pathname = ima_d_path(&file->f_path, &pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname, "collect_data", "failed-mprotect", result, 0); if (pathbuf) __putname(pathbuf); return result; } /** * ima_bprm_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_check(struct linux_binprm *bprm) { int ret; struct lsm_prop prop; security_current_getlsmprop_subj(&prop); ret = process_measurement(bprm->file, current_cred(), &prop, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) return ret; security_cred_getlsmprop(bprm->cred, &prop); return process_measurement(bprm->file, bprm->cred, &prop, NULL, 0, MAY_EXEC, CREDS_CHECK); } /** * ima_bprm_creds_for_exec - collect/store/appraise measurement. * @bprm: contains the linux_binprm structure * * Based on the IMA policy and the execveat(2) AT_EXECVE_CHECK flag, measure * and appraise the integrity of a file to be executed by script interpreters. * Unlike any of the other LSM hooks where the kernel enforces file integrity, * enforcing file integrity is left up to the discretion of the script * interpreter (userspace). * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_creds_for_exec(struct linux_binprm *bprm) { /* * As security_bprm_check() is called multiple times, both * the script and the shebang interpreter are measured, appraised, * and audited. Limit usage of this LSM hook to just measuring, * appraising, and auditing the indirect script execution * (e.g. ./sh example.sh). */ if (!bprm->is_check) return 0; return ima_bprm_check(bprm); } /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND * * Measure files based on the ima_must_measure() policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_check(struct file *file, int mask) { struct lsm_prop prop; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { struct ima_iint_cache *iint = NULL, tmp_iint; int rc, hash_algo; if (ima_policy_flag) { iint = ima_iint_find(inode); if (iint) mutex_lock(&iint->mutex); } if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) { if (iint) mutex_unlock(&iint->mutex); memset(&tmp_iint, 0, sizeof(tmp_iint)); mutex_init(&tmp_iint.mutex); rc = ima_collect_measurement(&tmp_iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) { /* ima_hash could be allocated in case of failure. */ if (rc != -ENOMEM) kfree(tmp_iint.ima_hash); return -EOPNOTSUPP; } iint = &tmp_iint; mutex_lock(&iint->mutex); } if (!iint) return -EOPNOTSUPP; /* * ima_file_hash can be called when ima_collect_measurement has still * not been called, we might not always have a hash. */ if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) { mutex_unlock(&iint->mutex); return -EOPNOTSUPP; } if (buf) { size_t copied_size; copied_size = min_t(size_t, iint->ima_hash->length, buf_size); memcpy(buf, iint->ima_hash->digest, copied_size); } hash_algo = iint->ima_hash->algo; mutex_unlock(&iint->mutex); if (iint == &tmp_iint) kfree(iint->ima_hash); return hash_algo; } /** * ima_file_hash - return a measurement of the file * @file: pointer to the file * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The file hash returned is based on the entire file, including the appended * signature. * * If the measurement cannot be performed, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_file_hash(struct file *file, char *buf, size_t buf_size) { if (!file) return -EINVAL; return __ima_inode_hash(file_inode(file), file, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_file_hash); /** * ima_inode_hash - return the stored measurement if the inode has been hashed * and is in the iint cache. * @inode: pointer to the inode * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The hash returned is based on the entire contents, including the appended * signature. * * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { if (!inode) return -EINVAL; return __ima_inode_hash(inode, NULL, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ static void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct ima_iint_cache *iint; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for writing the security xattrs */ set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); iint->ima_file_status = INTEGRITY_PASS; } /** * ima_post_path_mknod - mark as a new inode * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct ima_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for re-opening empty files */ iint->flags |= IMA_NEW_FILE; } /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit * @read_id: caller identifier * @contents: whether a subsequent call will be made to ima_post_read_file() * * Permit reading a file based on policy. The policy rules are written * in terms of the policy identifier. Appraising the integrity of * a file requires a file descriptor. * * For permission return 0, otherwise return -EACCES. */ static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; struct lsm_prop prop; /* * Do devices using pre-allocated memory run the risk of the * firmware being accessible to the device prior to the completion * of IMA's signature verification any more than when using two * buffers? It may be desirable to include the buffer address * in this API and walk all the dma_map_single() mappings to check. */ /* * There will be a call made to ima_post_read_file() with * a filled buffer, so we don't need to perform an extra * read early here. */ if (contents) return 0; /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_READ, func); } const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, [READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK, [READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK, [READING_POLICY] = POLICY_CHECK }; /** * ima_post_read_file - in memory collect/appraise/audit measurement * @file: pointer to the file to be measured/appraised/audit * @buf: pointer to in memory file contents * @size: size of in memory file contents * @read_id: caller identifier * * Measure/appraise/audit in memory file based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; struct lsm_prop prop; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) return 0; if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; return 0; } func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, buf, size, MAY_READ, func); } /** * ima_load_data - appraise decision based on policy * @id: kernel load data caller identifier * @contents: whether the full contents will be available in a later * call to ima_post_load_data(). * * Callers of this LSM hook can not measure, appraise, or audit the * data provided by userspace. Enforce policy rules requiring a file * signature (eg. kexec'ed kernel image). * * For permission return 0, otherwise return -EACCES. */ static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; ima_enforce = (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_ima_get_secureboot()) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; } if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); if (ima_enforce && (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; default: break; } return 0; } /** * ima_post_load_data - appraise decision based on policy * @buf: pointer to in memory file contents * @size: size of in memory file contents * @load_id: kernel load data caller identifier * @description: @load_id-specific description of contents * * Measure/appraise/audit in memory buffer based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id load_id, char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && (ima_appraise & IMA_APPRAISE_ENFORCE)) { pr_err("Prevent firmware loading_store.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } return 0; } /* * Measure the init_module syscall buffer containing the ELF image. */ if (load_id == LOADING_MODULE) ima_measure_critical_data("modules", "init_module", buf, size, true, NULL, 0); return 0; } /** * process_buffer_measurement - Measure the buffer or the buffer data hash * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). * @eventname: event name to be used for the buffer entry. * @func: IMA hook * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; struct ima_template_entry *entry = NULL; struct ima_iint_cache iint = {}; struct ima_event_data event_data = {.iint = &iint, .filename = eventname, .buf = buf, .buf_len = size}; struct ima_template_desc *template; struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); char digest_hash[IMA_MAX_DIGEST_SIZE]; int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; struct lsm_prop prop; if (digest && digest_len < digest_hash_len) return -EINVAL; if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); if (!template) { ret = -EINVAL; audit_cause = "ima_template_desc_buf"; goto out; } /* * Both LSM hooks and auxiliary based buffer measurements are * based on policy. To avoid code duplication, differentiate * between the LSM hooks and auxiliary buffer measurements, * retrieving the policy rule information only for the LSM hook * buffer measurements. */ if (func) { security_current_getlsmprop_subj(&prop); action = ima_get_action(idmap, inode, current_cred(), &prop, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } if (!pcr) pcr = CONFIG_IMA_MEASURE_PCR_IDX; iint.ima_hash = hash_hdr; iint.ima_hash->algo = ima_hash_algo; iint.ima_hash->length = hash_digest_size[ima_hash_algo]; ret = ima_calc_buffer_hash(buf, size, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } if (buf_hash) { memcpy(digest_hash, hash_hdr->digest, digest_hash_len); ret = ima_calc_buffer_hash(digest_hash, digest_hash_len, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } event_data.buf = digest_hash; event_data.buf_len = digest_hash_len; } if (digest) memcpy(digest, iint.ima_hash->digest, digest_hash_len); if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) return 1; ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; goto out; } ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr); if (ret < 0) { audit_cause = "store_entry"; ima_free_template_entry(entry); } out: if (ret < 0) integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname, func_measure_str(func), audit_cause, ret, 0, ret); return ret; } /** * ima_kexec_cmdline - measure kexec cmdline boot args * @kernel_fd: file descriptor of the kexec kernel being loaded * @buf: pointer to buffer * @size: size of buffer * * Buffers can only be measured, not appraised. */ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { if (!buf || !size) return; CLASS(fd, f)(kernel_fd); if (fd_empty(f)) return; process_buffer_measurement(file_mnt_idmap(fd_file(f)), file_inode(fd_file(f)), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); } /** * ima_measure_critical_data - measure kernel integrity critical data * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); } EXPORT_SYMBOL_GPL(ima_measure_critical_data); #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS /** * ima_kernel_module_request - Prevent crypto-pkcs1(rsa,*) requests * @kmod_name: kernel module name * * Avoid a verification loop where verifying the signature of the modprobe * binary requires executing modprobe itself. Since the modprobe iint->mutex * is already held when the signature verification is performed, a deadlock * occurs as soon as modprobe is executed within the critical region, since * the same lock cannot be taken again. * * This happens when public_key_verify_signature(), in case of RSA algorithm, * use alg_name to store internal information in order to construct an * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name * in order to load a kernel module with same name. * * Since we don't have any real "crypto-pkcs1(rsa,*)" kernel modules, * we are safe to fail such module request from crypto_larval_lookup(), and * avoid the verification loop. * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1(rsa,", 17) == 0) return -EINVAL; return 0; } #endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ static int __init init_ima(void) { int error; /*Note that turning IMA off is intentionally limited to kdump kernel.*/ if (ima_disabled && is_kdump_kernel()) { pr_info("IMA functionality is disabled"); return 0; } ima_appraise_parse_cmdline(); ima_init_template_list(); hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); if (error && strcmp(hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH) != 0) { pr_info("Allocating %s failed, going to use default hash algorithm %s\n", hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH); hash_setup_done = 0; hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); } if (error) return error; error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier); if (error) pr_warn("Couldn't register LSM notifier, error %d\n", error); if (!error) ima_update_policy_flags(); return error; } static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(bprm_creds_for_exec, ima_bprm_creds_for_exec), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu), }; static const struct lsm_id ima_lsmid = { .name = "ima", .id = LSM_ID_IMA, }; static int __init init_ima_lsm(void) { ima_iintcache_init(); security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); init_ima_appraise_lsm(&ima_lsmid); return 0; } struct lsm_blob_sizes ima_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct ima_iint_cache *), }; DEFINE_LSM(ima) = { .name = "ima", .init = init_ima_lsm, .order = LSM_ORDER_LAST, .blobs = &ima_blob_sizes, }; late_initcall(init_ima); /* Start IMA after the TPM is available */ |
open /syzkaller/managers/ci-qemu-native-arm64-kvm/kernel/security/selinux/flask.h: no such file or directory
| 1 1 187 179 177 36 279 280 187 177 2 2 12 10 4 10 10 2 216 212 215 215 178 177 179 216 121 121 121 112 12 12 12 12 121 3 3 1 2 1 1 1 1 1 2 1 1 3 1 2 1 1 3 2 2 2 2 1 1 1 1 2 2 1 1 2 1 1 1 1 1 1 105 105 105 105 103 5 34 105 91 14 105 105 105 105 105 105 91 14 14 105 105 105 105 105 105 105 23 23 22 2 4 6 14 15 14 1 5 5 5 1 2 2 1 1 5 4 1 4 1 9 9 6 3 1 1 8 1 1 1 1 1 3 3 2 3 2 2 2 2 3 3 1 2 2 2 1 1 1 1 1 1 1 1 5 5 4 1 8 3 8 5 5 5 107 101 98 98 99 98 98 98 98 98 99 99 98 104 107 107 12 105 105 105 105 105 110 114 102 106 106 105 105 3 3 5 5 4 4 3 98 98 99 99 86 12 1 1 99 87 12 2 1 1 1 1 1 1 1 6 2 4 12 1 11 100 100 100 100 1 1 1 103 103 103 103 103 2 1 1 1 1 5 5 5 7 105 105 105 4 4 4 5 5 4 4 3 4 4 4 5 4 4 4 4 5 5 5 4 4 1 1 1 1 1 98 98 98 98 2 2 2 2 105 105 49 49 48 1 3 45 242 10 98 3 103 105 105 105 105 105 105 105 104 105 105 91 14 53 53 4 48 32 16 1 136 136 1 135 133 1 1 2 1 3 3 21 21 1 11 12 24 4 20 119 119 103 18 21 97 120 4 118 2 2 4 2 2 4 4 4 4 4 4 4 2 2 207 206 206 207 201 6 205 207 205 207 207 4 205 207 67 140 206 207 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/coproc.c: * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Authors: Rusty Russell <rusty@rustcorp.com.au> * Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/bitfield.h> #include <linux/bsearch.h> #include <linux/cacheinfo.h> #include <linux/debugfs.h> #include <linux/kvm_host.h> #include <linux/mm.h> #include <linux/printk.h> #include <linux/uaccess.h> #include <linux/irqchip/arm-gic-v3.h> #include <asm/arm_pmuv3.h> #include <asm/cacheflush.h> #include <asm/cputype.h> #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/perf_event.h> #include <asm/sysreg.h> #include <trace/events/kvm.h> #include "sys_regs.h" #include "vgic/vgic.h" #include "trace.h" /* * For AArch32, we only take care of what is being trapped. Anything * that has to do with init and userspace access has to go via the * 64bit interface. */ static u64 sys_reg_to_index(const struct sys_reg_desc *reg); static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val); static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { kvm_inject_undefined(vcpu); return false; } static bool bad_trap(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r, const char *msg) { WARN_ONCE(1, "Unexpected %s\n", msg); print_sys_reg_instr(params); return undef_access(vcpu, params, r); } static bool read_from_write_only(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r) { return bad_trap(vcpu, params, r, "sys_reg read to write-only register"); } static bool write_to_read_only(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r) { return bad_trap(vcpu, params, r, "sys_reg write to read-only register"); } enum sr_loc_attr { SR_LOC_MEMORY = 0, /* Register definitely in memory */ SR_LOC_LOADED = BIT(0), /* Register on CPU, unless it cannot */ SR_LOC_MAPPED = BIT(1), /* Register in a different CPU register */ SR_LOC_XLATED = BIT(2), /* Register translated to fit another reg */ SR_LOC_SPECIAL = BIT(3), /* Demanding register, implies loaded */ }; struct sr_loc { enum sr_loc_attr loc; enum vcpu_sysreg map_reg; u64 (*xlate)(u64); }; static enum sr_loc_attr locate_direct_register(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg) { switch (reg) { case SCTLR_EL1: case CPACR_EL1: case TTBR0_EL1: case TTBR1_EL1: case TCR_EL1: case TCR2_EL1: case PIR_EL1: case PIRE0_EL1: case POR_EL1: case ESR_EL1: case AFSR0_EL1: case AFSR1_EL1: case FAR_EL1: case MAIR_EL1: case VBAR_EL1: case CONTEXTIDR_EL1: case AMAIR_EL1: case CNTKCTL_EL1: case ELR_EL1: case SPSR_EL1: case ZCR_EL1: case SCTLR2_EL1: /* * EL1 registers which have an ELx2 mapping are loaded if * we're not in hypervisor context. */ return is_hyp_ctxt(vcpu) ? SR_LOC_MEMORY : SR_LOC_LOADED; case TPIDR_EL0: case TPIDRRO_EL0: case TPIDR_EL1: case PAR_EL1: case DACR32_EL2: case IFSR32_EL2: case DBGVCR32_EL2: /* These registers are always loaded, no matter what */ return SR_LOC_LOADED; default: /* Non-mapped EL2 registers are by definition in memory. */ return SR_LOC_MEMORY; } } static void locate_mapped_el2_register(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg, enum vcpu_sysreg map_reg, u64 (*xlate)(u64), struct sr_loc *loc) { if (!is_hyp_ctxt(vcpu)) { loc->loc = SR_LOC_MEMORY; return; } loc->loc = SR_LOC_LOADED | SR_LOC_MAPPED; loc->map_reg = map_reg; WARN_ON(locate_direct_register(vcpu, map_reg) != SR_LOC_MEMORY); if (xlate != NULL && !vcpu_el2_e2h_is_set(vcpu)) { loc->loc |= SR_LOC_XLATED; loc->xlate = xlate; } } #define MAPPED_EL2_SYSREG(r, m, t) \ case r: { \ locate_mapped_el2_register(vcpu, r, m, t, loc); \ break; \ } static void locate_register(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg, struct sr_loc *loc) { if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU)) { loc->loc = SR_LOC_MEMORY; return; } switch (reg) { MAPPED_EL2_SYSREG(SCTLR_EL2, SCTLR_EL1, translate_sctlr_el2_to_sctlr_el1 ); MAPPED_EL2_SYSREG(CPTR_EL2, CPACR_EL1, translate_cptr_el2_to_cpacr_el1 ); MAPPED_EL2_SYSREG(TTBR0_EL2, TTBR0_EL1, translate_ttbr0_el2_to_ttbr0_el1 ); MAPPED_EL2_SYSREG(TTBR1_EL2, TTBR1_EL1, NULL ); MAPPED_EL2_SYSREG(TCR_EL2, TCR_EL1, translate_tcr_el2_to_tcr_el1 ); MAPPED_EL2_SYSREG(VBAR_EL2, VBAR_EL1, NULL ); MAPPED_EL2_SYSREG(AFSR0_EL2, AFSR0_EL1, NULL ); MAPPED_EL2_SYSREG(AFSR1_EL2, AFSR1_EL1, NULL ); MAPPED_EL2_SYSREG(ESR_EL2, ESR_EL1, NULL ); MAPPED_EL2_SYSREG(FAR_EL2, FAR_EL1, NULL ); MAPPED_EL2_SYSREG(MAIR_EL2, MAIR_EL1, NULL ); MAPPED_EL2_SYSREG(TCR2_EL2, TCR2_EL1, NULL ); MAPPED_EL2_SYSREG(PIR_EL2, PIR_EL1, NULL ); MAPPED_EL2_SYSREG(PIRE0_EL2, PIRE0_EL1, NULL ); MAPPED_EL2_SYSREG(POR_EL2, POR_EL1, NULL ); MAPPED_EL2_SYSREG(AMAIR_EL2, AMAIR_EL1, NULL ); MAPPED_EL2_SYSREG(ELR_EL2, ELR_EL1, NULL ); MAPPED_EL2_SYSREG(SPSR_EL2, SPSR_EL1, NULL ); MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1, NULL ); MAPPED_EL2_SYSREG(SCTLR2_EL2, SCTLR2_EL1, NULL ); case CNTHCTL_EL2: /* CNTHCTL_EL2 is super special, until we support NV2.1 */ loc->loc = ((is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) ? SR_LOC_SPECIAL : SR_LOC_MEMORY); break; default: loc->loc = locate_direct_register(vcpu, reg); } } static u64 read_sr_from_cpu(enum vcpu_sysreg reg) { u64 val = 0x8badf00d8badf00d; switch (reg) { case SCTLR_EL1: val = read_sysreg_s(SYS_SCTLR_EL12); break; case CPACR_EL1: val = read_sysreg_s(SYS_CPACR_EL12); break; case TTBR0_EL1: val = read_sysreg_s(SYS_TTBR0_EL12); break; case TTBR1_EL1: val = read_sysreg_s(SYS_TTBR1_EL12); break; case TCR_EL1: val = read_sysreg_s(SYS_TCR_EL12); break; case TCR2_EL1: val = read_sysreg_s(SYS_TCR2_EL12); break; case PIR_EL1: val = read_sysreg_s(SYS_PIR_EL12); break; case PIRE0_EL1: val = read_sysreg_s(SYS_PIRE0_EL12); break; case POR_EL1: val = read_sysreg_s(SYS_POR_EL12); break; case ESR_EL1: val = read_sysreg_s(SYS_ESR_EL12); break; case AFSR0_EL1: val = read_sysreg_s(SYS_AFSR0_EL12); break; case AFSR1_EL1: val = read_sysreg_s(SYS_AFSR1_EL12); break; case FAR_EL1: val = read_sysreg_s(SYS_FAR_EL12); break; case MAIR_EL1: val = read_sysreg_s(SYS_MAIR_EL12); break; case VBAR_EL1: val = read_sysreg_s(SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break; case AMAIR_EL1: val = read_sysreg_s(SYS_AMAIR_EL12); break; case CNTKCTL_EL1: val = read_sysreg_s(SYS_CNTKCTL_EL12); break; case ELR_EL1: val = read_sysreg_s(SYS_ELR_EL12); break; case SPSR_EL1: val = read_sysreg_s(SYS_SPSR_EL12); break; case ZCR_EL1: val = read_sysreg_s(SYS_ZCR_EL12); break; case SCTLR2_EL1: val = read_sysreg_s(SYS_SCTLR2_EL12); break; case TPIDR_EL0: val = read_sysreg_s(SYS_TPIDR_EL0); break; case TPIDRRO_EL0: val = read_sysreg_s(SYS_TPIDRRO_EL0); break; case TPIDR_EL1: val = read_sysreg_s(SYS_TPIDR_EL1); break; case PAR_EL1: val = read_sysreg_par(); break; case DACR32_EL2: val = read_sysreg_s(SYS_DACR32_EL2); break; case IFSR32_EL2: val = read_sysreg_s(SYS_IFSR32_EL2); break; case DBGVCR32_EL2: val = read_sysreg_s(SYS_DBGVCR32_EL2); break; default: WARN_ON_ONCE(1); } return val; } static void write_sr_to_cpu(enum vcpu_sysreg reg, u64 val) { switch (reg) { case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; case TCR2_EL1: write_sysreg_s(val, SYS_TCR2_EL12); break; case PIR_EL1: write_sysreg_s(val, SYS_PIR_EL12); break; case PIRE0_EL1: write_sysreg_s(val, SYS_PIRE0_EL12); break; case POR_EL1: write_sysreg_s(val, SYS_POR_EL12); break; case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break; case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break; case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break; case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break; case SPSR_EL1: write_sysreg_s(val, SYS_SPSR_EL12); break; case ZCR_EL1: write_sysreg_s(val, SYS_ZCR_EL12); break; case SCTLR2_EL1: write_sysreg_s(val, SYS_SCTLR2_EL12); break; case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break; case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break; case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break; default: WARN_ON_ONCE(1); } } u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg) { struct sr_loc loc = {}; locate_register(vcpu, reg, &loc); WARN_ON_ONCE(!has_vhe() && loc.loc != SR_LOC_MEMORY); if (loc.loc & SR_LOC_SPECIAL) { u64 val; WARN_ON_ONCE(loc.loc & ~SR_LOC_SPECIAL); /* * CNTHCTL_EL2 requires some special treatment to account * for the bits that can be set via CNTKCTL_EL1 when E2H==1. */ switch (reg) { case CNTHCTL_EL2: val = read_sysreg_el1(SYS_CNTKCTL); val &= CNTKCTL_VALID_BITS; val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS; return val; default: WARN_ON_ONCE(1); } } if (loc.loc & SR_LOC_LOADED) { enum vcpu_sysreg map_reg = reg; if (loc.loc & SR_LOC_MAPPED) map_reg = loc.map_reg; if (!(loc.loc & SR_LOC_XLATED)) { u64 val = read_sr_from_cpu(map_reg); if (reg >= __SANITISED_REG_START__) val = kvm_vcpu_apply_reg_masks(vcpu, reg, val); return val; } } return __vcpu_sys_reg(vcpu, reg); } void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, enum vcpu_sysreg reg) { struct sr_loc loc = {}; locate_register(vcpu, reg, &loc); WARN_ON_ONCE(!has_vhe() && loc.loc != SR_LOC_MEMORY); if (loc.loc & SR_LOC_SPECIAL) { WARN_ON_ONCE(loc.loc & ~SR_LOC_SPECIAL); switch (reg) { case CNTHCTL_EL2: /* * If E2H=1, some of the bits are backed by * CNTKCTL_EL1, while the rest is kept in memory. * Yes, this is fun stuff. */ write_sysreg_el1(val, SYS_CNTKCTL); break; default: WARN_ON_ONCE(1); } } if (loc.loc & SR_LOC_LOADED) { enum vcpu_sysreg map_reg = reg; u64 xlated_val; if (reg >= __SANITISED_REG_START__) val = kvm_vcpu_apply_reg_masks(vcpu, reg, val); if (loc.loc & SR_LOC_MAPPED) map_reg = loc.map_reg; if (loc.loc & SR_LOC_XLATED) xlated_val = loc.xlate(val); else xlated_val = val; write_sr_to_cpu(map_reg, xlated_val); /* * Fall through to write the backing store anyway, which * allows translated registers to be directly read without a * reverse translation. */ } __vcpu_assign_sys_reg(vcpu, reg, val); } /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ #define CSSELR_MAX 14 /* * Returns the minimum line size for the selected cache, expressed as * Log2(bytes). */ static u8 get_min_cache_line_size(bool icache) { u64 ctr = read_sanitised_ftr_reg(SYS_CTR_EL0); u8 field; if (icache) field = SYS_FIELD_GET(CTR_EL0, IminLine, ctr); else field = SYS_FIELD_GET(CTR_EL0, DminLine, ctr); /* * Cache line size is represented as Log2(words) in CTR_EL0. * Log2(bytes) can be derived with the following: * * Log2(words) + 2 = Log2(bytes / 4) + 2 * = Log2(bytes) - 2 + 2 * = Log2(bytes) */ return field + 2; } /* Which cache CCSIDR represents depends on CSSELR value. */ static u32 get_ccsidr(struct kvm_vcpu *vcpu, u32 csselr) { u8 line_size; if (vcpu->arch.ccsidr) return vcpu->arch.ccsidr[csselr]; line_size = get_min_cache_line_size(csselr & CSSELR_EL1_InD); /* * Fabricate a CCSIDR value as the overriding value does not exist. * The real CCSIDR value will not be used as it can vary by the * physical CPU which the vcpu currently resides in. * * The line size is determined with get_min_cache_line_size(), which * should be valid for all CPUs even if they have different cache * configuration. * * The associativity bits are cleared, meaning the geometry of all data * and unified caches (which are guaranteed to be PIPT and thus * non-aliasing) are 1 set and 1 way. * Guests should not be doing cache operations by set/way at all, and * for this reason, we trap them and attempt to infer the intent, so * that we can flush the entire guest's address space at the appropriate * time. The exposed geometry minimizes the number of the traps. * [If guests should attempt to infer aliasing properties from the * geometry (which is not permitted by the architecture), they would * only do so for virtually indexed caches.] * * We don't check if the cache level exists as it is allowed to return * an UNKNOWN value if not. */ return SYS_FIELD_PREP(CCSIDR_EL1, LineSize, line_size - 4); } static int set_ccsidr(struct kvm_vcpu *vcpu, u32 csselr, u32 val) { u8 line_size = FIELD_GET(CCSIDR_EL1_LineSize, val) + 4; u32 *ccsidr = vcpu->arch.ccsidr; u32 i; if ((val & CCSIDR_EL1_RES0) || line_size < get_min_cache_line_size(csselr & CSSELR_EL1_InD)) return -EINVAL; if (!ccsidr) { if (val == get_ccsidr(vcpu, csselr)) return 0; ccsidr = kmalloc_array(CSSELR_MAX, sizeof(u32), GFP_KERNEL_ACCOUNT); if (!ccsidr) return -ENOMEM; for (i = 0; i < CSSELR_MAX; i++) ccsidr[i] = get_ccsidr(vcpu, i); vcpu->arch.ccsidr = ccsidr; } ccsidr[csselr] = val; return 0; } static bool access_rw(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) vcpu_write_sys_reg(vcpu, p->regval, r->reg); else p->regval = vcpu_read_sys_reg(vcpu, r->reg); return true; } /* * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). */ static bool access_dcsw(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!p->is_write) return read_from_write_only(vcpu, p, r); /* * Only track S/W ops if we don't have FWB. It still indicates * that the guest is a bit broken (S/W operations should only * be done by firmware, knowing that there is only a single * CPU left in the system, and certainly not from non-secure * software). */ if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) kvm_set_way_flush(vcpu); return true; } static bool access_dcgsw(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!kvm_has_mte(vcpu->kvm)) return undef_access(vcpu, p, r); /* Treat MTE S/W ops as we treat the classic ones: with contempt */ return access_dcsw(vcpu, p, r); } static void get_access_mask(const struct sys_reg_desc *r, u64 *mask, u64 *shift) { switch (r->aarch32_map) { case AA32_LO: *mask = GENMASK_ULL(31, 0); *shift = 0; break; case AA32_HI: *mask = GENMASK_ULL(63, 32); *shift = 32; break; default: *mask = GENMASK_ULL(63, 0); *shift = 0; break; } } /* * Generic accessor for VM registers. Only called as long as HCR_TVM * is set. If the guest enables the MMU, we stop trapping the VM * sys_regs and leave it in complete control of the caches. */ static bool access_vm_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { bool was_enabled = vcpu_has_cache_enabled(vcpu); u64 val, mask, shift; BUG_ON(!p->is_write); get_access_mask(r, &mask, &shift); if (~mask) { val = vcpu_read_sys_reg(vcpu, r->reg); val &= ~mask; } else { val = 0; } val |= (p->regval & (mask >> shift)) << shift; vcpu_write_sys_reg(vcpu, val, r->reg); kvm_toggle_cache(vcpu, was_enabled); return true; } static bool access_actlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 mask, shift; if (p->is_write) return ignore_write(vcpu, p); get_access_mask(r, &mask, &shift); p->regval = (vcpu_read_sys_reg(vcpu, r->reg) & mask) >> shift; return true; } /* * Trap handler for the GICv3 SGI generation system register. * Forward the request to the VGIC emulation. * The cp15_64 code makes sure this automatically works * for both AArch64 and AArch32 accesses. */ static bool access_gic_sgi(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { bool g1; if (!kvm_has_gicv3(vcpu->kvm)) return undef_access(vcpu, p, r); if (!p->is_write) return read_from_write_only(vcpu, p, r); /* * In a system where GICD_CTLR.DS=1, a ICC_SGI0R_EL1 access generates * Group0 SGIs only, while ICC_SGI1R_EL1 can generate either group, * depending on the SGI configuration. ICC_ASGI1R_EL1 is effectively * equivalent to ICC_SGI0R_EL1, as there is no "alternative" secure * group. */ if (p->Op0 == 0) { /* AArch32 */ switch (p->Op1) { default: /* Keep GCC quiet */ case 0: /* ICC_SGI1R */ g1 = true; break; case 1: /* ICC_ASGI1R */ case 2: /* ICC_SGI0R */ g1 = false; break; } } else { /* AArch64 */ switch (p->Op2) { default: /* Keep GCC quiet */ case 5: /* ICC_SGI1R_EL1 */ g1 = true; break; case 6: /* ICC_ASGI1R_EL1 */ case 7: /* ICC_SGI0R_EL1 */ g1 = false; break; } } vgic_v3_dispatch_sgi(vcpu, p->regval, g1); return true; } static bool access_gic_sre(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!kvm_has_gicv3(vcpu->kvm)) return undef_access(vcpu, p, r); if (p->is_write) return ignore_write(vcpu, p); if (p->Op1 == 4) { /* ICC_SRE_EL2 */ p->regval = KVM_ICC_SRE_EL2; } else { /* ICC_SRE_EL1 */ p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre; } return true; } static bool trap_raz_wi(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return ignore_write(vcpu, p); else return read_zero(vcpu, p); } /* * ARMv8.1 mandates at least a trivial LORegion implementation, where all the * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 * system, these registers should UNDEF. LORID_EL1 being a RO register, we * treat it separately. */ static bool trap_loregion(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sr = reg_to_encoding(r); if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, LO, IMP)) return undef_access(vcpu, p, r); if (p->is_write && sr == SYS_LORID_EL1) return write_to_read_only(vcpu, p, r); return trap_raz_wi(vcpu, p, r); } static bool trap_oslar_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!p->is_write) return read_from_write_only(vcpu, p, r); kvm_debug_handle_oslar(vcpu, p->regval); return true; } static bool trap_oslsr_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = __vcpu_sys_reg(vcpu, r->reg); return true; } static int set_oslsr_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { /* * The only modifiable bit is the OSLK bit. Refuse the write if * userspace attempts to change any other bit in the register. */ if ((val ^ rd->val) & ~OSLSR_EL1_OSLK) return -EINVAL; __vcpu_assign_sys_reg(vcpu, rd->reg, val); return 0; } static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { return ignore_write(vcpu, p); } else { p->regval = read_sysreg(dbgauthstatus_el1); return true; } } static bool trap_debug_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { access_rw(vcpu, p, r); kvm_debug_set_guest_ownership(vcpu); return true; } /* * reg_to_dbg/dbg_to_reg * * A 32 bit write to a debug register leave top bits alone * A 32 bit read from a debug register only returns the bottom bits */ static void reg_to_dbg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd, u64 *dbg_reg) { u64 mask, shift, val; get_access_mask(rd, &mask, &shift); val = *dbg_reg; val &= ~mask; val |= (p->regval & (mask >> shift)) << shift; *dbg_reg = val; } static void dbg_to_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd, u64 *dbg_reg) { u64 mask, shift; get_access_mask(rd, &mask, &shift); p->regval = (*dbg_reg & mask) >> shift; } static u64 *demux_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { struct kvm_guest_debug_arch *dbg = &vcpu->arch.vcpu_debug_state; switch (rd->Op2) { case 0b100: return &dbg->dbg_bvr[rd->CRm]; case 0b101: return &dbg->dbg_bcr[rd->CRm]; case 0b110: return &dbg->dbg_wvr[rd->CRm]; case 0b111: return &dbg->dbg_wcr[rd->CRm]; default: KVM_BUG_ON(1, vcpu->kvm); return NULL; } } static bool trap_dbg_wb_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { u64 *reg = demux_wb_reg(vcpu, rd); if (!reg) return false; if (p->is_write) reg_to_dbg(vcpu, p, rd, reg); else dbg_to_reg(vcpu, p, rd, reg); kvm_debug_set_guest_ownership(vcpu); return true; } static int set_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { u64 *reg = demux_wb_reg(vcpu, rd); if (!reg) return -EINVAL; *reg = val; return 0; } static int get_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 *val) { u64 *reg = demux_wb_reg(vcpu, rd); if (!reg) return -EINVAL; *val = *reg; return 0; } static u64 reset_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { u64 *reg = demux_wb_reg(vcpu, rd); /* * Bail early if we couldn't find storage for the register, the * KVM_BUG_ON() in demux_wb_reg() will prevent this VM from ever * being run. */ if (!reg) return 0; *reg = rd->val; return rd->val; } static u64 reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 amair = read_sysreg(amair_el1); vcpu_write_sys_reg(vcpu, amair, AMAIR_EL1); return amair; } static u64 reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 actlr = read_sysreg(actlr_el1); vcpu_write_sys_reg(vcpu, actlr, ACTLR_EL1); return actlr; } static u64 reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 mpidr; /* * Map the vcpu_id into the first three affinity level fields of * the MPIDR. We limit the number of VCPUs in level 0 due to a * limitation to 16 CPUs in that level in the ICC_SGIxR registers * of the GICv3 to be able to address each CPU directly when * sending IPIs. */ mpidr = (vcpu->vcpu_id & 0x0f) << MPIDR_LEVEL_SHIFT(0); mpidr |= ((vcpu->vcpu_id >> 4) & 0xff) << MPIDR_LEVEL_SHIFT(1); mpidr |= ((vcpu->vcpu_id >> 12) & 0xff) << MPIDR_LEVEL_SHIFT(2); mpidr |= (1ULL << 31); vcpu_write_sys_reg(vcpu, mpidr, MPIDR_EL1); return mpidr; } static unsigned int hidden_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return REG_HIDDEN; } static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (kvm_vcpu_has_pmu(vcpu)) return 0; return REG_HIDDEN; } static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 mask = BIT(ARMV8_PMU_CYCLE_IDX); u8 n = vcpu->kvm->arch.nr_pmu_counters; if (n) mask |= GENMASK(n - 1, 0); reset_unknown(vcpu, r); __vcpu_rmw_sys_reg(vcpu, r->reg, &=, mask); return __vcpu_sys_reg(vcpu, r->reg); } static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { reset_unknown(vcpu, r); __vcpu_rmw_sys_reg(vcpu, r->reg, &=, GENMASK(31, 0)); return __vcpu_sys_reg(vcpu, r->reg); } static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { /* This thing will UNDEF, who cares about the reset value? */ if (!kvm_vcpu_has_pmu(vcpu)) return 0; reset_unknown(vcpu, r); __vcpu_rmw_sys_reg(vcpu, r->reg, &=, kvm_pmu_evtyper_mask(vcpu->kvm)); return __vcpu_sys_reg(vcpu, r->reg); } static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { reset_unknown(vcpu, r); __vcpu_rmw_sys_reg(vcpu, r->reg, &=, PMSELR_EL0_SEL_MASK); return __vcpu_sys_reg(vcpu, r->reg); } static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr = 0; if (!kvm_supports_32bit_el0()) pmcr |= ARMV8_PMU_PMCR_LC; /* * The value of PMCR.N field is included when the * vCPU register is read via kvm_vcpu_read_pmcr(). */ __vcpu_assign_sys_reg(vcpu, r->reg, pmcr); return __vcpu_sys_reg(vcpu, r->reg); } static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) { u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0); bool enabled = (reg & flags) || vcpu_mode_priv(vcpu); if (!enabled) kvm_inject_undefined(vcpu); return !enabled; } static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu) { return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_EN); } static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu) { return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN); } static bool pmu_access_cycle_counter_el0_disabled(struct kvm_vcpu *vcpu) { return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN); } static bool pmu_access_event_counter_el0_disabled(struct kvm_vcpu *vcpu) { return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN); } static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 val; if (pmu_access_el0_disabled(vcpu)) return false; if (p->is_write) { /* * Only update writeable bits of PMCR (continuing into * kvm_pmu_handle_pmcr() as well) */ val = kvm_vcpu_read_pmcr(vcpu); val &= ~ARMV8_PMU_PMCR_MASK; val |= p->regval & ARMV8_PMU_PMCR_MASK; if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; kvm_pmu_handle_pmcr(vcpu, val); } else { /* PMCR.P & PMCR.C are RAZ */ val = kvm_vcpu_read_pmcr(vcpu) & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C); p->regval = val; } return true; } static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (pmu_access_event_counter_el0_disabled(vcpu)) return false; if (p->is_write) __vcpu_assign_sys_reg(vcpu, PMSELR_EL0, p->regval); else /* return PMSELR.SEL field */ p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0) & PMSELR_EL0_SEL_MASK; return true; } static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 pmceid, mask, shift; BUG_ON(p->is_write); if (pmu_access_el0_disabled(vcpu)) return false; get_access_mask(r, &mask, &shift); pmceid = kvm_pmu_get_pmceid(vcpu, (p->Op2 & 1)); pmceid &= mask; pmceid >>= shift; p->regval = pmceid; return true; } static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx) { u64 pmcr, val; pmcr = kvm_vcpu_read_pmcr(vcpu); val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr); if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) { kvm_inject_undefined(vcpu); return false; } return true; } static int get_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { u64 idx; if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 0) /* PMCCNTR_EL0 */ idx = ARMV8_PMU_CYCLE_IDX; else /* PMEVCNTRn_EL0 */ idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); *val = kvm_pmu_get_counter_value(vcpu, idx); return 0; } static int set_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u64 idx; if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 0) /* PMCCNTR_EL0 */ idx = ARMV8_PMU_CYCLE_IDX; else /* PMEVCNTRn_EL0 */ idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); kvm_pmu_set_counter_value_user(vcpu, idx, val); return 0; } static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 idx = ~0UL; if (r->CRn == 9 && r->CRm == 13) { if (r->Op2 == 2) { /* PMXEVCNTR_EL0 */ if (pmu_access_event_counter_el0_disabled(vcpu)) return false; idx = SYS_FIELD_GET(PMSELR_EL0, SEL, __vcpu_sys_reg(vcpu, PMSELR_EL0)); } else if (r->Op2 == 0) { /* PMCCNTR_EL0 */ if (pmu_access_cycle_counter_el0_disabled(vcpu)) return false; idx = ARMV8_PMU_CYCLE_IDX; } } else if (r->CRn == 0 && r->CRm == 9) { /* PMCCNTR */ if (pmu_access_event_counter_el0_disabled(vcpu)) return false; idx = ARMV8_PMU_CYCLE_IDX; } else if (r->CRn == 14 && (r->CRm & 12) == 8) { /* PMEVCNTRn_EL0 */ if (pmu_access_event_counter_el0_disabled(vcpu)) return false; idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); } /* Catch any decoding mistake */ WARN_ON(idx == ~0UL); if (!pmu_counter_idx_valid(vcpu, idx)) return false; if (p->is_write) { if (pmu_access_el0_disabled(vcpu)) return false; kvm_pmu_set_counter_value(vcpu, idx, p->regval); } else { p->regval = kvm_pmu_get_counter_value(vcpu, idx); } return true; } static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 idx, reg; if (pmu_access_el0_disabled(vcpu)) return false; if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) { /* PMXEVTYPER_EL0 */ idx = SYS_FIELD_GET(PMSELR_EL0, SEL, __vcpu_sys_reg(vcpu, PMSELR_EL0)); reg = PMEVTYPER0_EL0 + idx; } else if (r->CRn == 14 && (r->CRm & 12) == 12) { idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); if (idx == ARMV8_PMU_CYCLE_IDX) reg = PMCCFILTR_EL0; else /* PMEVTYPERn_EL0 */ reg = PMEVTYPER0_EL0 + idx; } else { BUG(); } if (!pmu_counter_idx_valid(vcpu, idx)) return false; if (p->is_write) { kvm_pmu_set_counter_event_type(vcpu, p->regval, idx); kvm_vcpu_pmu_restore_guest(vcpu); } else { p->regval = __vcpu_sys_reg(vcpu, reg); } return true; } static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u64 mask = kvm_pmu_accessible_counter_mask(vcpu); __vcpu_assign_sys_reg(vcpu, r->reg, val & mask); kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return 0; } static int get_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { u64 mask = kvm_pmu_accessible_counter_mask(vcpu); *val = __vcpu_sys_reg(vcpu, r->reg) & mask; return 0; } static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 val, mask; if (pmu_access_el0_disabled(vcpu)) return false; mask = kvm_pmu_accessible_counter_mask(vcpu); if (p->is_write) { val = p->regval & mask; if (r->Op2 & 0x1) /* accessing PMCNTENSET_EL0 */ __vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, |=, val); else /* accessing PMCNTENCLR_EL0 */ __vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, ~val); kvm_pmu_reprogram_counter_mask(vcpu, val); } else { p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); } return true; } static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 mask = kvm_pmu_accessible_counter_mask(vcpu); if (check_pmu_access_disabled(vcpu, 0)) return false; if (p->is_write) { u64 val = p->regval & mask; if (r->Op2 & 0x1) /* accessing PMINTENSET_EL1 */ __vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, |=, val); else /* accessing PMINTENCLR_EL1 */ __vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, ~val); } else { p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1); } return true; } static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 mask = kvm_pmu_accessible_counter_mask(vcpu); if (pmu_access_el0_disabled(vcpu)) return false; if (p->is_write) { if (r->CRm & 0x2) /* accessing PMOVSSET_EL0 */ __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, (p->regval & mask)); else /* accessing PMOVSCLR_EL0 */ __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, ~(p->regval & mask)); } else { p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); } return true; } static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 mask; if (!p->is_write) return read_from_write_only(vcpu, p, r); if (pmu_write_swinc_el0_disabled(vcpu)) return false; mask = kvm_pmu_accessible_counter_mask(vcpu); kvm_pmu_software_increment(vcpu, p->regval & mask); return true; } static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { if (!vcpu_mode_priv(vcpu)) return undef_access(vcpu, p, r); __vcpu_assign_sys_reg(vcpu, PMUSERENR_EL0, (p->regval & ARMV8_PMU_USERENR_MASK)); } else { p->regval = __vcpu_sys_reg(vcpu, PMUSERENR_EL0) & ARMV8_PMU_USERENR_MASK; } return true; } static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { *val = kvm_vcpu_read_pmcr(vcpu); return 0; } static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u8 new_n = FIELD_GET(ARMV8_PMU_PMCR_N, val); struct kvm *kvm = vcpu->kvm; mutex_lock(&kvm->arch.config_lock); /* * The vCPU can't have more counters than the PMU hardware * implements. Ignore this error to maintain compatibility * with the existing KVM behavior. */ if (!kvm_vm_has_ran_once(kvm) && !vcpu_has_nv(vcpu) && new_n <= kvm_arm_pmu_get_max_counters(kvm)) kvm->arch.nr_pmu_counters = new_n; mutex_unlock(&kvm->arch.config_lock); /* * Ignore writes to RES0 bits, read only bits that are cleared on * vCPU reset, and writable bits that KVM doesn't support yet. * (i.e. only PMCR.N and bits [7:0] are mutable from userspace) * The LP bit is RES0 when FEAT_PMUv3p5 is not supported on the vCPU. * But, we leave the bit as it is here, as the vCPU's PMUver might * be changed later (NOTE: the bit will be cleared on first vCPU run * if necessary). */ val &= ARMV8_PMU_PMCR_MASK; /* The LC bit is RES1 when AArch32 is not supported */ if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; __vcpu_assign_sys_reg(vcpu, r->reg, val); kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return 0; } /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ get_dbg_wb_reg, set_dbg_wb_reg }, \ { SYS_DESC(SYS_DBGBCRn_EL1(n)), \ trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ get_dbg_wb_reg, set_dbg_wb_reg }, \ { SYS_DESC(SYS_DBGWVRn_EL1(n)), \ trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ get_dbg_wb_reg, set_dbg_wb_reg }, \ { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0, \ get_dbg_wb_reg, set_dbg_wb_reg } #define PMU_SYS_REG(name) \ SYS_DESC(SYS_##name), .reset = reset_pmu_reg, \ .visibility = pmu_visibility /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ { PMU_SYS_REG(PMEVCNTRn_EL0(n)), \ .reset = reset_pmevcntr, .get_user = get_pmu_evcntr, \ .set_user = set_pmu_evcntr, \ .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), } /* Macro to expand the PMEVTYPERn_EL0 register */ #define PMU_PMEVTYPER_EL0(n) \ { PMU_SYS_REG(PMEVTYPERn_EL0(n)), \ .reset = reset_pmevtyper, \ .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), } /* Macro to expand the AMU counter and type registers*/ #define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access } #define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access } #define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access } #define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access } static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN; } /* * If we land here on a PtrAuth access, that is because we didn't * fixup the access on exit by allowing the PtrAuth sysregs. The only * way this happens is when the guest does not have PtrAuth support * enabled. */ #define __PTRAUTH_KEY(k) \ { SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \ .visibility = ptrauth_visibility} #define PTRAUTH_KEY(k) \ __PTRAUTH_KEY(k ## KEYLO_EL1), \ __PTRAUTH_KEY(k ## KEYHI_EL1) static bool access_arch_timer(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { enum kvm_arch_timers tmr; enum kvm_arch_timer_regs treg; u64 reg = reg_to_encoding(r); switch (reg) { case SYS_CNTP_TVAL_EL0: if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) tmr = TIMER_HPTIMER; else tmr = TIMER_PTIMER; treg = TIMER_REG_TVAL; break; case SYS_CNTV_TVAL_EL0: if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) tmr = TIMER_HVTIMER; else tmr = TIMER_VTIMER; treg = TIMER_REG_TVAL; break; case SYS_AARCH32_CNTP_TVAL: case SYS_CNTP_TVAL_EL02: tmr = TIMER_PTIMER; treg = TIMER_REG_TVAL; break; case SYS_CNTV_TVAL_EL02: tmr = TIMER_VTIMER; treg = TIMER_REG_TVAL; break; case SYS_CNTHP_TVAL_EL2: tmr = TIMER_HPTIMER; treg = TIMER_REG_TVAL; break; case SYS_CNTHV_TVAL_EL2: tmr = TIMER_HVTIMER; treg = TIMER_REG_TVAL; break; case SYS_CNTP_CTL_EL0: if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) tmr = TIMER_HPTIMER; else tmr = TIMER_PTIMER; treg = TIMER_REG_CTL; break; case SYS_CNTV_CTL_EL0: if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) tmr = TIMER_HVTIMER; else tmr = TIMER_VTIMER; treg = TIMER_REG_CTL; break; case SYS_AARCH32_CNTP_CTL: case SYS_CNTP_CTL_EL02: tmr = TIMER_PTIMER; treg = TIMER_REG_CTL; break; case SYS_CNTV_CTL_EL02: tmr = TIMER_VTIMER; treg = TIMER_REG_CTL; break; case SYS_CNTHP_CTL_EL2: tmr = TIMER_HPTIMER; treg = TIMER_REG_CTL; break; case SYS_CNTHV_CTL_EL2: tmr = TIMER_HVTIMER; treg = TIMER_REG_CTL; break; case SYS_CNTP_CVAL_EL0: if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) tmr = TIMER_HPTIMER; else tmr = TIMER_PTIMER; treg = TIMER_REG_CVAL; break; case SYS_CNTV_CVAL_EL0: if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) tmr = TIMER_HVTIMER; else tmr = TIMER_VTIMER; treg = TIMER_REG_CVAL; break; case SYS_AARCH32_CNTP_CVAL: case SYS_CNTP_CVAL_EL02: tmr = TIMER_PTIMER; treg = TIMER_REG_CVAL; break; case SYS_CNTV_CVAL_EL02: tmr = TIMER_VTIMER; treg = TIMER_REG_CVAL; break; case SYS_CNTHP_CVAL_EL2: tmr = TIMER_HPTIMER; treg = TIMER_REG_CVAL; break; case SYS_CNTHV_CVAL_EL2: tmr = TIMER_HVTIMER; treg = TIMER_REG_CVAL; break; case SYS_CNTPCT_EL0: case SYS_CNTPCTSS_EL0: if (is_hyp_ctxt(vcpu)) tmr = TIMER_HPTIMER; else tmr = TIMER_PTIMER; treg = TIMER_REG_CNT; break; case SYS_AARCH32_CNTPCT: case SYS_AARCH32_CNTPCTSS: tmr = TIMER_PTIMER; treg = TIMER_REG_CNT; break; case SYS_CNTVCT_EL0: case SYS_CNTVCTSS_EL0: if (is_hyp_ctxt(vcpu)) tmr = TIMER_HVTIMER; else tmr = TIMER_VTIMER; treg = TIMER_REG_CNT; break; case SYS_AARCH32_CNTVCT: case SYS_AARCH32_CNTVCTSS: tmr = TIMER_VTIMER; treg = TIMER_REG_CNT; break; default: print_sys_reg_msg(p, "%s", "Unhandled trapped timer register"); return undef_access(vcpu, p, r); } if (p->is_write) kvm_arm_timer_write_sysreg(vcpu, tmr, treg, p->regval); else p->regval = kvm_arm_timer_read_sysreg(vcpu, tmr, treg); return true; } static bool access_hv_timer(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!vcpu_el2_e2h_is_set(vcpu)) return undef_access(vcpu, p, r); return access_arch_timer(vcpu, p, r); } static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp, s64 new, s64 cur) { struct arm64_ftr_bits kvm_ftr = *ftrp; /* Some features have different safe value type in KVM than host features */ switch (id) { case SYS_ID_AA64DFR0_EL1: switch (kvm_ftr.shift) { case ID_AA64DFR0_EL1_PMUVer_SHIFT: kvm_ftr.type = FTR_LOWER_SAFE; break; case ID_AA64DFR0_EL1_DebugVer_SHIFT: kvm_ftr.type = FTR_LOWER_SAFE; break; } break; case SYS_ID_DFR0_EL1: if (kvm_ftr.shift == ID_DFR0_EL1_PerfMon_SHIFT) kvm_ftr.type = FTR_LOWER_SAFE; break; } return arm64_ftr_safe_value(&kvm_ftr, new, cur); } /* * arm64_check_features() - Check if a feature register value constitutes * a subset of features indicated by the idreg's KVM sanitised limit. * * This function will check if each feature field of @val is the "safe" value * against idreg's KVM sanitised limit return from reset() callback. * If a field value in @val is the same as the one in limit, it is always * considered the safe value regardless For register fields that are not in * writable, only the value in limit is considered the safe value. * * Return: 0 if all the fields are safe. Otherwise, return negative errno. */ static int arm64_check_features(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { const struct arm64_ftr_reg *ftr_reg; const struct arm64_ftr_bits *ftrp = NULL; u32 id = reg_to_encoding(rd); u64 writable_mask = rd->val; u64 limit = rd->reset(vcpu, rd); u64 mask = 0; /* * Hidden and unallocated ID registers may not have a corresponding * struct arm64_ftr_reg. Of course, if the register is RAZ we know the * only safe value is 0. */ if (sysreg_visible_as_raz(vcpu, rd)) return val ? -E2BIG : 0; ftr_reg = get_arm64_ftr_reg(id); if (!ftr_reg) return -EINVAL; ftrp = ftr_reg->ftr_bits; for (; ftrp && ftrp->width; ftrp++) { s64 f_val, f_lim, safe_val; u64 ftr_mask; ftr_mask = arm64_ftr_mask(ftrp); if ((ftr_mask & writable_mask) != ftr_mask) continue; f_val = arm64_ftr_value(ftrp, val); f_lim = arm64_ftr_value(ftrp, limit); mask |= ftr_mask; if (f_val == f_lim) safe_val = f_val; else safe_val = kvm_arm64_ftr_safe_value(id, ftrp, f_val, f_lim); if (safe_val != f_val) return -E2BIG; } /* For fields that are not writable, values in limit are the safe values. */ if ((val & ~mask) != (limit & ~mask)) return -E2BIG; return 0; } static u8 pmuver_to_perfmon(u8 pmuver) { switch (pmuver) { case ID_AA64DFR0_EL1_PMUVer_IMP: return ID_DFR0_EL1_PerfMon_PMUv3; case ID_AA64DFR0_EL1_PMUVer_IMP_DEF: return ID_DFR0_EL1_PerfMon_IMPDEF; default: /* Anything ARMv8.1+ and NI have the same value. For now. */ return pmuver; } } static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val); static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val); static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val); /* Read a sanitised cpufeature ID register by sys_reg_desc */ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u32 id = reg_to_encoding(r); u64 val; if (sysreg_visible_as_raz(vcpu, r)) return 0; val = read_sanitised_ftr_reg(id); switch (id) { case SYS_ID_AA64DFR0_EL1: val = sanitise_id_aa64dfr0_el1(vcpu, val); break; case SYS_ID_AA64PFR0_EL1: val = sanitise_id_aa64pfr0_el1(vcpu, val); break; case SYS_ID_AA64PFR1_EL1: val = sanitise_id_aa64pfr1_el1(vcpu, val); break; case SYS_ID_AA64PFR2_EL1: val &= ID_AA64PFR2_EL1_FPMR | (kvm_has_mte(vcpu->kvm) ? ID_AA64PFR2_EL1_MTEFAR | ID_AA64PFR2_EL1_MTESTOREONLY : 0); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) val &= ~(ID_AA64ISAR1_EL1_APA | ID_AA64ISAR1_EL1_API | ID_AA64ISAR1_EL1_GPA | ID_AA64ISAR1_EL1_GPI); break; case SYS_ID_AA64ISAR2_EL1: if (!vcpu_has_ptrauth(vcpu)) val &= ~(ID_AA64ISAR2_EL1_APA3 | ID_AA64ISAR2_EL1_GPA3); if (!cpus_have_final_cap(ARM64_HAS_WFXT) || has_broken_cntvoff()) val &= ~ID_AA64ISAR2_EL1_WFxT; break; case SYS_ID_AA64ISAR3_EL1: val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_LSFE | ID_AA64ISAR3_EL1_FAMINMAX; break; case SYS_ID_AA64MMFR2_EL1: val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; val &= ~ID_AA64MMFR2_EL1_NV; break; case SYS_ID_AA64MMFR3_EL1: val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_SCTLRX | ID_AA64MMFR3_EL1_S1POE | ID_AA64MMFR3_EL1_S1PIE; break; case SYS_ID_MMFR4_EL1: val &= ~ID_MMFR4_EL1_CCIDX; break; } if (vcpu_has_nv(vcpu)) val = limit_nv_id_reg(vcpu->kvm, id, val); return val; } static u64 kvm_read_sanitised_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return __kvm_read_sanitised_id_reg(vcpu, r); } static u64 read_id_reg(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return kvm_read_vm_id_reg(vcpu->kvm, reg_to_encoding(r)); } static bool is_feature_id_reg(u32 encoding) { return (sys_reg_Op0(encoding) == 3 && (sys_reg_Op1(encoding) < 2 || sys_reg_Op1(encoding) == 3) && sys_reg_CRn(encoding) == 0 && sys_reg_CRm(encoding) <= 7); } /* * Return true if the register's (Op0, Op1, CRn, CRm, Op2) is * (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8, which is the range of ID * registers KVM maintains on a per-VM basis. * * Additionally, the implementation ID registers and CTR_EL0 are handled as * per-VM registers. */ static inline bool is_vm_ftr_id_reg(u32 id) { switch (id) { case SYS_CTR_EL0: case SYS_MIDR_EL1: case SYS_REVIDR_EL1: case SYS_AIDR_EL1: return true; default: return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 && sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 && sys_reg_CRm(id) < 8); } } static inline bool is_vcpu_ftr_id_reg(u32 id) { return is_feature_id_reg(id) && !is_vm_ftr_id_reg(id); } static inline bool is_aa32_id_reg(u32 id) { return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 && sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 && sys_reg_CRm(id) <= 3); } static unsigned int id_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u32 id = reg_to_encoding(r); switch (id) { case SYS_ID_AA64ZFR0_EL1: if (!vcpu_has_sve(vcpu)) return REG_RAZ; break; } return 0; } static unsigned int aa32_id_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { /* * AArch32 ID registers are UNKNOWN if AArch32 isn't implemented at any * EL. Promote to RAZ/WI in order to guarantee consistency between * systems. */ if (!kvm_supports_32bit_el0()) return REG_RAZ | REG_USER_WI; return id_visibility(vcpu, r); } static unsigned int raz_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return REG_RAZ; } /* cpufeature ID register access trap handlers */ static bool access_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = read_id_reg(vcpu, r); return true; } /* Visibility overrides for SVE-specific control registers */ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (vcpu_has_sve(vcpu)) return 0; return REG_HIDDEN; } static unsigned int sme_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SME, IMP)) return 0; return REG_HIDDEN; } static unsigned int fp8_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (kvm_has_fpmr(vcpu->kvm)) return 0; return REG_HIDDEN; } static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val) { if (!vcpu_has_sve(vcpu)) val &= ~ID_AA64PFR0_EL1_SVE_MASK; /* * The default is to expose CSV2 == 1 if the HW isn't affected. * Although this is a per-CPU feature, we make it global because * asymmetric systems are just a nuisance. * * Userspace can override this as long as it doesn't promise * the impossible. */ if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) { val &= ~ID_AA64PFR0_EL1_CSV2_MASK; val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, CSV2, IMP); } if (arm64_get_meltdown_state() == SPECTRE_UNAFFECTED) { val &= ~ID_AA64PFR0_EL1_CSV3_MASK; val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, CSV3, IMP); } if (vgic_is_v3(vcpu->kvm)) { val &= ~ID_AA64PFR0_EL1_GIC_MASK; val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); } val &= ~ID_AA64PFR0_EL1_AMU_MASK; /* * MPAM is disabled by default as KVM also needs a set of PARTID to * program the MPAMVPMx_EL2 PARTID remapping registers with. But some * older kernels let the guest see the ID bit. */ val &= ~ID_AA64PFR0_EL1_MPAM_MASK; return val; } static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val) { u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); if (!kvm_has_mte(vcpu->kvm)) { val &= ~ID_AA64PFR1_EL1_MTE; val &= ~ID_AA64PFR1_EL1_MTE_frac; } if (!(cpus_have_final_cap(ARM64_HAS_RASV1P1_EXTN) && SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, pfr0) == ID_AA64PFR0_EL1_RAS_IMP)) val &= ~ID_AA64PFR1_EL1_RAS_frac; val &= ~ID_AA64PFR1_EL1_SME; val &= ~ID_AA64PFR1_EL1_RNDR_trap; val &= ~ID_AA64PFR1_EL1_NMI; val &= ~ID_AA64PFR1_EL1_GCS; val &= ~ID_AA64PFR1_EL1_THE; val &= ~ID_AA64PFR1_EL1_MTEX; val &= ~ID_AA64PFR1_EL1_PFAR; val &= ~ID_AA64PFR1_EL1_MPAM_frac; return val; } static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val) { val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8); /* * Only initialize the PMU version if the vCPU was configured with one. */ val &= ~ID_AA64DFR0_EL1_PMUVer_MASK; if (kvm_vcpu_has_pmu(vcpu)) val |= SYS_FIELD_PREP(ID_AA64DFR0_EL1, PMUVer, kvm_arm_pmu_get_pmuver_limit()); /* Hide SPE from guests */ val &= ~ID_AA64DFR0_EL1_PMSVer_MASK; /* Hide BRBE from guests */ val &= ~ID_AA64DFR0_EL1_BRBE_MASK; return val; } /* * Older versions of KVM erroneously claim support for FEAT_DoubleLock with * NV-enabled VMs on unsupporting hardware. Silently ignore the incorrect * value if it is consistent with the bug. */ static bool ignore_feat_doublelock(struct kvm_vcpu *vcpu, u64 val) { u8 host, user; if (!vcpu_has_nv(vcpu)) return false; host = SYS_FIELD_GET(ID_AA64DFR0_EL1, DoubleLock, read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1)); user = SYS_FIELD_GET(ID_AA64DFR0_EL1, DoubleLock, val); return host == ID_AA64DFR0_EL1_DoubleLock_NI && user == ID_AA64DFR0_EL1_DoubleLock_IMP; } static int set_id_aa64dfr0_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { u8 debugver = SYS_FIELD_GET(ID_AA64DFR0_EL1, DebugVer, val); u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, val); /* * Prior to commit 3d0dba5764b9 ("KVM: arm64: PMU: Move the * ID_AA64DFR0_EL1.PMUver limit to VM creation"), KVM erroneously * exposed an IMP_DEF PMU to userspace and the guest on systems w/ * non-architectural PMUs. Of course, PMUv3 is the only game in town for * PMU virtualization, so the IMP_DEF value was rather user-hostile. * * At minimum, we're on the hook to allow values that were given to * userspace by KVM. Cover our tracks here and replace the IMP_DEF value * with a more sensible NI. The value of an ID register changing under * the nose of the guest is unfortunate, but is certainly no more * surprising than an ill-guided PMU driver poking at impdef system * registers that end in an UNDEF... */ if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) val &= ~ID_AA64DFR0_EL1_PMUVer_MASK; /* * ID_AA64DFR0_EL1.DebugVer is one of those awkward fields with a * nonzero minimum safe value. */ if (debugver < ID_AA64DFR0_EL1_DebugVer_IMP) return -EINVAL; if (ignore_feat_doublelock(vcpu, val)) { val &= ~ID_AA64DFR0_EL1_DoubleLock; val |= SYS_FIELD_PREP_ENUM(ID_AA64DFR0_EL1, DoubleLock, NI); } return set_id_reg(vcpu, rd, val); } static u64 read_sanitised_id_dfr0_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { u8 perfmon; u64 val = read_sanitised_ftr_reg(SYS_ID_DFR0_EL1); val &= ~ID_DFR0_EL1_PerfMon_MASK; if (kvm_vcpu_has_pmu(vcpu)) { perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit()); val |= SYS_FIELD_PREP(ID_DFR0_EL1, PerfMon, perfmon); } val = ID_REG_LIMIT_FIELD_ENUM(val, ID_DFR0_EL1, CopDbg, Debugv8p8); return val; } static int set_id_dfr0_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { u8 perfmon = SYS_FIELD_GET(ID_DFR0_EL1, PerfMon, val); u8 copdbg = SYS_FIELD_GET(ID_DFR0_EL1, CopDbg, val); if (perfmon == ID_DFR0_EL1_PerfMon_IMPDEF) { val &= ~ID_DFR0_EL1_PerfMon_MASK; perfmon = 0; } /* * Allow DFR0_EL1.PerfMon to be set from userspace as long as * it doesn't promise more than what the HW gives us on the * AArch64 side (as everything is emulated with that), and * that this is a PMUv3. */ if (perfmon != 0 && perfmon < ID_DFR0_EL1_PerfMon_PMUv3) return -EINVAL; if (copdbg < ID_DFR0_EL1_CopDbg_Armv8) return -EINVAL; return set_id_reg(vcpu, rd, val); } static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 user_val) { u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); u64 mpam_mask = ID_AA64PFR0_EL1_MPAM_MASK; /* * Commit 011e5f5bf529f ("arm64/cpufeature: Add remaining feature bits * in ID_AA64PFR0 register") exposed the MPAM field of AA64PFR0_EL1 to * guests, but didn't add trap handling. KVM doesn't support MPAM and * always returns an UNDEF for these registers. The guest must see 0 * for this field. * * But KVM must also accept values from user-space that were provided * by KVM. On CPUs that support MPAM, permit user-space to write * the sanitizied value to ID_AA64PFR0_EL1.MPAM, but ignore this field. */ if ((hw_val & mpam_mask) == (user_val & mpam_mask)) user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK; /* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */ if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) || !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) || (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val))) return -EINVAL; /* * If we are running on a GICv5 host and support FEAT_GCIE_LEGACY, then * we support GICv3. Fail attempts to do anything but set that to IMP. */ if (vgic_is_v3_compat(vcpu->kvm) && FIELD_GET(ID_AA64PFR0_EL1_GIC_MASK, user_val) != ID_AA64PFR0_EL1_GIC_IMP) return -EINVAL; return set_id_reg(vcpu, rd, user_val); } static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 user_val) { u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); u64 mpam_mask = ID_AA64PFR1_EL1_MPAM_frac_MASK; u8 mte = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE, hw_val); u8 user_mte_frac = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE_frac, user_val); u8 hw_mte_frac = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE_frac, hw_val); /* See set_id_aa64pfr0_el1 for comment about MPAM */ if ((hw_val & mpam_mask) == (user_val & mpam_mask)) user_val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK; /* * Previously MTE_frac was hidden from guest. However, if the * hardware supports MTE2 but not MTE_ASYM_FAULT then a value * of 0 for this field indicates that the hardware supports * MTE_ASYNC. Whereas, 0xf indicates MTE_ASYNC is not supported. * * As KVM must accept values from KVM provided by user-space, * when ID_AA64PFR1_EL1.MTE is 2 allow user-space to set * ID_AA64PFR1_EL1.MTE_frac to 0. However, ignore it to avoid * incorrectly claiming hardware support for MTE_ASYNC in the * guest. */ if (mte == ID_AA64PFR1_EL1_MTE_MTE2 && hw_mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI && user_mte_frac == ID_AA64PFR1_EL1_MTE_frac_ASYNC) { user_val &= ~ID_AA64PFR1_EL1_MTE_frac_MASK; user_val |= hw_val & ID_AA64PFR1_EL1_MTE_frac_MASK; } return set_id_reg(vcpu, rd, user_val); } /* * Allow userspace to de-feature a stage-2 translation granule but prevent it * from claiming the impossible. */ #define tgran2_val_allowed(tg, safe, user) \ ({ \ u8 __s = SYS_FIELD_GET(ID_AA64MMFR0_EL1, tg, safe); \ u8 __u = SYS_FIELD_GET(ID_AA64MMFR0_EL1, tg, user); \ \ __s == __u || __u == ID_AA64MMFR0_EL1_##tg##_NI; \ }) static int set_id_aa64mmfr0_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 user_val) { u64 sanitized_val = kvm_read_sanitised_id_reg(vcpu, rd); if (!vcpu_has_nv(vcpu)) return set_id_reg(vcpu, rd, user_val); if (!tgran2_val_allowed(TGRAN4_2, sanitized_val, user_val) || !tgran2_val_allowed(TGRAN16_2, sanitized_val, user_val) || !tgran2_val_allowed(TGRAN64_2, sanitized_val, user_val)) return -EINVAL; return set_id_reg(vcpu, rd, user_val); } static int set_id_aa64mmfr2_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 user_val) { u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); u64 nv_mask = ID_AA64MMFR2_EL1_NV_MASK; /* * We made the mistake to expose the now deprecated NV field, * so allow userspace to write it, but silently ignore it. */ if ((hw_val & nv_mask) == (user_val & nv_mask)) user_val &= ~nv_mask; return set_id_reg(vcpu, rd, user_val); } static int set_ctr_el0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 user_val) { u8 user_L1Ip = SYS_FIELD_GET(CTR_EL0, L1Ip, user_val); /* * Both AIVIVT (0b01) and VPIPT (0b00) are documented as reserved. * Hence only allow to set VIPT(0b10) or PIPT(0b11) for L1Ip based * on what hardware reports. * * Using a VIPT software model on PIPT will lead to over invalidation, * but still correct. Hence, we can allow downgrading PIPT to VIPT, * but not the other way around. This is handled via arm64_ftr_safe_value() * as CTR_EL0 ftr_bits has L1Ip field with type FTR_EXACT and safe value * set as VIPT. */ switch (user_L1Ip) { case CTR_EL0_L1Ip_RESERVED_VPIPT: case CTR_EL0_L1Ip_RESERVED_AIVIVT: return -EINVAL; case CTR_EL0_L1Ip_VIPT: case CTR_EL0_L1Ip_PIPT: return set_id_reg(vcpu, rd, user_val); default: return -ENOENT; } } /* * cpufeature ID register user accessors * * For now, these registers are immutable for userspace, so no values * are stored, and for set_id_reg() we don't allow the effective value * to be changed. */ static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 *val) { /* * Avoid locking if the VM has already started, as the ID registers are * guaranteed to be invariant at that point. */ if (kvm_vm_has_ran_once(vcpu->kvm)) { *val = read_id_reg(vcpu, rd); return 0; } mutex_lock(&vcpu->kvm->arch.config_lock); *val = read_id_reg(vcpu, rd); mutex_unlock(&vcpu->kvm->arch.config_lock); return 0; } static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { u32 id = reg_to_encoding(rd); int ret; mutex_lock(&vcpu->kvm->arch.config_lock); /* * Once the VM has started the ID registers are immutable. Reject any * write that does not match the final register value. */ if (kvm_vm_has_ran_once(vcpu->kvm)) { if (val != read_id_reg(vcpu, rd)) ret = -EBUSY; else ret = 0; mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; } ret = arm64_check_features(vcpu, rd, val); if (!ret) kvm_set_vm_id_reg(vcpu->kvm, id, val); mutex_unlock(&vcpu->kvm->arch.config_lock); /* * arm64_check_features() returns -E2BIG to indicate the register's * feature set is a superset of the maximally-allowed register value. * While it would be nice to precisely describe this to userspace, the * existing UAPI for KVM_SET_ONE_REG has it that invalid register * writes return -EINVAL. */ if (ret == -E2BIG) ret = -EINVAL; return ret; } void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val) { u64 *p = __vm_id_reg(&kvm->arch, reg); lockdep_assert_held(&kvm->arch.config_lock); if (KVM_BUG_ON(kvm_vm_has_ran_once(kvm) || !p, kvm)) return; *p = val; } static int get_raz_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 *val) { *val = 0; return 0; } static int set_wi_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { return 0; } static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = kvm_read_vm_id_reg(vcpu->kvm, SYS_CTR_EL0); return true; } static bool access_clidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = __vcpu_sys_reg(vcpu, r->reg); return true; } /* * Fabricate a CLIDR_EL1 value instead of using the real value, which can vary * by the physical CPU which the vcpu currently resides in. */ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0); u64 clidr; u8 loc; if ((ctr_el0 & CTR_EL0_IDC)) { /* * Data cache clean to the PoU is not required so LoUU and LoUIS * will not be set and a unified cache, which will be marked as * LoC, will be added. * * If not DIC, let the unified cache L2 so that an instruction * cache can be added as L1 later. */ loc = (ctr_el0 & CTR_EL0_DIC) ? 1 : 2; clidr = CACHE_TYPE_UNIFIED << CLIDR_CTYPE_SHIFT(loc); } else { /* * Data cache clean to the PoU is required so let L1 have a data * cache and mark it as LoUU and LoUIS. As L1 has a data cache, * it can be marked as LoC too. */ loc = 1; clidr = 1 << CLIDR_LOUU_SHIFT; clidr |= 1 << CLIDR_LOUIS_SHIFT; clidr |= CACHE_TYPE_DATA << CLIDR_CTYPE_SHIFT(1); } /* * Instruction cache invalidation to the PoU is required so let L1 have * an instruction cache. If L1 already has a data cache, it will be * CACHE_TYPE_SEPARATE. */ if (!(ctr_el0 & CTR_EL0_DIC)) clidr |= CACHE_TYPE_INST << CLIDR_CTYPE_SHIFT(1); clidr |= loc << CLIDR_LOC_SHIFT; /* * Add tag cache unified to data cache. Allocation tags and data are * unified in a cache line so that it looks valid even if there is only * one cache line. */ if (kvm_has_mte(vcpu->kvm)) clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc); __vcpu_assign_sys_reg(vcpu, r->reg, clidr); return __vcpu_sys_reg(vcpu, r->reg); } static int set_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val) { u64 ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0); u64 idc = !CLIDR_LOC(val) || (!CLIDR_LOUIS(val) && !CLIDR_LOUU(val)); if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc)) return -EINVAL; __vcpu_assign_sys_reg(vcpu, rd->reg, val); return 0; } static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { int reg = r->reg; if (p->is_write) vcpu_write_sys_reg(vcpu, p->regval, reg); else p->regval = vcpu_read_sys_reg(vcpu, reg); return true; } static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 csselr; if (p->is_write) return write_to_read_only(vcpu, p, r); csselr = vcpu_read_sys_reg(vcpu, CSSELR_EL1); csselr &= CSSELR_EL1_Level | CSSELR_EL1_InD; if (csselr < CSSELR_MAX) p->regval = get_ccsidr(vcpu, csselr); return true; } static unsigned int mte_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (kvm_has_mte(vcpu->kvm)) return 0; return REG_HIDDEN; } #define MTE_REG(name) { \ SYS_DESC(SYS_##name), \ .access = undef_access, \ .reset = reset_unknown, \ .reg = name, \ .visibility = mte_visibility, \ } static unsigned int el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (vcpu_has_nv(vcpu)) return 0; return REG_HIDDEN; } static bool bad_vncr_trap(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { /* * We really shouldn't be here, and this is likely the result * of a misconfigured trap, as this register should target the * VNCR page, and nothing else. */ return bad_trap(vcpu, p, r, "trap of VNCR-backed register"); } static bool bad_redir_trap(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { /* * We really shouldn't be here, and this is likely the result * of a misconfigured trap, as this register should target the * corresponding EL1, and nothing else. */ return bad_trap(vcpu, p, r, "trap of EL2 register redirected to EL1"); } #define EL2_REG_FILTERED(name, acc, rst, v, filter) { \ SYS_DESC(SYS_##name), \ .access = acc, \ .reset = rst, \ .reg = name, \ .visibility = filter, \ .val = v, \ } #define EL2_REG(name, acc, rst, v) \ EL2_REG_FILTERED(name, acc, rst, v, el2_visibility) #define EL2_REG_VNCR(name, rst, v) EL2_REG(name, bad_vncr_trap, rst, v) #define EL2_REG_VNCR_FILT(name, vis) \ EL2_REG_FILTERED(name, bad_vncr_trap, reset_val, 0, vis) #define EL2_REG_VNCR_GICv3(name) \ EL2_REG_VNCR_FILT(name, hidden_visibility) #define EL2_REG_REDIR(name, rst, v) EL2_REG(name, bad_redir_trap, rst, v) /* * Since reset() callback and field val are not used for idregs, they will be * used for specific purposes for idregs. * The reset() would return KVM sanitised register value. The value would be the * same as the host kernel sanitised value if there is no KVM sanitisation. * The val would be used as a mask indicating writable fields for the idreg. * Only bits with 1 are writable from userspace. This mask might not be * necessary in the future whenever all ID registers are enabled as writable * from userspace. */ #define ID_DESC_DEFAULT_CALLBACKS \ .access = access_id_reg, \ .get_user = get_id_reg, \ .set_user = set_id_reg, \ .visibility = id_visibility, \ .reset = kvm_read_sanitised_id_reg #define ID_DESC(name) \ SYS_DESC(SYS_##name), \ ID_DESC_DEFAULT_CALLBACKS /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ ID_DESC(name), \ .val = 0, \ } /* sys_reg_desc initialiser for known cpufeature ID registers */ #define AA32_ID_SANITISED(name) { \ ID_DESC(name), \ .visibility = aa32_id_visibility, \ .val = 0, \ } /* sys_reg_desc initialiser for writable ID registers */ #define ID_WRITABLE(name, mask) { \ ID_DESC(name), \ .val = mask, \ } /* sys_reg_desc initialiser for cpufeature ID registers that need filtering */ #define ID_FILTERED(sysreg, name, mask) { \ ID_DESC(sysreg), \ .set_user = set_##name, \ .val = (mask), \ } /* * sys_reg_desc initialiser for architecturally unallocated cpufeature ID * register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2 * (1 <= crm < 8, 0 <= Op2 < 8). */ #define ID_UNALLOCATED(crm, op2) { \ .name = "S3_0_0_" #crm "_" #op2, \ Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2), \ ID_DESC_DEFAULT_CALLBACKS, \ .visibility = raz_visibility, \ .val = 0, \ } /* * sys_reg_desc initialiser for known ID registers that we hide from guests. * For now, these are exposed just like unallocated ID regs: they appear * RAZ for the guest. */ #define ID_HIDDEN(name) { \ ID_DESC(name), \ .visibility = raz_visibility, \ .val = 0, \ } static bool access_sp_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) __vcpu_assign_sys_reg(vcpu, SP_EL1, p->regval); else p->regval = __vcpu_sys_reg(vcpu, SP_EL1); return true; } static bool access_elr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) vcpu_write_sys_reg(vcpu, p->regval, ELR_EL1); else p->regval = vcpu_read_sys_reg(vcpu, ELR_EL1); return true; } static bool access_spsr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) __vcpu_assign_sys_reg(vcpu, SPSR_EL1, p->regval); else p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1); return true; } static bool access_cntkctl_el12(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) __vcpu_assign_sys_reg(vcpu, CNTKCTL_EL1, p->regval); else p->regval = __vcpu_sys_reg(vcpu, CNTKCTL_EL1); return true; } static u64 reset_hcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 val = r->val; if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1)) val |= HCR_E2H; __vcpu_assign_sys_reg(vcpu, r->reg, val); return __vcpu_sys_reg(vcpu, r->reg); } static unsigned int __el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, unsigned int (*fn)(const struct kvm_vcpu *, const struct sys_reg_desc *)) { return el2_visibility(vcpu, rd) ?: fn(vcpu, rd); } static unsigned int sve_el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { return __el2_visibility(vcpu, rd, sve_visibility); } static unsigned int vncr_el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (el2_visibility(vcpu, rd) == 0 && kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) return 0; return REG_HIDDEN; } static unsigned int sctlr2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (kvm_has_sctlr2(vcpu->kvm)) return 0; return REG_HIDDEN; } static unsigned int sctlr2_el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { return __el2_visibility(vcpu, rd, sctlr2_visibility); } static bool access_zcr_el2(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { unsigned int vq; if (guest_hyp_sve_traps_enabled(vcpu)) { kvm_inject_nested_sve_trap(vcpu); return false; } if (!p->is_write) { p->regval = __vcpu_sys_reg(vcpu, ZCR_EL2); return true; } vq = SYS_FIELD_GET(ZCR_ELx, LEN, p->regval) + 1; vq = min(vq, vcpu_sve_max_vq(vcpu)); __vcpu_assign_sys_reg(vcpu, ZCR_EL2, vq - 1); return true; } static bool access_gic_vtr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = kvm_get_guest_vtr_el2(); return true; } static bool access_gic_misr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = vgic_v3_get_misr(vcpu); return true; } static bool access_gic_eisr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = vgic_v3_get_eisr(vcpu); return true; } static bool access_gic_elrsr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); p->regval = vgic_v3_get_elrsr(vcpu); return true; } static unsigned int s1poe_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (kvm_has_s1poe(vcpu->kvm)) return 0; return REG_HIDDEN; } static unsigned int s1poe_el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { return __el2_visibility(vcpu, rd, s1poe_visibility); } static unsigned int tcr2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (kvm_has_tcr2(vcpu->kvm)) return 0; return REG_HIDDEN; } static unsigned int tcr2_el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { return __el2_visibility(vcpu, rd, tcr2_visibility); } static unsigned int fgt2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (el2_visibility(vcpu, rd) == 0 && kvm_has_feat(vcpu->kvm, ID_AA64MMFR0_EL1, FGT, FGT2)) return 0; return REG_HIDDEN; } static unsigned int fgt_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (el2_visibility(vcpu, rd) == 0 && kvm_has_feat(vcpu->kvm, ID_AA64MMFR0_EL1, FGT, IMP)) return 0; return REG_HIDDEN; } static unsigned int s1pie_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { if (kvm_has_s1pie(vcpu->kvm)) return 0; return REG_HIDDEN; } static unsigned int s1pie_el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { return __el2_visibility(vcpu, rd, s1pie_visibility); } static bool access_mdcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u64 hpmn, val, old = __vcpu_sys_reg(vcpu, MDCR_EL2); if (!p->is_write) { p->regval = old; return true; } val = p->regval; hpmn = FIELD_GET(MDCR_EL2_HPMN, val); /* * If HPMN is out of bounds, limit it to what we actually * support. This matches the UNKNOWN definition of the field * in that case, and keeps the emulation simple. Sort of. */ if (hpmn > vcpu->kvm->arch.nr_pmu_counters) { hpmn = vcpu->kvm->arch.nr_pmu_counters; u64p_replace_bits(&val, hpmn, MDCR_EL2_HPMN); } __vcpu_assign_sys_reg(vcpu, MDCR_EL2, val); /* * Request a reload of the PMU to enable/disable the counters * affected by HPME. */ if ((old ^ val) & MDCR_EL2_HPME) kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return true; } static bool access_ras(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { struct kvm *kvm = vcpu->kvm; switch(reg_to_encoding(r)) { case SYS_ERXPFGCDN_EL1: case SYS_ERXPFGCTL_EL1: case SYS_ERXPFGF_EL1: case SYS_ERXMISC2_EL1: case SYS_ERXMISC3_EL1: if (!(kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1) || (kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, RAS, IMP) && kvm_has_feat(kvm, ID_AA64PFR1_EL1, RAS_frac, RASv1p1)))) { kvm_inject_undefined(vcpu); return false; } break; default: if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) { kvm_inject_undefined(vcpu); return false; } } return trap_raz_wi(vcpu, p, r); } /* * For historical (ahem ABI) reasons, KVM treated MIDR_EL1, REVIDR_EL1, and * AIDR_EL1 as "invariant" registers, meaning userspace cannot change them. * The values made visible to userspace were the register values of the boot * CPU. * * At the same time, reads from these registers at EL1 previously were not * trapped, allowing the guest to read the actual hardware value. On big-little * machines, this means the VM can see different values depending on where a * given vCPU got scheduled. * * These registers are now trapped as collateral damage from SME, and what * follows attempts to give a user / guest view consistent with the existing * ABI. */ static bool access_imp_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return write_to_read_only(vcpu, p, r); /* * Return the VM-scoped implementation ID register values if userspace * has made them writable. */ if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &vcpu->kvm->arch.flags)) return access_id_reg(vcpu, p, r); /* * Otherwise, fall back to the old behavior of returning the value of * the current CPU. */ switch (reg_to_encoding(r)) { case SYS_REVIDR_EL1: p->regval = read_sysreg(revidr_el1); break; case SYS_AIDR_EL1: p->regval = read_sysreg(aidr_el1); break; default: WARN_ON_ONCE(1); } return true; } static u64 __ro_after_init boot_cpu_midr_val; static u64 __ro_after_init boot_cpu_revidr_val; static u64 __ro_after_init boot_cpu_aidr_val; static void init_imp_id_regs(void) { boot_cpu_midr_val = read_sysreg(midr_el1); boot_cpu_revidr_val = read_sysreg(revidr_el1); boot_cpu_aidr_val = read_sysreg(aidr_el1); } static u64 reset_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { switch (reg_to_encoding(r)) { case SYS_MIDR_EL1: return boot_cpu_midr_val; case SYS_REVIDR_EL1: return boot_cpu_revidr_val; case SYS_AIDR_EL1: return boot_cpu_aidr_val; default: KVM_BUG_ON(1, vcpu->kvm); return 0; } } static int set_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct kvm *kvm = vcpu->kvm; u64 expected; guard(mutex)(&kvm->arch.config_lock); expected = read_id_reg(vcpu, r); if (expected == val) return 0; if (!test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags)) return -EINVAL; /* * Once the VM has started the ID registers are immutable. Reject the * write if userspace tries to change it. */ if (kvm_vm_has_ran_once(kvm)) return -EBUSY; /* * Any value is allowed for the implementation ID registers so long as * it is within the writable mask. */ if ((val & r->val) != val) return -EINVAL; kvm_set_vm_id_reg(kvm, reg_to_encoding(r), val); return 0; } #define IMPLEMENTATION_ID(reg, mask) { \ SYS_DESC(SYS_##reg), \ .access = access_imp_id_reg, \ .get_user = get_id_reg, \ .set_user = set_imp_id_reg, \ .reset = reset_imp_id_reg, \ .val = mask, \ } static u64 reset_mdcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { __vcpu_assign_sys_reg(vcpu, r->reg, vcpu->kvm->arch.nr_pmu_counters); return vcpu->kvm->arch.nr_pmu_counters; } /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 * * Debug handling: We do trap most, if not all debug related system * registers. The implementation is good enough to ensure that a guest * can use these with minimal performance degradation. The drawback is * that we don't implement any of the external debug architecture. * This should be revisited if we ever encounter a more demanding * guest... */ static const struct sys_reg_desc sys_reg_descs[] = { DBG_BCR_BVR_WCR_WVR_EL1(0), DBG_BCR_BVR_WCR_WVR_EL1(1), { SYS_DESC(SYS_MDCCINT_EL1), trap_debug_regs, reset_val, MDCCINT_EL1, 0 }, { SYS_DESC(SYS_MDSCR_EL1), trap_debug_regs, reset_val, MDSCR_EL1, 0 }, DBG_BCR_BVR_WCR_WVR_EL1(2), DBG_BCR_BVR_WCR_WVR_EL1(3), DBG_BCR_BVR_WCR_WVR_EL1(4), DBG_BCR_BVR_WCR_WVR_EL1(5), DBG_BCR_BVR_WCR_WVR_EL1(6), DBG_BCR_BVR_WCR_WVR_EL1(7), DBG_BCR_BVR_WCR_WVR_EL1(8), DBG_BCR_BVR_WCR_WVR_EL1(9), DBG_BCR_BVR_WCR_WVR_EL1(10), DBG_BCR_BVR_WCR_WVR_EL1(11), DBG_BCR_BVR_WCR_WVR_EL1(12), DBG_BCR_BVR_WCR_WVR_EL1(13), DBG_BCR_BVR_WCR_WVR_EL1(14), DBG_BCR_BVR_WCR_WVR_EL1(15), { SYS_DESC(SYS_MDRAR_EL1), trap_raz_wi }, { SYS_DESC(SYS_OSLAR_EL1), trap_oslar_el1 }, { SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1, reset_val, OSLSR_EL1, OSLSR_EL1_OSLM_IMPLEMENTED, .set_user = set_oslsr_el1, }, { SYS_DESC(SYS_OSDLR_EL1), trap_raz_wi }, { SYS_DESC(SYS_DBGPRCR_EL1), trap_raz_wi }, { SYS_DESC(SYS_DBGCLAIMSET_EL1), trap_raz_wi }, { SYS_DESC(SYS_DBGCLAIMCLR_EL1), trap_raz_wi }, { SYS_DESC(SYS_DBGAUTHSTATUS_EL1), trap_dbgauthstatus_el1 }, { SYS_DESC(SYS_MDCCSR_EL0), trap_raz_wi }, { SYS_DESC(SYS_DBGDTR_EL0), trap_raz_wi }, // DBGDTR[TR]X_EL0 share the same encoding { SYS_DESC(SYS_DBGDTRTX_EL0), trap_raz_wi }, { SYS_DESC(SYS_DBGVCR32_EL2), undef_access, reset_val, DBGVCR32_EL2, 0 }, IMPLEMENTATION_ID(MIDR_EL1, GENMASK_ULL(31, 0)), { SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 }, IMPLEMENTATION_ID(REVIDR_EL1, GENMASK_ULL(63, 0)), /* * ID regs: all ID_SANITISED() entries here must have corresponding * entries in arm64_ftr_regs[]. */ /* AArch64 mappings of the AArch32 ID registers */ /* CRm=1 */ AA32_ID_SANITISED(ID_PFR0_EL1), AA32_ID_SANITISED(ID_PFR1_EL1), { SYS_DESC(SYS_ID_DFR0_EL1), .access = access_id_reg, .get_user = get_id_reg, .set_user = set_id_dfr0_el1, .visibility = aa32_id_visibility, .reset = read_sanitised_id_dfr0_el1, .val = ID_DFR0_EL1_PerfMon_MASK | ID_DFR0_EL1_CopDbg_MASK, }, ID_HIDDEN(ID_AFR0_EL1), AA32_ID_SANITISED(ID_MMFR0_EL1), AA32_ID_SANITISED(ID_MMFR1_EL1), AA32_ID_SANITISED(ID_MMFR2_EL1), AA32_ID_SANITISED(ID_MMFR3_EL1), /* CRm=2 */ AA32_ID_SANITISED(ID_ISAR0_EL1), AA32_ID_SANITISED(ID_ISAR1_EL1), AA32_ID_SANITISED(ID_ISAR2_EL1), AA32_ID_SANITISED(ID_ISAR3_EL1), AA32_ID_SANITISED(ID_ISAR4_EL1), AA32_ID_SANITISED(ID_ISAR5_EL1), AA32_ID_SANITISED(ID_MMFR4_EL1), AA32_ID_SANITISED(ID_ISAR6_EL1), /* CRm=3 */ AA32_ID_SANITISED(MVFR0_EL1), AA32_ID_SANITISED(MVFR1_EL1), AA32_ID_SANITISED(MVFR2_EL1), ID_UNALLOCATED(3,3), AA32_ID_SANITISED(ID_PFR2_EL1), ID_HIDDEN(ID_DFR1_EL1), AA32_ID_SANITISED(ID_MMFR5_EL1), ID_UNALLOCATED(3,7), /* AArch64 ID registers */ /* CRm=4 */ ID_FILTERED(ID_AA64PFR0_EL1, id_aa64pfr0_el1, ~(ID_AA64PFR0_EL1_AMU | ID_AA64PFR0_EL1_MPAM | ID_AA64PFR0_EL1_SVE | ID_AA64PFR0_EL1_AdvSIMD | ID_AA64PFR0_EL1_FP)), ID_FILTERED(ID_AA64PFR1_EL1, id_aa64pfr1_el1, ~(ID_AA64PFR1_EL1_PFAR | ID_AA64PFR1_EL1_MTEX | ID_AA64PFR1_EL1_THE | ID_AA64PFR1_EL1_GCS | ID_AA64PFR1_EL1_MTE_frac | ID_AA64PFR1_EL1_NMI | ID_AA64PFR1_EL1_RNDR_trap | ID_AA64PFR1_EL1_SME | ID_AA64PFR1_EL1_RES0 | ID_AA64PFR1_EL1_MPAM_frac | ID_AA64PFR1_EL1_MTE)), ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR | ID_AA64PFR2_EL1_MTEFAR | ID_AA64PFR2_EL1_MTESTOREONLY), ID_UNALLOCATED(4,3), ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0), ID_HIDDEN(ID_AA64SMFR0_EL1), ID_UNALLOCATED(4,6), ID_WRITABLE(ID_AA64FPFR0_EL1, ~ID_AA64FPFR0_EL1_RES0), /* CRm=5 */ /* * Prior to FEAT_Debugv8.9, the architecture defines context-aware * breakpoints (CTX_CMPs) as the highest numbered breakpoints (BRPs). * KVM does not trap + emulate the breakpoint registers, and as such * cannot support a layout that misaligns with the underlying hardware. * While it may be possible to describe a subset that aligns with * hardware, just prevent changes to BRPs and CTX_CMPs altogether for * simplicity. * * See DDI0487K.a, section D2.8.3 Breakpoint types and linking * of breakpoints for more details. */ ID_FILTERED(ID_AA64DFR0_EL1, id_aa64dfr0_el1, ID_AA64DFR0_EL1_DoubleLock_MASK | ID_AA64DFR0_EL1_WRPs_MASK | ID_AA64DFR0_EL1_PMUVer_MASK | ID_AA64DFR0_EL1_DebugVer_MASK), ID_SANITISED(ID_AA64DFR1_EL1), ID_UNALLOCATED(5,2), ID_UNALLOCATED(5,3), ID_HIDDEN(ID_AA64AFR0_EL1), ID_HIDDEN(ID_AA64AFR1_EL1), ID_UNALLOCATED(5,6), ID_UNALLOCATED(5,7), /* CRm=6 */ ID_WRITABLE(ID_AA64ISAR0_EL1, ~ID_AA64ISAR0_EL1_RES0), ID_WRITABLE(ID_AA64ISAR1_EL1, ~(ID_AA64ISAR1_EL1_GPI | ID_AA64ISAR1_EL1_GPA | ID_AA64ISAR1_EL1_API | ID_AA64ISAR1_EL1_APA)), ID_WRITABLE(ID_AA64ISAR2_EL1, ~(ID_AA64ISAR2_EL1_RES0 | ID_AA64ISAR2_EL1_APA3 | ID_AA64ISAR2_EL1_GPA3)), ID_WRITABLE(ID_AA64ISAR3_EL1, (ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_LSFE | ID_AA64ISAR3_EL1_FAMINMAX)), ID_UNALLOCATED(6,4), ID_UNALLOCATED(6,5), ID_UNALLOCATED(6,6), ID_UNALLOCATED(6,7), /* CRm=7 */ ID_FILTERED(ID_AA64MMFR0_EL1, id_aa64mmfr0_el1, ~(ID_AA64MMFR0_EL1_RES0 | ID_AA64MMFR0_EL1_ASIDBITS)), ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 | ID_AA64MMFR1_EL1_XNX | ID_AA64MMFR1_EL1_VH | ID_AA64MMFR1_EL1_VMIDBits)), ID_FILTERED(ID_AA64MMFR2_EL1, id_aa64mmfr2_el1, ~(ID_AA64MMFR2_EL1_RES0 | ID_AA64MMFR2_EL1_EVT | ID_AA64MMFR2_EL1_FWB | ID_AA64MMFR2_EL1_IDS | ID_AA64MMFR2_EL1_NV | ID_AA64MMFR2_EL1_CCIDX)), ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_SCTLRX | ID_AA64MMFR3_EL1_S1PIE | ID_AA64MMFR3_EL1_S1POE)), ID_WRITABLE(ID_AA64MMFR4_EL1, ID_AA64MMFR4_EL1_NV_frac), ID_UNALLOCATED(7,5), ID_UNALLOCATED(7,6), ID_UNALLOCATED(7,7), { SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 }, { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 }, { SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 }, { SYS_DESC(SYS_SCTLR2_EL1), access_vm_reg, reset_val, SCTLR2_EL1, 0, .visibility = sctlr2_visibility }, MTE_REG(RGSR_EL1), MTE_REG(GCR_EL1), { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TRFCR_EL1), undef_access }, { SYS_DESC(SYS_SMPRI_EL1), undef_access }, { SYS_DESC(SYS_SMCR_EL1), undef_access }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 }, { SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 }, { SYS_DESC(SYS_TCR2_EL1), access_vm_reg, reset_val, TCR2_EL1, 0, .visibility = tcr2_visibility }, PTRAUTH_KEY(APIA), PTRAUTH_KEY(APIB), PTRAUTH_KEY(APDA), PTRAUTH_KEY(APDB), PTRAUTH_KEY(APGA), { SYS_DESC(SYS_SPSR_EL1), access_spsr}, { SYS_DESC(SYS_ELR_EL1), access_elr}, { SYS_DESC(SYS_ICC_PMR_EL1), undef_access }, { SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 }, { SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 }, { SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 }, { SYS_DESC(SYS_ERRIDR_EL1), access_ras }, { SYS_DESC(SYS_ERRSELR_EL1), access_ras }, { SYS_DESC(SYS_ERXFR_EL1), access_ras }, { SYS_DESC(SYS_ERXCTLR_EL1), access_ras }, { SYS_DESC(SYS_ERXSTATUS_EL1), access_ras }, { SYS_DESC(SYS_ERXADDR_EL1), access_ras }, { SYS_DESC(SYS_ERXPFGF_EL1), access_ras }, { SYS_DESC(SYS_ERXPFGCTL_EL1), access_ras }, { SYS_DESC(SYS_ERXPFGCDN_EL1), access_ras }, { SYS_DESC(SYS_ERXMISC0_EL1), access_ras }, { SYS_DESC(SYS_ERXMISC1_EL1), access_ras }, { SYS_DESC(SYS_ERXMISC2_EL1), access_ras }, { SYS_DESC(SYS_ERXMISC3_EL1), access_ras }, MTE_REG(TFSR_EL1), MTE_REG(TFSRE0_EL1), { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, { SYS_DESC(SYS_PMSCR_EL1), undef_access }, { SYS_DESC(SYS_PMSNEVFR_EL1), undef_access }, { SYS_DESC(SYS_PMSICR_EL1), undef_access }, { SYS_DESC(SYS_PMSIRR_EL1), undef_access }, { SYS_DESC(SYS_PMSFCR_EL1), undef_access }, { SYS_DESC(SYS_PMSEVFR_EL1), undef_access }, { SYS_DESC(SYS_PMSLATFR_EL1), undef_access }, { SYS_DESC(SYS_PMSIDR_EL1), undef_access }, { SYS_DESC(SYS_PMBLIMITR_EL1), undef_access }, { SYS_DESC(SYS_PMBPTR_EL1), undef_access }, { SYS_DESC(SYS_PMBSR_EL1), undef_access }, { SYS_DESC(SYS_PMSDSFR_EL1), undef_access }, /* PMBIDR_EL1 is not trapped */ { PMU_SYS_REG(PMINTENSET_EL1), .access = access_pminten, .reg = PMINTENSET_EL1, .get_user = get_pmreg, .set_user = set_pmreg }, { PMU_SYS_REG(PMINTENCLR_EL1), .access = access_pminten, .reg = PMINTENSET_EL1, .get_user = get_pmreg, .set_user = set_pmreg }, { SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1, .visibility = s1pie_visibility }, { SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1, .visibility = s1pie_visibility }, { SYS_DESC(SYS_POR_EL1), NULL, reset_unknown, POR_EL1, .visibility = s1poe_visibility }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, { SYS_DESC(SYS_LORSA_EL1), trap_loregion }, { SYS_DESC(SYS_LOREA_EL1), trap_loregion }, { SYS_DESC(SYS_LORN_EL1), trap_loregion }, { SYS_DESC(SYS_LORC_EL1), trap_loregion }, { SYS_DESC(SYS_MPAMIDR_EL1), undef_access }, { SYS_DESC(SYS_LORID_EL1), trap_loregion }, { SYS_DESC(SYS_MPAM1_EL1), undef_access }, { SYS_DESC(SYS_MPAM0_EL1), undef_access }, { SYS_DESC(SYS_VBAR_EL1), access_rw, reset_val, VBAR_EL1, 0 }, { SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 }, { SYS_DESC(SYS_ICC_IAR0_EL1), undef_access }, { SYS_DESC(SYS_ICC_EOIR0_EL1), undef_access }, { SYS_DESC(SYS_ICC_HPPIR0_EL1), undef_access }, { SYS_DESC(SYS_ICC_BPR0_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP0R0_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP0R1_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP0R2_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP0R3_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP1R0_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP1R1_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP1R2_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP1R3_EL1), undef_access }, { SYS_DESC(SYS_ICC_DIR_EL1), undef_access }, { SYS_DESC(SYS_ICC_RPR_EL1), undef_access }, { SYS_DESC(SYS_ICC_SGI1R_EL1), access_gic_sgi }, { SYS_DESC(SYS_ICC_ASGI1R_EL1), access_gic_sgi }, { SYS_DESC(SYS_ICC_SGI0R_EL1), access_gic_sgi }, { SYS_DESC(SYS_ICC_IAR1_EL1), undef_access }, { SYS_DESC(SYS_ICC_EOIR1_EL1), undef_access }, { SYS_DESC(SYS_ICC_HPPIR1_EL1), undef_access }, { SYS_DESC(SYS_ICC_BPR1_EL1), undef_access }, { SYS_DESC(SYS_ICC_CTLR_EL1), undef_access }, { SYS_DESC(SYS_ICC_SRE_EL1), access_gic_sre }, { SYS_DESC(SYS_ICC_IGRPEN0_EL1), undef_access }, { SYS_DESC(SYS_ICC_IGRPEN1_EL1), undef_access }, { SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 }, { SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 }, { SYS_DESC(SYS_ACCDATA_EL1), undef_access }, { SYS_DESC(SYS_SCXTNUM_EL1), undef_access }, { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, { SYS_DESC(SYS_CLIDR_EL1), access_clidr, reset_clidr, CLIDR_EL1, .set_user = set_clidr, .val = ~CLIDR_EL1_RES0 }, { SYS_DESC(SYS_CCSIDR2_EL1), undef_access }, { SYS_DESC(SYS_SMIDR_EL1), undef_access }, IMPLEMENTATION_ID(AIDR_EL1, GENMASK_ULL(63, 0)), { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, ID_FILTERED(CTR_EL0, ctr_el0, CTR_EL0_DIC_MASK | CTR_EL0_IDC_MASK | CTR_EL0_DminLine_MASK | CTR_EL0_L1Ip_MASK | CTR_EL0_IminLine_MASK), { SYS_DESC(SYS_SVCR), undef_access, reset_val, SVCR, 0, .visibility = sme_visibility }, { SYS_DESC(SYS_FPMR), undef_access, reset_val, FPMR, 0, .visibility = fp8_visibility }, { PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr, .reg = PMCR_EL0, .get_user = get_pmcr, .set_user = set_pmcr }, { PMU_SYS_REG(PMCNTENSET_EL0), .access = access_pmcnten, .reg = PMCNTENSET_EL0, .get_user = get_pmreg, .set_user = set_pmreg }, { PMU_SYS_REG(PMCNTENCLR_EL0), .access = access_pmcnten, .reg = PMCNTENSET_EL0, .get_user = get_pmreg, .set_user = set_pmreg }, { PMU_SYS_REG(PMOVSCLR_EL0), .access = access_pmovs, .reg = PMOVSSET_EL0, .get_user = get_pmreg, .set_user = set_pmreg }, /* * PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was * previously (and pointlessly) advertised in the past... */ { PMU_SYS_REG(PMSWINC_EL0), .get_user = get_raz_reg, .set_user = set_wi_reg, .access = access_pmswinc, .reset = NULL }, { PMU_SYS_REG(PMSELR_EL0), .access = access_pmselr, .reset = reset_pmselr, .reg = PMSELR_EL0 }, { PMU_SYS_REG(PMCEID0_EL0), .access = access_pmceid, .reset = NULL }, { PMU_SYS_REG(PMCEID1_EL0), .access = access_pmceid, .reset = NULL }, { PMU_SYS_REG(PMCCNTR_EL0), .access = access_pmu_evcntr, .reset = reset_unknown, .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr, .set_user = set_pmu_evcntr }, { PMU_SYS_REG(PMXEVTYPER_EL0), .access = access_pmu_evtyper, .reset = NULL }, { PMU_SYS_REG(PMXEVCNTR_EL0), .access = access_pmu_evcntr, .reset = NULL }, /* * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ { PMU_SYS_REG(PMUSERENR_EL0), .access = access_pmuserenr, .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 }, { PMU_SYS_REG(PMOVSSET_EL0), .access = access_pmovs, .reg = PMOVSSET_EL0, .get_user = get_pmreg, .set_user = set_pmreg }, { SYS_DESC(SYS_POR_EL0), NULL, reset_unknown, POR_EL0, .visibility = s1poe_visibility }, { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, { SYS_DESC(SYS_TPIDR2_EL0), undef_access }, { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, { SYS_DESC(SYS_AMCR_EL0), undef_access }, { SYS_DESC(SYS_AMCFGR_EL0), undef_access }, { SYS_DESC(SYS_AMCGCR_EL0), undef_access }, { SYS_DESC(SYS_AMUSERENR_EL0), undef_access }, { SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access }, { SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access }, { SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access }, { SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access }, AMU_AMEVCNTR0_EL0(0), AMU_AMEVCNTR0_EL0(1), AMU_AMEVCNTR0_EL0(2), AMU_AMEVCNTR0_EL0(3), AMU_AMEVCNTR0_EL0(4), AMU_AMEVCNTR0_EL0(5), AMU_AMEVCNTR0_EL0(6), AMU_AMEVCNTR0_EL0(7), AMU_AMEVCNTR0_EL0(8), AMU_AMEVCNTR0_EL0(9), AMU_AMEVCNTR0_EL0(10), AMU_AMEVCNTR0_EL0(11), AMU_AMEVCNTR0_EL0(12), AMU_AMEVCNTR0_EL0(13), AMU_AMEVCNTR0_EL0(14), AMU_AMEVCNTR0_EL0(15), AMU_AMEVTYPER0_EL0(0), AMU_AMEVTYPER0_EL0(1), AMU_AMEVTYPER0_EL0(2), AMU_AMEVTYPER0_EL0(3), AMU_AMEVTYPER0_EL0(4), AMU_AMEVTYPER0_EL0(5), AMU_AMEVTYPER0_EL0(6), AMU_AMEVTYPER0_EL0(7), AMU_AMEVTYPER0_EL0(8), AMU_AMEVTYPER0_EL0(9), AMU_AMEVTYPER0_EL0(10), AMU_AMEVTYPER0_EL0(11), AMU_AMEVTYPER0_EL0(12), AMU_AMEVTYPER0_EL0(13), AMU_AMEVTYPER0_EL0(14), AMU_AMEVTYPER0_EL0(15), AMU_AMEVCNTR1_EL0(0), AMU_AMEVCNTR1_EL0(1), AMU_AMEVCNTR1_EL0(2), AMU_AMEVCNTR1_EL0(3), AMU_AMEVCNTR1_EL0(4), AMU_AMEVCNTR1_EL0(5), AMU_AMEVCNTR1_EL0(6), AMU_AMEVCNTR1_EL0(7), AMU_AMEVCNTR1_EL0(8), AMU_AMEVCNTR1_EL0(9), AMU_AMEVCNTR1_EL0(10), AMU_AMEVCNTR1_EL0(11), AMU_AMEVCNTR1_EL0(12), AMU_AMEVCNTR1_EL0(13), AMU_AMEVCNTR1_EL0(14), AMU_AMEVCNTR1_EL0(15), AMU_AMEVTYPER1_EL0(0), AMU_AMEVTYPER1_EL0(1), AMU_AMEVTYPER1_EL0(2), AMU_AMEVTYPER1_EL0(3), AMU_AMEVTYPER1_EL0(4), AMU_AMEVTYPER1_EL0(5), AMU_AMEVTYPER1_EL0(6), AMU_AMEVTYPER1_EL0(7), AMU_AMEVTYPER1_EL0(8), AMU_AMEVTYPER1_EL0(9), AMU_AMEVTYPER1_EL0(10), AMU_AMEVTYPER1_EL0(11), AMU_AMEVTYPER1_EL0(12), AMU_AMEVTYPER1_EL0(13), AMU_AMEVTYPER1_EL0(14), AMU_AMEVTYPER1_EL0(15), { SYS_DESC(SYS_CNTPCT_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTVCT_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTPCTSS_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTVCTSS_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTV_TVAL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTV_CTL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTV_CVAL_EL0), access_arch_timer }, /* PMEVCNTRn_EL0 */ PMU_PMEVCNTR_EL0(0), PMU_PMEVCNTR_EL0(1), PMU_PMEVCNTR_EL0(2), PMU_PMEVCNTR_EL0(3), PMU_PMEVCNTR_EL0(4), PMU_PMEVCNTR_EL0(5), PMU_PMEVCNTR_EL0(6), PMU_PMEVCNTR_EL0(7), PMU_PMEVCNTR_EL0(8), PMU_PMEVCNTR_EL0(9), PMU_PMEVCNTR_EL0(10), PMU_PMEVCNTR_EL0(11), PMU_PMEVCNTR_EL0(12), PMU_PMEVCNTR_EL0(13), PMU_PMEVCNTR_EL0(14), PMU_PMEVCNTR_EL0(15), PMU_PMEVCNTR_EL0(16), PMU_PMEVCNTR_EL0(17), PMU_PMEVCNTR_EL0(18), PMU_PMEVCNTR_EL0(19), PMU_PMEVCNTR_EL0(20), PMU_PMEVCNTR_EL0(21), PMU_PMEVCNTR_EL0(22), PMU_PMEVCNTR_EL0(23), PMU_PMEVCNTR_EL0(24), PMU_PMEVCNTR_EL0(25), PMU_PMEVCNTR_EL0(26), PMU_PMEVCNTR_EL0(27), PMU_PMEVCNTR_EL0(28), PMU_PMEVCNTR_EL0(29), PMU_PMEVCNTR_EL0(30), /* PMEVTYPERn_EL0 */ PMU_PMEVTYPER_EL0(0), PMU_PMEVTYPER_EL0(1), PMU_PMEVTYPER_EL0(2), PMU_PMEVTYPER_EL0(3), PMU_PMEVTYPER_EL0(4), PMU_PMEVTYPER_EL0(5), PMU_PMEVTYPER_EL0(6), PMU_PMEVTYPER_EL0(7), PMU_PMEVTYPER_EL0(8), PMU_PMEVTYPER_EL0(9), PMU_PMEVTYPER_EL0(10), PMU_PMEVTYPER_EL0(11), PMU_PMEVTYPER_EL0(12), PMU_PMEVTYPER_EL0(13), PMU_PMEVTYPER_EL0(14), PMU_PMEVTYPER_EL0(15), PMU_PMEVTYPER_EL0(16), PMU_PMEVTYPER_EL0(17), PMU_PMEVTYPER_EL0(18), PMU_PMEVTYPER_EL0(19), PMU_PMEVTYPER_EL0(20), PMU_PMEVTYPER_EL0(21), PMU_PMEVTYPER_EL0(22), PMU_PMEVTYPER_EL0(23), PMU_PMEVTYPER_EL0(24), PMU_PMEVTYPER_EL0(25), PMU_PMEVTYPER_EL0(26), PMU_PMEVTYPER_EL0(27), PMU_PMEVTYPER_EL0(28), PMU_PMEVTYPER_EL0(29), PMU_PMEVTYPER_EL0(30), /* * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ { PMU_SYS_REG(PMCCFILTR_EL0), .access = access_pmu_evtyper, .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 }, EL2_REG_VNCR(VPIDR_EL2, reset_unknown, 0), EL2_REG_VNCR(VMPIDR_EL2, reset_unknown, 0), EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), EL2_REG_FILTERED(SCTLR2_EL2, access_vm_reg, reset_val, 0, sctlr2_el2_visibility), EL2_REG_VNCR(HCR_EL2, reset_hcr, 0), EL2_REG(MDCR_EL2, access_mdcr, reset_mdcr, 0), EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1), EL2_REG_VNCR(HSTR_EL2, reset_val, 0), EL2_REG_VNCR_FILT(HFGRTR_EL2, fgt_visibility), EL2_REG_VNCR_FILT(HFGWTR_EL2, fgt_visibility), EL2_REG_VNCR(HFGITR_EL2, reset_val, 0), EL2_REG_VNCR(HACR_EL2, reset_val, 0), EL2_REG_FILTERED(ZCR_EL2, access_zcr_el2, reset_val, 0, sve_el2_visibility), EL2_REG_VNCR(HCRX_EL2, reset_val, 0), EL2_REG(TTBR0_EL2, access_rw, reset_val, 0), EL2_REG(TTBR1_EL2, access_rw, reset_val, 0), EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1), EL2_REG_FILTERED(TCR2_EL2, access_rw, reset_val, TCR2_EL2_RES1, tcr2_el2_visibility), EL2_REG_VNCR(VTTBR_EL2, reset_val, 0), EL2_REG_VNCR(VTCR_EL2, reset_val, 0), EL2_REG_FILTERED(VNCR_EL2, bad_vncr_trap, reset_val, 0, vncr_el2_visibility), { SYS_DESC(SYS_DACR32_EL2), undef_access, reset_unknown, DACR32_EL2 }, EL2_REG_VNCR_FILT(HDFGRTR2_EL2, fgt2_visibility), EL2_REG_VNCR_FILT(HDFGWTR2_EL2, fgt2_visibility), EL2_REG_VNCR_FILT(HFGRTR2_EL2, fgt2_visibility), EL2_REG_VNCR_FILT(HFGWTR2_EL2, fgt2_visibility), EL2_REG_VNCR_FILT(HDFGRTR_EL2, fgt_visibility), EL2_REG_VNCR_FILT(HDFGWTR_EL2, fgt_visibility), EL2_REG_VNCR_FILT(HAFGRTR_EL2, fgt_visibility), EL2_REG_VNCR_FILT(HFGITR2_EL2, fgt2_visibility), EL2_REG_REDIR(SPSR_EL2, reset_val, 0), EL2_REG_REDIR(ELR_EL2, reset_val, 0), { SYS_DESC(SYS_SP_EL1), access_sp_el1}, /* AArch32 SPSR_* are RES0 if trapped from a NV guest */ { SYS_DESC(SYS_SPSR_irq), .access = trap_raz_wi }, { SYS_DESC(SYS_SPSR_abt), .access = trap_raz_wi }, { SYS_DESC(SYS_SPSR_und), .access = trap_raz_wi }, { SYS_DESC(SYS_SPSR_fiq), .access = trap_raz_wi }, { SYS_DESC(SYS_IFSR32_EL2), undef_access, reset_unknown, IFSR32_EL2 }, EL2_REG(AFSR0_EL2, access_rw, reset_val, 0), EL2_REG(AFSR1_EL2, access_rw, reset_val, 0), EL2_REG_REDIR(ESR_EL2, reset_val, 0), EL2_REG_VNCR(VSESR_EL2, reset_unknown, 0), { SYS_DESC(SYS_FPEXC32_EL2), undef_access, reset_val, FPEXC32_EL2, 0x700 }, EL2_REG_REDIR(FAR_EL2, reset_val, 0), EL2_REG(HPFAR_EL2, access_rw, reset_val, 0), EL2_REG(MAIR_EL2, access_rw, reset_val, 0), EL2_REG_FILTERED(PIRE0_EL2, access_rw, reset_val, 0, s1pie_el2_visibility), EL2_REG_FILTERED(PIR_EL2, access_rw, reset_val, 0, s1pie_el2_visibility), EL2_REG_FILTERED(POR_EL2, access_rw, reset_val, 0, s1poe_el2_visibility), EL2_REG(AMAIR_EL2, access_rw, reset_val, 0), { SYS_DESC(SYS_MPAMHCR_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPMV_EL2), undef_access }, { SYS_DESC(SYS_MPAM2_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM0_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM1_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM2_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM3_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM4_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM5_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM6_EL2), undef_access }, { SYS_DESC(SYS_MPAMVPM7_EL2), undef_access }, EL2_REG(VBAR_EL2, access_rw, reset_val, 0), { SYS_DESC(SYS_RVBAR_EL2), undef_access }, { SYS_DESC(SYS_RMR_EL2), undef_access }, EL2_REG_VNCR(VDISR_EL2, reset_unknown, 0), EL2_REG_VNCR_GICv3(ICH_AP0R0_EL2), EL2_REG_VNCR_GICv3(ICH_AP0R1_EL2), EL2_REG_VNCR_GICv3(ICH_AP0R2_EL2), EL2_REG_VNCR_GICv3(ICH_AP0R3_EL2), EL2_REG_VNCR_GICv3(ICH_AP1R0_EL2), EL2_REG_VNCR_GICv3(ICH_AP1R1_EL2), EL2_REG_VNCR_GICv3(ICH_AP1R2_EL2), EL2_REG_VNCR_GICv3(ICH_AP1R3_EL2), { SYS_DESC(SYS_ICC_SRE_EL2), access_gic_sre }, EL2_REG_VNCR_GICv3(ICH_HCR_EL2), { SYS_DESC(SYS_ICH_VTR_EL2), access_gic_vtr }, { SYS_DESC(SYS_ICH_MISR_EL2), access_gic_misr }, { SYS_DESC(SYS_ICH_EISR_EL2), access_gic_eisr }, { SYS_DESC(SYS_ICH_ELRSR_EL2), access_gic_elrsr }, EL2_REG_VNCR_GICv3(ICH_VMCR_EL2), EL2_REG_VNCR_GICv3(ICH_LR0_EL2), EL2_REG_VNCR_GICv3(ICH_LR1_EL2), EL2_REG_VNCR_GICv3(ICH_LR2_EL2), EL2_REG_VNCR_GICv3(ICH_LR3_EL2), EL2_REG_VNCR_GICv3(ICH_LR4_EL2), EL2_REG_VNCR_GICv3(ICH_LR5_EL2), EL2_REG_VNCR_GICv3(ICH_LR6_EL2), EL2_REG_VNCR_GICv3(ICH_LR7_EL2), EL2_REG_VNCR_GICv3(ICH_LR8_EL2), EL2_REG_VNCR_GICv3(ICH_LR9_EL2), EL2_REG_VNCR_GICv3(ICH_LR10_EL2), EL2_REG_VNCR_GICv3(ICH_LR11_EL2), EL2_REG_VNCR_GICv3(ICH_LR12_EL2), EL2_REG_VNCR_GICv3(ICH_LR13_EL2), EL2_REG_VNCR_GICv3(ICH_LR14_EL2), EL2_REG_VNCR_GICv3(ICH_LR15_EL2), EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0), EL2_REG(TPIDR_EL2, access_rw, reset_val, 0), EL2_REG_VNCR(CNTVOFF_EL2, reset_val, 0), EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0), { SYS_DESC(SYS_CNTHP_TVAL_EL2), access_arch_timer }, EL2_REG(CNTHP_CTL_EL2, access_arch_timer, reset_val, 0), EL2_REG(CNTHP_CVAL_EL2, access_arch_timer, reset_val, 0), { SYS_DESC(SYS_CNTHV_TVAL_EL2), access_hv_timer }, EL2_REG(CNTHV_CTL_EL2, access_hv_timer, reset_val, 0), EL2_REG(CNTHV_CVAL_EL2, access_hv_timer, reset_val, 0), { SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 }, { SYS_DESC(SYS_CNTP_TVAL_EL02), access_arch_timer }, { SYS_DESC(SYS_CNTP_CTL_EL02), access_arch_timer }, { SYS_DESC(SYS_CNTP_CVAL_EL02), access_arch_timer }, { SYS_DESC(SYS_CNTV_TVAL_EL02), access_arch_timer }, { SYS_DESC(SYS_CNTV_CTL_EL02), access_arch_timer }, { SYS_DESC(SYS_CNTV_CVAL_EL02), access_arch_timer }, EL2_REG(SP_EL2, NULL, reset_unknown, 0), }; static bool handle_at_s1e01(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 op = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); __kvm_at_s1e01(vcpu, op, p->regval); return true; } static bool handle_at_s1e2(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 op = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); /* There is no FGT associated with AT S1E2A :-( */ if (op == OP_AT_S1E2A && !kvm_has_feat(vcpu->kvm, ID_AA64ISAR2_EL1, ATS1A, IMP)) { kvm_inject_undefined(vcpu); return false; } __kvm_at_s1e2(vcpu, op, p->regval); return true; } static bool handle_at_s12(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 op = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); __kvm_at_s12(vcpu, op, p->regval); return true; } static bool kvm_supported_tlbi_s12_op(struct kvm_vcpu *vpcu, u32 instr) { struct kvm *kvm = vpcu->kvm; u8 CRm = sys_reg_CRm(instr); if (sys_reg_CRn(instr) == TLBI_CRn_nXS && !kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)) return false; if (CRm == TLBI_CRm_nROS && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) return false; return true; } static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); write_lock(&vcpu->kvm->mmu_lock); /* * Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the * corresponding VMIDs. */ kvm_nested_s2_unmap(vcpu->kvm, true); write_unlock(&vcpu->kvm->mmu_lock); return true; } static bool kvm_supported_tlbi_ipas2_op(struct kvm_vcpu *vpcu, u32 instr) { struct kvm *kvm = vpcu->kvm; u8 CRm = sys_reg_CRm(instr); u8 Op2 = sys_reg_Op2(instr); if (sys_reg_CRn(instr) == TLBI_CRn_nXS && !kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)) return false; if (CRm == TLBI_CRm_IPAIS && (Op2 == 2 || Op2 == 6) && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) return false; if (CRm == TLBI_CRm_IPAONS && (Op2 == 0 || Op2 == 4) && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) return false; if (CRm == TLBI_CRm_IPAONS && (Op2 == 3 || Op2 == 7) && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) return false; return true; } /* Only defined here as this is an internal "abstraction" */ union tlbi_info { struct { u64 start; u64 size; } range; struct { u64 addr; } ipa; struct { u64 addr; u32 encoding; } va; }; static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu, const union tlbi_info *info) { /* * The unmap operation is allowed to drop the MMU lock and block, which * means that @mmu could be used for a different context than the one * currently being invalidated. * * This behavior is still safe, as: * * 1) The vCPU(s) that recycled the MMU are responsible for invalidating * the entire MMU before reusing it, which still honors the intent * of a TLBI. * * 2) Until the guest TLBI instruction is 'retired' (i.e. increment PC * and ERET to the guest), other vCPUs are allowed to use stale * translations. * * 3) Accidentally unmapping an unrelated MMU context is nonfatal, and * at worst may cause more aborts for shadow stage-2 fills. * * Dropping the MMU lock also implies that shadow stage-2 fills could * happen behind the back of the TLBI. This is still safe, though, as * the L1 needs to put its stage-2 in a consistent state before doing * the TLBI. */ kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true); } static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); u64 limit, vttbr; if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); limit = BIT_ULL(kvm_get_pa_bits(vcpu->kvm)); kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr), &(union tlbi_info) { .range = { .start = 0, .size = limit, }, }, s2_mmu_unmap_range); return true; } static bool handle_ripas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); u64 base, range; if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); /* * Because the shadow S2 structure doesn't necessarily reflect that * of the guest's S2 (different base granule size, for example), we * decide to ignore TTL and only use the described range. */ base = decode_range_tlbi(p->regval, &range, NULL); kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr), &(union tlbi_info) { .range = { .start = base, .size = range, }, }, s2_mmu_unmap_range); return true; } static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu, const union tlbi_info *info) { unsigned long max_size; u64 base_addr; /* * We drop a number of things from the supplied value: * * - NS bit: we're non-secure only. * * - IPA[51:48]: We don't support 52bit IPA just yet... * * And of course, adjust the IPA to be on an actual address. */ base_addr = (info->ipa.addr & GENMASK_ULL(35, 0)) << 12; max_size = compute_tlb_inval_range(mmu, info->ipa.addr); base_addr &= ~(max_size - 1); /* * See comment in s2_mmu_unmap_range() for why this is allowed to * reschedule. */ kvm_stage2_unmap_range(mmu, base_addr, max_size, true); } static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr), &(union tlbi_info) { .ipa = { .addr = p->regval, }, }, s2_mmu_unmap_ipa); return true; } static void s2_mmu_tlbi_s1e1(struct kvm_s2_mmu *mmu, const union tlbi_info *info) { WARN_ON(__kvm_tlbi_s1e2(mmu, info->va.addr, info->va.encoding)); } static bool handle_tlbi_el2(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); if (!kvm_supported_tlbi_s1e2_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); kvm_handle_s1e2_tlbi(vcpu, sys_encoding, p->regval); return true; } static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); /* * If we're here, this is because we've trapped on a EL1 TLBI * instruction that affects the EL1 translation regime while * we're running in a context that doesn't allow us to let the * HW do its thing (aka vEL2): * * - HCR_EL2.E2H == 0 : a non-VHE guest * - HCR_EL2.{E2H,TGE} == { 1, 0 } : a VHE guest in guest mode * * Another possibility is that we are invalidating the EL2 context * using EL1 instructions, but that we landed here because we need * additional invalidation for structures that are not held in the * CPU TLBs (such as the VNCR pseudo-TLB and its EL2 mapping). In * that case, we are guaranteed that HCR_EL2.{E2H,TGE} == { 1, 1 } * as we don't allow an NV-capable L1 in a nVHE configuration. * * We don't expect these helpers to ever be called when running * in a vEL1 context. */ WARN_ON(!vcpu_is_el2(vcpu)); if (!kvm_supported_tlbi_s1e1_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) { kvm_handle_s1e2_tlbi(vcpu, sys_encoding, p->regval); return true; } kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(__vcpu_sys_reg(vcpu, VTTBR_EL2)), &(union tlbi_info) { .va = { .addr = p->regval, .encoding = sys_encoding, }, }, s2_mmu_tlbi_s1e1); return true; } #define SYS_INSN(insn, access_fn) \ { \ SYS_DESC(OP_##insn), \ .access = (access_fn), \ } static struct sys_reg_desc sys_insn_descs[] = { { SYS_DESC(SYS_DC_ISW), access_dcsw }, { SYS_DESC(SYS_DC_IGSW), access_dcgsw }, { SYS_DESC(SYS_DC_IGDSW), access_dcgsw }, SYS_INSN(AT_S1E1R, handle_at_s1e01), SYS_INSN(AT_S1E1W, handle_at_s1e01), SYS_INSN(AT_S1E0R, handle_at_s1e01), SYS_INSN(AT_S1E0W, handle_at_s1e01), SYS_INSN(AT_S1E1RP, handle_at_s1e01), SYS_INSN(AT_S1E1WP, handle_at_s1e01), { SYS_DESC(SYS_DC_CSW), access_dcsw }, { SYS_DESC(SYS_DC_CGSW), access_dcgsw }, { SYS_DESC(SYS_DC_CGDSW), access_dcgsw }, { SYS_DESC(SYS_DC_CISW), access_dcsw }, { SYS_DESC(SYS_DC_CIGSW), access_dcgsw }, { SYS_DESC(SYS_DC_CIGDSW), access_dcgsw }, SYS_INSN(TLBI_VMALLE1OS, handle_tlbi_el1), SYS_INSN(TLBI_VAE1OS, handle_tlbi_el1), SYS_INSN(TLBI_ASIDE1OS, handle_tlbi_el1), SYS_INSN(TLBI_VAAE1OS, handle_tlbi_el1), SYS_INSN(TLBI_VALE1OS, handle_tlbi_el1), SYS_INSN(TLBI_VAALE1OS, handle_tlbi_el1), SYS_INSN(TLBI_RVAE1IS, handle_tlbi_el1), SYS_INSN(TLBI_RVAAE1IS, handle_tlbi_el1), SYS_INSN(TLBI_RVALE1IS, handle_tlbi_el1), SYS_INSN(TLBI_RVAALE1IS, handle_tlbi_el1), SYS_INSN(TLBI_VMALLE1IS, handle_tlbi_el1), SYS_INSN(TLBI_VAE1IS, handle_tlbi_el1), SYS_INSN(TLBI_ASIDE1IS, handle_tlbi_el1), SYS_INSN(TLBI_VAAE1IS, handle_tlbi_el1), SYS_INSN(TLBI_VALE1IS, handle_tlbi_el1), SYS_INSN(TLBI_VAALE1IS, handle_tlbi_el1), SYS_INSN(TLBI_RVAE1OS, handle_tlbi_el1), SYS_INSN(TLBI_RVAAE1OS, handle_tlbi_el1), SYS_INSN(TLBI_RVALE1OS, handle_tlbi_el1), SYS_INSN(TLBI_RVAALE1OS, handle_tlbi_el1), SYS_INSN(TLBI_RVAE1, handle_tlbi_el1), SYS_INSN(TLBI_RVAAE1, handle_tlbi_el1), SYS_INSN(TLBI_RVALE1, handle_tlbi_el1), SYS_INSN(TLBI_RVAALE1, handle_tlbi_el1), SYS_INSN(TLBI_VMALLE1, handle_tlbi_el1), SYS_INSN(TLBI_VAE1, handle_tlbi_el1), SYS_INSN(TLBI_ASIDE1, handle_tlbi_el1), SYS_INSN(TLBI_VAAE1, handle_tlbi_el1), SYS_INSN(TLBI_VALE1, handle_tlbi_el1), SYS_INSN(TLBI_VAALE1, handle_tlbi_el1), SYS_INSN(TLBI_VMALLE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_VAE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_ASIDE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_VAAE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_VALE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_VAALE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAAE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVALE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAALE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_VMALLE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_VAE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_ASIDE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_VAAE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_VALE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_VAALE1ISNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAAE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVALE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAALE1OSNXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAAE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_RVALE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_RVAALE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_VMALLE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_VAE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_ASIDE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_VAAE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_VALE1NXS, handle_tlbi_el1), SYS_INSN(TLBI_VAALE1NXS, handle_tlbi_el1), SYS_INSN(AT_S1E2R, handle_at_s1e2), SYS_INSN(AT_S1E2W, handle_at_s1e2), SYS_INSN(AT_S12E1R, handle_at_s12), SYS_INSN(AT_S12E1W, handle_at_s12), SYS_INSN(AT_S12E0R, handle_at_s12), SYS_INSN(AT_S12E0W, handle_at_s12), SYS_INSN(AT_S1E2A, handle_at_s1e2), SYS_INSN(TLBI_IPAS2E1IS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2E1IS, handle_ripas2e1is), SYS_INSN(TLBI_IPAS2LE1IS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1IS, handle_ripas2e1is), SYS_INSN(TLBI_ALLE2OS, handle_tlbi_el2), SYS_INSN(TLBI_VAE2OS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1OS, handle_alle1is), SYS_INSN(TLBI_VALE2OS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1OS, handle_vmalls12e1is), SYS_INSN(TLBI_RVAE2IS, handle_tlbi_el2), SYS_INSN(TLBI_RVALE2IS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE2IS, handle_tlbi_el2), SYS_INSN(TLBI_VAE2IS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1IS, handle_alle1is), SYS_INSN(TLBI_VALE2IS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is), SYS_INSN(TLBI_IPAS2E1OS, handle_ipas2e1is), SYS_INSN(TLBI_IPAS2E1, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2E1, handle_ripas2e1is), SYS_INSN(TLBI_RIPAS2E1OS, handle_ripas2e1is), SYS_INSN(TLBI_IPAS2LE1OS, handle_ipas2e1is), SYS_INSN(TLBI_IPAS2LE1, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1, handle_ripas2e1is), SYS_INSN(TLBI_RIPAS2LE1OS, handle_ripas2e1is), SYS_INSN(TLBI_RVAE2OS, handle_tlbi_el2), SYS_INSN(TLBI_RVALE2OS, handle_tlbi_el2), SYS_INSN(TLBI_RVAE2, handle_tlbi_el2), SYS_INSN(TLBI_RVALE2, handle_tlbi_el2), SYS_INSN(TLBI_ALLE2, handle_tlbi_el2), SYS_INSN(TLBI_VAE2, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1, handle_alle1is), SYS_INSN(TLBI_VALE2, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is), SYS_INSN(TLBI_IPAS2E1ISNXS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2E1ISNXS, handle_ripas2e1is), SYS_INSN(TLBI_IPAS2LE1ISNXS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1ISNXS, handle_ripas2e1is), SYS_INSN(TLBI_ALLE2OSNXS, handle_tlbi_el2), SYS_INSN(TLBI_VAE2OSNXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1OSNXS, handle_alle1is), SYS_INSN(TLBI_VALE2OSNXS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1OSNXS, handle_vmalls12e1is), SYS_INSN(TLBI_RVAE2ISNXS, handle_tlbi_el2), SYS_INSN(TLBI_RVALE2ISNXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE2ISNXS, handle_tlbi_el2), SYS_INSN(TLBI_VAE2ISNXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1ISNXS, handle_alle1is), SYS_INSN(TLBI_VALE2ISNXS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1ISNXS, handle_vmalls12e1is), SYS_INSN(TLBI_IPAS2E1OSNXS, handle_ipas2e1is), SYS_INSN(TLBI_IPAS2E1NXS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2E1NXS, handle_ripas2e1is), SYS_INSN(TLBI_RIPAS2E1OSNXS, handle_ripas2e1is), SYS_INSN(TLBI_IPAS2LE1OSNXS, handle_ipas2e1is), SYS_INSN(TLBI_IPAS2LE1NXS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1NXS, handle_ripas2e1is), SYS_INSN(TLBI_RIPAS2LE1OSNXS, handle_ripas2e1is), SYS_INSN(TLBI_RVAE2OSNXS, handle_tlbi_el2), SYS_INSN(TLBI_RVALE2OSNXS, handle_tlbi_el2), SYS_INSN(TLBI_RVAE2NXS, handle_tlbi_el2), SYS_INSN(TLBI_RVALE2NXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE2NXS, handle_tlbi_el2), SYS_INSN(TLBI_VAE2NXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1NXS, handle_alle1is), SYS_INSN(TLBI_VALE2NXS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1NXS, handle_vmalls12e1is), }; static bool trap_dbgdidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { return ignore_write(vcpu, p); } else { u64 dfr = kvm_read_vm_id_reg(vcpu->kvm, SYS_ID_AA64DFR0_EL1); u32 el3 = kvm_has_feat(vcpu->kvm, ID_AA64PFR0_EL1, EL3, IMP); p->regval = ((SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr) << 28) | (SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr) << 24) | (SYS_FIELD_GET(ID_AA64DFR0_EL1, CTX_CMPs, dfr) << 20) | (SYS_FIELD_GET(ID_AA64DFR0_EL1, DebugVer, dfr) << 16) | (1 << 15) | (el3 << 14) | (el3 << 12)); return true; } } /* * AArch32 debug register mappings * * AArch32 DBGBVRn is mapped to DBGBVRn_EL1[31:0] * AArch32 DBGBXVRn is mapped to DBGBVRn_EL1[63:32] * * None of the other registers share their location, so treat them as * if they were 64bit. */ #define DBG_BCR_BVR_WCR_WVR(n) \ /* DBGBVRn */ \ { AA32(LO), Op1( 0), CRn( 0), CRm((n)), Op2( 4), \ trap_dbg_wb_reg, NULL, n }, \ /* DBGBCRn */ \ { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_dbg_wb_reg, NULL, n }, \ /* DBGWVRn */ \ { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_dbg_wb_reg, NULL, n }, \ /* DBGWCRn */ \ { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_dbg_wb_reg, NULL, n } #define DBGBXVR(n) \ { AA32(HI), Op1( 0), CRn( 1), CRm((n)), Op2( 1), \ trap_dbg_wb_reg, NULL, n } /* * Trapped cp14 registers. We generally ignore most of the external * debug, on the principle that they don't really make sense to a * guest. Revisit this one day, would this principle change. */ static const struct sys_reg_desc cp14_regs[] = { /* DBGDIDR */ { Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgdidr }, /* DBGDTRRXext */ { Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(0), /* DBGDSCRint */ { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(1), /* DBGDCCINT */ { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug_regs, NULL, MDCCINT_EL1 }, /* DBGDSCRext */ { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug_regs, NULL, MDSCR_EL1 }, DBG_BCR_BVR_WCR_WVR(2), /* DBGDTR[RT]Xint */ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi }, /* DBGDTR[RT]Xext */ { Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(3), DBG_BCR_BVR_WCR_WVR(4), DBG_BCR_BVR_WCR_WVR(5), /* DBGWFAR */ { Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi }, /* DBGOSECCR */ { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(6), /* DBGVCR */ { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug_regs, NULL, DBGVCR32_EL2 }, DBG_BCR_BVR_WCR_WVR(7), DBG_BCR_BVR_WCR_WVR(8), DBG_BCR_BVR_WCR_WVR(9), DBG_BCR_BVR_WCR_WVR(10), DBG_BCR_BVR_WCR_WVR(11), DBG_BCR_BVR_WCR_WVR(12), DBG_BCR_BVR_WCR_WVR(13), DBG_BCR_BVR_WCR_WVR(14), DBG_BCR_BVR_WCR_WVR(15), /* DBGDRAR (32bit) */ { Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi }, DBGBXVR(0), /* DBGOSLAR */ { Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_oslar_el1 }, DBGBXVR(1), /* DBGOSLSR */ { Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1, NULL, OSLSR_EL1 }, DBGBXVR(2), DBGBXVR(3), /* DBGOSDLR */ { Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi }, DBGBXVR(4), /* DBGPRCR */ { Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi }, DBGBXVR(5), DBGBXVR(6), DBGBXVR(7), DBGBXVR(8), DBGBXVR(9), DBGBXVR(10), DBGBXVR(11), DBGBXVR(12), DBGBXVR(13), DBGBXVR(14), DBGBXVR(15), /* DBGDSAR (32bit) */ { Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi }, /* DBGDEVID2 */ { Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi }, /* DBGDEVID1 */ { Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi }, /* DBGDEVID */ { Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi }, /* DBGCLAIMSET */ { Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi }, /* DBGCLAIMCLR */ { Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi }, /* DBGAUTHSTATUS */ { Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 }, }; /* Trapped cp14 64bit registers */ static const struct sys_reg_desc cp14_64_regs[] = { /* DBGDRAR (64bit) */ { Op1( 0), CRm( 1), .access = trap_raz_wi }, /* DBGDSAR (64bit) */ { Op1( 0), CRm( 2), .access = trap_raz_wi }, }; #define CP15_PMU_SYS_REG(_map, _Op1, _CRn, _CRm, _Op2) \ AA32(_map), \ Op1(_Op1), CRn(_CRn), CRm(_CRm), Op2(_Op2), \ .visibility = pmu_visibility /* Macro to expand the PMEVCNTRn register */ #define PMU_PMEVCNTR(n) \ { CP15_PMU_SYS_REG(DIRECT, 0, 0b1110, \ (0b1000 | (((n) >> 3) & 0x3)), ((n) & 0x7)), \ .access = access_pmu_evcntr } /* Macro to expand the PMEVTYPERn register */ #define PMU_PMEVTYPER(n) \ { CP15_PMU_SYS_REG(DIRECT, 0, 0b1110, \ (0b1100 | (((n) >> 3) & 0x3)), ((n) & 0x7)), \ .access = access_pmu_evtyper } /* * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding, * depending on the way they are accessed (as a 32bit or a 64bit * register). */ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr }, { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, SCTLR_EL1 }, /* ACTLR */ { AA32(LO), Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr, NULL, ACTLR_EL1 }, /* ACTLR2 */ { AA32(HI), Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr, NULL, ACTLR_EL1 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, TTBR1_EL1 }, /* TTBCR */ { AA32(LO), Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, TCR_EL1 }, /* TTBCR2 */ { AA32(HI), Op1( 0), CRn( 2), CRm( 0), Op2( 3), access_vm_reg, NULL, TCR_EL1 }, { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, DACR32_EL2 }, { CP15_SYS_DESC(SYS_ICC_PMR_EL1), undef_access }, /* DFSR */ { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, ESR_EL1 }, { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, IFSR32_EL2 }, /* ADFSR */ { Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, AFSR0_EL1 }, /* AIFSR */ { Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, AFSR1_EL1 }, /* DFAR */ { AA32(LO), Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, FAR_EL1 }, /* IFAR */ { AA32(HI), Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, FAR_EL1 }, /* * DC{C,I,CI}SW operations: */ { Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw }, { Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw }, { Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw }, /* PMU */ { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 0), .access = access_pmcr }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 1), .access = access_pmcnten }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 2), .access = access_pmcnten }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 3), .access = access_pmovs }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 4), .access = access_pmswinc }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 5), .access = access_pmselr }, { CP15_PMU_SYS_REG(LO, 0, 9, 12, 6), .access = access_pmceid }, { CP15_PMU_SYS_REG(LO, 0, 9, 12, 7), .access = access_pmceid }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 0), .access = access_pmu_evcntr }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 1), .access = access_pmu_evtyper }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 2), .access = access_pmu_evcntr }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 0), .access = access_pmuserenr }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 1), .access = access_pminten }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 2), .access = access_pminten }, { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 3), .access = access_pmovs }, { CP15_PMU_SYS_REG(HI, 0, 9, 14, 4), .access = access_pmceid }, { CP15_PMU_SYS_REG(HI, 0, 9, 14, 5), .access = access_pmceid }, /* PMMIR */ { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 6), .access = trap_raz_wi }, /* PRRR/MAIR0 */ { AA32(LO), Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, MAIR_EL1 }, /* NMRR/MAIR1 */ { AA32(HI), Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, MAIR_EL1 }, /* AMAIR0 */ { AA32(LO), Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, AMAIR_EL1 }, /* AMAIR1 */ { AA32(HI), Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, AMAIR_EL1 }, { CP15_SYS_DESC(SYS_ICC_IAR0_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_EOIR0_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_HPPIR0_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_BPR0_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP0R0_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP0R1_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP0R2_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP0R3_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP1R0_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP1R1_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP1R2_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_AP1R3_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_DIR_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_RPR_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_IAR1_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_EOIR1_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_HPPIR1_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_BPR1_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_CTLR_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_SRE_EL1), access_gic_sre }, { CP15_SYS_DESC(SYS_ICC_IGRPEN0_EL1), undef_access }, { CP15_SYS_DESC(SYS_ICC_IGRPEN1_EL1), undef_access }, { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, CONTEXTIDR_EL1 }, /* Arch Tmers */ { SYS_DESC(SYS_AARCH32_CNTP_TVAL), access_arch_timer }, { SYS_DESC(SYS_AARCH32_CNTP_CTL), access_arch_timer }, /* PMEVCNTRn */ PMU_PMEVCNTR(0), PMU_PMEVCNTR(1), PMU_PMEVCNTR(2), PMU_PMEVCNTR(3), PMU_PMEVCNTR(4), PMU_PMEVCNTR(5), PMU_PMEVCNTR(6), PMU_PMEVCNTR(7), PMU_PMEVCNTR(8), PMU_PMEVCNTR(9), PMU_PMEVCNTR(10), PMU_PMEVCNTR(11), PMU_PMEVCNTR(12), PMU_PMEVCNTR(13), PMU_PMEVCNTR(14), PMU_PMEVCNTR(15), PMU_PMEVCNTR(16), PMU_PMEVCNTR(17), PMU_PMEVCNTR(18), PMU_PMEVCNTR(19), PMU_PMEVCNTR(20), PMU_PMEVCNTR(21), PMU_PMEVCNTR(22), PMU_PMEVCNTR(23), PMU_PMEVCNTR(24), PMU_PMEVCNTR(25), PMU_PMEVCNTR(26), PMU_PMEVCNTR(27), PMU_PMEVCNTR(28), PMU_PMEVCNTR(29), PMU_PMEVCNTR(30), /* PMEVTYPERn */ PMU_PMEVTYPER(0), PMU_PMEVTYPER(1), PMU_PMEVTYPER(2), PMU_PMEVTYPER(3), PMU_PMEVTYPER(4), PMU_PMEVTYPER(5), PMU_PMEVTYPER(6), PMU_PMEVTYPER(7), PMU_PMEVTYPER(8), PMU_PMEVTYPER(9), PMU_PMEVTYPER(10), PMU_PMEVTYPER(11), PMU_PMEVTYPER(12), PMU_PMEVTYPER(13), PMU_PMEVTYPER(14), PMU_PMEVTYPER(15), PMU_PMEVTYPER(16), PMU_PMEVTYPER(17), PMU_PMEVTYPER(18), PMU_PMEVTYPER(19), PMU_PMEVTYPER(20), PMU_PMEVTYPER(21), PMU_PMEVTYPER(22), PMU_PMEVTYPER(23), PMU_PMEVTYPER(24), PMU_PMEVTYPER(25), PMU_PMEVTYPER(26), PMU_PMEVTYPER(27), PMU_PMEVTYPER(28), PMU_PMEVTYPER(29), PMU_PMEVTYPER(30), /* PMCCFILTR */ { CP15_PMU_SYS_REG(DIRECT, 0, 14, 15, 7), .access = access_pmu_evtyper }, { Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr }, { Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr }, /* CCSIDR2 */ { Op1(1), CRn( 0), CRm( 0), Op2(2), undef_access }, { Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, CSSELR_EL1 }, }; static const struct sys_reg_desc cp15_64_regs[] = { { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 }, { CP15_PMU_SYS_REG(DIRECT, 0, 0, 9, 0), .access = access_pmu_evcntr }, { Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI1R */ { SYS_DESC(SYS_AARCH32_CNTPCT), access_arch_timer }, { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 }, { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ { SYS_DESC(SYS_AARCH32_CNTVCT), access_arch_timer }, { Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */ { SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer }, { SYS_DESC(SYS_AARCH32_CNTPCTSS), access_arch_timer }, { SYS_DESC(SYS_AARCH32_CNTVCTSS), access_arch_timer }, }; static bool check_sysreg_table(const struct sys_reg_desc *table, unsigned int n, bool reset_check) { unsigned int i; for (i = 0; i < n; i++) { if (reset_check && table[i].reg && !table[i].reset) { kvm_err("sys_reg table %pS entry %d (%s) lacks reset\n", &table[i], i, table[i].name); return false; } if (i && cmp_sys_reg(&table[i-1], &table[i]) >= 0) { kvm_err("sys_reg table %pS entry %d (%s -> %s) out of order\n", &table[i], i, table[i - 1].name, table[i].name); return false; } } return true; } int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu) { kvm_inject_undefined(vcpu); return 1; } static void perform_access(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r) { trace_kvm_sys_access(*vcpu_pc(vcpu), params, r); /* Check for regs disabled by runtime config */ if (sysreg_hidden(vcpu, r)) { kvm_inject_undefined(vcpu); return; } /* * Not having an accessor means that we have configured a trap * that we don't know how to handle. This certainly qualifies * as a gross bug that should be fixed right away. */ BUG_ON(!r->access); /* Skip instruction if instructed so */ if (likely(r->access(vcpu, params, r))) kvm_incr_pc(vcpu); } /* * emulate_cp -- tries to match a sys_reg access in a handling table, and * call the corresponding trap handler. * * @params: pointer to the descriptor of the access * @table: array of trap descriptors * @num: size of the trap descriptor array * * Return true if the access has been handled, false if not. */ static bool emulate_cp(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *table, size_t num) { const struct sys_reg_desc *r; if (!table) return false; /* Not handled */ r = find_reg(params, table, num); if (r) { perform_access(vcpu, params, r); return true; } /* Not handled */ return false; } static void unhandled_cp_access(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { u8 esr_ec = kvm_vcpu_trap_get_class(vcpu); int cp = -1; switch (esr_ec) { case ESR_ELx_EC_CP15_32: case ESR_ELx_EC_CP15_64: cp = 15; break; case ESR_ELx_EC_CP14_MR: case ESR_ELx_EC_CP14_64: cp = 14; break; default: WARN_ON(1); } print_sys_reg_msg(params, "Unsupported guest CP%d access at: %08lx [%08lx]\n", cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); } /** * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP14/CP15 access * @vcpu: The VCPU pointer * @global: &struct sys_reg_desc * @nr_global: size of the @global array */ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, const struct sys_reg_desc *global, size_t nr_global) { struct sys_reg_params params; u64 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); int Rt2 = (esr >> 10) & 0x1f; params.CRm = (esr >> 1) & 0xf; params.is_write = ((esr & 1) == 0); params.Op0 = 0; params.Op1 = (esr >> 16) & 0xf; params.Op2 = 0; params.CRn = 0; /* * Make a 64-bit value out of Rt and Rt2. As we use the same trap * backends between AArch32 and AArch64, we get away with it. */ if (params.is_write) { params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff; params.regval |= vcpu_get_reg(vcpu, Rt2) << 32; } /* * If the table contains a handler, handle the * potential register operation in the case of a read and return * with success. */ if (emulate_cp(vcpu, ¶ms, global, nr_global)) { /* Split up the value between registers for the read side */ if (!params.is_write) { vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval)); vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval)); } return 1; } unhandled_cp_access(vcpu, ¶ms); return 1; } static bool emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params); /* * The CP10 ID registers are architecturally mapped to AArch64 feature * registers. Abuse that fact so we can rely on the AArch64 handler for accesses * from AArch32. */ static bool kvm_esr_cp10_id_to_sys64(u64 esr, struct sys_reg_params *params) { u8 reg_id = (esr >> 10) & 0xf; bool valid; params->is_write = ((esr & 1) == 0); params->Op0 = 3; params->Op1 = 0; params->CRn = 0; params->CRm = 3; /* CP10 ID registers are read-only */ valid = !params->is_write; switch (reg_id) { /* MVFR0 */ case 0b0111: params->Op2 = 0; break; /* MVFR1 */ case 0b0110: params->Op2 = 1; break; /* MVFR2 */ case 0b0101: params->Op2 = 2; break; default: valid = false; } if (valid) return true; kvm_pr_unimpl("Unhandled cp10 register %s: %u\n", str_write_read(params->is_write), reg_id); return false; } /** * kvm_handle_cp10_id() - Handles a VMRS trap on guest access to a 'Media and * VFP Register' from AArch32. * @vcpu: The vCPU pointer * * MVFR{0-2} are architecturally mapped to the AArch64 MVFR{0-2}_EL1 registers. * Work out the correct AArch64 system register encoding and reroute to the * AArch64 system register emulation. */ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu) { int Rt = kvm_vcpu_sys_get_rt(vcpu); u64 esr = kvm_vcpu_get_esr(vcpu); struct sys_reg_params params; /* UNDEF on any unhandled register access */ if (!kvm_esr_cp10_id_to_sys64(esr, ¶ms)) { kvm_inject_undefined(vcpu); return 1; } if (emulate_sys_reg(vcpu, ¶ms)) vcpu_set_reg(vcpu, Rt, params.regval); return 1; } /** * kvm_emulate_cp15_id_reg() - Handles an MRC trap on a guest CP15 access where * CRn=0, which corresponds to the AArch32 feature * registers. * @vcpu: the vCPU pointer * @params: the system register access parameters. * * Our cp15 system register tables do not enumerate the AArch32 feature * registers. Conveniently, our AArch64 table does, and the AArch32 system * register encoding can be trivially remapped into the AArch64 for the feature * registers: Append op0=3, leaving op1, CRn, CRm, and op2 the same. * * According to DDI0487G.b G7.3.1, paragraph "Behavior of VMSAv8-32 32-bit * System registers with (coproc=0b1111, CRn==c0)", read accesses from this * range are either UNKNOWN or RES0. Rerouting remains architectural as we * treat undefined registers in this range as RAZ. */ static int kvm_emulate_cp15_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { int Rt = kvm_vcpu_sys_get_rt(vcpu); /* Treat impossible writes to RO registers as UNDEFINED */ if (params->is_write) { unhandled_cp_access(vcpu, params); return 1; } params->Op0 = 3; /* * All registers where CRm > 3 are known to be UNKNOWN/RAZ from AArch32. * Avoid conflicting with future expansion of AArch64 feature registers * and simply treat them as RAZ here. */ if (params->CRm > 3) params->regval = 0; else if (!emulate_sys_reg(vcpu, params)) return 1; vcpu_set_reg(vcpu, Rt, params->regval); return 1; } /** * kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access * @vcpu: The VCPU pointer * @params: &struct sys_reg_params * @global: &struct sys_reg_desc * @nr_global: size of the @global array */ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *global, size_t nr_global) { int Rt = kvm_vcpu_sys_get_rt(vcpu); params->regval = vcpu_get_reg(vcpu, Rt); if (emulate_cp(vcpu, params, global, nr_global)) { if (!params->is_write) vcpu_set_reg(vcpu, Rt, params->regval); return 1; } unhandled_cp_access(vcpu, params); return 1; } int kvm_handle_cp15_64(struct kvm_vcpu *vcpu) { return kvm_handle_cp_64(vcpu, cp15_64_regs, ARRAY_SIZE(cp15_64_regs)); } int kvm_handle_cp15_32(struct kvm_vcpu *vcpu) { struct sys_reg_params params; params = esr_cp1x_32_to_params(kvm_vcpu_get_esr(vcpu)); /* * Certain AArch32 ID registers are handled by rerouting to the AArch64 * system register table. Registers in the ID range where CRm=0 are * excluded from this scheme as they do not trivially map into AArch64 * system register encodings, except for AIDR/REVIDR. */ if (params.Op1 == 0 && params.CRn == 0 && (params.CRm || params.Op2 == 6 /* REVIDR */)) return kvm_emulate_cp15_id_reg(vcpu, ¶ms); if (params.Op1 == 1 && params.CRn == 0 && params.CRm == 0 && params.Op2 == 7 /* AIDR */) return kvm_emulate_cp15_id_reg(vcpu, ¶ms); return kvm_handle_cp_32(vcpu, ¶ms, cp15_regs, ARRAY_SIZE(cp15_regs)); } int kvm_handle_cp14_64(struct kvm_vcpu *vcpu) { return kvm_handle_cp_64(vcpu, cp14_64_regs, ARRAY_SIZE(cp14_64_regs)); } int kvm_handle_cp14_32(struct kvm_vcpu *vcpu) { struct sys_reg_params params; params = esr_cp1x_32_to_params(kvm_vcpu_get_esr(vcpu)); return kvm_handle_cp_32(vcpu, ¶ms, cp14_regs, ARRAY_SIZE(cp14_regs)); } /** * emulate_sys_reg - Emulate a guest access to an AArch64 system register * @vcpu: The VCPU pointer * @params: Decoded system register parameters * * Return: true if the system register access was successful, false otherwise. */ static bool emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { const struct sys_reg_desc *r; r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); if (likely(r)) { perform_access(vcpu, params, r); return true; } print_sys_reg_msg(params, "Unsupported guest sys_reg access at: %lx [%08lx]\n", *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); return false; } static const struct sys_reg_desc *idregs_debug_find(struct kvm *kvm, u8 pos) { unsigned long i, idreg_idx = 0; for (i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) { const struct sys_reg_desc *r = &sys_reg_descs[i]; if (!is_vm_ftr_id_reg(reg_to_encoding(r))) continue; if (idreg_idx == pos) return r; idreg_idx++; } return NULL; } static void *idregs_debug_start(struct seq_file *s, loff_t *pos) { struct kvm *kvm = s->private; u8 *iter; mutex_lock(&kvm->arch.config_lock); iter = &kvm->arch.idreg_debugfs_iter; if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags) && *iter == (u8)~0) { *iter = *pos; if (!idregs_debug_find(kvm, *iter)) iter = NULL; } else { iter = ERR_PTR(-EBUSY); } mutex_unlock(&kvm->arch.config_lock); return iter; } static void *idregs_debug_next(struct seq_file *s, void *v, loff_t *pos) { struct kvm *kvm = s->private; (*pos)++; if (idregs_debug_find(kvm, kvm->arch.idreg_debugfs_iter + 1)) { kvm->arch.idreg_debugfs_iter++; return &kvm->arch.idreg_debugfs_iter; } return NULL; } static void idregs_debug_stop(struct seq_file *s, void *v) { struct kvm *kvm = s->private; if (IS_ERR(v)) return; mutex_lock(&kvm->arch.config_lock); kvm->arch.idreg_debugfs_iter = ~0; mutex_unlock(&kvm->arch.config_lock); } static int idregs_debug_show(struct seq_file *s, void *v) { const struct sys_reg_desc *desc; struct kvm *kvm = s->private; desc = idregs_debug_find(kvm, kvm->arch.idreg_debugfs_iter); if (!desc->name) return 0; seq_printf(s, "%20s:\t%016llx\n", desc->name, kvm_read_vm_id_reg(kvm, reg_to_encoding(desc))); return 0; } static const struct seq_operations idregs_debug_sops = { .start = idregs_debug_start, .next = idregs_debug_next, .stop = idregs_debug_stop, .show = idregs_debug_show, }; DEFINE_SEQ_ATTRIBUTE(idregs_debug); void kvm_sys_regs_create_debugfs(struct kvm *kvm) { kvm->arch.idreg_debugfs_iter = ~0; debugfs_create_file("idregs", 0444, kvm->debugfs_dentry, kvm, &idregs_debug_fops); } static void reset_vm_ftr_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *reg) { u32 id = reg_to_encoding(reg); struct kvm *kvm = vcpu->kvm; if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags)) return; kvm_set_vm_id_reg(kvm, id, reg->reset(vcpu, reg)); } static void reset_vcpu_ftr_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *reg) { if (kvm_vcpu_initialized(vcpu)) return; reg->reset(vcpu, reg); } /** * kvm_reset_sys_regs - sets system registers to reset value * @vcpu: The VCPU pointer * * This function finds the right table above and sets the registers on the * virtual CPU struct to their architecturally defined reset values. */ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; unsigned long i; for (i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) { const struct sys_reg_desc *r = &sys_reg_descs[i]; if (!r->reset) continue; if (is_vm_ftr_id_reg(reg_to_encoding(r))) reset_vm_ftr_id_reg(vcpu, r); else if (is_vcpu_ftr_id_reg(reg_to_encoding(r))) reset_vcpu_ftr_id_reg(vcpu, r); else r->reset(vcpu, r); if (r->reg >= __SANITISED_REG_START__ && r->reg < NR_SYS_REGS) __vcpu_rmw_sys_reg(vcpu, r->reg, |=, 0); } set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags); if (kvm_vcpu_has_pmu(vcpu)) kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); } /** * kvm_handle_sys_reg -- handles a system instruction or mrs/msr instruction * trap on a guest execution * @vcpu: The VCPU pointer */ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu) { const struct sys_reg_desc *desc = NULL; struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); int sr_idx; trace_kvm_handle_sys_reg(esr); if (triage_sysreg_trap(vcpu, &sr_idx)) return 1; params = esr_sys64_to_params(esr); params.regval = vcpu_get_reg(vcpu, Rt); /* System registers have Op0=={2,3}, as per DDI487 J.a C5.1.2 */ if (params.Op0 == 2 || params.Op0 == 3) desc = &sys_reg_descs[sr_idx]; else desc = &sys_insn_descs[sr_idx]; perform_access(vcpu, ¶ms, desc); /* Read from system register? */ if (!params.is_write && (params.Op0 == 2 || params.Op0 == 3)) vcpu_set_reg(vcpu, Rt, params.regval); return 1; } /****************************************************************************** * Userspace API *****************************************************************************/ static bool index_to_params(u64 id, struct sys_reg_params *params) { switch (id & KVM_REG_SIZE_MASK) { case KVM_REG_SIZE_U64: /* Any unused index bits means it's not valid. */ if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK | KVM_REG_ARM64_SYSREG_OP0_MASK | KVM_REG_ARM64_SYSREG_OP1_MASK | KVM_REG_ARM64_SYSREG_CRN_MASK | KVM_REG_ARM64_SYSREG_CRM_MASK | KVM_REG_ARM64_SYSREG_OP2_MASK)) return false; params->Op0 = ((id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT); params->Op1 = ((id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT); params->CRn = ((id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT); params->CRm = ((id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT); params->Op2 = ((id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT); return true; default: return false; } } const struct sys_reg_desc *get_reg_by_id(u64 id, const struct sys_reg_desc table[], unsigned int num) { struct sys_reg_params params; if (!index_to_params(id, ¶ms)) return NULL; return find_reg(¶ms, table, num); } /* Decode an index value, and find the sys_reg_desc entry. */ static const struct sys_reg_desc * id_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id, const struct sys_reg_desc table[], unsigned int num) { const struct sys_reg_desc *r; /* We only do sys_reg for now. */ if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG) return NULL; r = get_reg_by_id(id, table, num); /* Not saved in the sys_reg array and not otherwise accessible? */ if (r && (!(r->reg || r->get_user) || sysreg_hidden(vcpu, r))) r = NULL; return r; } static int demux_c15_get(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) { u32 val; u32 __user *uval = uaddr; /* Fail if we have unknown bits set. */ if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) return -ENOENT; switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { case KVM_REG_ARM_DEMUX_ID_CCSIDR: if (KVM_REG_SIZE(id) != 4) return -ENOENT; val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) >> KVM_REG_ARM_DEMUX_VAL_SHIFT; if (val >= CSSELR_MAX) return -ENOENT; return put_user(get_ccsidr(vcpu, val), uval); default: return -ENOENT; } } static int demux_c15_set(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) { u32 val, newval; u32 __user *uval = uaddr; /* Fail if we have unknown bits set. */ if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) return -ENOENT; switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { case KVM_REG_ARM_DEMUX_ID_CCSIDR: if (KVM_REG_SIZE(id) != 4) return -ENOENT; val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) >> KVM_REG_ARM_DEMUX_VAL_SHIFT; if (val >= CSSELR_MAX) return -ENOENT; if (get_user(newval, uval)) return -EFAULT; return set_ccsidr(vcpu, val, newval); default: return -ENOENT; } } int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num) { u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr; const struct sys_reg_desc *r; u64 val; int ret; r = id_to_sys_reg_desc(vcpu, reg->id, table, num); if (!r || sysreg_hidden(vcpu, r)) return -ENOENT; if (r->get_user) { ret = (r->get_user)(vcpu, r, &val); } else { val = __vcpu_sys_reg(vcpu, r->reg); ret = 0; } if (!ret) ret = put_user(val, uaddr); return ret; } int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(unsigned long)reg->addr; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) return demux_c15_get(vcpu, reg->id, uaddr); return kvm_sys_reg_get_user(vcpu, reg, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); } int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num) { u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr; const struct sys_reg_desc *r; u64 val; int ret; if (get_user(val, uaddr)) return -EFAULT; r = id_to_sys_reg_desc(vcpu, reg->id, table, num); if (!r || sysreg_hidden(vcpu, r)) return -ENOENT; if (sysreg_user_write_ignore(vcpu, r)) return 0; if (r->set_user) { ret = (r->set_user)(vcpu, r, val); } else { __vcpu_assign_sys_reg(vcpu, r->reg, val); ret = 0; } return ret; } int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(unsigned long)reg->addr; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) return demux_c15_set(vcpu, reg->id, uaddr); return kvm_sys_reg_set_user(vcpu, reg, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); } static unsigned int num_demux_regs(void) { return CSSELR_MAX; } static int write_demux_regids(u64 __user *uindices) { u64 val = KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX; unsigned int i; val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; for (i = 0; i < CSSELR_MAX; i++) { if (put_user(val | i, uindices)) return -EFAULT; uindices++; } return 0; } static u64 sys_reg_to_index(const struct sys_reg_desc *reg) { return (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM64_SYSREG | (reg->Op0 << KVM_REG_ARM64_SYSREG_OP0_SHIFT) | (reg->Op1 << KVM_REG_ARM64_SYSREG_OP1_SHIFT) | (reg->CRn << KVM_REG_ARM64_SYSREG_CRN_SHIFT) | (reg->CRm << KVM_REG_ARM64_SYSREG_CRM_SHIFT) | (reg->Op2 << KVM_REG_ARM64_SYSREG_OP2_SHIFT)); } static bool copy_reg_to_user(const struct sys_reg_desc *reg, u64 __user **uind) { if (!*uind) return true; if (put_user(sys_reg_to_index(reg), *uind)) return false; (*uind)++; return true; } static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 __user **uind, unsigned int *total) { /* * Ignore registers we trap but don't save, * and for which no custom user accessor is provided. */ if (!(rd->reg || rd->get_user)) return 0; if (sysreg_hidden(vcpu, rd)) return 0; if (!copy_reg_to_user(rd, uind)) return -EFAULT; (*total)++; return 0; } /* Assumed ordered tables, see kvm_sys_reg_table_init. */ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind) { const struct sys_reg_desc *i2, *end2; unsigned int total = 0; int err; i2 = sys_reg_descs; end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs); while (i2 != end2) { err = walk_one_sys_reg(vcpu, i2++, &uind, &total); if (err) return err; } return total; } unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu) { return num_demux_regs() + walk_sys_regs(vcpu, (u64 __user *)NULL); } int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { int err; err = walk_sys_regs(vcpu, uindices); if (err < 0) return err; uindices += err; return write_demux_regids(uindices); } #define KVM_ARM_FEATURE_ID_RANGE_INDEX(r) \ KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(r), \ sys_reg_Op1(r), \ sys_reg_CRn(r), \ sys_reg_CRm(r), \ sys_reg_Op2(r)) int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range) { const void *zero_page = page_to_virt(ZERO_PAGE(0)); u64 __user *masks = (u64 __user *)range->addr; /* Only feature id range is supported, reserved[13] must be zero. */ if (range->range || memcmp(range->reserved, zero_page, sizeof(range->reserved))) return -EINVAL; /* Wipe the whole thing first */ if (clear_user(masks, KVM_ARM_FEATURE_ID_RANGE_SIZE * sizeof(__u64))) return -EFAULT; for (int i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) { const struct sys_reg_desc *reg = &sys_reg_descs[i]; u32 encoding = reg_to_encoding(reg); u64 val; if (!is_feature_id_reg(encoding) || !reg->set_user) continue; if (!reg->val || (is_aa32_id_reg(encoding) && !kvm_supports_32bit_el0())) { continue; } val = reg->val; if (put_user(val, (masks + KVM_ARM_FEATURE_ID_RANGE_INDEX(encoding)))) return -EFAULT; } return 0; } static void vcpu_set_hcr(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; if (has_vhe() || has_hvhe()) vcpu->arch.hcr_el2 |= HCR_E2H; if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) { /* route synchronous external abort exceptions to EL2 */ vcpu->arch.hcr_el2 |= HCR_TEA; /* trap error record accesses */ vcpu->arch.hcr_el2 |= HCR_TERR; } if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) vcpu->arch.hcr_el2 |= HCR_FWB; if (cpus_have_final_cap(ARM64_HAS_EVT) && !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE) && kvm_read_vm_id_reg(kvm, SYS_CTR_EL0) == read_sanitised_ftr_reg(SYS_CTR_EL0)) vcpu->arch.hcr_el2 |= HCR_TID4; else vcpu->arch.hcr_el2 |= HCR_TID2; if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; if (kvm_has_mte(vcpu->kvm)) vcpu->arch.hcr_el2 |= HCR_ATA; /* * In the absence of FGT, we cannot independently trap TLBI * Range instructions. This isn't great, but trapping all * TLBIs would be far worse. Live with it... */ if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) vcpu->arch.hcr_el2 |= HCR_TTLBOS; } void kvm_calculate_traps(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; mutex_lock(&kvm->arch.config_lock); vcpu_set_hcr(vcpu); vcpu_set_ich_hcr(vcpu); vcpu_set_hcrx(vcpu); if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags)) goto out; compute_fgu(kvm, HFGRTR_GROUP); compute_fgu(kvm, HFGITR_GROUP); compute_fgu(kvm, HDFGRTR_GROUP); compute_fgu(kvm, HAFGRTR_GROUP); compute_fgu(kvm, HFGRTR2_GROUP); compute_fgu(kvm, HFGITR2_GROUP); compute_fgu(kvm, HDFGRTR2_GROUP); set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags); out: mutex_unlock(&kvm->arch.config_lock); } /* * Perform last adjustments to the ID registers that are implied by the * configuration outside of the ID regs themselves, as well as any * initialisation that directly depend on these ID registers (such as * RES0/RES1 behaviours). This is not the place to configure traps though. * * Because this can be called once per CPU, changes must be idempotent. */ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; guard(mutex)(&kvm->arch.config_lock); if (!(static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) && irqchip_in_kernel(kvm) && kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)) { kvm->arch.id_regs[IDREG_IDX(SYS_ID_AA64PFR0_EL1)] &= ~ID_AA64PFR0_EL1_GIC_MASK; kvm->arch.id_regs[IDREG_IDX(SYS_ID_PFR1_EL1)] &= ~ID_PFR1_EL1_GIC_MASK; } if (vcpu_has_nv(vcpu)) { int ret = kvm_init_nv_sysregs(vcpu); if (ret) return ret; } return 0; } int __init kvm_sys_reg_table_init(void) { const struct sys_reg_desc *gicv3_regs; bool valid = true; unsigned int i, sz; int ret = 0; /* Make sure tables are unique and in order. */ valid &= check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), true); valid &= check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs), false); valid &= check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs), false); valid &= check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), false); valid &= check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), false); valid &= check_sysreg_table(sys_insn_descs, ARRAY_SIZE(sys_insn_descs), false); gicv3_regs = vgic_v3_get_sysreg_table(&sz); valid &= check_sysreg_table(gicv3_regs, sz, false); if (!valid) return -EINVAL; init_imp_id_regs(); ret = populate_nv_trap_config(); check_feature_map(); for (i = 0; !ret && i < ARRAY_SIZE(sys_reg_descs); i++) ret = populate_sysreg_config(sys_reg_descs + i, i); for (i = 0; !ret && i < ARRAY_SIZE(sys_insn_descs); i++) ret = populate_sysreg_config(sys_insn_descs + i, i); return ret; } |
| 255 255 255 254 255 255 187 187 5 5 5 255 255 255 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.c - library routines for handling generic kernel objects * * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2007 Novell Inc. * * Please see the file Documentation/core-api/kobject.rst for critical information * about using the kobject interface. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/random.h> /** * kobject_namespace() - Return @kobj's namespace tag. * @kobj: kobject in question * * Returns namespace tag of @kobj if its parent has namespace ops enabled * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ const void *kobject_namespace(const struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE) return NULL; return kobj->ktype->namespace(kobj); } /** * kobject_get_ownership() - Get sysfs ownership data for @kobj. * @kobj: kobject in question * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns initial uid/gid pair that should be used when creating sysfs * representation of given kobject. Normally used to adjust ownership of * objects in a container. */ void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; if (kobj->ktype->get_ownership) kobj->ktype->get_ownership(kobj, uid, gid); } static bool kobj_ns_type_is_valid(enum kobj_ns_type type) { if ((type <= KOBJ_NS_TYPE_NONE) || (type >= KOBJ_NS_TYPES)) return false; return true; } static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); if (error) return error; if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { sysfs_remove_dir(kobj); return error; } } /* * @kobj->sd may be deleted by an ancestor going away. Hold an * extra reference so that it stays until @kobj is gone. */ sysfs_get(kobj->sd); /* * If @kobj has ns_ops, its children need to be filtered based on * their namespace tags. Enable namespace support on @kobj->sd. */ ops = kobj_child_ns_ops(kobj); if (ops) { BUG_ON(!kobj_ns_type_is_valid(ops->type)); BUG_ON(!kobj_ns_type_registered(ops->type)); sysfs_enable_ns(kobj->sd); } return 0; } static int get_kobj_path_length(const struct kobject *kobj) { int length = 1; const struct kobject *parent = kobj; /* walk up the ancestors until we hit the one pointing to the * root. * Add 1 to strlen for leading '/' of each level. */ do { if (kobject_name(parent) == NULL) return 0; length += strlen(kobject_name(parent)) + 1; parent = parent->parent; } while (parent); return length; } static int fill_kobj_path(const struct kobject *kobj, char *path, int length) { const struct kobject *parent; --length; for (parent = kobj; parent; parent = parent->parent) { int cur = strlen(kobject_name(parent)); /* back up enough to print this name with '/' */ length -= cur; if (length <= 0) return -EINVAL; memcpy(path + length, kobject_name(parent), cur); *(path + --length) = '/'; } pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; } /** * kobject_get_path() - Allocate memory and fill in the path for @kobj. * @kobj: kobject in question, with which to build the path * @gfp_mask: the allocation type used to allocate the path * * Return: The newly allocated memory, caller must free with kfree(). */ char *kobject_get_path(const struct kobject *kobj, gfp_t gfp_mask) { char *path; int len; retry: len = get_kobj_path_length(kobj); if (len == 0) return NULL; path = kzalloc(len, gfp_mask); if (!path) return NULL; if (fill_kobj_path(kobj, path, len)) { kfree(path); goto retry; } return path; } EXPORT_SYMBOL_GPL(kobject_get_path); /* add the kobject to its kset's list */ static void kobj_kset_join(struct kobject *kobj) { if (!kobj->kset) return; kset_get(kobj->kset); spin_lock(&kobj->kset->list_lock); list_add_tail(&kobj->entry, &kobj->kset->list); spin_unlock(&kobj->kset->list_lock); } /* remove the kobject from its kset's list */ static void kobj_kset_leave(struct kobject *kobj) { if (!kobj->kset) return; spin_lock(&kobj->kset->list_lock); list_del_init(&kobj->entry); spin_unlock(&kobj->kset->list_lock); kset_put(kobj->kset); } static void kobject_init_internal(struct kobject *kobj) { if (!kobj) return; kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); kobj->state_in_sysfs = 0; kobj->state_add_uevent_sent = 0; kobj->state_remove_uevent_sent = 0; kobj->state_initialized = 1; } static int kobject_add_internal(struct kobject *kobj) { int error = 0; struct kobject *parent; if (!kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { WARN(1, "kobject: (%p): attempted to be registered with empty name!\n", kobj); return -EINVAL; } parent = kobject_get(kobj->parent); /* join kset if set, use it as parent if we do not already have one */ if (kobj->kset) { if (!parent) parent = kobject_get(&kobj->kset->kobj); kobj_kset_join(kobj); kobj->parent = parent; } pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "<NULL>", kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>"); error = create_dir(kobj); if (error) { kobj_kset_leave(kobj); kobject_put(parent); kobj->parent = NULL; /* be noisy on error issues */ if (error == -EEXIST) pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", __func__, kobject_name(kobj)); else pr_err("%s failed for %s (error: %d parent: %s)\n", __func__, kobject_name(kobj), error, parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; return error; } /** * kobject_set_name_vargs() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * @vargs: vargs to format the string. */ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *s; if (kobj->name && !fmt) return 0; s = kvasprintf_const(GFP_KERNEL, fmt, vargs); if (!s) return -ENOMEM; /* * ewww... some of these buggers have '/' in the name ... If * that's the case, we need to make sure we have an actual * allocated copy to modify, since kvasprintf_const may have * returned something from .rodata. */ if (strchr(s, '/')) { char *t; t = kstrdup(s, GFP_KERNEL); kfree_const(s); if (!t) return -ENOMEM; s = strreplace(t, '/', '!'); } kfree_const(kobj->name); kobj->name = s; return 0; } /** * kobject_set_name() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * * This sets the name of the kobject. If you have already added the * kobject to the system, you must call kobject_rename() in order to * change the name of the kobject. */ int kobject_set_name(struct kobject *kobj, const char *fmt, ...) { va_list vargs; int retval; va_start(vargs, fmt); retval = kobject_set_name_vargs(kobj, fmt, vargs); va_end(vargs); return retval; } EXPORT_SYMBOL(kobject_set_name); /** * kobject_init() - Initialize a kobject structure. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * * This function will properly initialize a kobject such that it can then * be passed to the kobject_add() call. * * After this function is called, the kobject MUST be cleaned up by a call * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) { char *err_str; if (!kobj) { err_str = "invalid kobject pointer!"; goto error; } if (!ktype) { err_str = "must have a ktype to be initialized properly!\n"; goto error; } if (kobj->state_initialized) { /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); dump_stack_lvl(KERN_ERR); } kobject_init_internal(kobj); kobj->ktype = ktype; return; error: pr_err("kobject (%p): %s\n", kobj, err_str); dump_stack_lvl(KERN_ERR); } EXPORT_SYMBOL(kobject_init); static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, struct kobject *parent, const char *fmt, va_list vargs) { int retval; retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { pr_err("can not set name properly!\n"); return retval; } kobj->parent = parent; return kobject_add_internal(kobj); } /** * kobject_add() - The main kobject add function. * @kobj: the kobject to add * @parent: pointer to the parent of the kobject. * @fmt: format to name the kobject with. * * The kobject name is set and added to the kobject hierarchy in this * function. * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * * Note, no "add" uevent will be created with this call, the caller should set * up all of the necessary sysfs files for the object and then call * kobject_uevent() with the UEVENT_ADD parameter to ensure that * userspace is properly notified of this kobject's creation. * * Return: If this function returns an error, kobject_put() must be * called to properly clean up the memory associated with the * object. Under no instance should the kobject that is passed * to this function be directly freed with a call to kfree(), * that can leak memory. * * If this function returns success, kobject_put() must also be called * in order to properly clean up the memory associated with the object. * * In short, once this function is called, kobject_put() MUST be called * when the use of the object is finished in order to properly free * everything. */ int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; if (!kobj) return -EINVAL; if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); dump_stack_lvl(KERN_ERR); return -EINVAL; } va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL(kobject_add); /** * kobject_init_and_add() - Initialize a kobject structure and add it to * the kobject hierarchy. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * @parent: pointer to the parent of this kobject. * @fmt: the name of the kobject. * * This function combines the call to kobject_init() and kobject_add(). * * If this function returns an error, kobject_put() must be called to * properly clean up the memory associated with the object. This is the * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; kobject_init(kobj, ktype); va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL_GPL(kobject_init_and_add); /** * kobject_rename() - Change the name of an object. * @kobj: object in question. * @new_name: object's new name * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of kobject_rename * on the same kobject and to ensure that new_name is valid and * won't conflict with other kobjects. */ int kobject_rename(struct kobject *kobj, const char *new_name) { int error = 0; const char *devpath = NULL; const char *dup_name = NULL, *name; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; if (!kobj->parent) { kobject_put(kobj); return -EINVAL; } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; name = dup_name = kstrdup_const(new_name, GFP_KERNEL); if (!name) { error = -ENOMEM; goto out; } error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj)); if (error) goto out; /* Install the new kobject name */ dup_name = kobj->name; kobj->name = name; /* This function is mostly/only used for network interface. * Some hotplug package track interfaces by their name and * therefore want to know when the name is changed by the user. */ kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kfree_const(dup_name); kfree(devpath_string); kfree(devpath); kobject_put(kobj); return error; } EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move() - Move object to another parent. * @kobj: object in question. * @new_parent: object's new parent (can be NULL) */ int kobject_move(struct kobject *kobj, struct kobject *new_parent) { int error; struct kobject *old_parent; const char *devpath = NULL; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; new_parent = kobject_get(new_parent); if (!new_parent) { if (kobj->kset) new_parent = kobject_get(&kobj->kset->kobj); } /* old object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj)); if (error) goto out; old_parent = kobj->parent; kobj->parent = new_parent; new_parent = NULL; kobject_put(old_parent); kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kobject_put(new_parent); kobject_put(kobj); kfree(devpath_string); kfree(devpath); return error; } EXPORT_SYMBOL_GPL(kobject_move); static void __kobject_del(struct kobject *kobj) { struct kernfs_node *sd; const struct kobj_type *ktype; sd = kobj->sd; ktype = get_ktype(kobj); if (ktype) sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { pr_debug("'%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } sysfs_remove_dir(kobj); sysfs_put(sd); kobj->state_in_sysfs = 0; kobj_kset_leave(kobj); kobj->parent = NULL; } /** * kobject_del() - Unlink kobject from hierarchy. * @kobj: object. * * This is the function that should be called to delete an object * successfully added via kobject_add(). */ void kobject_del(struct kobject *kobj) { struct kobject *parent; if (!kobj) return; parent = kobj->parent; __kobject_del(kobj); kobject_put(parent); } EXPORT_SYMBOL(kobject_del); /** * kobject_get() - Increment refcount for object. * @kobj: object. */ struct kobject *kobject_get(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n", kobject_name(kobj), kobj); kref_get(&kobj->kref); } return kobj; } EXPORT_SYMBOL(kobject_get); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kobj) return NULL; if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; return kobj; } EXPORT_SYMBOL(kobject_get_unless_zero); /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup */ static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { /* avoid dropping the parent reference unnecessarily */ parent = NULL; } if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { pr_debug("'%s': free name\n", name); kfree_const(name); } kobject_put(parent); } #ifdef CONFIG_DEBUG_KOBJECT_RELEASE static void kobject_delayed_cleanup(struct work_struct *work) { kobject_cleanup(container_of(to_delayed_work(work), struct kobject, release)); } #endif static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * get_random_u32_below(4); pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif } /** * kobject_put() - Decrement refcount for object. * @kobj: object. * * Decrement the refcount, and if 0, call kobject_cleanup(). */ void kobject_put(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n", kobject_name(kobj), kobj); kref_put(&kobj->kref, kobject_release); } } EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { pr_debug("(%p): %s\n", kobj, __func__); kfree(kobj); } static const struct kobj_type dynamic_kobj_ktype = { .release = dynamic_kobj_release, .sysfs_ops = &kobj_sysfs_ops, }; /** * kobject_create() - Create a struct kobject dynamically. * * This function creates a kobject structure dynamically and sets it up * to be a "dynamic" kobject with a default release function set up. * * If the kobject was not able to be created, NULL will be returned. * The kobject structure returned from here must be cleaned up with a * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ static struct kobject *kobject_create(void) { struct kobject *kobj; kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); if (!kobj) return NULL; kobject_init(kobj, &dynamic_kobj_ktype); return kobj; } /** * kobject_create_and_add() - Create a struct kobject dynamically and * register it with sysfs. * @name: the name for the kobject * @parent: the parent kobject of this kobject, if any. * * This function creates a kobject structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kobject_put() and the structure will be dynamically freed when * it is no longer being used. * * If the kobject was not able to be created, NULL will be returned. */ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent) { struct kobject *kobj; int retval; kobj = kobject_create(); if (!kobj) return NULL; retval = kobject_add(kobj, parent, "%s", name); if (retval) { pr_warn("%s: kobject_add error: %d\n", __func__, retval); kobject_put(kobj); kobj = NULL; } return kobj; } EXPORT_SYMBOL_GPL(kobject_create_and_add); /** * kset_init() - Initialize a kset for use. * @k: kset */ void kset_init(struct kset *k) { kobject_init_internal(&k->kobj); INIT_LIST_HEAD(&k->list); spin_lock_init(&k->list_lock); } /* default kobject attribute operations */ static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->show) ret = kattr->show(kobj, kattr, buf); return ret; } static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->store) ret = kattr->store(kobj, kattr, buf, count); return ret; } const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; EXPORT_SYMBOL_GPL(kobj_sysfs_ops); /** * kset_register() - Initialize and add a kset. * @k: kset. * * NOTE: On error, the kset.kobj.name allocated by() kobj_set_name() * is freed, it can not be used any more. */ int kset_register(struct kset *k) { int err; if (!k) return -EINVAL; if (!k->kobj.ktype) { pr_err("must have a ktype to be initialized properly!\n"); return -EINVAL; } kset_init(k); err = kobject_add_internal(&k->kobj); if (err) { kfree_const(k->kobj.name); /* Set it to NULL to avoid accessing bad pointer in callers. */ k->kobj.name = NULL; return err; } kobject_uevent(&k->kobj, KOBJ_ADD); return 0; } EXPORT_SYMBOL(kset_register); /** * kset_unregister() - Remove a kset. * @k: kset. */ void kset_unregister(struct kset *k) { if (!k) return; kobject_del(&k->kobj); kobject_put(&k->kobj); } EXPORT_SYMBOL(kset_unregister); /** * kset_find_obj() - Search for object in kset. * @kset: kset we're looking in. * @name: object's name. * * Lock kset via @kset->subsys, and iterate over @kset->list, * looking for a matching kobject. If matching object is found * take a reference and return the object. */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get_unless_zero(k); break; } } spin_unlock(&kset->list_lock); return ret; } EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); pr_debug("'%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } static void kset_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); } static const struct kobj_type kset_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = kset_release, .get_ownership = kset_get_ownership, }; /** * kset_create() - Create a struct kset dynamically. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically. This structure can * then be registered with the system and show up in sysfs with a call to * kset_register(). When you are finished with this structure, if * kset_register() has been called, call kset_unregister() and the * structure will be dynamically freed when it is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int retval; kset = kzalloc(sizeof(*kset), GFP_KERNEL); if (!kset) return NULL; retval = kobject_set_name(&kset->kobj, "%s", name); if (retval) { kfree(kset); return NULL; } kset->uevent_ops = uevent_ops; kset->kobj.parent = parent_kobj; /* * The kobject of this kset will have a type of kset_ktype and belong to * no kset itself. That way we can properly free it when it is * finished being used. */ kset->kobj.ktype = &kset_ktype; kset->kobj.kset = NULL; return kset; } /** * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kset_unregister() and the structure will be dynamically freed when it * is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int error; kset = kset_create(name, uevent_ops, parent_kobj); if (!kset) return NULL; error = kset_register(kset); if (error) { kfree(kset); return NULL; } return kset; } EXPORT_SYMBOL_GPL(kset_create_and_add); static DEFINE_SPINLOCK(kobj_ns_type_lock); static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) { enum kobj_ns_type type = ops->type; int error; spin_lock(&kobj_ns_type_lock); error = -EINVAL; if (!kobj_ns_type_is_valid(type)) goto out; error = -EBUSY; if (kobj_ns_ops_tbl[type]) goto out; error = 0; kobj_ns_ops_tbl[type] = ops; out: spin_unlock(&kobj_ns_type_lock); return error; } int kobj_ns_type_registered(enum kobj_ns_type type) { int registered = 0; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type)) registered = kobj_ns_ops_tbl[type] != NULL; spin_unlock(&kobj_ns_type_lock); return registered; } const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *parent) { const struct kobj_ns_type_operations *ops = NULL; if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; } const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj) { return kobj_child_ns_ops(kobj->parent); } bool kobj_ns_current_may_mount(enum kobj_ns_type type) { bool may_mount = true; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); spin_unlock(&kobj_ns_type_lock); return may_mount; } void *kobj_ns_grab_current(enum kobj_ns_type type) { void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } EXPORT_SYMBOL_GPL(kobj_ns_drop); |
| 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu-vm.c - vmalloc area based chunk allocation * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * Chunks are mapped into vmalloc areas and populated page by page. * This is the default chunk allocator. */ #include "internal.h" static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { /* must not be used on pre-mapped chunk */ WARN_ON(chunk->immutable); return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } /** * pcpu_get_pages - get temp pages array * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses * should be serialized by pcpu_alloc_mutex. * * RETURNS: * Pointer to temp pages array on success. */ static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); lockdep_assert_held(&pcpu_alloc_mutex); if (!pages) pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); return pages; } /** * pcpu_free_pages - free pages which were allocated for @chunk * @chunk: chunk pages were allocated for * @pages: array of pages to be freed, indexed by pcpu_page_idx() * @page_start: page index of the first page to be freed * @page_end: page index of the last page to be freed + 1 * * Free pages [@page_start and @page_end) in @pages for all units. * The pages were allocated for @chunk. */ static void pcpu_free_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page = pages[pcpu_page_idx(cpu, i)]; if (page) __free_page(page); } } } /** * pcpu_alloc_pages - allocates pages for @chunk * @chunk: target chunk * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() * @page_start: page index of the first page to be allocated * @page_end: page index of the last page to be allocated + 1 * @gfp: allocation flags passed to the underlying allocator * * Allocate pages [@page_start,@page_end) into @pages for all units. * The allocation is for @chunk. Percpu core doesn't care about the * content of @pages and will pass it verbatim to pcpu_map_pages(). */ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end, gfp_t gfp) { unsigned int cpu, tcpu; int i; gfp |= __GFP_HIGHMEM; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); if (!*pagep) goto err; } } return 0; err: while (--i >= page_start) __free_page(pages[pcpu_page_idx(cpu, i)]); for_each_possible_cpu(tcpu) { if (tcpu == cpu) break; for (i = page_start; i < page_end; i++) __free_page(pages[pcpu_page_idx(tcpu, i)]); } return -ENOMEM; } /** * pcpu_pre_unmap_flush - flush cache prior to unmapping * @chunk: chunk the regions to be flushed belongs to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages in [@page_start,@page_end) of @chunk are about to be * unmapped. Flush cache. As each flushing trial can be very * expensive, issue flush on the whole region at once rather than * doing it for each cpu. This could be an overkill but is more * scalable. */ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vunmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) { vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT)); } /** * pcpu_unmap_pages - unmap pages out of a pcpu_chunk * @chunk: chunk of interest * @pages: pages array which can be used to pass information to free * @page_start: page index of the first page to unmap * @page_end: page index of the last page to unmap + 1 * * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. * Corresponding elements in @pages were cleared by the caller and can * be used to carry information to pcpu_free_pages() which will be * called after all unmaps are finished. The caller should call * proper pre/post flush functions. */ static void pcpu_unmap_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page; page = pcpu_chunk_page(chunk, cpu, i); WARN_ON(!page); pages[pcpu_page_idx(cpu, i)] = page; } __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), page_end - page_start); } } /** * pcpu_post_unmap_tlb_flush - flush TLB after unmapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush * TLB for the regions. This can be skipped if the area is to be * returned to vmalloc as vmalloc will handle TLB flushing lazily. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_tlb_kernel_range( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static int __pcpu_map_pages(unsigned long addr, struct page **pages, int nr_pages) { return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT), PAGE_KERNEL, pages, PAGE_SHIFT); } /** * pcpu_map_pages - map pages into a pcpu_chunk * @chunk: chunk of interest * @pages: pages array containing pages to be mapped * @page_start: page index of the first page to map * @page_end: page index of the last page to map + 1 * * For each cpu, map pages [@page_start,@page_end) into @chunk. The * caller is responsible for calling pcpu_post_map_flush() after all * mappings are complete. * * This function is responsible for setting up whatever is necessary for * reverse lookup (addr -> chunk). */ static int pcpu_map_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu, tcpu; int i, err; for_each_possible_cpu(cpu) { err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), &pages[pcpu_page_idx(cpu, page_start)], page_end - page_start); if (err < 0) goto err; for (i = page_start; i < page_end; i++) pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], chunk); } return 0; err: for_each_possible_cpu(tcpu) { __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); if (tcpu == cpu) break; } pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } /** * pcpu_post_map_flush - flush cache after mapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been mapped. Flush * cache. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } /** * pcpu_populate_chunk - populate and map an area of a pcpu_chunk * @chunk: chunk of interest * @page_start: the start page * @page_end: the end page * @gfp: allocation flags passed to the underlying memory allocator * * For each cpu, populate and map pages [@page_start,@page_end) into * @chunk. * * CONTEXT: * pcpu_alloc_mutex, does GFP_KERNEL allocation. */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp) { struct page **pages; pages = pcpu_get_pages(); if (!pages) return -ENOMEM; if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) return -ENOMEM; if (pcpu_map_pages(chunk, pages, page_start, page_end)) { pcpu_free_pages(chunk, pages, page_start, page_end); return -ENOMEM; } pcpu_post_map_flush(chunk, page_start, page_end); return 0; } /** * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk * @chunk: chunk to depopulate * @page_start: the start page * @page_end: the end page * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. * * Caller is required to call pcpu_post_unmap_tlb_flush() if not returning the * region back to vmalloc() which will lazily flush the tlb. * * CONTEXT: * pcpu_alloc_mutex. */ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end) { struct page **pages; /* * If control reaches here, there must have been at least one * successful population attempt so the temp pages array must * be available now. */ pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ pcpu_pre_unmap_flush(chunk, page_start, page_end); pcpu_unmap_pages(chunk, pages, page_start, page_end); pcpu_free_pages(chunk, pages, page_start, page_end); } static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; } chunk->data = vms; chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(chunk->base_addr); return chunk; } static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; pcpu_stats_chunk_dealloc(); trace_percpu_destroy_chunk(chunk->base_addr); if (chunk->data) pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); pcpu_free_chunk(chunk); } static struct page *pcpu_addr_to_page(void *addr) { return vmalloc_to_page(addr); } static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) { /* no extra restriction */ return 0; } /** * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim * @chunk: chunk of interest * * This is the entry point for percpu reclaim. If a chunk qualifies, it is then * isolated and managed in separate lists at the back of pcpu_slot: sidelined * and to_depopulate respectively. The to_depopulate list holds chunks slated * for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once * they are on this list. Once depopulated, they are moved onto the sidelined * list which enables them to be pulled back in for allocation if no other chunk * can suffice the allocation. */ static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) { /* do not reclaim either the first chunk or reserved chunk */ if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk) return false; /* * If it is isolated, it may be on the sidelined list so move it back to * the to_depopulate list. If we hit at least 1/4 pages empty pages AND * there is no system-wide shortage of empty pages aside from this * chunk, move it to the to_depopulate list. */ return ((chunk->isolated && chunk->nr_empty_pop_pages) || (pcpu_nr_empty_pop_pages > (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) && chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); } |
| 91 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_CURRENT_H #define __ASM_CURRENT_H #include <linux/compiler.h> #ifndef __ASSEMBLY__ struct task_struct; /* * We don't use read_sysreg() as we want the compiler to cache the value where * possible. */ static __always_inline struct task_struct *get_current(void) { unsigned long sp_el0; asm ("mrs %0, sp_el0" : "=r" (sp_el0)); return (struct task_struct *)sp_el0; } #define current get_current() #endif /* __ASSEMBLY__ */ #endif /* __ASM_CURRENT_H */ |
| 127 126 101 33 45 127 127 129 126 45 1 1 249 4 249 249 249 249 4 4 4 4 23 2 4 117 45 126 126 127 126 127 128 128 128 129 4 4 4 4 4 24 23 24 24 24 24 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include <linux/kernel_stat.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> #include <linux/jiffies.h> #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> #include "tick-internal.h" #include "timer_migration.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of * LVL_SIZE buckets. Each level is driven by its own clock and therefore each * level has a different granularity. * * The level granularity is: LVL_CLK_DIV ^ level * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and * therefore the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading * the timers into the lower array levels. The previous 'classic' timer wheel * implementation of the kernel already violated the 'exact' expiry by adding * slack to the expiry time to provide batched expiration. The granularity * levels provide implicit batching. * * This is an optimization of the original timer wheel implementation for the * majority of the timer wheel use cases: timeouts. The vast majority of * timeout timers (networking, disk I/O ...) are canceled before expiry. If * the timeout expires it indicates that normal operation is disturbed, so it * does not matter much whether the timeout comes with a slight delay. * * The only exception to this are networking timers with a small expiry * time. They rely on the granularity. Those fit into the first wheel level, * which has HZ granularity. * * We don't have cascading anymore. timers with a expiry time above the * capacity of the last wheel level are force expired at the maximum timeout * value of the last wheel level. From data sampling we know that the maximum * value observed is 5 days (network connection tracking), so this should not * be an issue. * * The currently chosen array constants values are a good compromise between * array size and granularity. * * This results in the following granularity and range levels: * * HZ 1000 steps * Level Offset Granularity Range * 0 0 1 ms 0 ms - 63 ms * 1 64 8 ms 64 ms - 511 ms * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) * * HZ 300 * Level Offset Granularity Range * 0 0 3 ms 0 ms - 210 ms * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) * * HZ 250 * Level Offset Granularity Range * 0 0 4 ms 0 ms - 255 ms * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) * * HZ 100 * Level Offset Granularity Range * 0 0 10 ms 0 ms - 630 ms * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ /* Clock divisor for the next level */ #define LVL_CLK_SHIFT 3 #define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) #define LVL_CLK_MASK (LVL_CLK_DIV - 1) #define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) #define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) /* * The time start value for each level to select the bucket at enqueue * time. We start from the last possible delta of the previous level * so that we can later add an extra LVL_GRAN(n) to n (see calc_index()). */ #define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) /* Size of each clock level */ #define LVL_BITS 6 #define LVL_SIZE (1UL << LVL_BITS) #define LVL_MASK (LVL_SIZE - 1) #define LVL_OFFS(n) ((n) * LVL_SIZE) /* Level depth */ #if HZ > 100 # define LVL_DEPTH 9 # else # define LVL_DEPTH 8 #endif /* The cutoff (max. capacity of the wheel) */ #define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) #define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) /* * The resulting wheel size. If NOHZ is configured we allocate two * wheels so we have a separate storage for the deferrable timers. */ #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON /* * If multiple bases need to be locked, use the base ordering for lock * nesting, i.e. lowest number first. */ # define NR_BASES 3 # define BASE_LOCAL 0 # define BASE_GLOBAL 1 # define BASE_DEF 2 #else # define NR_BASES 1 # define BASE_LOCAL 0 # define BASE_GLOBAL 0 # define BASE_DEF 0 #endif /** * struct timer_base - Per CPU timer base (number of base depends on config) * @lock: Lock protecting the timer_base * @running_timer: When expiring timers, the lock is dropped. To make * sure not to race against deleting/modifying a * currently running timer, the pointer is set to the * timer, which expires at the moment. If no timer is * running, the pointer is NULL. * @expiry_lock: PREEMPT_RT only: Lock is taken in softirq around * timer expiry callback execution and when trying to * delete a running timer and it wasn't successful in * the first glance. It prevents priority inversion * when callback was preempted on a remote CPU and a * caller tries to delete the running timer. It also * prevents a life lock, when the task which tries to * delete a timer preempted the softirq thread which * is running the timer callback function. * @timer_waiters: PREEMPT_RT only: Tells, if there is a waiter * waiting for the end of the timer callback function * execution. * @clk: clock of the timer base; is updated before enqueue * of a timer; during expiry, it is 1 offset ahead of * jiffies to avoid endless requeuing to current * jiffies * @next_expiry: expiry value of the first timer; it is updated when * finding the next timer and during enqueue; the * value is not valid, when next_expiry_recalc is set * @cpu: Number of CPU the timer base belongs to * @next_expiry_recalc: States, whether a recalculation of next_expiry is * required. Value is set true, when a timer was * deleted. * @is_idle: Is set, when timer_base is idle. It is triggered by NOHZ * code. This state is only used in standard * base. Deferrable timers, which are enqueued remotely * never wake up an idle CPU. So no matter of supporting it * for this base. * @timers_pending: Is set, when a timer is pending in the base. It is only * reliable when next_expiry_recalc is not set. * @pending_map: bitmap of the timer wheel; each bit reflects a * bucket of the wheel. When a bit is set, at least a * single timer is enqueued in the related bucket. * @vectors: Array of lists; Each array member reflects a bucket * of the timer wheel. The list contains all timers * which are enqueued into a specific bucket. */ struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; #ifdef CONFIG_PREEMPT_RT spinlock_t expiry_lock; atomic_t timer_waiters; #endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; bool next_expiry_recalc; bool is_idle; bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #ifdef CONFIG_NO_HZ_COMMON static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP static unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { if (sysctl_timer_migration && tick_nohz_active) static_branch_enable(&timers_migration_enabled); else static_branch_disable(&timers_migration_enabled); } #ifdef CONFIG_SYSCTL static int timer_migration_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&timer_keys_mutex); ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(); mutex_unlock(&timer_keys_mutex); return ret; } static const struct ctl_table timer_sysctl[] = { { .procname = "timer_migration", .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = timer_migration_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static int __init timer_sysctl_init(void) { register_sysctl("kernel", timer_sysctl); return 0; } device_initcall(timer_sysctl_init); #endif /* CONFIG_SYSCTL */ #else /* CONFIG_SMP */ static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ static void timer_update_keys(struct work_struct *work) { mutex_lock(&timer_keys_mutex); timers_update_migration(); static_branch_enable(&timers_nohz_active); mutex_unlock(&timer_keys_mutex); } void timers_update_nohz(void) { schedule_work(&timer_update_work); } static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); } #else static inline bool is_timers_nohz_active(void) { return false; } #endif /* NO_HZ_COMMON */ static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { int rem; unsigned long original = j; /* * We don't want all cpus firing their timers at once hitting the * same lock or cachelines, so we skew each extra cpu with an extra * 3 jiffies. This 3 jiffies came originally from the mm/ code which * already did this. * The skew is done by adding 3*cpunr, then round, then subtract this * extra offset again. */ j += cpu * 3; rem = j % HZ; /* * If the target jiffy is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. * But never round down if @force_up is set. */ if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; /* * Make sure j is still in the future. Otherwise return the * unmodified value. */ return time_is_after_jiffies(j) ? j : original; } /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, true) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), true); } EXPORT_SYMBOL_GPL(round_jiffies_up); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { return __round_jiffies_up_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); static inline unsigned int timer_get_idx(struct timer_list *timer) { return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; } static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | idx << TIMER_ARRAYSHIFT; } /* * Helper function to calculate the array index for a given expiry * time. */ static inline unsigned calc_index(unsigned long expires, unsigned lvl, unsigned long *bucket_expiry) { /* * The timer wheel has to guarantee that a timer does not fire * early. Early expiry can happen due to: * - Timer is armed at the edge of a tick * - Truncation of the expiry time in the outer wheel levels * * Round up with level granularity to prevent this. */ expires = (expires >> LVL_SHIFT(lvl)) + 1; *bucket_expiry = expires << LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } static int calc_wheel_index(unsigned long expires, unsigned long clk, unsigned long *bucket_expiry) { unsigned long delta = expires - clk; unsigned int idx; if (delta < LVL_START(1)) { idx = calc_index(expires, 0, bucket_expiry); } else if (delta < LVL_START(2)) { idx = calc_index(expires, 1, bucket_expiry); } else if (delta < LVL_START(3)) { idx = calc_index(expires, 2, bucket_expiry); } else if (delta < LVL_START(4)) { idx = calc_index(expires, 3, bucket_expiry); } else if (delta < LVL_START(5)) { idx = calc_index(expires, 4, bucket_expiry); } else if (delta < LVL_START(6)) { idx = calc_index(expires, 5, bucket_expiry); } else if (delta < LVL_START(7)) { idx = calc_index(expires, 6, bucket_expiry); } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { idx = calc_index(expires, 7, bucket_expiry); } else if ((long) delta < 0) { idx = clk & LVL_MASK; *bucket_expiry = clk; } else { /* * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ if (delta >= WHEEL_TIMEOUT_CUTOFF) expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1, bucket_expiry); } return idx; } static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { /* * Deferrable timers do not prevent the CPU from entering dynticks and * are not taken into account on the idle/nohz_full path. An IPI when a * new deferrable timer is enqueued will wake up the remote CPU but * nothing will be done with the deferrable timer base. Therefore skip * the remote IPI for deferrable timers completely. */ if (!is_timers_nohz_active() || timer->flags & TIMER_DEFERRABLE) return; /* * We might have to IPI the remote CPU if the base is idle and the * timer is pinned. If it is a non pinned timer, it is only queued * on the remote CPU, when timer was running during queueing. Then * everything is handled by remote CPU anyway. If the other CPU is * on the way to idle then it can't set base->is_idle as we hold * the base lock: */ if (base->is_idle) { WARN_ON_ONCE(!(timer->flags & TIMER_PINNED || tick_nohz_full_cpu(base->cpu))); wake_up_nohz_cpu(base->cpu); } } /* * Enqueue the timer into the hash bucket, mark it pending in * the bitmap, store the index in the timer flags then wake up * the target CPU if needed. */ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, unsigned int idx, unsigned long bucket_expiry) { hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); trace_timer_start(timer, bucket_expiry); /* * Check whether this is the new first expiring timer. The * effective expiry time of the timer is required here * (bucket_expiry) instead of timer->expires. */ if (time_before(bucket_expiry, base->next_expiry)) { /* * Set the next expiry time and kick the CPU so it * can reevaluate the wheel: */ WRITE_ONCE(base->next_expiry, bucket_expiry); base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { unsigned long bucket_expiry; unsigned int idx; idx = calc_wheel_index(timer->expires, base->clk, &bucket_expiry); enqueue_timer(base, timer, idx, bucket_expiry); } #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr timer_debug_descr; struct timer_hint { void (*function)(struct timer_list *t); long offset; }; #define TIMER_HINT(fn, container, timr, hintfn) \ { \ .function = fn, \ .offset = offsetof(container, hintfn) - \ offsetof(container, timr) \ } static const struct timer_hint timer_hints[] = { TIMER_HINT(delayed_work_timer_fn, struct delayed_work, timer, work.func), TIMER_HINT(kthread_delayed_work_timer_fn, struct kthread_delayed_work, timer, work.func), }; static void *timer_debug_hint(void *addr) { struct timer_list *timer = addr; int i; for (i = 0; i < ARRAY_SIZE(timer_hints); i++) { if (timer_hints[i].function == timer->function) { void (**fn)(void) = addr + timer_hints[i].offset; return *fn; } } return timer->function; } static bool timer_is_static_object(void *addr) { struct timer_list *timer = addr; return (timer->entry.pprev == NULL && timer->entry.next == TIMER_ENTRY_STATIC); } /* * timer_fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: timer_delete_sync(timer); debug_object_init(timer, &timer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static void stub_timer(struct timer_list *unused) { WARN_ON(1); } /* * timer_fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * timer_fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: timer_delete_sync(timer); debug_object_free(timer, &timer_debug_descr); return true; default: return false; } } /* * timer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; default: return false; } } static const struct debug_obj_descr timer_debug_descr = { .name = "timer_list", .debug_hint = timer_debug_hint, .is_static_object = timer_is_static_object, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) { debug_object_init(timer, &timer_debug_descr); } static inline void debug_timer_activate(struct timer_list *timer) { debug_object_activate(timer, &timer_debug_descr); } static inline void debug_timer_deactivate(struct timer_list *timer) { debug_object_deactivate(timer, &timer_debug_descr); } static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); void timer_init_key_on_stack(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL_GPL(timer_init_key_on_stack); void timer_destroy_on_stack(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } EXPORT_SYMBOL_GPL(timer_destroy_on_stack); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { debug_timer_init(timer); trace_timer_init(timer); } static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); trace_timer_cancel(timer); } static inline void debug_assert_init(struct timer_list *timer) { debug_timer_assert_init(timer); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { timer->entry.pprev = NULL; timer->function = func; if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS)) flags &= TIMER_INIT_FLAGS; timer->flags = flags | raw_smp_processor_id(); lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** * timer_init_key - initialize a timer * @timer: the timer to be initialized * @func: timer callback function * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * * timer_init_key() must be done to a timer prior to calling *any* of the * other timer functions. */ void timer_init_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_init(timer); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL(timer_init_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct hlist_node *entry = &timer->entry; debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL; entry->next = LIST_POISON2; } static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { unsigned idx = timer_get_idx(timer); if (!timer_pending(timer)) return 0; if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) { __clear_bit(idx, base->pending_map); base->next_expiry_recalc = true; } detach_timer(timer, clear_pending); return 1; } static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) index = BASE_DEF; return per_cpu_ptr(&timer_bases[index], cpu); } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) index = BASE_DEF; return this_cpu_ptr(&timer_bases[index]); } static inline struct timer_base *get_timer_base(u32 tflags) { return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } static inline void __forward_timer_base(struct timer_base *base, unsigned long basej) { /* * Check whether we can forward the base. We can only do that when * @basej is past base->clk otherwise we might rewind base->clk. */ if (time_before_eq(basej, base->clk)) return; /* * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ if (time_after(base->next_expiry, basej)) { base->clk = basej; } else { if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) return; base->clk = base->next_expiry; } } static inline void forward_timer_base(struct timer_base *base) { __forward_timer_base(base, READ_ONCE(jiffies)); } /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means * that all timers which are tied to this base are locked, and the base itself * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found in the base->vectors array. * * When a timer is migrating then the TIMER_MIGRATING flag is set and we need * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { for (;;) { struct timer_base *base; u32 tf; /* * We need to use READ_ONCE() here, otherwise the compiler * might re-read @tf between the check for TIMER_MIGRATING * and spin_lock(). */ tf = READ_ONCE(timer->flags); if (!(tf & TIMER_MIGRATING)) { base = get_timer_base(tf); raw_spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; raw_spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } #define MOD_TIMER_PENDING_ONLY 0x01 #define MOD_TIMER_REDUCE 0x02 #define MOD_TIMER_NOTPENDING 0x04 static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { unsigned long clk = 0, flags, bucket_expiry; struct timer_base *base, *new_base; unsigned int idx = UINT_MAX; int ret = 0; debug_assert_init(timer); /* * This is a common optimization triggered by the networking code - if * the timer is re-modified to have the same timeout or ends up in the * same array bucket then just return: */ if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) { /* * The downside of this optimization is that it can result in * larger granularity than you would get from adding a new * timer with this expiry. */ long diff = timer->expires - expires; if (!diff) return 1; if (options & MOD_TIMER_REDUCE && diff <= 0) return 1; /* * We lock timer base and calculate the bucket index right * here. If the timer ends up in the same bucket, then we * just update the expiry time and avoid the whole * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated * while holding base lock to prevent a race against the * shutdown code. */ if (!timer->function) goto out_unlock; forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && time_before_eq(timer->expires, expires)) { ret = 1; goto out_unlock; } clk = base->clk; idx = calc_wheel_index(expires, clk, &bucket_expiry); /* * Retrieve and compare the array index of the pending * timer. If it matches set the expiry to the new value so a * subsequent call will exit in the expires check above. */ if (idx == timer_get_idx(timer)) { if (!(options & MOD_TIMER_REDUCE)) timer->expires = expires; else if (time_after(timer->expires, expires)) timer->expires = expires; ret = 1; goto out_unlock; } } else { base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated * while holding base lock to prevent a race against the * shutdown code. */ if (!timer->function) goto out_unlock; forward_timer_base(base); } ret = detach_if_pending(timer, base, false); if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; new_base = get_timer_this_cpu_base(timer->flags); if (base != new_base) { /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); forward_timer_base(base); } } debug_timer_activate(timer); timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance * between calculating 'idx' and possibly switching the base, only * enqueue_timer() is required. Otherwise we need to (re)calculate * the wheel index via internal_add_timer(). */ if (idx != UINT_MAX && clk == base->clk) enqueue_timer(base, timer, idx, bucket_expiry); else internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * mod_timer_pending - Modify a pending timer's timeout * @timer: The pending timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), but * will not activate inactive timers. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and not modified or was in * shutdown state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY); } EXPORT_SYMBOL(mod_timer_pending); /** * mod_timer - Modify a timer's timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * timer_delete(timer); timer->expires = expires; add_timer(timer); * * mod_timer() is more efficient than the above open coded sequence. In * case that the timer is inactive, the timer_delete() part is a NOP. The * timer is in any case activated with the new expiry time @expires. * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * * If @timer->function == NULL then the start operation is silently * discarded. In this case the return value is 0 and meaningless. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires did * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, 0); } EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only * modify an enqueued timer if that would reduce the expiration time. If * @timer is not enqueued it starts the timer. * * If @timer->function == NULL then the start operation is silently * discarded. * * Return: * * %0 - The timer was inactive and started or was in shutdown * state and the operation was discarded * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires * did not change the effective expiry time such that the * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_REDUCE); } EXPORT_SYMBOL(timer_reduce); /** * add_timer - Start a timer * @timer: The timer to be started * * Start @timer to expire at @timer->expires in the future. @timer->expires * is the absolute expiry time measured in 'jiffies'. When the timer expires * timer->function(timer) will be invoked from soft interrupt context. * * The @timer->expires and @timer->function fields must be set prior * to calling this function. * * If @timer->function == NULL then the start operation is silently * discarded. * * If @timer->expires is already in the past @timer will be queued to * expire at the next timer tick. * * This can only operate on an inactive timer. Attempts to invoke this on * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { if (WARN_ON_ONCE(timer_pending(timer))) return; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer); /** * add_timer_local() - Start a timer on the local CPU * @timer: The timer to be started * * Same as add_timer() except that the timer flag TIMER_PINNED is set. * * See add_timer() for further details. */ void add_timer_local(struct timer_list *timer) { if (WARN_ON_ONCE(timer_pending(timer))) return; timer->flags |= TIMER_PINNED; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer_local); /** * add_timer_global() - Start a timer without TIMER_PINNED flag set * @timer: The timer to be started * * Same as add_timer() except that the timer flag TIMER_PINNED is unset. * * See add_timer() for further details. */ void add_timer_global(struct timer_list *timer) { if (WARN_ON_ONCE(timer_pending(timer))) return; timer->flags &= ~TIMER_PINNED; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer_global); /** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * * Same as add_timer() except that it starts the timer on the given CPU and * the TIMER_PINNED flag is set. When timer shouldn't be a pinned timer in * the next round, add_timer_global() should be used instead as it unsets * the TIMER_PINNED flag. * * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { struct timer_base *new_base, *base; unsigned long flags; debug_assert_init(timer); if (WARN_ON_ONCE(timer_pending(timer))) return; /* Make sure timer flags have TIMER_PINNED flag set */ timer->flags |= TIMER_PINNED; new_base = get_timer_cpu_base(timer->flags, cpu); /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the * wrong base locked. See lock_timer_base(). */ base = lock_timer_base(timer, &flags); /* * Has @timer been shutdown? This needs to be evaluated while * holding base lock to prevent a race against the shutdown code. */ if (!timer->function) goto out_unlock; if (base != new_base) { timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } forward_timer_base(base); debug_timer_activate(timer); internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); /** * __timer_delete - Internal function: Deactivate a timer * @timer: The timer to be deactivated * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the time. In that * case any attempt to rearm @timer after this function returns will be * silently ignored. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; int ret = 0; debug_assert_init(timer); /* * If @shutdown is set then the lock has to be taken whether the * timer is pending or not to protect against a concurrent rearm * which might hit between the lockless pending check and the lock * acquisition. By taking the lock it is ensured that such a newly * enqueued timer is dequeued and cannot end up with * timer->function == NULL in the expiry code. * * If timer->function is currently executed, then this makes sure * that the callback cannot requeue the timer. */ if (timer_pending(timer) || shutdown) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); } return ret; } /** * timer_delete - Deactivate a timer * @timer: The timer to be deactivated * * The function only deactivates a pending timer, but contrary to * timer_delete_sync() it does not take into account whether the timer's * callback function is concurrently executed on a different CPU or not. * It neither prevents rearming of the timer. If @timer can be rearmed * concurrently then the return value of this function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete(struct timer_list *timer) { return __timer_delete(timer, false); } EXPORT_SYMBOL(timer_delete); /** * timer_shutdown - Deactivate a timer and prevent rearming * @timer: The timer to be deactivated * * The function does not wait for an eventually running timer callback on a * different CPU but it prevents rearming of the timer. Any attempt to arm * @timer after this function returns will be silently ignored. * * This function is useful for teardown code and should only be used when * timer_shutdown_sync() cannot be invoked due to locking or context constraints. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown(struct timer_list *timer) { return __timer_delete(timer, true); } EXPORT_SYMBOL_GPL(timer_shutdown); /** * __try_to_del_timer_sync - Internal function: Try to deactivate a timer * @timer: Timer to deactivate * @shutdown: If true, this indicates that the timer is about to be * shutdown permanently. * * If @shutdown is true then @timer->function is set to NULL under the * timer base lock which prevents further rearming of the timer. Any * attempt to rearm @timer after this function returns will be silently * ignored. * * This function cannot guarantee that the timer cannot be rearmed * right after dropping the base lock if @shutdown is false. That * needs to be prevented by the calling code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; int ret = -1; debug_assert_init(timer); base = lock_timer_base(timer, &flags); if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); if (shutdown) timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * timer_delete_sync_try - Try to deactivate a timer * @timer: Timer to deactivate * * This function tries to deactivate a timer. On success the timer is not * queued and the timer callback function is not running on any CPU. * * This function does not guarantee that the timer cannot be rearmed right * after dropping the base lock. That needs to be prevented by the calling * code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ int timer_delete_sync_try(struct timer_list *timer) { return __try_to_del_timer_sync(timer, false); } EXPORT_SYMBOL(timer_delete_sync_try); #ifdef CONFIG_PREEMPT_RT static __init void timer_base_init_expiry_lock(struct timer_base *base) { spin_lock_init(&base->expiry_lock); } static inline void timer_base_lock_expiry(struct timer_base *base) { spin_lock(&base->expiry_lock); } static inline void timer_base_unlock_expiry(struct timer_base *base) { spin_unlock(&base->expiry_lock); } /* * The counterpart to del_timer_wait_running(). * * If there is a waiter for base->expiry_lock, then it was waiting for the * timer callback to finish. Drop expiry_lock and reacquire it. That allows * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) __releases(&base->lock) __releases(&base->expiry_lock) __acquires(&base->expiry_lock) __acquires(&base->lock) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); raw_spin_lock_irq(&base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion, if the softirq thread on a remote CPU * got preempted, and it prevents a life lock when the task which tries to * delete a timer preempted the softirq thread running the timer callback * function. */ static void del_timer_wait_running(struct timer_list *timer) { u32 tf; tf = READ_ONCE(timer->flags); if (!(tf & (TIMER_MIGRATING | TIMER_IRQSAFE))) { struct timer_base *base = get_timer_base(tf); /* * Mark the base as contended and grab the expiry lock, * which is held by the softirq across the timer * callback. Drop the lock immediately so the softirq can * expire the next timer. In theory the timer could already * be running again, but that's more than unlikely and just * causes another wait loop. */ atomic_inc(&base->timer_waiters); spin_lock_bh(&base->expiry_lock); atomic_dec(&base->timer_waiters); spin_unlock_bh(&base->expiry_lock); } } #else static inline void timer_base_init_expiry_lock(struct timer_base *base) { } static inline void timer_base_lock_expiry(struct timer_base *base) { } static inline void timer_base_unlock_expiry(struct timer_base *base) { } static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif /** * __timer_delete_sync - Internal function: Deactivate a timer and wait * for the handler to finish. * @timer: The timer to be deactivated * @shutdown: If true, @timer->function will be set to NULL under the * timer base lock which prevents rearming of @timer * * If @shutdown is not set the timer can be rearmed later. If the timer can * be rearmed concurrently, i.e. after dropping the base lock then the * return value is meaningless. * * If @shutdown is set then @timer->function is set to NULL under timer * base lock which prevents rearming of the timer. Any attempt to rearm * a shutdown timer is silently ignored. * * If the timer should be reused after shutdown it has to be initialized * again. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ static int __timer_delete_sync(struct timer_list *timer, bool shutdown) { int ret; #ifdef CONFIG_LOCKDEP unsigned long flags; /* * If lockdep gives a backtrace here, please reference * the synchronization rules above. */ local_irq_save(flags); lock_map_acquire(&timer->lockdep_map); lock_map_release(&timer->lockdep_map); local_irq_restore(flags); #endif /* * don't use it in hardirq context, because it * could lead to deadlock. */ WARN_ON(in_hardirq() && !(timer->flags & TIMER_IRQSAFE)); /* * Must be able to sleep on PREEMPT_RT because of the slowpath in * del_timer_wait_running(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(timer->flags & TIMER_IRQSAFE)) lockdep_assert_preemption_enabled(); do { ret = __try_to_del_timer_sync(timer, shutdown); if (unlikely(ret < 0)) { del_timer_wait_running(timer); cpu_relax(); } } while (ret < 0); return ret; } /** * timer_delete_sync - Deactivate a timer and wait for the handler to finish. * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must * not hold locks which would prevent completion of the timer's callback * function. The timer's handler must not call add_timer_on(). Upon exit * the timer is not queued and the handler is not running on any CPU. * * For !irqsafe timers, the caller must not hold locks that are held in * interrupt context. Even if the lock has nothing to do with the timer in * question. Here's why:: * * CPU0 CPU1 * ---- ---- * <SOFTIRQ> * call_timer_fn(); * base->running_timer = mytimer; * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * * Now timer_delete_sync() will never return and never release somelock. * The interrupt on the other CPU is waiting to grab somelock but it has * interrupted the softirq that CPU0 is waiting to finish. * * This function cannot guarantee that the timer is not rearmed again by * some concurrent or preempting code, right after it dropped the base * lock. If there is the possibility of a concurrent rearm then the return * value of the function is meaningless. * * If such a guarantee is needed, e.g. for teardown situations then use * timer_shutdown_sync() instead. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int timer_delete_sync(struct timer_list *timer) { return __timer_delete_sync(timer, false); } EXPORT_SYMBOL(timer_delete_sync); /** * timer_shutdown_sync - Shutdown a timer and prevent rearming * @timer: The timer to be shutdown * * When the function returns it is guaranteed that: * - @timer is not queued * - The callback function of @timer is not running * - @timer cannot be enqueued again. Any attempt to rearm * @timer is silently ignored. * * See timer_delete_sync() for synchronization rules. * * This function is useful for final teardown of an infrastructure where * the timer is subject to a circular dependency problem. * * A common pattern for this is a timer and a workqueue where the timer can * schedule work and work can arm the timer. On shutdown the workqueue must * be destroyed and the timer must be prevented from rearming. Unless the * code has conditionals like 'if (mything->in_shutdown)' to prevent that * there is no way to get this correct with timer_delete_sync(). * * timer_shutdown_sync() is solving the problem. The correct ordering of * calls in this case is: * * timer_shutdown_sync(&mything->timer); * workqueue_destroy(&mything->workqueue); * * After this 'mything' can be safely freed. * * This obviously implies that the timer is not required to be functional * for the rest of the shutdown operation. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending */ int timer_shutdown_sync(struct timer_list *timer) { return __timer_delete_sync(timer, true); } EXPORT_SYMBOL_GPL(timer_shutdown_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), unsigned long baseclk) { int count = preempt_count(); #ifdef CONFIG_LOCKDEP /* * It is permissible to free the timer from inside the * function that is called from it, this we need to take into * account for lockdep too. To avoid bogus "held lock freed" * warnings as well as problems when looking into * timer->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &timer->lockdep_map); #endif /* * Couple the lock chain with the lock chain at * timer_delete_sync() by acquiring the lock_map around the fn() * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); trace_timer_expire_entry(timer, baseclk); fn(timer); trace_timer_expire_exit(timer); lock_map_release(&lockdep_map); if (count != preempt_count()) { WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n", fn, count, preempt_count()); /* * Restore the preempt count. That gives us a decent * chance to survive and extract information. If the * callback kept a lock held, bad luck, but not worse * than the BUG() we had. */ preempt_count_set(count); } } static void expire_timers(struct timer_base *base, struct hlist_head *head) { /* * This value is required only for tracing. base->clk was * incremented directly before expire_timers was called. But expiry * is related to the old base->clk value. */ unsigned long baseclk = base->clk - 1; while (!hlist_empty(head)) { struct timer_list *timer; void (*fn)(struct timer_list *); timer = hlist_entry(head->first, struct timer_list, entry); base->running_timer = timer; detach_timer(timer, true); fn = timer->function; if (WARN_ON_ONCE(!fn)) { /* Should never happen. Emphasis on should! */ base->running_timer = NULL; continue; } if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock(&base->lock); base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); } } } static int collect_expired_timers(struct timer_base *base, struct hlist_head *heads) { unsigned long clk = base->clk = base->next_expiry; struct hlist_head *vec; int i, levels = 0; unsigned int idx; for (i = 0; i < LVL_DEPTH; i++) { idx = (clk & LVL_MASK) + i * LVL_SIZE; if (__test_and_clear_bit(idx, base->pending_map)) { vec = base->vectors + idx; hlist_move_list(vec, heads++); levels++; } /* Is it time to look at the next level? */ if (clk & LVL_CLK_MASK) break; /* Shift clock for the next level granularity */ clk >>= LVL_CLK_SHIFT; } return levels; } /* * Find the next pending bucket of a level. Search from level start (@offset) * + @clk upwards and if nothing there, search from start of the level * (@offset) up to @offset + clk. */ static int next_pending_bucket(struct timer_base *base, unsigned offset, unsigned clk) { unsigned pos, start = offset + clk; unsigned end = offset + LVL_SIZE; pos = find_next_bit(base->pending_map, end, start); if (pos < end) return pos - start; pos = find_next_bit(base->pending_map, start, offset); return pos < start ? pos + LVL_SIZE - start : -1; } /* * Search the first expiring timer in the various clock levels. Caller must * hold base->lock. * * Store next expiry time in base->next_expiry. */ static void timer_recalc_next_expiry(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; next = base->clk + TIMER_NEXT_MAX_DELTA; clk = base->clk; for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) { int pos = next_pending_bucket(base, offset, clk & LVL_MASK); unsigned long lvl_clk = clk & LVL_CLK_MASK; if (pos >= 0) { unsigned long tmp = clk + (unsigned long) pos; tmp <<= LVL_SHIFT(lvl); if (time_before(tmp, next)) next = tmp; /* * If the next expiration happens before we reach * the next level, no need to check further. */ if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK)) break; } /* * Clock for the next level. If the current level clock lower * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next * expiring jiffy. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 * * we have to look at all levels @index 0. With * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 2 * * LVL0 has the next expiring bucket @index 2. The upper * levels have the next expiring bucket @index 1. * * In case that the propagation wraps the next level the same * rules apply: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 F 2 * * So after looking at LVL0 we get: * * LVL5 LVL4 LVL3 LVL2 LVL1 * 0 0 0 1 0 * * So no propagation from LVL1 to LVL2 because that happened * with the add already, but then we need to propagate further * from LVL2 to LVL3. * * So the simple check whether the lower bits of the current * level are 0 or not is sufficient for all cases. */ adj = lvl_clk ? 1 : 0; clk >>= LVL_CLK_SHIFT; clk += adj; } WRITE_ONCE(base->next_expiry, next); base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + TIMER_NEXT_MAX_DELTA); } #ifdef CONFIG_NO_HZ_COMMON /* * Check, if the next hrtimer event is before the next timer wheel * event: */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { u64 nextevt = hrtimer_get_next_event(); /* * If high resolution timers are enabled * hrtimer_get_next_event() returns KTIME_MAX. */ if (expires <= nextevt) return expires; /* * If the next timer is already expired, return the tick base * time so the tick is fired immediately. */ if (nextevt <= basem) return basem; /* * Round up to the next jiffy. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. * * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3 */ return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } static unsigned long next_timer_interrupt(struct timer_base *base, unsigned long basej) { if (base->next_expiry_recalc) timer_recalc_next_expiry(base); /* * Move next_expiry for the empty base into the future to prevent an * unnecessary raise of the timer softirq when the next_expiry value * will be reached even if there is no timer pending. * * This update is also required to make timer_base::next_expiry values * easy comparable to find out which base holds the first pending timer. */ if (!base->timers_pending) WRITE_ONCE(base->next_expiry, basej + TIMER_NEXT_MAX_DELTA); return base->next_expiry; } static unsigned long fetch_next_timer_interrupt(unsigned long basej, u64 basem, struct timer_base *base_local, struct timer_base *base_global, struct timer_events *tevt) { unsigned long nextevt, nextevt_local, nextevt_global; bool local_first; nextevt_local = next_timer_interrupt(base_local, basej); nextevt_global = next_timer_interrupt(base_global, basej); local_first = time_before_eq(nextevt_local, nextevt_global); nextevt = local_first ? nextevt_local : nextevt_global; /* * If the @nextevt is at max. one tick away, use @nextevt and store * it in the local expiry value. The next global event is irrelevant in * this case and can be left as KTIME_MAX. */ if (time_before_eq(nextevt, basej + 1)) { /* If we missed a tick already, force 0 delta */ if (time_before(nextevt, basej)) nextevt = basej; tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * This is required for the remote check only but it doesn't * hurt, when it is done for both call sites: * * * The remote callers will only take care of the global timers * as local timers will be handled by CPU itself. When not * updating tevt->global with the already missed first global * timer, it is possible that it will be missed completely. * * * The local callers will ignore the tevt->global anyway, when * nextevt is max. one tick away. */ if (!local_first) tevt->global = tevt->local; return nextevt; } /* * Update tevt.* values: * * If the local queue expires first, then the global event can be * ignored. If the global queue is empty, nothing to do either. */ if (!local_first && base_global->timers_pending) tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC; if (base_local->timers_pending) tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC; return nextevt; } # ifdef CONFIG_SMP /** * fetch_next_timer_interrupt_remote() - Store next timers into @tevt * @basej: base time jiffies * @basem: base time clock monotonic * @tevt: Pointer to the storage for the expiry values * @cpu: Remote CPU * * Stores the next pending local and global timer expiry values in the * struct pointed to by @tevt. If a queue is empty the corresponding * field is set to KTIME_MAX. If local event expires before global * event, global event is set to KTIME_MAX as well. * * Caller needs to make sure timer base locks are held (use * timer_lock_remote_bases() for this purpose). */ void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, struct timer_events *tevt, unsigned int cpu) { struct timer_base *base_local, *base_global; /* Preset local / global events */ tevt->local = tevt->global = KTIME_MAX; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_held(&base_local->lock); lockdep_assert_held(&base_global->lock); fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt); } /** * timer_unlock_remote_bases - unlock timer bases of cpu * @cpu: Remote CPU * * Unlocks the remote timer bases. */ void timer_unlock_remote_bases(unsigned int cpu) __releases(timer_bases[BASE_LOCAL]->lock) __releases(timer_bases[BASE_GLOBAL]->lock) { struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock); } /** * timer_lock_remote_bases - lock timer bases of cpu * @cpu: Remote CPU * * Locks the remote timer bases. */ void timer_lock_remote_bases(unsigned int cpu) __acquires(timer_bases[BASE_LOCAL]->lock) __acquires(timer_bases[BASE_GLOBAL]->lock) { struct timer_base *base_local, *base_global; base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); lockdep_assert_irqs_disabled(); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); } /** * timer_base_is_idle() - Return whether timer base is set idle * * Returns value of local timer base is_idle value. */ bool timer_base_is_idle(void) { return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle); } static void __run_timer_base(struct timer_base *base); /** * timer_expire_remote() - expire global timers of cpu * @cpu: Remote CPU * * Expire timers of global base of remote CPU. */ void timer_expire_remote(unsigned int cpu) { struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); __run_timer_base(base); } static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { u64 next_tmigr; if (timer_base_idle) next_tmigr = tmigr_cpu_new_timer(tevt->global); else if (tick_stop_path) next_tmigr = tmigr_cpu_deactivate(tevt->global); else next_tmigr = tmigr_quick_check(tevt->global); /* * If the CPU is the last going idle in timer migration hierarchy, make * sure the CPU will wake up in time to handle remote timers. * next_tmigr == KTIME_MAX if other CPUs are still active. */ if (next_tmigr < tevt->local) { u64 tmp; /* If we missed a tick already, force 0 delta */ if (next_tmigr < basem) next_tmigr = basem; tmp = div_u64(next_tmigr - basem, TICK_NSEC); *nextevt = basej + (unsigned long)tmp; tevt->local = next_tmigr; } } # else static void timer_use_tmigr(unsigned long basej, u64 basem, unsigned long *nextevt, bool *tick_stop_path, bool timer_base_idle, struct timer_events *tevt) { /* * Make sure first event is written into tevt->local to not miss a * timer on !SMP systems. */ tevt->local = min_t(u64, tevt->local, tevt->global); } # endif /* CONFIG_SMP */ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, bool *idle) { struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX }; struct timer_base *base_local, *base_global; unsigned long nextevt; bool idle_is_possible; /* * When the CPU is offline, the tick is cancelled and nothing is supposed * to try to stop it. */ if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) { if (idle) *idle = true; return tevt.local; } base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]); base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]); raw_spin_lock(&base_local->lock); raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); nextevt = fetch_next_timer_interrupt(basej, basem, base_local, base_global, &tevt); /* * If the next event is only one jiffy ahead there is no need to call * timer migration hierarchy related functions. The value for the next * global timer in @tevt struct equals then KTIME_MAX. This is also * true, when the timer base is idle. * * The proper timer migration hierarchy function depends on the callsite * and whether timer base is idle or not. @nextevt will be updated when * this CPU needs to handle the first timer migration hierarchy * event. See timer_use_tmigr() for detailed information. */ idle_is_possible = time_after(nextevt, basej + 1); if (idle_is_possible) timer_use_tmigr(basej, basem, &nextevt, idle, base_local->is_idle, &tevt); /* * We have a fresh next event. Check whether we can forward the * base. */ __forward_timer_base(base_local, basej); __forward_timer_base(base_global, basej); /* * Set base->is_idle only when caller is timer_base_try_to_set_idle() */ if (idle) { /* * Bases are idle if the next event is more than a tick * away. Caution: @nextevt could have changed by enqueueing a * global timer into timer migration hierarchy. Therefore a new * check is required here. * * If the base is marked idle then any timer add operation must * forward the base clk itself to keep granularity small. This * idle logic is only maintained for the BASE_LOCAL and * BASE_GLOBAL base, deferrable timers may still see large * granularity skew (by design). */ if (!base_local->is_idle && time_after(nextevt, basej + 1)) { base_local->is_idle = true; /* * Global timers queued locally while running in a task * in nohz_full mode need a self-IPI to kick reprogramming * in IRQ tail. */ if (tick_nohz_full_cpu(base_local->cpu)) base_global->is_idle = true; trace_timer_base_idle(true, base_local->cpu); } *idle = base_local->is_idle; /* * When timer base is not set idle, undo the effect of * tmigr_cpu_deactivate() to prevent inconsistent states - active * timer base but inactive timer migration hierarchy. * * When timer base was already marked idle, nothing will be * changed here. */ if (!base_local->is_idle && idle_is_possible) tmigr_cpu_activate(); } raw_spin_unlock(&base_global->lock); raw_spin_unlock(&base_local->lock); return cmp_next_hrtimer_event(basem, tevt.local); } /** * get_next_timer_interrupt() - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. If timer of global base was queued into * timer migration hierarchy, first global timer is not taken into account. If * it was the last CPU of timer migration hierarchy going idle, first global * event is taken into account. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { return __get_next_timer_interrupt(basej, basem, NULL); } /** * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases * @basej: base time jiffies * @basem: base time clock monotonic * @idle: pointer to store the value of timer_base->is_idle on return; * *idle contains the information whether tick was already stopped * * Returns the tick aligned clock monotonic time of the next pending timer or * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is * returned as well. */ u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) { if (*idle) return KTIME_MAX; return __get_next_timer_interrupt(basej, basem, idle); } /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */ void timer_clear_idle(void) { /* * We do this unlocked. The worst outcome is a remote pinned timer * enqueue sending a pointless IPI, but taking the lock would just * make the window for sending the IPI a few instructions smaller * for the cost of taking the lock in the exit from idle * path. Required for BASE_LOCAL only. */ __this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false); if (tick_nohz_full_cpu(smp_processor_id())) __this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false); trace_timer_base_idle(false, smp_processor_id()); /* Activate without holding the timer_base->lock */ tmigr_cpu_activate(); } #endif /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */ static inline void __run_timers(struct timer_base *base) { struct hlist_head heads[LVL_DEPTH]; int levels; lockdep_assert_held(&base->lock); if (base->running_timer) return; while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* * The two possible reasons for not finding any expired * timer at this clk are that all matching timers have been * dequeued or no timer has been queued since * base::next_expiry was set to base::clk + * TIMER_NEXT_MAX_DELTA. */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); /* * While executing timers, base->clk is set 1 offset ahead of * jiffies to avoid endless requeuing to current jiffies. */ base->clk++; timer_recalc_next_expiry(base); while (levels--) expire_timers(base, heads + levels); } } static void __run_timer_base(struct timer_base *base) { /* Can race against a remote CPU updating next_expiry under the lock */ if (time_before(jiffies, READ_ONCE(base->next_expiry))) return; timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); __run_timers(base); raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } static void run_timer_base(int index) { struct timer_base *base = this_cpu_ptr(&timer_bases[index]); __run_timer_base(base); } /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(void) { run_timer_base(BASE_LOCAL); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { run_timer_base(BASE_GLOBAL); run_timer_base(BASE_DEF); if (is_timers_nohz_active()) tmigr_handle_remote(); } } /* * Called by the local, per-CPU timer interrupt on SMP. */ static void run_local_timers(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); hrtimer_run_queues(); for (int i = 0; i < NR_BASES; i++, base++) { /* * Raise the softirq only if required. * * timer_base::next_expiry can be written by a remote CPU while * holding the lock. If this write happens at the same time than * the lockless local read, sanity checker could complain about * data corruption. * * There are two possible situations where * timer_base::next_expiry is written by a remote CPU: * * 1. Remote CPU expires global timers of this CPU and updates * timer_base::next_expiry of BASE_GLOBAL afterwards in * next_timer_interrupt() or timer_recalc_next_expiry(). The * worst outcome is a superfluous raise of the timer softirq * when the not yet updated value is read. * * 2. A new first pinned timer is enqueued by a remote CPU * and therefore timer_base::next_expiry of BASE_LOCAL is * updated. When this update is missed, this isn't a * problem, as an IPI is executed nevertheless when the CPU * was idle before. When the CPU wasn't idle but the update * is missed, then the timer would expire one jiffy late - * bad luck. * * Those unlikely corner cases where the worst outcome is only a * one jiffy delay or a superfluous raise of the softirq are * not that expensive as doing the check always while holding * the lock. * * Possible remote writers are using WRITE_ONCE(). Local reader * uses therefore READ_ONCE(). */ if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) || (i == BASE_DEF && tmigr_requires_handle_remote())) { raise_timer_softirq(TIMER_SOFTIRQ); return; } } } /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. */ void update_process_times(int user_tick) { struct task_struct *p = current; /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); rcu_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); #endif sched_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { struct timer_list *timer; int cpu = new_base->cpu; while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } int timers_prepare_cpu(unsigned int cpu) { struct timer_base *base; int b; for (b = 0; b < NR_BASES; b++) { base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + TIMER_NEXT_MAX_DELTA; base->next_expiry_recalc = false; base->timers_pending = false; base->is_idle = false; } return 0; } int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; struct timer_base *new_base; int b, i; for (b = 0; b < NR_BASES; b++) { old_base = per_cpu_ptr(&timer_bases[b], cpu); new_base = get_cpu_ptr(&timer_bases[b]); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock_irq(&new_base->lock); raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); /* * The current CPUs base clock might be stale. Update it * before moving the timers over. */ forward_timer_base(new_base); WARN_ON_ONCE(old_base->running_timer); old_base->running_timer = NULL; for (i = 0; i < WHEEL_SIZE; i++) migrate_timer_list(new_base, old_base->vectors + i); raw_spin_unlock(&old_base->lock); raw_spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } return 0; } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) { struct timer_base *base; int i; for (i = 0; i < NR_BASES; i++) { base = per_cpu_ptr(&timer_bases[i], cpu); base->cpu = cpu; raw_spin_lock_init(&base->lock); base->clk = jiffies; base->next_expiry = base->clk + TIMER_NEXT_MAX_DELTA; timer_base_init_expiry_lock(base); } } static void __init init_timer_cpus(void) { int cpu; for_each_possible_cpu(cpu) init_timer_cpu(cpu); } void __init timers_init(void) { init_timer_cpus(); posix_cputimers_init_work(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> struct fs_struct { int users; seqlock_t seq; int umask; int in_exec; struct path root, pwd; } __randomize_layout; extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, const struct path *); extern void set_fs_pwd(struct fs_struct *, const struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void free_fs_struct(struct fs_struct *); extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { read_seqlock_excl(&fs->seq); *root = fs->root; path_get(root); read_sequnlock_excl(&fs->seq); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { read_seqlock_excl(&fs->seq); *pwd = fs->pwd; path_get(pwd); read_sequnlock_excl(&fs->seq); } extern bool current_chrooted(void); #endif /* _LINUX_FS_STRUCT_H */ |
| 950 314 1044 1050 1053 1048 314 314 314 945 945 945 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(rstat_base_lock); static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); /* * Determines whether a given css can participate in rstat. * css's that are cgroup::self use rstat for base stats. * Other css's associated with a subsystem use rstat only when * they define the ss->css_rstat_flush callback. */ static inline bool css_uses_rstat(struct cgroup_subsys_state *css) { return css_is_self(css) || css->ss->css_rstat_flush != NULL; } static struct css_rstat_cpu *css_rstat_cpu( struct cgroup_subsys_state *css, int cpu) { return per_cpu_ptr(css->rstat_cpu, cpu); } static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu( struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_base_cpu, cpu); } static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss) { if (ss) return &ss->rstat_ss_lock; return &rstat_base_lock; } static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) { if (ss) return per_cpu_ptr(ss->lhead, cpu); return per_cpu_ptr(&rstat_backlog_list, cpu); } /** * css_rstat_updated - keep track of updated rstat_cpu * @css: target cgroup subsystem state * @cpu: cpu on which rstat_cpu was updated * * Atomically inserts the css in the ss's llist for the given cpu. This is * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist * will be processed at the flush time to create the update tree. * * NOTE: if the user needs the guarantee that the updater either add itself in * the lockless list or the concurrent flusher flushes its updated stats, a * memory barrier is needed before the call to css_rstat_updated() i.e. a * barrier after updating the per-cpu stats and before calling * css_rstat_updated(). */ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct css_rstat_cpu __percpu *rstatc_pcpu; struct llist_node *self; /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; lockdep_assert_preemption_disabled(); /* * For archs withnot nmi safe cmpxchg or percpu ops support, ignore * the requests from nmi context. */ if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) || !IS_ENABLED(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS)) && in_nmi()) return; rstatc = css_rstat_cpu(css, cpu); /* * If already on list return. This check is racy and smp_mb() is needed * to pair it with the smp_mb() in css_process_update_tree() if the * guarantee that the updated stats are visible to concurrent flusher is * needed. */ if (llist_on_list(&rstatc->lnode)) return; /* * This function can be renentered by irqs and nmis for the same cgroup * and may try to insert the same per-cpu lnode into the llist. Note * that llist_add() does not protect against such scenarios. * * To protect against such stacked contexts of irqs/nmis, we use the * fact that lnode points to itself when not on a list and then use * this_cpu_cmpxchg() to atomically set to NULL to select the winner * which will call llist_add(). The losers can assume the insertion is * successful and the winner will eventually add the per-cpu lnode to * the llist. */ self = &rstatc->lnode; rstatc_pcpu = css->rstat_cpu; if (this_cpu_cmpxchg(rstatc_pcpu->lnode.next, self, NULL) != self) return; lhead = ss_lhead_cpu(css->ss, cpu); llist_add(&rstatc->lnode, lhead); } static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu) { /* put @css and all ancestors on the corresponding updated lists */ while (true) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); struct cgroup_subsys_state *parent = css->parent; struct css_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = css; break; } prstatc = css_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = css; css = parent; } } static void css_process_update_tree(struct cgroup_subsys *ss, int cpu) { struct llist_head *lhead = ss_lhead_cpu(ss, cpu); struct llist_node *lnode; while ((lnode = llist_del_first_init(lhead))) { struct css_rstat_cpu *rstatc; /* * smp_mb() is needed here (more specifically in between * init_llist_node() and per-cpu stats flushing) if the * guarantee is required by a rstat user where etiher the * updater should add itself on the lockless list or the * flusher flush the stats updated by the updater who have * observed that they are already on the list. The * corresponding barrier pair for this one should be before * css_rstat_updated() by the user. * * For now, there aren't any such user, so not adding the * barrier here but if such a use-case arise, please add * smp_mb() here. */ rstatc = container_of(lnode, struct css_rstat_cpu, lnode); __css_process_update_tree(rstatc->owner, cpu); } } /** * css_rstat_push_children - push children css's into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of css's to be flushed * * Iteratively traverse down the css_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list via the rstat_flush_next pointer built from the * tail backward like "pushing" css's into a stack. The root is pushed by * the caller. */ static struct cgroup_subsys_state *css_rstat_push_children( struct cgroup_subsys_state *head, struct cgroup_subsys_state *child, int cpu) { struct cgroup_subsys_state *cnext = child; /* Next head of child css level */ struct cgroup_subsys_state *ghead = NULL; /* Head of grandchild css level */ struct cgroup_subsys_state *parent, *grandchild; struct css_rstat_cpu *crstatc; child->rstat_flush_next = NULL; /* * The subsystem rstat lock must be held for the whole duration from * here as the rstat_flush_next list is being constructed to when * it is consumed later in css_rstat_flush(). */ lockdep_assert_held(ss_rstat_lock(head->ss)); /* * Notation: -> updated_next pointer * => rstat_flush_next pointer * * Assuming the following sample updated_children lists: * P: C1 -> C2 -> P * C1: G11 -> G12 -> C1 * C2: G21 -> G22 -> C2 * * After 1st iteration: * head => C2 => C1 => NULL * ghead => G21 => G11 => NULL * * After 2nd iteration: * head => G12 => G11 => G22 => G21 => C2 => C1 => NULL */ next_level: while (cnext) { child = cnext; cnext = child->rstat_flush_next; parent = child->parent; /* updated_next is parent cgroup terminated if !NULL */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = css_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { cnext = ghead; ghead = NULL; goto next_level; } return head; } /** * css_rstat_updated_list - build a list of updated css's to be flushed * @root: root of the css subtree to traverse * @cpu: target cpu * Return: A singly linked list of css's to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned css is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child css's if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent css. An exception * here is the css root whose updated_next can be self terminated. */ static struct cgroup_subsys_state *css_rstat_updated_list( struct cgroup_subsys_state *root, int cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu); struct cgroup_subsys_state *head = NULL, *parent, *child; css_process_update_tree(root->ss, cpu); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) return NULL; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = root->parent; if (parent) { struct css_rstat_cpu *prstatc; struct cgroup_subsys_state **nextp; prstatc = css_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct css_rstat_cpu *nrstatc; nrstatc = css_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = css_rstat_push_children(head, child, cpu); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for css_rstat_updated() and * css_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __css_rstat_lock(struct cgroup_subsys_state *css, int cpu_in_loop) __acquires(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; bool contended; lock = ss_rstat_lock(css->ss); contended = !spin_trylock_irq(lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __css_rstat_unlock(struct cgroup_subsys_state *css, int cpu_in_loop) __releases(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; lock = ss_rstat_lock(css->ss); trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(lock); } /** * css_rstat_flush - flush stats in @css's rstat subtree * @css: target cgroup subsystem state * * Collect all per-cpu stats in @css's subtree into the global counters * and propagate them upwards. After this function returns, all rstat * nodes in the subtree have up-to-date ->stat. * * This also gets all rstat nodes in the subtree including @css off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void css_rstat_flush(struct cgroup_subsys_state *css) { int cpu; bool is_self = css_is_self(css); /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; might_sleep(); for_each_possible_cpu(cpu) { struct cgroup_subsys_state *pos; /* Reacquire for each CPU to avoid disabling IRQs too long */ __css_rstat_lock(css, cpu); pos = css_rstat_updated_list(css, cpu); for (; pos; pos = pos->rstat_flush_next) { if (is_self) { cgroup_base_stat_flush(pos->cgroup, cpu); bpf_rstat_flush(pos->cgroup, cgroup_parent(pos->cgroup), cpu); } else pos->ss->css_rstat_flush(pos, cpu); } __css_rstat_unlock(css, cpu); if (!cond_resched()) cpu_relax(); } } int css_rstat_init(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; int cpu; bool is_self = css_is_self(css); if (is_self) { /* the root cgrp has rstat_base_cpu preallocated */ if (!cgrp->rstat_base_cpu) { cgrp->rstat_base_cpu = alloc_percpu(struct cgroup_rstat_base_cpu); if (!cgrp->rstat_base_cpu) return -ENOMEM; } } else if (css->ss->css_rstat_flush == NULL) return 0; /* the root cgrp's self css has rstat_cpu preallocated */ if (!css->rstat_cpu) { css->rstat_cpu = alloc_percpu(struct css_rstat_cpu); if (!css->rstat_cpu) { if (is_self) free_percpu(cgrp->rstat_base_cpu); return -ENOMEM; } } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); rstatc->owner = rstatc->updated_children = css; init_llist_node(&rstatc->lnode); if (is_self) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); u64_stats_init(&rstatbc->bsync); } } return 0; } void css_rstat_exit(struct cgroup_subsys_state *css) { int cpu; if (!css_uses_rstat(css)) return; if (!css->rstat_cpu) return; css_rstat_flush(css); /* sanity check */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); if (WARN_ON_ONCE(rstatc->updated_children != css) || WARN_ON_ONCE(rstatc->updated_next)) return; } if (css_is_self(css)) { struct cgroup *cgrp = css->cgroup; free_percpu(cgrp->rstat_base_cpu); cgrp->rstat_base_cpu = NULL; } free_percpu(css->rstat_cpu); css->rstat_cpu = NULL; } /** * ss_rstat_init - subsystem-specific rstat initialization * @ss: target subsystem * * If @ss is NULL, the static locks associated with the base stats * are initialized. If @ss is non-NULL, the subsystem-specific locks * are initialized. */ int __init ss_rstat_init(struct cgroup_subsys *ss) { int cpu; if (ss) { ss->lhead = alloc_percpu(struct llist_head); if (!ss->lhead) return -ENOMEM; } spin_lock_init(ss_rstat_lock(ss)); for_each_possible_cpu(cpu) init_llist_head(ss_lhead_cpu(ss, cpu)); return 0; } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif dst_bstat->ntime += src_bstat->ntime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif dst_bstat->ntime -= src_bstat->ntime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_base_cpu *rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_base_cpu *prstatbc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatbc->bsync); delta = rstatbc->bstat; } while (__u64_stats_fetch_retry(&rstatbc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatbc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatbc->last_bstat, &delta); cgroup_base_stat_add(&rstatbc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatbc->subtree_bstat; prstatbc = cgroup_rstat_base_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatbc->last_subtree_bstat); cgroup_base_stat_add(&prstatbc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatbc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_base_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = get_cpu_ptr(cgrp->rstat_base_cpu); *flags = u64_stats_update_begin_irqsave(&rstatbc->bsync); return rstatbc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_base_cpu *rstatbc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatbc->bsync, flags); css_rstat_updated(&cgrp->self, smp_processor_id()); put_cpu_ptr(rstatbc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatbc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_NICE: rstatbc->bstat.ntime += delta_exec; fallthrough; case CPUTIME_USER: rstatbc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatbc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatbc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif bstat->ntime += cpustat[CPUTIME_NICE]; } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_base_stat bstat; if (cgroup_parent(cgrp)) { css_rstat_flush(&cgrp->self); __css_rstat_lock(&cgrp->self, -1); bstat = cgrp->bstat; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &bstat.cputime.utime, &bstat.cputime.stime); __css_rstat_unlock(&cgrp->self, -1); } else { root_cgroup_cputime(&bstat); } do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC); do_div(bstat.cputime.utime, NSEC_PER_USEC); do_div(bstat.cputime.stime, NSEC_PER_USEC); do_div(bstat.ntime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n" "nice_usec %llu\n", bstat.cputime.sum_exec_runtime, bstat.cputime.utime, bstat.cputime.stime, bstat.ntime); cgroup_force_idle_show(seq, &bstat); } /* Add bpf kfuncs for css_rstat_updated() and css_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, css_rstat_updated) BTF_ID_FLAGS(func, css_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Generic netlink support functions to configure an SMC-R PNET table * * Copyright IBM Corp. 2016 * * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> */ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> #include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> #include <uapi/linux/if.h> #include <uapi/linux/smc.h> #include <rdma/ib_verbs.h> #include <net/netns/generic.h> #include "smc_netns.h" #include "smc_pnet.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_core.h" static struct net_device *__pnet_find_base_ndev(struct net_device *ndev); static struct net_device *pnet_find_base_ndev(struct net_device *ndev); static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [SMC_PNETID_IBNAME] = { .type = NLA_NUL_STRING, .len = IB_DEVICE_NAME_MAX - 1 }, [SMC_PNETID_IBPORT] = { .type = NLA_U8 } }; static struct genl_family smc_pnet_nl_family; enum smc_pnet_nametype { SMC_PNET_ETH = 1, SMC_PNET_IB = 2, }; /* pnet entry stored in pnet table */ struct smc_pnetentry { struct list_head list; char pnet_name[SMC_MAX_PNETID_LEN + 1]; enum smc_pnet_nametype type; union { struct { char eth_name[IFNAMSIZ + 1]; struct net_device *ndev; netdevice_tracker dev_tracker; }; struct { char ib_name[IB_DEVICE_NAME_MAX + 1]; u8 ib_port; }; }; }; /* Check if the pnetid is set */ bool smc_pnet_is_pnetid_set(u8 *pnetid) { if (pnetid[0] == 0 || pnetid[0] == _S) return false; return true; } /* Check if two given pnetids match */ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2) { int i; for (i = 0; i < SMC_MAX_PNETID_LEN; i++) { if ((pnetid1[i] == 0 || pnetid1[i] == _S) && (pnetid2[i] == 0 || pnetid2[i] == _S)) break; if (pnetid1[i] != pnetid2[i]) return false; } return true; } /* Remove a pnetid from the pnet table. */ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct smc_ib_device *ibdev; struct smcd_dev *smcd; struct smc_net *sn; int rc = -ENOENT; int ibport; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* remove table entry */ mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || smc_pnet_match(pnetelem->pnet_name, pnet_name)) { list_del(&pnetelem->list); if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pr_warn_ratelimited("smc: net device %s " "erased user defined " "pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); } kfree(pnetelem); rc = 0; } } mutex_unlock(&pnettable->lock); /* if this is not the initial namespace, stop here */ if (net != &init_net) return rc; /* remove ib devices */ mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && (!pnet_name || smc_pnet_match(pnet_name, ibdev->pnetid[ibport]))) { pr_warn_ratelimited("smc: ib device %s ibport " "%d erased user defined " "pnetid %.16s\n", ibdev->ibdev->name, ibport + 1, ibdev->pnetid[ibport]); memset(ibdev->pnetid[ibport], 0, SMC_MAX_PNETID_LEN); ibdev->pnetid_by_user[ibport] = false; rc = 0; } } } mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->pnetid_by_user && (!pnet_name || smc_pnet_match(pnet_name, smcd->pnetid))) { pr_warn_ratelimited("smc: smcd device %s " "erased user defined pnetid " "%.16s\n", dev_name(smcd->ops->get_dev(smcd)), smcd->pnetid); memset(smcd->pnetid, 0, SMC_MAX_PNETID_LEN); smcd->pnetid_by_user = false; rc = 0; } } mutex_unlock(&smcd_dev_list.mutex); return rc; } /* Add the reference to a given network device to the pnet table. */ static int smc_pnet_add_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { netdev_hold(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); pnetelem->ndev = ndev; rc = 0; pr_warn_ratelimited("smc: adding net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Remove the reference to a given network device from the pnet table. */ static int smc_pnet_remove_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pnetelem->ndev = NULL; rc = 0; pr_warn_ratelimited("smc: removing net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Apply pnetid to ib device when no pnetid is set. */ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, char *pnet_name) { bool applied = false; mutex_lock(&smc_ib_devices.mutex); if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } mutex_unlock(&smc_ib_devices.mutex); return applied; } /* Apply pnetid to smcd device when no pnetid is set. */ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) { bool applied = false; mutex_lock(&smcd_dev_list.mutex); if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } mutex_unlock(&smcd_dev_list.mutex); return applied; } /* The limit for pnetid is 16 characters. * Valid characters should be (single-byte character set) a-z, A-Z, 0-9. * Lower case letters are converted to upper case. * Interior blanks should not be used. */ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) { char *bf = skip_spaces(pnet_name); size_t len = strlen(bf); char *end = bf + len; if (!len) return false; while (--end >= bf && isspace(*end)) ; if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) return false; *pnetid++ = islower(*bf) ? toupper(*bf) : *bf; bf++; } *pnetid = '\0'; return true; } /* Find an infiniband device by a given name. The device might not exist. */ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || (ibdev->ibdev->dev.parent && !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, IB_DEVICE_NAME_MAX - 1))) { goto out; } } ibdev = NULL; out: mutex_unlock(&smc_ib_devices.mutex); return ibdev; } /* Find an smcd device by a given name. The device might not exist. */ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(smcd_dev->ops->get_dev(smcd_dev)), smcd_name, IB_DEVICE_NAME_MAX - 1)) goto out; } smcd_dev = NULL; out: mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, char *eth_name, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct net_device *ndev, *base_ndev; u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; bool new_netdev; int rc; /* check if (base) netdev already has a pnetid. If there is one, we do * not want to add a pnet table entry */ rc = -EEXIST; ndev = dev_get_by_name(net, eth_name); /* dev_hold() */ if (ndev) { base_ndev = pnet_find_base_ndev(ndev); if (!smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid)) goto out_put; } /* add a new netdev entry to the pnet table if there isn't one */ rc = -ENOMEM; new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) goto out_put; new_pe->type = SMC_PNET_ETH; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strscpy(new_pe->eth_name, eth_name); rc = -EEXIST; new_netdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { new_netdev = false; break; } } if (new_netdev) { if (ndev) { new_pe->ndev = ndev; netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_ATOMIC); } list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } if (ndev) pr_warn_ratelimited("smc: net device %s " "applied user defined pnetid %.16s\n", new_pe->eth_name, new_pe->pnet_name); return 0; out_put: dev_put(ndev); return rc; } static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, u8 ib_port, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct smc_ib_device *ib_dev; bool smcddev_applied = true; bool ibdev_applied = true; struct smcd_dev *smcd; struct device *dev; bool new_ibdev; /* try to apply the pnetid to active devices */ ib_dev = smc_pnet_find_ib(ib_name); if (ib_dev) { ibdev_applied = smc_pnet_apply_ib(ib_dev, ib_port, pnet_name); if (ibdev_applied) pr_warn_ratelimited("smc: ib device %s ibport %d " "applied user defined pnetid " "%.16s\n", ib_dev->ibdev->name, ib_port, ib_dev->pnetid[ib_port - 1]); } smcd = smc_pnet_find_smcd(ib_name); if (smcd) { smcddev_applied = smc_pnet_apply_smcd(smcd, pnet_name); if (smcddev_applied) { dev = smcd->ops->get_dev(smcd); pr_warn_ratelimited("smc: smcd device %s " "applied user defined pnetid " "%.16s\n", dev_name(dev), smcd->pnetid); } } /* Apply fails when a device has a hardware-defined pnetid set, do not * add a pnet table entry in that case. */ if (!ibdev_applied || !smcddev_applied) return -EEXIST; /* add a new ib entry to the pnet table if there isn't one */ new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) return -ENOMEM; new_pe->type = SMC_PNET_IB; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX); new_pe->ib_port = ib_port; new_ibdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { new_ibdev = false; break; } } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; } /* Append a pnetid to the end of the pnet table if not already on this list. */ static int smc_pnet_enter(struct net *net, struct nlattr *tb[]) { char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct smc_pnettable *pnettable; bool new_netdev = false; bool new_ibdev = false; struct smc_net *sn; u8 ibport = 1; char *string; int rc; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; rc = -EINVAL; if (!tb[SMC_PNETID_NAME]) goto error; string = (char *)nla_data(tb[SMC_PNETID_NAME]); if (!smc_pnetid_valid(string, pnet_name)) goto error; if (tb[SMC_PNETID_ETHNAME]) { string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); rc = smc_pnet_add_eth(pnettable, net, string, pnet_name); if (!rc) new_netdev = true; else if (rc != -EEXIST) goto error; } /* if this is not the initial namespace, stop here */ if (net != &init_net) return new_netdev ? 0 : -EEXIST; rc = -EINVAL; if (tb[SMC_PNETID_IBNAME]) { string = (char *)nla_data(tb[SMC_PNETID_IBNAME]); string = strim(string); if (tb[SMC_PNETID_IBPORT]) { ibport = nla_get_u8(tb[SMC_PNETID_IBPORT]); if (ibport < 1 || ibport > SMC_MAX_PORTS) goto error; } rc = smc_pnet_add_ib(pnettable, string, ibport, pnet_name); if (!rc) new_ibdev = true; else if (rc != -EEXIST) goto error; } return (new_netdev || new_ibdev) ? 0 : -EEXIST; error: return rc; } /* Convert an smc_pnetentry to a netlink attribute sequence */ static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem) { if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name)) return -1; if (pnetelem->type == SMC_PNET_ETH) { if (nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->eth_name)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a")) return -1; } if (pnetelem->type == SMC_PNET_IB) { if (nla_put_string(msg, SMC_PNETID_IBNAME, pnetelem->ib_name) || nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") || nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff)) return -1; } return 0; } static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); return smc_pnet_enter(net, info->attrs); } static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; return smc_pnet_remove_by_pnetid(net, (char *)nla_data(info->attrs[SMC_PNETID_NAME])); } static int smc_pnet_dump_start(struct netlink_callback *cb) { cb->args[0] = 0; return 0; } static int smc_pnet_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, u32 flags, struct smc_pnetentry *pnetelem) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family, flags, SMC_PNETID_GET); if (!hdr) return -ENOMEM; if (smc_pnet_set_nla(skb, pnetelem) < 0) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; } genlmsg_end(skb, hdr); return 0; } static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid, int start_idx) { struct smc_pnettable *pnettable; struct smc_pnetentry *pnetelem; struct smc_net *sn; int idx = 0; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* dump pnettable entries */ mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; if (idx++ < start_idx) continue; /* if this is not the initial namespace, dump only netdev */ if (net != &init_net && pnetelem->type != SMC_PNET_ETH) continue; if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI, pnetelem)) { --idx; break; } } mutex_unlock(&pnettable->lock); return idx; } static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx; idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NULL, cb->args[0]); cb->args[0] = idx; return skb->len; } /* Retrieve one PNETID entry */ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct sk_buff *msg; void *hdr; if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; _smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq, nla_data(info->attrs[SMC_PNETID_NAME]), 0); /* finish multi part message and send it */ hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, NLM_F_MULTI); if (!hdr) { nlmsg_free(msg); return -EMSGSIZE; } return genlmsg_reply(msg, info); } /* Remove and delete all pnetids from pnet table. */ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); smc_pnet_remove_by_pnetid(net, NULL); return 0; } /* SMC_PNETID generic netlink operation definition */ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start }, { .cmd = SMC_PNETID_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_flush } }; /* SMC_PNETID family definition */ static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, .policy = smc_pnet_policy, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, .n_ops = ARRAY_SIZE(smc_pnet_ops), .resv_start_op = SMC_PNETID_FLUSH + 1, }; bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe; bool rc = false; read_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pe, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { rc = true; goto unlock; } } unlock: read_unlock(&sn->pnetids_ndev.lock); return rc; } static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pi; pe = kzalloc(sizeof(*pe), GFP_KERNEL); if (!pe) return -ENOMEM; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pi->pnetid)) { refcount_inc(&pi->refcnt); kfree(pe); goto unlock; } } refcount_set(&pe->refcnt, 1); memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN); list_add_tail(&pe->list, &sn->pnetids_ndev.list); unlock: write_unlock(&sn->pnetids_ndev.lock); return 0; } static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pe2; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { if (refcount_dec_and_test(&pe->refcnt)) { list_del(&pe->list); kfree(pe); } break; } } write_unlock(&sn->pnetids_ndev.lock); } static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev, u8 *ndev_pnetid) { struct net_device *base_dev; base_dev = __pnet_find_base_ndev(dev); if (base_dev->flags & IFF_UP && !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port, ndev_pnetid)) { /* add to PNETIDs list */ smc_pnet_add_pnetid(net, ndev_pnetid); } } /* create initial list of netdevice pnetids */ static void smc_pnet_create_pnetids_list(struct net *net) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; /* Newly created netns do not have devices. * Do not even acquire rtnl. */ if (list_empty(&net->dev_base_head)) return; /* Note: This might not be needed, because smc_pnet_netdev_event() * is also calling smc_pnet_add_base_pnetid() when handling * NETDEV_UP event. */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); rtnl_unlock(); } /* clean up list of netdevice pnetids */ static void smc_pnet_destroy_pnetids_list(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *temp_pe; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) { list_del(&pe->list); kfree(pe); } write_unlock(&sn->pnetids_ndev.lock); } static int smc_pnet_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(event_dev); u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; switch (event) { case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_REGISTER: smc_pnet_add_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_UP: smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid); return NOTIFY_OK; case NETDEV_DOWN: event_dev = __pnet_find_base_ndev(event_dev); if (!smc_pnetid_by_dev_port(event_dev->dev.parent, event_dev->dev_port, ndev_pnetid)) { /* remove from PNETIDs list */ smc_pnet_remove_pnetid(net, ndev_pnetid); } return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block smc_netdev_notifier = { .notifier_call = smc_pnet_netdev_event }; /* init network namespace */ int smc_pnet_net_init(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnettable *pnettable = &sn->pnettable; struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock); smc_pnet_create_pnetids_list(net); return 0; } int __init smc_pnet_init(void) { int rc; rc = genl_register_family(&smc_pnet_nl_family); if (rc) return rc; rc = register_netdevice_notifier(&smc_netdev_notifier); if (rc) genl_unregister_family(&smc_pnet_nl_family); return rc; } /* exit network namespace */ void smc_pnet_net_exit(struct net *net) { /* flush pnet table */ smc_pnet_remove_by_pnetid(net, NULL); smc_pnet_destroy_pnetids_list(net); } void smc_pnet_exit(void) { unregister_netdevice_notifier(&smc_netdev_notifier); genl_unregister_family(&smc_pnet_nl_family); } static struct net_device *__pnet_find_base_ndev(struct net_device *ndev) { int i, nest_lvl; ASSERT_RTNL(); nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; if (list_empty(lower)) break; lower = lower->next; ndev = netdev_lower_get_next(ndev, &lower); } return ndev; } /* Determine one base device for stacked net devices. * If the lower device level contains more than one devices * (for instance with bonding slaves), just the first device * is used to reach a base device. */ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { rtnl_lock(); ndev = __pnet_find_base_ndev(ndev); rtnl_unlock(); return ndev; } static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, u8 *pnetid) { struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_pnetentry *pnetelem; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, struct smc_init_info *ini) { if (!ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, NULL)) { ini->ib_dev = ibdev; ini->ib_port = i; return 0; } if (ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, NULL, &ini->smcrv2)) { ini->smcrv2.ib_dev_v2 = ibdev; ini->smcrv2.ib_port_v2 = i; return 0; } return -ENODEV; } /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, struct smc_ib_device *known_dev, struct net *net) { struct smc_ib_device *ibdev; int i; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev || !rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) goto out; } } } out: mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id, vlan_id and net namespace */ void smc_pnet_find_alt_roce(struct smc_link_group *lgr, struct smc_init_info *ini, struct smc_ib_device *known_dev) { struct net *net = lgr->net; _smc_pnet_find_roce_by_pnetid(lgr->pnet_id, ini, known_dev, net); } /* if handshake network device belongs to a roce device, return its * IB device and port */ static void smc_pnet_find_rdma_dev(struct net_device *netdev, struct smc_init_info *ini) { struct net *net = dev_net(netdev); struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; /* check rdma net namespace */ if (!rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; ndev = ib_device_get_netdev(ibdev->ibdev, i); if (!ndev) continue; dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) break; } } } mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. * Searching stops at the first matching active IB device port with vlan_id * configured. * If nothing found, check pnetid table. * If nothing found, try to use handshake device */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *base_ndev; struct net *net; base_ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); if (smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(base_ndev, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { smc_pnet_find_rdma_dev(base_ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); } static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct smcd_dev *ismdev; ndev = pnet_find_base_ndev(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away && (!ini->ism_peer_gid[0].gid || !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id, ismdev))) { ini->ism_dev[0] = ismdev; break; } } mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: * determine ib_device and port belonging to used internal TCP socket * ethernet interface. */ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_roce_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); ini->ism_dev[0] = NULL; if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_ism_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } /* Lookup and apply a pnet table entry to the given ib device. */ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) { char *ib_name = smcibdev->ibdev->name; struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && tmp_pe->ib_port == ib_port) { smc_pnet_apply_ib(smcibdev, ib_port, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } /* Lookup and apply a pnet table entry to the given smcd device. */ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) { const char *ib_name = dev_name(smcddev->ops->get_dev(smcddev)); struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { smc_pnet_apply_smcd(smcddev, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } |
| 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015 Imagination Technologies Ltd * Author: Qais Yousef <qais.yousef@imgtec.com> * * This file contains driver APIs to the IPI subsystem. */ #define pr_fmt(fmt) "genirq/ipi: " fmt #include <linux/irqdomain.h> #include <linux/irq.h> /** * irq_reserve_ipi() - Setup an IPI to destination cpumask * @domain: IPI domain * @dest: cpumask of CPUs which can receive the IPI * * Allocate a virq that can be used to send IPI to any CPU in dest mask. * * Return: Linux IRQ number on success or error code on failure */ int irq_reserve_ipi(struct irq_domain *domain, const struct cpumask *dest) { unsigned int nr_irqs, offset; struct irq_data *data; int virq, i; if (!domain ||!irq_domain_is_ipi(domain)) { pr_warn("Reservation on a non IPI domain\n"); return -EINVAL; } if (!cpumask_subset(dest, cpu_possible_mask)) { pr_warn("Reservation is not in possible_cpu_mask\n"); return -EINVAL; } nr_irqs = cpumask_weight(dest); if (!nr_irqs) { pr_warn("Reservation for empty destination mask\n"); return -EINVAL; } if (irq_domain_is_ipi_single(domain)) { /* * If the underlying implementation uses a single HW irq on * all cpus then we only need a single Linux irq number for * it. We have no restrictions vs. the destination mask. The * underlying implementation can deal with holes nicely. */ nr_irqs = 1; offset = 0; } else { unsigned int next; /* * The IPI requires a separate HW irq on each CPU. We require * that the destination mask is consecutive. If an * implementation needs to support holes, it can reserve * several IPI ranges. */ offset = cpumask_first(dest); /* * Find a hole and if found look for another set bit after the * hole. For now we don't support this scenario. */ next = cpumask_next_zero(offset, dest); if (next < nr_cpu_ids) next = cpumask_next(next, dest); if (next < nr_cpu_ids) { pr_warn("Destination mask has holes\n"); return -EINVAL; } } virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE, NULL); if (virq <= 0) { pr_warn("Can't reserve IPI, failed to alloc descs\n"); return -ENOMEM; } virq = __irq_domain_alloc_irqs(domain, virq, nr_irqs, NUMA_NO_NODE, (void *) dest, true, NULL); if (virq <= 0) { pr_warn("Can't reserve IPI, failed to alloc hw irqs\n"); goto free_descs; } for (i = 0; i < nr_irqs; i++) { data = irq_get_irq_data(virq + i); cpumask_copy(data->common->affinity, dest); data->common->ipi_offset = offset; irq_set_status_flags(virq + i, IRQ_NO_BALANCING); } return virq; free_descs: irq_free_descs(virq, nr_irqs); return -EBUSY; } /** * irq_destroy_ipi() - unreserve an IPI that was previously allocated * @irq: Linux IRQ number to be destroyed * @dest: cpumask of CPUs which should have the IPI removed * * The IPIs allocated with irq_reserve_ipi() are returned to the system * destroying all virqs associated with them. * * Return: %0 on success or error code on failure. */ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest) { struct irq_data *data = irq_get_irq_data(irq); const struct cpumask *ipimask; struct irq_domain *domain; unsigned int nr_irqs; if (!irq || !data) return -EINVAL; domain = data->domain; if (WARN_ON(domain == NULL)) return -EINVAL; if (!irq_domain_is_ipi(domain)) { pr_warn("Trying to destroy a non IPI domain!\n"); return -EINVAL; } ipimask = irq_data_get_affinity_mask(data); if (!ipimask || WARN_ON(!cpumask_subset(dest, ipimask))) /* * Must be destroying a subset of CPUs to which this IPI * was set up to target */ return -EINVAL; if (irq_domain_is_ipi_per_cpu(domain)) { irq = irq + cpumask_first(dest) - data->common->ipi_offset; nr_irqs = cpumask_weight(dest); } else { nr_irqs = 1; } irq_domain_free_irqs(irq, nr_irqs); return 0; } /** * ipi_get_hwirq - Get the hwirq associated with an IPI to a CPU * @irq: Linux IRQ number * @cpu: the target CPU * * When dealing with coprocessors IPI, we need to inform the coprocessor of * the hwirq it needs to use to receive and send IPIs. * * Return: hwirq value on success or INVALID_HWIRQ on failure. */ irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu) { struct irq_data *data = irq_get_irq_data(irq); const struct cpumask *ipimask; if (!data || cpu >= nr_cpu_ids) return INVALID_HWIRQ; ipimask = irq_data_get_affinity_mask(data); if (!ipimask || !cpumask_test_cpu(cpu, ipimask)) return INVALID_HWIRQ; /* * Get the real hardware irq number if the underlying implementation * uses a separate irq per cpu. If the underlying implementation uses * a single hardware irq for all cpus then the IPI send mechanism * needs to take care of the cpu destinations. */ if (irq_domain_is_ipi_per_cpu(data->domain)) data = irq_get_irq_data(irq + cpu - data->common->ipi_offset); return data ? irqd_to_hwirq(data) : INVALID_HWIRQ; } EXPORT_SYMBOL_GPL(ipi_get_hwirq); static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, const struct cpumask *dest, unsigned int cpu) { const struct cpumask *ipimask; if (!chip || !data) return -EINVAL; if (!chip->ipi_send_single && !chip->ipi_send_mask) return -EINVAL; if (cpu >= nr_cpu_ids) return -EINVAL; ipimask = irq_data_get_affinity_mask(data); if (!ipimask) return -EINVAL; if (dest) { if (!cpumask_subset(dest, ipimask)) return -EINVAL; } else { if (!cpumask_test_cpu(cpu, ipimask)) return -EINVAL; } return 0; } /** * __ipi_send_single - send an IPI to a target Linux SMP CPU * @desc: pointer to irq_desc of the IRQ * @cpu: destination CPU, must in the destination mask passed to * irq_reserve_ipi() * * This function is for architecture or core code to speed up IPI sending. Not * usable from driver code. * * Return: %0 on success or negative error number on failure. */ int __ipi_send_single(struct irq_desc *desc, unsigned int cpu) { struct irq_data *data = irq_desc_get_irq_data(desc); struct irq_chip *chip = irq_data_get_irq_chip(data); #ifdef DEBUG /* * Minimise the overhead by omitting the checks for Linux SMP IPIs. * Since the callers should be arch or core code which is generally * trusted, only check for errors when debugging. */ if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu))) return -EINVAL; #endif if (!chip->ipi_send_single) { chip->ipi_send_mask(data, cpumask_of(cpu)); return 0; } /* FIXME: Store this information in irqdata flags */ if (irq_domain_is_ipi_per_cpu(data->domain) && cpu != data->common->ipi_offset) { /* use the correct data for that cpu */ unsigned irq = data->irq + cpu - data->common->ipi_offset; data = irq_get_irq_data(irq); } chip->ipi_send_single(data, cpu); return 0; } /** * __ipi_send_mask - send an IPI to target Linux SMP CPU(s) * @desc: pointer to irq_desc of the IRQ * @dest: dest CPU(s), must be a subset of the mask passed to * irq_reserve_ipi() * * This function is for architecture or core code to speed up IPI sending. Not * usable from driver code. * * Return: %0 on success or negative error number on failure. */ int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest) { struct irq_data *data = irq_desc_get_irq_data(desc); struct irq_chip *chip = irq_data_get_irq_chip(data); unsigned int cpu; #ifdef DEBUG /* * Minimise the overhead by omitting the checks for Linux SMP IPIs. * Since the callers should be arch or core code which is generally * trusted, only check for errors when debugging. */ if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0))) return -EINVAL; #endif if (chip->ipi_send_mask) { chip->ipi_send_mask(data, dest); return 0; } if (irq_domain_is_ipi_per_cpu(data->domain)) { unsigned int base = data->irq; for_each_cpu(cpu, dest) { unsigned irq = base + cpu - data->common->ipi_offset; data = irq_get_irq_data(irq); chip->ipi_send_single(data, cpu); } } else { for_each_cpu(cpu, dest) chip->ipi_send_single(data, cpu); } return 0; } /** * ipi_send_single - Send an IPI to a single CPU * @virq: Linux IRQ number from irq_reserve_ipi() * @cpu: destination CPU, must in the destination mask passed to * irq_reserve_ipi() * * Return: %0 on success or negative error number on failure. */ int ipi_send_single(unsigned int virq, unsigned int cpu) { struct irq_desc *desc = irq_to_desc(virq); struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL; struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL; if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu))) return -EINVAL; return __ipi_send_single(desc, cpu); } EXPORT_SYMBOL_GPL(ipi_send_single); /** * ipi_send_mask - Send an IPI to target CPU(s) * @virq: Linux IRQ number from irq_reserve_ipi() * @dest: dest CPU(s), must be a subset of the mask passed to * irq_reserve_ipi() * * Return: %0 on success or negative error number on failure. */ int ipi_send_mask(unsigned int virq, const struct cpumask *dest) { struct irq_desc *desc = irq_to_desc(virq); struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL; struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL; if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0))) return -EINVAL; return __ipi_send_mask(desc, dest); } EXPORT_SYMBOL_GPL(ipi_send_mask); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_LOCAL64_H #define _ASM_GENERIC_LOCAL64_H #include <linux/percpu.h> #include <asm/types.h> /* * A signed long type for operations which are atomic for a single CPU. * Usually used in combination with per-cpu variables. * * This is the default implementation, which uses atomic64_t. Which is * rather pointless. The whole point behind local64_t is that some processors * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs * running on this CPU. local64_t allows exploitation of such capabilities. */ /* Implement in terms of atomics. */ #if BITS_PER_LONG == 64 #include <asm/local.h> typedef struct { local_t a; } local64_t; #define LOCAL64_INIT(i) { LOCAL_INIT(i) } #define local64_read(l) local_read(&(l)->a) #define local64_set(l,i) local_set((&(l)->a),(i)) #define local64_inc(l) local_inc(&(l)->a) #define local64_dec(l) local_dec(&(l)->a) #define local64_add(i,l) local_add((i),(&(l)->a)) #define local64_sub(i,l) local_sub((i),(&(l)->a)) #define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a)) #define local64_dec_and_test(l) local_dec_and_test(&(l)->a) #define local64_inc_and_test(l) local_inc_and_test(&(l)->a) #define local64_add_negative(i, l) local_add_negative((i), (&(l)->a)) #define local64_add_return(i, l) local_add_return((i), (&(l)->a)) #define local64_sub_return(i, l) local_sub_return((i), (&(l)->a)) #define local64_inc_return(l) local_inc_return(&(l)->a) static inline s64 local64_cmpxchg(local64_t *l, s64 old, s64 new) { return local_cmpxchg(&l->a, old, new); } static inline bool local64_try_cmpxchg(local64_t *l, s64 *old, s64 new) { return local_try_cmpxchg(&l->a, (long *)old, new); } #define local64_xchg(l, n) local_xchg((&(l)->a), (n)) #define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u)) #define local64_inc_not_zero(l) local_inc_not_zero(&(l)->a) /* Non-atomic variants, ie. preemption disabled and won't be touched * in interrupt, etc. Some archs can optimize this case well. */ #define __local64_inc(l) local64_set((l), local64_read(l) + 1) #define __local64_dec(l) local64_set((l), local64_read(l) - 1) #define __local64_add(i,l) local64_set((l), local64_read(l) + (i)) #define __local64_sub(i,l) local64_set((l), local64_read(l) - (i)) #else /* BITS_PER_LONG != 64 */ #include <linux/atomic.h> /* Don't use typedef: don't want them to be mixed with atomic_t's. */ typedef struct { atomic64_t a; } local64_t; #define LOCAL64_INIT(i) { ATOMIC_LONG_INIT(i) } #define local64_read(l) atomic64_read(&(l)->a) #define local64_set(l,i) atomic64_set((&(l)->a),(i)) #define local64_inc(l) atomic64_inc(&(l)->a) #define local64_dec(l) atomic64_dec(&(l)->a) #define local64_add(i,l) atomic64_add((i),(&(l)->a)) #define local64_sub(i,l) atomic64_sub((i),(&(l)->a)) #define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a)) #define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a) #define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a) #define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a)) #define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a)) #define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a)) #define local64_inc_return(l) atomic64_inc_return(&(l)->a) #define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n)) #define local64_try_cmpxchg(l, po, n) atomic64_try_cmpxchg((&(l)->a), (po), (n)) #define local64_xchg(l, n) atomic64_xchg((&(l)->a), (n)) #define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u)) #define local64_inc_not_zero(l) atomic64_inc_not_zero(&(l)->a) /* Non-atomic variants, ie. preemption disabled and won't be touched * in interrupt, etc. Some archs can optimize this case well. */ #define __local64_inc(l) local64_set((l), local64_read(l) + 1) #define __local64_dec(l) local64_set((l), local64_read(l) - 1) #define __local64_add(i,l) local64_set((l), local64_read(l) + (i)) #define __local64_sub(i,l) local64_set((l), local64_read(l) - (i)) #endif /* BITS_PER_LONG != 64 */ #endif /* _ASM_GENERIC_LOCAL64_H */ |
| 29 29 29 29 29 29 17 18 18 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include "internal.h" static void clear_shadow_entries(struct address_space *mapping, unsigned long start, unsigned long max) { XA_STATE(xas, &mapping->i_pages, start); struct folio *folio; /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return; xas_set_update(&xas, workingset_update_node); spin_lock(&mapping->host->i_lock); xas_lock_irq(&xas); /* Clear all shadow entries from start to max */ xas_for_each(&xas, folio, max) { if (xa_is_value(folio)) xas_store(&xas, NULL); } xas_unlock_irq(&xas); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the folio_batch may be altered by this function by removing * exceptional entries similar to what folio_batch_remove_exceptionals() does. * Please note that indices[] has entries in ascending order as guaranteed by * either find_get_entries() or find_lock_entries(). */ static void truncate_folio_batch_exceptionals(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, indices[0]); int nr = folio_batch_count(fbatch); struct folio *folio; int i, j; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; for (j = 0; j < nr; j++) if (xa_is_value(fbatch->folios[j])) break; if (j == nr) return; if (dax_mapping(mapping)) { for (i = j; i < nr; i++) { if (xa_is_value(fbatch->folios[i])) { /* * File systems should already have called * dax_break_layout_entry() to remove all DAX * entries while holding a lock to prevent * establishing new entries. Therefore we * shouldn't find any here. */ WARN_ON_ONCE(1); /* * Delete the mapping so truncate_pagecache() * doesn't loop forever. */ dax_delete_mapping_entry(mapping, indices[i]); } } goto out; } xas_set(&xas, indices[j]); xas_set_update(&xas, workingset_update_node); spin_lock(&mapping->host->i_lock); xas_lock_irq(&xas); xas_for_each(&xas, folio, indices[nr-1]) { if (xa_is_value(folio)) xas_store(&xas, NULL); } xas_unlock_irq(&xas); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); out: folio_batch_remove_exceptionals(fbatch); } /** * folio_invalidate - Invalidate part or all of a folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * folio_invalidate() is called when all or part of the folio has become * invalidated by a truncate operation. * * folio_invalidate() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void folio_invalidate(struct folio *folio, size_t offset, size_t length) { const struct address_space_operations *aops = folio->mapping->a_ops; if (aops->invalidate_folio) aops->invalidate_folio(folio, offset, length); } EXPORT_SYMBOL_GPL(folio_invalidate); /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bail out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_folio(struct folio *folio) { if (folio_mapped(folio)) unmap_mapping_folio(folio); if (folio_needs_release(folio)) folio_invalidate(folio, 0, folio_size(folio)); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ folio_cancel_dirty(folio); } int truncate_inode_folio(struct address_space *mapping, struct folio *folio) { if (folio->mapping != mapping) return -EIO; truncate_cleanup_folio(folio); filemap_remove_folio(folio); return 0; } /* * Handle partial folios. The folio may be entirely within the * range if a split has raced with us. If not, we zero the part of the * folio that's within the [start, end] range, and then split the folio if * it's large. split_page_range() will discard pages which now lie beyond * i_size, and we rely on the caller to discard pages which lie within a * newly created hole. * * Returns false if splitting failed so the caller can avoid * discarding the entire folio which is stubbornly unsplit. */ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { loff_t pos = folio_pos(folio); size_t size = folio_size(folio); unsigned int offset, length; struct page *split_at, *split_at2; if (pos < start) offset = start - pos; else offset = 0; if (pos + size <= (u64)end) length = size - offset; else length = end + 1 - pos - offset; folio_wait_writeback(folio); if (length == size) { truncate_inode_folio(folio->mapping, folio); return true; } /* * We may be zeroing pages we're about to discard, but it avoids * doing a complex calculation here, and then doing the zeroing * anyway if the page split fails. */ if (!mapping_inaccessible(folio->mapping)) folio_zero_range(folio, offset, length); if (folio_needs_release(folio)) folio_invalidate(folio, offset, length); if (!folio_test_large(folio)) return true; split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE); if (!try_folio_split(folio, split_at, NULL)) { /* * try to split at offset + length to make sure folios within * the range can be dropped, especially to avoid memory waste * for shmem truncate */ struct folio *folio2; if (offset + length == size) goto no_split; split_at2 = folio_page(folio, PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE); folio2 = page_folio(split_at2); if (!folio_try_get(folio2)) goto no_split; if (!folio_test_large(folio2)) goto out; if (!folio_trylock(folio2)) goto out; /* * make sure folio2 is large and does not change its mapping. * Its split result does not matter here. */ if (folio_test_large(folio2) && folio2->mapping == folio->mapping) try_folio_split(folio2, split_at2, NULL); folio_unlock(folio2); out: folio_put(folio2); no_split: return true; } if (folio_test_dirty(folio)) return false; truncate_inode_folio(folio->mapping, folio); return true; } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_folio(struct address_space *mapping, struct folio *folio) { if (!mapping) return -EINVAL; /* * Only punch for normal data pages for now. * Handling other types like directories would need more auditing. */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; return truncate_inode_folio(mapping, folio); } EXPORT_SYMBOL(generic_error_remove_folio); /** * mapping_evict_folio() - Remove an unused folio from the page-cache. * @mapping: The mapping this folio belongs to. * @folio: The folio to remove. * * Safely remove one folio from the page cache. * It only drops clean, unused folios. * * Context: Folio must be locked. * Return: The number of pages successfully removed. */ long mapping_evict_folio(struct address_space *mapping, struct folio *folio) { /* The page may have been truncated before it was locked */ if (!mapping) return 0; if (folio_test_dirty(folio) || folio_test_writeback(folio)) return 0; /* The refcount will be elevated if any page in the folio is mapped */ if (folio_ref_count(folio) > folio_nr_pages(folio) + folio_has_private(folio) + 1) return 0; if (!filemap_release_folio(folio, 0)) return 0; return remove_mapping(mapping, folio); } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. * * Note that since ->invalidate_folio() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; struct folio *folio; bool same_folio; if (mapping_empty(mapping)) return; /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' * to the highest possible pgoff_t and since the type is * unsigned we're using -1. */ end = -1; else end = (lend + 1) >> PAGE_SHIFT; folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, &index, end - 1, &fbatch, indices)) { truncate_folio_batch_exceptionals(mapping, &fbatch, indices); for (i = 0; i < folio_batch_count(&fbatch); i++) truncate_cleanup_folio(fbatch.folios[i]); delete_from_page_cache_batch(mapping, &fbatch); for (i = 0; i < folio_batch_count(&fbatch); i++) folio_unlock(fbatch.folios[i]); folio_batch_release(&fbatch); cond_resched(); } same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0); if (!IS_ERR(folio)) { same_folio = lend < folio_pos(folio) + folio_size(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio_next_index(folio); if (same_folio) end = folio->index; } folio_unlock(folio); folio_put(folio); folio = NULL; } if (!same_folio) { folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT, FGP_LOCK, 0); if (!IS_ERR(folio)) { if (!truncate_inode_partial_folio(folio, lstart, lend)) end = folio->index; folio_unlock(folio); folio_put(folio); } } index = start; while (index < end) { cond_resched(); if (!find_get_entries(mapping, &index, end - 1, &fbatch, indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; /* Otherwise restart to make sure all gone */ index = start; continue; } for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) continue; folio_lock(folio); VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); truncate_inode_folio(mapping, folio); folio_unlock(folio); } truncate_folio_batch_exceptionals(mapping, &fbatch, indices); folio_batch_release(&fbatch); } } EXPORT_SYMBOL(truncate_inode_pages_range); /** * truncate_inode_pages - truncate *all* the pages from an offset * @mapping: mapping to truncate * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_rwsem and * mapping->invalidate_lock. * * Note: When this function returns, there can be a page in the process of * deletion (inside __filemap_remove_folio()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { truncate_inode_pages_range(mapping, lstart, (loff_t)-1); } EXPORT_SYMBOL(truncate_inode_pages); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_rwsem. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the * inode teardown. Tell it when the address space is exiting, * so that it does not install eviction information after the * final truncate has begun. */ mapping_set_exiting(mapping); if (!mapping_empty(mapping)) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree * modification that does not see AS_EXITING is * completed before starting the final truncate. */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); } truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); /** * mapping_try_invalidate - Invalidate all the evictable folios of one inode * @mapping: the address_space which holds the folios to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * @nr_failed: How many folio invalidations failed * * This function is similar to invalidate_mapping_pages(), except that it * returns the number of folios which could not be evicted in @nr_failed. */ unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; folio_batch_init(&fbatch); while (find_lock_entries(mapping, &index, end, &fbatch, indices)) { bool xa_has_values = false; int nr = folio_batch_count(&fbatch); for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) { xa_has_values = true; count++; continue; } ret = mapping_evict_folio(mapping, folio); folio_unlock(folio); /* * Invalidation is a hint that the folio is no longer * of interest and try to speed up its reclaim. */ if (!ret) { deactivate_file_folio(folio); /* Likely in the lru cache of a remote CPU */ if (nr_failed) (*nr_failed)++; } count += ret; } if (xa_has_values) clear_shadow_entries(mapping, indices[0], indices[nr-1]); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); } return count; } /** * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode * @mapping: the address_space which holds the cache to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function removes pages that are clean, unmapped and unlocked, * as well as shadow entries. It will not block on IO activity. * * If you want to remove all the pages of one inode, regardless of * their use and writeback state, use truncate_inode_pages(). * * Return: The number of indices that had their contents invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { return mapping_try_invalidate(mapping, start, end, NULL); } EXPORT_SYMBOL(invalidate_mapping_pages); static int folio_launder(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return 0; if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) return 0; return mapping->a_ops->launder_folio(folio); } /* * This is like mapping_evict_folio(), except it ignores the folio's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave folios behind because * shrink_folio_list() has a temp ref on them, or because they're transiently * sitting in the folio_add_lru() caches. */ int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, gfp_t gfp) { int ret; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_mapped(folio)) unmap_mapping_folio(folio); BUG_ON(folio_mapped(folio)); ret = folio_launder(mapping, folio); if (ret) return ret; if (folio->mapping != mapping) return -EBUSY; if (!filemap_release_folio(folio, gfp)) return -EBUSY; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); if (folio_test_dirty(folio)) goto failed; BUG_ON(folio_has_private(folio)); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); return 1; failed: xa_unlock_irq(&mapping->i_pages); spin_unlock(&mapping->host->i_lock); return -EBUSY; } /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space * @start: the page offset 'from' which to invalidate * @end: the page offset 'to' which to invalidate (inclusive) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; if (mapping_empty(mapping)) return 0; folio_batch_init(&fbatch); index = start; while (find_get_entries(mapping, &index, end, &fbatch, indices)) { bool xa_has_values = false; int nr = folio_batch_count(&fbatch); for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ if (xa_is_value(folio)) { xa_has_values = true; if (dax_mapping(mapping) && !dax_invalidate_mapping_entry_sync(mapping, indices[i])) ret = -EBUSY; continue; } if (!did_range_unmap && folio_mapped(folio)) { /* * If folio is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, indices[i], (1 + end - indices[i]), false); did_range_unmap = 1; } folio_lock(folio); if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); continue; } VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL); if (ret2 < 0) ret = ret2; folio_unlock(folio); } if (xa_has_values) clear_shadow_entries(mapping, indices[0], indices[nr-1]); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); } /* * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for * efficiency so that truncate_inode_pages does fewer * single-page unmaps. However after this first call, and * before truncate_inode_pages finishes, it is possible for * private pages to be COWed, which remain after * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ unmap_mapping_range(mapping, holebegin, 0, 1); truncate_inode_pages(mapping, newsize); unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_rwsem but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { loff_t oldsize = inode->i_size; i_size_write(inode, newsize); if (newsize > oldsize) pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or * by write starting after current i_size. We mark the page straddling * current i_size RO so that page_mkwrite() is called on the first * write access to the page. The filesystem will update its per-block * information before user writes to the page via mmap after the i_size * has been changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the folio will already see the new i_size. * The function must be called while we still hold i_rwsem - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; struct folio *folio; WARN_ON(to > inode->i_size); if (from >= to || bsize >= PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; folio = filemap_lock_folio(inode->i_mapping, from / PAGE_SIZE); /* Folio not cached? Nothing to do */ if (IS_ERR(folio)) return; /* * See folio_clear_dirty_for_io() for details why folio_mark_dirty() * is needed. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * The post-eof range of the folio must be zeroed before it is exposed * to the file. Writeback normally does this, but since i_size has been * increased we handle it here. */ if (folio_test_dirty(folio)) { unsigned int offset, end; offset = from - folio_pos(folio); end = min_t(unsigned int, to - folio_pos(folio), folio_size(folio)); folio_zero_segment(folio, offset, end); } folio_unlock(folio); folio_put(folio); } EXPORT_SYMBOL(pagecache_isize_extended); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; loff_t unmap_start = round_up(lstart, PAGE_SIZE); loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; /* * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are * doing their own page rounding first. Note that unmap_mapping_range * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* * Unlike in truncate_pagecache, unmap_mapping_range is called only * once (before truncating pagecache), and without "even_cows" flag: * hole-punching should not remove private COWed pages from the hole. */ if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); truncate_inode_pages_range(mapping, lstart, lend); } EXPORT_SYMBOL(truncate_pagecache_range); |
| 883 886 43 887 6 6 3 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /* * Add to a counter while respecting batch size. * * There are 2 implementations, both dealing with the following problem: * * The decision slow path/fast path and the actual update must be atomic. * Otherwise a call in process context could check the current values and * decide that the fast path can be used. If now an interrupt occurs before * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters), * then the this_cpu_add() that is executed after the interrupt has completed * can produce values larger than "batch" or even overflows. */ #ifdef CONFIG_HAVE_CMPXCHG_LOCAL /* * Safety against interrupts is achieved in 2 ways: * 1. the fast path uses local cmpxchg (note: no lock prefix) * 2. the slow path operates with interrupts disabled */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; count = this_cpu_read(*fbc->counters); do { if (unlikely(abs(count + amount) >= batch)) { raw_spin_lock_irqsave(&fbc->lock, flags); /* * Note: by now we might have migrated to another CPU * or the value might have changed. */ count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); return; } } while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount)); } #else /* * local_irq_save() is used to make the function irq safe: * - The slow path would be ok as protected by an irq-safe spinlock. * - this_cpu_add would be ok as it is irq-safe by definition. */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; local_irq_save(flags); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { raw_spin_lock(&fbc->lock); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock(&fbc->lock); } else { this_cpu_add(*fbc->counters, amount); } local_irq_restore(flags); } #endif EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive(). * * We use the cpu mask of (cpu_online_mask | cpu_dying_mask) to capture sums * from CPUs that are in the process of being taken offline. Dying cpus have * been removed from the online mask, but may not have had the hotplug dead * notifier called to fold the percpu count back into the global counter sum. * By including dying CPUs in the iteration mask, we avoid this race condition * so __percpu_counter_sum() just does the right thing when CPUs are being taken * offline. */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key) { unsigned long flags __maybe_unused; size_t counter_size; s32 __percpu *counters; u32 i; counter_size = ALIGN(sizeof(*counters), __alignof__(*counters)); counters = __alloc_percpu_gfp(nr_counters * counter_size, __alignof__(*counters), gfp); if (!counters) { fbc[0].counters = NULL; return -ENOMEM; } for (i = 0; i < nr_counters; i++) { raw_spin_lock_init(&fbc[i].lock); lockdep_set_class(&fbc[i].lock, key); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc[i].list); #endif fbc[i].count = amount; fbc[i].counters = (void __percpu *)counters + i * counter_size; debug_percpu_counter_activate(&fbc[i]); } #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_add(&fbc[i].list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init_many); void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { unsigned long flags __maybe_unused; u32 i; if (WARN_ON_ONCE(!fbc)) return; if (!fbc[0].counters) return; for (i = 0; i < nr_counters; i++) debug_percpu_counter_deactivate(&fbc[i]); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_del(&fbc[i].list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc[0].counters); for (i = 0; i < nr_counters; i++) fbc[i].counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy_many); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); /* * Compare counter, and add amount if total is: less than or equal to limit if * amount is positive, or greater than or equal to limit if amount is negative. * Return true if amount is added, or false if total would be beyond the limit. * * Negative limit is allowed, but unusual. * When negative amounts (subs) are given to percpu_counter_limited_add(), * the limit would most naturally be 0 - but other limits are also allowed. * * Overflow beyond S64_MAX is not allowed for: counter, limit and amount * are all assumed to be sane (far from S64_MIN and S64_MAX). */ bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch) { s64 count; s64 unknown; unsigned long flags; bool good = false; if (amount == 0) return true; local_irq_save(flags); unknown = batch * num_online_cpus(); count = __this_cpu_read(*fbc->counters); /* Skip taking the lock when safe */ if (abs(count + amount) <= batch && ((amount > 0 && fbc->count + unknown <= limit) || (amount < 0 && fbc->count - unknown >= limit))) { this_cpu_add(*fbc->counters, amount); local_irq_restore(flags); return true; } raw_spin_lock(&fbc->lock); count = fbc->count + amount; /* Skip percpu_counter_sum() when safe */ if (amount > 0) { if (count - unknown > limit) goto out; if (count + unknown <= limit) good = true; } else { if (count + unknown < limit) goto out; if (count - unknown >= limit) good = true; } if (!good) { s32 *pcount; int cpu; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { pcount = per_cpu_ptr(fbc->counters, cpu); count += *pcount; } if (amount > 0) { if (count > limit) goto out; } else { if (count < limit) goto out; } good = true; } count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); out: raw_spin_unlock(&fbc->lock); local_irq_restore(flags); return good; } static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 84 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> #include <linux/sched/isolation.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); folio_mark_accessed(bh->b_folio); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the folio has dirty or writeback buffers. If all the buffers * are unlocked and clean then the folio_test_dirty information is stale. If * any of the buffers are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; if (folio_test_writeback(folio)) *writeback = true; bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { put_bh(bh); __end_buffer_read_notouch(bh, uptodate); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL(end_buffer_write_sync); static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct folio *folio; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = ((loff_t)block << blkbits) / PAGE_SIZE; folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0); if (IS_ERR(folio)) goto out; /* * Folio lock protects the buffers. Callers that cannot block * will fallback to serializing vs try_to_free_buffers() via * the i_private_lock. */ if (atomic) spin_lock(&bd_mapping->i_private_lock); else folio_lock(folio); head = folio_buffers(folio); if (!head) goto out_unlock; /* * Upon a noref migration, the folio lock serializes here; * otherwise bail. */ if (test_bit_acquire(BH_Migrate, &head->b_state)) { WARN_ON(!atomic); goto out_unlock; } bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << blkbits); } out_unlock: if (atomic) spin_unlock(&bd_mapping->i_private_lock); else folio_unlock(folio); folio_put(folio); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; int folio_uptodate = 1; BUG_ON(!buffer_async_read(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) folio_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_read(folio, folio_uptodate); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); } struct postprocess_bh_ctx { struct work_struct work; struct buffer_head *bh; }; static void verify_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; bool valid; valid = fsverity_verify_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, valid); kfree(ctx); } static bool need_fsverity(struct buffer_head *bh) { struct folio *folio = bh->b_folio; struct inode *inode = folio->mapping->host; return fsverity_active(inode) && /* needed by ext4 */ folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); } static void decrypt_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); if (err == 0 && need_fsverity(bh)) { /* * We use different work queues for decryption and for verity * because verity may require reading metadata pages that need * decryption, and we shouldn't recurse to the same workqueue. */ INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); return; } end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_folio() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { struct inode *inode = bh->b_folio->mapping->host; bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode); bool verify = need_fsverity(bh); /* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */ if (uptodate && (decrypt || verify)) { struct postprocess_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { ctx->bh = bh; if (decrypt) { INIT_WORK(&ctx->work, decrypt_bh); fscrypt_enqueue_decrypt_work(&ctx->work); } else { INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); } return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_folio() - folios which are unlocked * during I/O, and which have the writeback flag cleared upon I/O completion. */ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; BUG_ON(!buffer_async_write(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_writeback(folio); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); } /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL(mark_buffer_async_write); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->i_private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for i_private_list is via the i_private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact, * mapping->i_private_list will always be protected by the backing blockdev's * ->i_private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->i_private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->i_private_list via these * utility functions are free to use i_private_lock and i_private_list for * whatever they want. The only requirement is that list_empty(i_private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's i_private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { return !list_empty(&inode->i_data.i_private_list); } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer * as you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head *p; int err = 0; spin_lock(lock); repeat: list_for_each_prev(p, list) { bh = BH_ENTRY(p); if (buffer_locked(bh)) { get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); goto repeat; } } spin_unlock(lock); return err; } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->i_private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { struct address_space *buffer_mapping = mapping->i_private_data; if (buffer_mapping == NULL || list_empty(&mapping->i_private_list)) return 0; return fsync_buffers_list(&buffer_mapping->i_private_lock, &mapping->i_private_list); } EXPORT_SYMBOL(sync_mapping_buffers); /** * generic_buffers_fsync_noflush - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int err; int ret; err = file_write_and_wait_range(file, start, end); if (err) return err; ret = sync_mapping_buffers(inode->i_mapping); if (!(inode->i_state & I_DIRTY_ALL)) goto out; if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; out: /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(generic_buffers_fsync_noflush); /** * generic_buffers_fsync - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. This also makes sure that * a device cache flush operation is called at the end. */ int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int ret; ret = generic_buffers_fsync_noflush(file, start, end, datasync); if (!ret) ret = blkdev_issue_flush(inode->i_sb->s_bdev); return ret; } EXPORT_SYMBOL(generic_buffers_fsync); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh; bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) write_dirty_buffer(bh, 0); put_bh(bh); } } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; struct address_space *buffer_mapping = bh->b_folio->mapping; mark_buffer_dirty(bh); if (!mapping->i_private_data) { mapping->i_private_data = buffer_mapping; } else { BUG_ON(mapping->i_private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->i_private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->i_private_list); bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); /** * block_dirty_folio - Mark a folio as dirty. * @mapping: The address space containing this folio. * @folio: The folio to mark dirty. * * Filesystems which use buffer_heads can use this function as their * ->dirty_folio implementation. Some filesystems need to do a little * work before calling this function. Filesystems which do not use * buffer_heads should call filemap_dirty_folio() instead. * * If the folio has buffers, the uptodate buffers are set dirty, to * preserve dirty-state coherency between the folio and the buffers. * Buffers added to a dirty folio are created dirty. * * The buffers are dirtied before the folio is dirtied. There's a small * race window in which writeback may see the folio cleanness but not the * buffer dirtiness. That's fine. If this code were to set the folio * dirty before the buffers, writeback could clear the folio dirty flag, * see a bunch of clean buffers and we'd end up with dirty buffers/clean * folio on the dirty folio list. * * We use i_private_lock to lock against try_to_free_buffers() while * using the folio's buffer list. This also prevents clean buffers * being added to the folio after it was set dirty. * * Context: May only be called from process context. Does not sleep. * Caller must ensure that @folio cannot be truncated during this call, * typically by holding the folio lock or having a page in the folio * mapped and holding the page table lock. * * Return: True if the folio was dirtied; false if it was already dirtied. */ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) { struct buffer_head *head; bool newly_dirty; spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ newly_dirty = !folio_test_set_dirty(folio); spin_unlock(&mapping->i_private_lock); if (newly_dirty) __folio_mark_dirty(folio, mapping, 1); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL(block_dirty_folio); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; LIST_HEAD(tmp); blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(lock); } } } spin_unlock(lock); blk_finish_plug(&plug); spin_lock(lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mapping->i_private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); } spin_unlock(lock); err2 = osync_buffers_list(lock, list); if (err) return err; else return err2; } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which * assumes that all the buffers are against the blockdev. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->i_private_list; struct address_space *buffer_mapping = mapping->i_private_data; spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); spin_unlock(&buffer_mapping->i_private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { int ret = 1; if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->i_private_list; struct address_space *buffer_mapping = mapping->i_private_data; spin_lock(&buffer_mapping->i_private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { ret = 0; break; } __remove_assoc_queue(bh); } spin_unlock(&buffer_mapping->i_private_lock); } return ret; } /* * Create the appropriate buffers when given a folio for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp) { struct buffer_head *bh, *head; long offset; struct mem_cgroup *memcg, *old_memcg; /* The folio lock pins the memcg */ memcg = folio_memcg(folio); old_memcg = set_active_memcg(memcg); head = NULL; offset = folio_size(folio); while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its folio */ folio_set_bh(bh, folio, offset); } out: set_active_memcg(old_memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(folio_alloc_buffers); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size) { gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; return folio_alloc_buffers(page_folio(page), size, gfp); } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct folio *folio, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; folio_attach_private(folio, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = bdev_nr_bytes(bdev); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev folio's buffers. */ static sector_t folio_init_buffers(struct folio *folio, struct block_device *bdev, unsigned size) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh = head; bool uptodate = folio_test_uptodate(folio); sector_t block = div_u64(folio_pos(folio), size); sector_t end_block = blkdev_max_block(bdev, size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache folio that contains the requested block. * * This is used purely for blockdev mappings. * * Returns false if we have a failure which cannot be cured by retrying * without sleeping. Returns true if we succeeded, or the caller should retry. */ static bool grow_dev_folio(struct block_device *bdev, sector_t block, pgoff_t index, unsigned size, gfp_t gfp) { struct address_space *mapping = bdev->bd_mapping; struct folio *folio; struct buffer_head *bh; sector_t end_block = 0; folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return false; bh = folio_buffers(folio); if (bh) { if (bh->b_size == size) { end_block = folio_init_buffers(folio, bdev, size); goto unlock; } /* * Retrying may succeed; for example the folio may finish * writeback, or buffers may be cleaned. This should not * happen very often; maybe we have old buffers attached to * this blockdev's page cache and we're trying to change * the block size? */ if (!try_to_free_buffers(folio)) { end_block = ~0ULL; goto unlock; } } bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT); if (!bh) goto unlock; /* * Link the folio to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the folio lock. */ spin_lock(&mapping->i_private_lock); link_dev_buffers(folio, bh); end_block = folio_init_buffers(folio, bdev, size); spin_unlock(&mapping->i_private_lock); unlock: folio_unlock(folio); folio_put(folio); return block < end_block; } /* * Create buffers for the specified block device block's folio. If * that folio was dirty, the buffers are set dirty also. Returns false * if we've hit a permanent error. */ static bool grow_buffers(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { loff_t pos; /* * Check for a block which lies outside our maximum possible * pagecache index. */ if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) { printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n", __func__, (unsigned long long)block, bdev); return false; } /* Create a folio with the proper size buffers */ return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { bool blocking = gfpflags_allow_blocking(gfp); if (WARN_ON_ONCE(!IS_ALIGNED(size, bdev_logical_block_size(bdev)))) { printk(KERN_ERR "getblk(): block size %d not aligned to logical block size %d\n", size, bdev_logical_block_size(bdev)); return NULL; } for (;;) { struct buffer_head *bh; if (!grow_buffers(bdev, block, size, gfp)) return NULL; if (blocking) bh = __find_get_block_nonatomic(bdev, block, size); else bh = __find_get_block(bdev, block, size); if (bh) return bh; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_folio() against that folio will discover all the uptodate * buffers, will set the folio uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct folio *folio = bh->b_folio; struct address_space *mapping = NULL; if (!folio_test_set_dirty(folio)) { mapping = folio->mapping; if (mapping) __folio_mark_dirty(folio, mapping, 0); } if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); void mark_buffer_write_io_error(struct buffer_head *bh) { set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_folio && bh->b_folio->mapping) mapping_set_error(bh->b_folio->mapping, -EIO); if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); } EXPORT_SYMBOL(mark_buffer_write_io_error); /** * __brelse - Release a buffer. * @bh: The buffer to release. * * This variant of brelse() can be called if @bh is guaranteed to not be NULL. */ void __brelse(struct buffer_head *bh) { if (atomic_read(&bh->b_count)) { put_bh(bh); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); /** * __bforget - Discard any dirty data in a buffer. * @bh: The buffer to forget. * * This variant of bforget() can be called if @bh is guaranteed to not * be NULL. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_folio->mapping; spin_lock(&buffer_mapping->i_private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->i_private_lock); } __brelse(bh); } EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); /* * the refcount of buffer_head in bh_lru prevents dropping the * attached page(i.e., try_to_free_buffers) so it could cause * failing page migration. * Skip putting upcoming bh into bh_lru until migration is done. */ if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return; } b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); if (cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return NULL; } for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL. Atomic context callers may also return NULL if the buffer is being * migrated; similarly the page is not marked accessed either. */ static struct buffer_head * find_get_block_common(struct block_device *bdev, sector_t block, unsigned size, bool atomic) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block, atomic); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { return find_get_block_common(bdev, block, size, true); } EXPORT_SYMBOL(__find_get_block); /* same as __find_get_block() but allows sleeping contexts */ struct buffer_head * __find_get_block_nonatomic(struct block_device *bdev, sector_t block, unsigned size) { return find_get_block_common(bdev, block, size, false); } EXPORT_SYMBOL(__find_get_block_nonatomic); /** * bdev_getblk - Get a buffer_head in a block device's buffer cache. * @bdev: The block device. * @block: The block number. * @size: The size of buffer_heads for this @bdev. * @gfp: The memory allocation flags to use. * * The returned buffer head has its reference count incremented, but is * not locked. The caller should call brelse() when it has finished * with the buffer. The buffer may not be uptodate. If needed, the * caller can bring it uptodate either by reading it or overwriting it. * * Return: The buffer head, or NULL if memory could not be allocated. */ struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh; if (gfpflags_allow_blocking(gfp)) bh = __find_get_block_nonatomic(bdev, block, size); else bh = __find_get_block(bdev, block, size); might_alloc(gfp); if (bh) return bh; return __getblk_slow(bdev, block, size, gfp); } EXPORT_SYMBOL(bdev_getblk); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = bdev_getblk(bdev, block, size, GFP_NOWAIT | __GFP_MOVABLE); if (likely(bh)) { bh_readahead(bh, REQ_RAHEAD); brelse(bh); } } EXPORT_SYMBOL(__breadahead); /** * __bread_gfp() - Read a block. * @bdev: The block device to read from. * @block: Block number in units of block size. * @size: The block size of this device in bytes. * @gfp: Not page allocation flags; see below. * * You are not expected to call this function. You should use one of * sb_bread(), sb_bread_unmovable() or __bread(). * * Read a specified block, and return the buffer head that refers to it. * If @gfp is 0, the memory will be allocated using the block device's * default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be * allocated from a movable area. Do not pass in a complete set of * GFP flags. * * The returned buffer head has its refcount increased. The caller should * call brelse() when it has finished with the buffer. * * Context: May sleep waiting for I/O. * Return: NULL if the block was unreadable. */ struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh; gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); /* * Prefer looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp |= __GFP_NOFAIL; bh = bdev_getblk(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL(__bread_gfp); static void __invalidate_bh_lrus(struct bh_lru *b) { int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } } /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); __invalidate_bh_lrus(b); put_cpu_var(bh_lrus); } bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); /* * It's called from workqueue context so we need a bh_lru_lock to close * the race with preemption/irq. */ void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset) { bh->b_folio = folio; BUG_ON(offset >= folio_size(folio)); if (folio_test_highmem(folio)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = folio_address(folio) + offset; } EXPORT_SYMBOL(folio_set_bh); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = READ_ONCE(bh->b_state); do { } while (!try_cmpxchg_relaxed(&bh->b_state, &b_state, b_state & ~BUFFER_FLAGS_DISCARD)); unlock_buffer(bh); } /** * block_invalidate_folio - Invalidate part or all of a buffer-backed folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidate_folio() is called when all or part of the folio has been * invalidated by a truncate operation. * * block_invalidate_folio() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct buffer_head *head, *bh, *next; size_t curr_off = 0; size_t stop = length + offset; BUG_ON(!folio_test_locked(folio)); /* * Check for overflow */ BUG_ON(stop > folio_size(folio) || stop < length); head = folio_buffers(folio); if (!head) return; bh = head; do { size_t next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire folio is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == folio_size(folio)) filemap_release_folio(folio, 0); out: folio_clear_mappedtodisk(folio); } EXPORT_SYMBOL(block_invalidate_folio); /* * We attach and possibly dirty the buffers atomically wrt * block_dirty_folio() via i_private_lock. try_to_free_buffers * is already excluded via the folio lock. */ struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL; head = folio_alloc_buffers(folio, blocksize, gfp); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&folio->mapping->i_private_lock); if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { if (folio_test_dirty(folio)) set_buffer_dirty(bh); if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } folio_attach_private(folio, head); spin_unlock(&folio->mapping->i_private_lock); return head; } EXPORT_SYMBOL(create_empty_buffers); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct folio_batch fbatch; pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE; pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE; folio_batch_init(&fbatch); while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) { count = folio_batch_count(&fbatch); for (i = 0; i < count; i++) { struct folio *folio = fbatch.folios[i]; if (!folio_buffers(folio)) continue; /* * We use folio lock instead of bd_mapping->i_private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ folio_lock(folio); /* Recheck when the folio is locked which pins bhs */ head = folio_buffers(folio); if (!head) goto unlock_page; bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: folio_unlock(folio); } folio_batch_release(&fbatch); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL(clean_bdev_aliases); static struct buffer_head *folio_create_buffers(struct folio *folio, struct inode *inode, unsigned int b_state) { struct buffer_head *bh; BUG_ON(!folio_test_locked(folio)); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, 1 << READ_ONCE(inode->i_blkbits), b_state); return bh; } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_folio is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_folio() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_folio() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_folio(struct inode *inode, struct folio *folio, get_block_t *get_block, struct writeback_control *wbc) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; size_t blocksize; int nr_underway = 0; blk_opf_t write_flags = wbc_to_write_flags(wbc); head = folio_create_buffers(folio, inode, (1 << BH_Dirty) | (1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from block_dirty_folio * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the folio stays dirty. * * Buffers outside i_size may be dirtied by block_dirty_folio; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; block = div_u64(folio_pos(folio), blocksize); last_block = div_u64(i_size_read(inode) - 1, blocksize); /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this folio can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_folio() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the folio. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { folio_redirty_for_writepage(wbc, folio); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The folio and its buffers are protected by the writeback flag, * so we can drop the bh refcounts early. */ BUG_ON(folio_test_writeback(folio)); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); err = 0; done: if (nr_underway == 0) { /* * The folio was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * write_dirty_buffer/submit_bh. A rare case. */ folio_end_writeback(folio); /* * The folio and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The folio is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { /* * The buffer may have been set dirty during * attachment to a dirty folio. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); BUG_ON(folio_test_writeback(folio)); mapping_set_error(folio->mapping, err); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); goto done; } EXPORT_SYMBOL(__block_write_full_folio); /* * If a folio has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!folio_test_uptodate(folio)) { size_t start, xend; start = max(from, block_start); xend = min(to, block_end); folio_zero_segment(folio, start, xend); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(folio_zero_new_buffers); static int iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { loff_t offset = (loff_t)block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ if (offset >= iomap->offset + iomap->length) return -EIO; switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); return 0; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); return 0; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) { /* * This can happen if truncating the block device races * with the check in the caller as i_size updates on * block devices aren't synchronized by i_rwsem for * block devices. */ if (S_ISBLK(inode->i_mode)) return -EIO; set_buffer_new(bh); } bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); return 0; default: WARN_ON_ONCE(1); return -EIO; } } int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap) { size_t from = offset_in_folio(folio, pos); size_t to = from + len; struct inode *inode = folio->mapping->host; size_t block_start, block_end; sector_t block; int err = 0; size_t blocksize; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!folio_test_locked(folio)); BUG_ON(to > folio_size(folio)); BUG_ON(from > to); head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; block = div_u64(folio_pos(folio), blocksize); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) err = get_block(inode, block, bh, 1); else err = iomap_to_bh(inode, block, bh, iomap); if (err) break; if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (folio_test_uptodate(folio)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) folio_zero_segments(folio, to, block_end, block_start, from); continue; } } if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { bh_read_nowait(bh, 0); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) folio_zero_new_buffers(folio, from, to); return err; } int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(folio, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); void block_commit_write(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; bool partial = false; unsigned blocksize; struct buffer_head *bh, *head; bh = head = folio_buffers(folio); if (!bh) return; blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = true; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } if (buffer_new(bh)) clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus read_folio() for * the next read(). Here we 'discover' whether the folio went * uptodate as a result of this (potentially partial) write. */ if (!partial) folio_mark_uptodate(folio); } EXPORT_SYMBOL(block_commit_write); /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct folio *folio; int status; folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); status = __block_write_begin_int(folio, pos, len, get_block, NULL); if (unlikely(status)) { folio_unlock(folio); folio_put(folio); folio = NULL; } *foliop = folio; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *folio) { size_t start = pos - folio_pos(folio); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so * we don't have to worry about a read_folio reading them * and overwriting a partial write. However if we have * encountered a short write and only partially written * into a buffer, it will not be marked uptodate, so a * read_folio might come in and destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate folio as a zero-length write, and force the * caller to redo the whole thing. */ if (!folio_test_uptodate(folio)) copied = 0; folio_zero_new_buffers(folio, start+copied, start+len); } flush_dcache_folio(folio); /* This could be a short (even 0-length) commit */ block_commit_write(folio, start, start + copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(pos, len, copied, folio); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } folio_unlock(folio); folio_put(folio); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); /* * block_is_partially_uptodate checks whether buffers within a folio are * uptodate or not. * * Returns true if all buffers which correspond to the specified part * of the folio are uptodate. */ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; bool ret = true; head = folio_buffers(folio); if (!head) return false; blocksize = head->b_size; to = min_t(unsigned, folio_size(folio) - from, count); to = from + to; if (from < blocksize && to > folio_size(folio) - blocksize) return false; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = false; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL(block_is_partially_uptodate); /* * Generic "read_folio" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the folio asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * folio once IO has completed. */ int block_read_full_folio(struct folio *folio, get_block_t *get_block) { struct inode *inode = folio->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *prev = NULL; size_t blocksize; int fully_mapped = 1; bool page_error = false; loff_t limit = i_size_read(inode); /* This is needed for ext4. */ if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) limit = inode->i_sb->s_maxbytes; head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; iblock = div_u64(folio_pos(folio), blocksize); lblock = div_u64(limit + blocksize - 1, blocksize); bh = head; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) page_error = true; } if (!buffer_mapped(bh)) { folio_zero_range(folio, bh_offset(bh), blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } mark_buffer_async_read(bh); if (prev) submit_bh(REQ_OP_READ, prev); prev = bh; } while (iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) folio_set_mappedtodisk(folio); /* * All buffers are uptodate or get_block() returned an error * when trying to map them - we must finish the read because * end_buffer_async_read() will never be called on any buffer * in this folio. */ if (prev) submit_bh(REQ_OP_READ, prev); else folio_end_read(folio, !page_error); return 0; } EXPORT_SYMBOL(block_read_full_folio); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; struct folio *folio; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (err) goto out; err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL(generic_cont_expand_simple); static int cont_expand_zero(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; const struct address_space_operations *aops = mapping->a_ops; unsigned int blocksize = i_blocksize(inode); struct folio *folio; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = aops->write_begin(iocb, mapping, curpos, len, &folio, &fsdata); if (err) goto out; folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(iocb, mapping, curpos, len, len, folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = aops->write_begin(iocb, mapping, curpos, len, &folio, &fsdata); if (err) goto out; folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(iocb, mapping, curpos, len, len, folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(iocb, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, foliop, get_block); } EXPORT_SYMBOL(cont_write_begin); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_rwsem here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; folio_lock(folio); size = i_size_read(inode); if ((folio->mapping != inode->i_mapping) || (folio_pos(folio) >= size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } end = folio_size(folio); /* folio is wholly or partially inside EOF */ if (folio_pos(folio) + end > size) end = size - folio_pos(folio); ret = __block_write_begin_int(folio, 0, end, get_block, NULL); if (unlikely(ret)) goto out_unlock; block_commit_write(folio, 0, end); folio_mark_dirty(folio); folio_wait_stable(folio); return 0; out_unlock: folio_unlock(folio); return ret; } EXPORT_SYMBOL(block_page_mkwrite); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned blocksize; sector_t iblock; size_t offset, length, pos; struct inode *inode = mapping->host; struct folio *folio; struct buffer_head *bh; int err = 0; blocksize = i_blocksize(inode); length = from & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits; folio = filemap_grab_folio(mapping, index); if (IS_ERR(folio)) return PTR_ERR(folio); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, blocksize, 0); /* Find the buffer that contains "offset" */ offset = offset_in_folio(folio, from); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = bh_read(bh, 0); /* Uhhuh. Read error. Complain and punt. */ if (err < 0) goto unlock; } folio_zero_range(folio, offset, length); mark_buffer_dirty(bh); unlock: folio_unlock(folio); folio_put(folio); return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic write folio function for buffer-backed address_spaces */ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, void *get_block) { struct inode * const inode = folio->mapping->host; loff_t i_size = i_size_read(inode); /* Is the folio fully inside i_size? */ if (folio_pos(folio) + folio_size(folio) <= i_size) return __block_write_full_folio(inode, folio, get_block, wbc); /* Is the folio fully outside i_size? (truncate in progress) */ if (folio_pos(folio) >= i_size) { folio_unlock(folio); return 0; /* don't care */ } /* * The folio straddles i_size. It must be zeroed out on each and every * writeback invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ folio_zero_segment(folio, offset_in_folio(folio, i_size), folio_size(folio)); return __block_write_full_folio(inode, folio, get_block, wbc); } sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { const enum req_op op = opf & REQ_OP_MASK; struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); if (buffer_meta(bh)) opf |= REQ_META; if (buffer_prio(bh)) opf |= REQ_PRIO; bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_write_hint = write_hint; bio_add_folio_nofail(bio, bh->b_folio, bh->b_size, bh_offset(bh)); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size); } submit_bio(bio); } void submit_bh(blk_opf_t opf, struct buffer_head *bh) { submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL); } EXPORT_SYMBOL(submit_bh); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE | op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; submit_bh(REQ_OP_WRITE | op_flags, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) return -EIO; } else { unlock_buffer(bh); } return 0; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static bool drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; folio_detach_private(folio); return true; failed: return false; } /** * try_to_free_buffers - Release buffers attached to this folio. * @folio: The folio. * * If any buffers are in use (dirty, under writeback, elevated refcount), * no buffers will be freed. * * If the folio is dirty but all the buffers are clean then we need to * be sure to mark the folio clean as well. This is because the folio * may be against a block device, and a later reattachment of buffers * to a dirty folio will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem folios: if all the buffers are * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with * i_private_lock. * * Exclusion against try_to_free_buffers may be obtained by either * locking the folio or by holding its mapping's i_private_lock. * * Context: Process context. @folio must be locked. Will not sleep. * Return: true if all buffers attached to this folio were freed. */ bool try_to_free_buffers(struct folio *folio) { struct address_space * const mapping = folio->mapping; struct buffer_head *buffers_to_free = NULL; bool ret = 0; BUG_ON(!folio_test_locked(folio)); if (folio_test_writeback(folio)) return false; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(folio, &buffers_to_free); goto out; } spin_lock(&mapping->i_private_lock); ret = drop_buffers(folio, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty folio. We * clean the folio here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the folio's buffers clean. We discover that here and clean * the folio also. * * i_private_lock must be held over this entire operation in order * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) folio_cancel_dirty(folio); spin_unlock(&mapping->i_private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __ro_after_init; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads __ro_after_init; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * __bh_read - Submit read for a locked buffer * @bh: struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @wait: wait until reading finish * * Returns zero on success or don't wait, and -EIO on error. */ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { int ret = 0; BUG_ON(!buffer_locked(bh)); get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ | op_flags, bh); if (wait) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } return ret; } EXPORT_SYMBOL(__bh_read); /** * __bh_read_batch - Submit read for a batch of unlocked buffers * @nr: entry number of the buffer batch * @bhs: a batch of struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @force_lock: force to get a lock on the buffer if set, otherwise drops any * buffer that cannot lock. * * Returns zero on success or don't wait, and -EIO on error. */ void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (buffer_uptodate(bh)) continue; if (force_lock) lock_buffer(bh); else if (!trylock_buffer(bh)) continue; if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(REQ_OP_READ | op_flags, bh); } } EXPORT_SYMBOL(__bh_read_batch); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = KMEM_CACHE(buffer_head, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 3 3 3 3 108 109 110 109 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of 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) 2004-2006 Trusted Computer Solutions, Inc. * * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support to import/export the MLS label from NetLabel * Copyright (C) Hewlett-Packard Development Company, L.P., 2006 */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <net/netlabel.h> #include "sidtab.h" #include "mls.h" #include "policydb.h" #include "services.h" /* * Return the length in bytes for the MLS fields of the * security context string representation of `context'. */ int mls_compute_context_len(struct policydb *p, struct context *context) { int i, l, len, head, prev; char *nm; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return 0; len = 1; /* for the beginning ":" */ for (l = 0; l < 2; l++) { u32 index_sens = context->range.level[l].sens; len += strlen(sym_name(p, SYM_LEVELS, index_sens - 1)); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (head != prev) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } nm = sym_name(p, SYM_CATS, i); len += strlen(nm) + 1; head = i; } prev = i; } if (prev != head) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else len++; } } return len; } /* * Write the security context string representation of * the MLS fields of `context' into the string `*scontext'. * Update `*scontext' to point to the end of the MLS fields. */ void mls_sid_to_context(struct policydb *p, struct context *context, char **scontext) { char *scontextp, *nm; int i, l, head, prev; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return; scontextp = *scontext; *scontextp = ':'; scontextp++; for (l = 0; l < 2; l++) { strcpy(scontextp, sym_name(p, SYM_LEVELS, context->range.level[l].sens - 1)); scontextp += strlen(scontextp); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (prev < 0) *scontextp++ = ':'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, i); strcpy(scontextp, nm); scontextp += strlen(nm); head = i; } prev = i; } if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else *scontextp++ = '-'; } } *scontext = scontextp; } int mls_level_isvalid(struct policydb *p, struct mls_level *l) { struct level_datum *levdatum; if (!l->sens || l->sens > p->p_levels.nprim) return 0; levdatum = symtab_search(&p->p_levels, sym_name(p, SYM_LEVELS, l->sens - 1)); if (!levdatum) return 0; /* * Return 1 iff all the bits set in l->cat are also be set in * levdatum->level->cat and no bit in l->cat is larger than * p->p_cats.nprim. */ return ebitmap_contains(&levdatum->level.cat, &l->cat, p->p_cats.nprim); } int mls_range_isvalid(struct policydb *p, struct mls_range *r) { return (mls_level_isvalid(p, &r->level[0]) && mls_level_isvalid(p, &r->level[1]) && mls_level_dom(&r->level[1], &r->level[0])); } /* * Return 1 if the MLS fields in the security context * structure `c' are valid. Return 0 otherwise. */ int mls_context_isvalid(struct policydb *p, struct context *c) { struct user_datum *usrdatum; if (!p->mls_enabled) return 1; if (!mls_range_isvalid(p, &c->range)) return 0; if (c->role == OBJECT_R_VAL) return 1; /* * User must be authorized for the MLS range. */ if (!c->user || c->user > p->p_users.nprim) return 0; usrdatum = p->user_val_to_struct[c->user - 1]; if (!mls_range_contains(usrdatum->range, c->range)) return 0; /* user may not be associated with range */ return 1; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `scontext'. * * This function modifies the string in place, inserting * NULL characters to terminate the MLS fields. * * If a def_sid is provided and no MLS field is present, * copy the MLS field of the associated default context. * Used for upgraded to MLS systems where objects may lack * MLS fields. * * Policy read-lock must be held for sidtab lookup. * */ int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext, struct context *context, struct sidtab *s, u32 def_sid) { char *sensitivity, *cur_cat, *next_cat, *rngptr; struct level_datum *levdatum; struct cat_datum *catdatum, *rngdatum; u32 i; int l, rc; char *rangep[2]; if (!pol->mls_enabled) { /* * With no MLS, only return -EINVAL if there is a MLS field * and it did not come from an xattr. */ if (oldc && def_sid == SECSID_NULL) return -EINVAL; return 0; } /* * No MLS component to the security context, try and map to * default if provided. */ if (!oldc) { struct context *defcon; if (def_sid == SECSID_NULL) return -EINVAL; defcon = sidtab_search(s, def_sid); if (!defcon) return -EINVAL; return mls_context_cpy(context, defcon); } /* * If we're dealing with a range, figure out where the two parts * of the range begin. */ rangep[0] = scontext; rangep[1] = strchr(scontext, '-'); if (rangep[1]) { rangep[1][0] = '\0'; rangep[1]++; } /* For each part of the range: */ for (l = 0; l < 2; l++) { /* Split sensitivity and category set. */ sensitivity = rangep[l]; if (sensitivity == NULL) break; next_cat = strchr(sensitivity, ':'); if (next_cat) *(next_cat++) = '\0'; /* Parse sensitivity. */ levdatum = symtab_search(&pol->p_levels, sensitivity); if (!levdatum) return -EINVAL; context->range.level[l].sens = levdatum->level.sens; /* Extract category set. */ while (next_cat != NULL) { cur_cat = next_cat; next_cat = strchr(next_cat, ','); if (next_cat != NULL) *(next_cat++) = '\0'; /* Separate into range if exists */ rngptr = strchr(cur_cat, '.'); if (rngptr != NULL) { /* Remove '.' */ *rngptr++ = '\0'; } catdatum = symtab_search(&pol->p_cats, cur_cat); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&context->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; /* If range, set all categories in range */ if (rngptr == NULL) continue; rngdatum = symtab_search(&pol->p_cats, rngptr); if (!rngdatum) return -EINVAL; if (catdatum->value >= rngdatum->value) return -EINVAL; for (i = catdatum->value; i < rngdatum->value; i++) { rc = ebitmap_set_bit( &context->range.level[l].cat, i, 1); if (rc) return rc; } } } /* If we didn't see a '-', the range start is also the range end. */ if (rangep[1] == NULL) { context->range.level[1].sens = context->range.level[0].sens; rc = ebitmap_cpy(&context->range.level[1].cat, &context->range.level[0].cat); if (rc) return rc; } return 0; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `str'. This function will allocate temporary memory with the * given constraints of gfp_mask. */ int mls_from_string(struct policydb *p, char *str, struct context *context, gfp_t gfp_mask) { char *tmpstr; int rc; if (!p->mls_enabled) return -EINVAL; tmpstr = kstrdup(str, gfp_mask); if (!tmpstr) { rc = -ENOMEM; } else { rc = mls_context_to_sid(p, ':', tmpstr, context, NULL, SECSID_NULL); kfree(tmpstr); } return rc; } /* * Copies the MLS range `range' into `context'. */ int mls_range_set(struct context *context, struct mls_range *range) { int l, rc = 0; /* Copy the MLS range into the context */ for (l = 0; l < 2; l++) { context->range.level[l].sens = range->level[l].sens; rc = ebitmap_cpy(&context->range.level[l].cat, &range->level[l].cat); if (rc) break; } return rc; } int mls_setup_user_range(struct policydb *p, struct context *fromcon, struct user_datum *user, struct context *usercon) { if (p->mls_enabled) { struct mls_level *fromcon_sen = &(fromcon->range.level[0]); struct mls_level *fromcon_clr = &(fromcon->range.level[1]); struct mls_level *user_low = &(user->range.level[0]); struct mls_level *user_clr = &(user->range.level[1]); struct mls_level *user_def = &(user->dfltlevel); struct mls_level *usercon_sen = &(usercon->range.level[0]); struct mls_level *usercon_clr = &(usercon->range.level[1]); /* Honor the user's default level if we can */ if (mls_level_between(user_def, fromcon_sen, fromcon_clr)) *usercon_sen = *user_def; else if (mls_level_between(fromcon_sen, user_def, user_clr)) *usercon_sen = *fromcon_sen; else if (mls_level_between(fromcon_clr, user_low, user_def)) *usercon_sen = *user_low; else return -EINVAL; /* Lower the clearance of available contexts if the clearance of "fromcon" is lower than that of the user's default clearance (but only if the "fromcon" clearance dominates the user's computed sensitivity level) */ if (mls_level_dom(user_clr, fromcon_clr)) *usercon_clr = *fromcon_clr; else if (mls_level_dom(fromcon_clr, user_clr)) *usercon_clr = *user_clr; else return -EINVAL; } return 0; } /* * Convert the MLS fields in the security context * structure `oldc' from the values specified in the * policy `oldp' to the values specified in the policy `newp', * storing the resulting context in `newc'. */ int mls_convert_context(struct policydb *oldp, struct policydb *newp, struct context *oldc, struct context *newc) { struct level_datum *levdatum; struct cat_datum *catdatum; struct ebitmap_node *node; u32 i; int l; if (!oldp->mls_enabled || !newp->mls_enabled) return 0; for (l = 0; l < 2; l++) { char *name = sym_name(oldp, SYM_LEVELS, oldc->range.level[l].sens - 1); levdatum = symtab_search(&newp->p_levels, name); if (!levdatum) return -EINVAL; newc->range.level[l].sens = levdatum->level.sens; ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node, i) { int rc; catdatum = symtab_search(&newp->p_cats, sym_name(oldp, SYM_CATS, i)); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&newc->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; } } return 0; } int mls_compute_sid(struct policydb *p, struct context *scontext, struct context *tcontext, u16 tclass, u32 specified, struct context *newcontext, bool sock) { struct range_trans rtr; struct mls_range *r; struct class_datum *cladatum; char default_range = 0; if (!p->mls_enabled) return 0; switch (specified) { case AVTAB_TRANSITION: /* Look for a range transition rule. */ rtr.source_type = scontext->type; rtr.target_type = tcontext->type; rtr.target_class = tclass; r = policydb_rangetr_search(p, &rtr); if (r) return mls_range_set(newcontext, r); if (tclass && tclass <= p->p_classes.nprim) { cladatum = p->class_val_to_struct[tclass - 1]; if (cladatum) default_range = cladatum->default_range; } switch (default_range) { case DEFAULT_SOURCE_LOW: return mls_context_cpy_low(newcontext, scontext); case DEFAULT_SOURCE_HIGH: return mls_context_cpy_high(newcontext, scontext); case DEFAULT_SOURCE_LOW_HIGH: return mls_context_cpy(newcontext, scontext); case DEFAULT_TARGET_LOW: return mls_context_cpy_low(newcontext, tcontext); case DEFAULT_TARGET_HIGH: return mls_context_cpy_high(newcontext, tcontext); case DEFAULT_TARGET_LOW_HIGH: return mls_context_cpy(newcontext, tcontext); case DEFAULT_GLBLUB: return mls_context_glblub(newcontext, scontext, tcontext); } fallthrough; case AVTAB_CHANGE: if ((tclass == p->process_class) || sock) /* Use the process MLS attributes. */ return mls_context_cpy(newcontext, scontext); else /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); case AVTAB_MEMBER: /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); } return -EINVAL; } #ifdef CONFIG_NETLABEL /** * mls_export_netlbl_lvl - Export the MLS sensitivity levels to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS sensitivity level into the * NetLabel MLS sensitivity level field. * */ void mls_export_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; secattr->attr.mls.lvl = context->range.level[0].sens - 1; secattr->flags |= NETLBL_SECATTR_MLS_LVL; } /** * mls_import_netlbl_lvl - Import the NetLabel MLS sensitivity levels * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context and the NetLabel security attributes, copy the * NetLabel MLS sensitivity level into the context. * */ void mls_import_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; context->range.level[0].sens = secattr->attr.mls.lvl + 1; context->range.level[1].sens = context->range.level[0].sens; } /** * mls_export_netlbl_cat - Export the MLS categories to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS categories into the NetLabel * MLS category field. Returns zero on success, negative values on failure. * */ int mls_export_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_export(&context->range.level[0].cat, &secattr->attr.mls.cat); if (rc == 0 && secattr->attr.mls.cat != NULL) secattr->flags |= NETLBL_SECATTR_MLS_CAT; return rc; } /** * mls_import_netlbl_cat - Import the MLS categories from NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Copy the NetLabel security attributes into the SELinux context; since the * NetLabel security attribute only contains a single MLS category use it for * both the low and high categories of the context. Returns zero on success, * negative values on failure. * */ int mls_import_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_import(&context->range.level[0].cat, secattr->attr.mls.cat); if (rc) goto import_netlbl_cat_failure; memcpy(&context->range.level[1].cat, &context->range.level[0].cat, sizeof(context->range.level[0].cat)); return 0; import_netlbl_cat_failure: ebitmap_destroy(&context->range.level[0].cat); return rc; } #endif /* CONFIG_NETLABEL */ |
| 7 7 344 217 102 102 35 1 1 1 260 156 346 5 194 198 346 4 345 218 31 156 1 156 20 149 151 16 112 14 14 139 138 1 136 258 98 34 6 29 340 343 342 1 346 344 350 | 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 | // 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 inline const struct fault_info *esr_to_fault_info(unsigned long esr) { return fault_info + (esr & ESR_ELx_FSC); } 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, esr)) 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(struct vm_area_struct *vma, unsigned int mm_flags) { if (!system_supports_poe()) return false; /* * We do not check whether an Overlay fault has occurred because we * cannot make a decision based solely on its value: * * - If Overlay is set, a fault did occur due to POE, but it may be * spurious in those cases where we update POR_EL0 without ISB (e.g. * on context-switch). We would then need to manually check POR_EL0 * against vma_pkey(vma), which is exactly what * arch_vma_access_permitted() does. * * - If Overlay is not set, we may still need to report a pkey fault. * This is the case if an access was made within a mapping but with no * page mapped, and POR_EL0 forbids the access (according to * vma_pkey()). Such access will result in a SIGSEGV regardless * because core code checks arch_vma_access_permitted(), but in order * to report the correct error code - SEGV_PKUERR - we must handle * that case here. */ 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; vm_flags_t 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 (!insn_may_access_user(regs->pc, esr)) 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(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(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); } add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); 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 if ARM64_MTE_FAR isn't supported. * Otherwise, bits 63:60 of FAR_EL1 are not UNKNOWN. */ if (!cpus_have_cap(ARM64_MTE_FAR)) 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); /* * 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); } |
| 290 301 49 301 301 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @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. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 29 184 51 1 17 53 29 29 85 48 50 24 12 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 | /* 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 */ AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, /* 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 void mapping_set_writeback_may_deadlock_on_reclaim(struct address_space *mapping) { set_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } static inline bool mapping_writeback_may_deadlock_on_reclaim(struct address_space *mapping) { return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &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 & FOLIO_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 *); /** * 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); } /** * 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_DONTCACHE - Uncached buffered IO * * %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 FGP_DONTCACHE ((__force fgf_t)0x00000100) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) static inline unsigned int filemap_get_order(size_t size) { unsigned int shift = ilog2(size); if (shift <= PAGE_SHIFT) return 0; return shift - PAGE_SHIFT; } /** * 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 order = filemap_get_order(size); if (!order) return 0; return (__force fgf_t)(order << 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); /** * write_begin_get_folio - Get folio for write_begin with flags. * @iocb: The kiocb passed from write_begin (may be NULL). * @mapping: The address space to search. * @index: The page cache index. * @len: Length of data being written. * * This is a helper for filesystem write_begin() implementations. * It wraps __filemap_get_folio(), setting appropriate flags in * the write begin context. * * Return: A folio or an ERR_PTR. */ static inline struct folio *write_begin_get_folio(const struct kiocb *iocb, struct address_space *mapping, pgoff_t index, size_t len) { fgf_t fgp_flags = FGP_WRITEBEGIN; fgp_flags |= fgf_set_order(len); if (iocb && iocb->ki_flags & IOCB_DONTCACHE) fgp_flags |= FGP_DONTCACHE; return __filemap_get_folio(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); } /** * 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 * * Returns locked page at given index in given cache, creating it if * needed, but do not wait if the page is locked or to reclaim memory. * 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)); } /** * 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 folio locked and ensure * e.g., shmem did not move this folio to the swap cache. * Return: true or false. */ static inline bool folio_contains(struct folio *folio, pgoff_t index) { VM_WARN_ON_ONCE_FOLIO(folio_test_swapcache(folio), folio); return index - folio->index < folio_nr_pages(folio); } 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 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); } /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. */ static inline loff_t folio_pos(const struct folio *folio) { return ((loff_t)folio->index) * PAGE_SIZE; } /* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) { struct folio *folio = page_folio(page); return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE; } /* * 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); } 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 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); /* * 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_folio() or * __readahead_batch() in a loop and attempt to start reads into each * folio 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 dropbehind; 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_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 folio *folio; 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, folio, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, folio)) continue; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); array[i++] = folio_page(folio, 0); rac->_batch_count += folio_nr_pages(folio); if (i == array_sz) break; } rcu_read_unlock(); return i; } /** * 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; } /** * 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 */ |
| 8 8 8 8 255 114 114 112 72 114 114 255 255 | 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 | /* 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; } /* * 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 { \ typeof(start) __flush_start = start; \ typeof(pages) __flush_pages = pages; \ int num = 0; \ int scale = 3; \ int shift = lpa2 ? 16 : PAGE_SHIFT; \ unsigned long addr; \ \ while (__flush_pages > 0) { \ if (!system_supports_tlb_range() || \ __flush_pages == 1 || \ (lpa2 && __flush_start != ALIGN(__flush_start, SZ_64K))) { \ addr = __TLBI_VADDR(__flush_start, asid); \ __tlbi_level(op, addr, tlb_level); \ if (tlbi_user) \ __tlbi_user_level(op, addr, tlb_level); \ __flush_start += stride; \ __flush_pages -= stride >> PAGE_SHIFT; \ continue; \ } \ \ num = __TLBI_RANGE_NUM(__flush_pages, scale); \ if (num >= 0) { \ addr = __TLBI_VADDR_RANGE(__flush_start >> shift, asid, \ scale, num, tlb_level); \ __tlbi(r##op, addr); \ if (tlbi_user) \ __tlbi_user(r##op, addr); \ __flush_start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \ __flush_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 mm_struct *mm, 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(mm); return; } dsb(ishst); asid = ASID(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(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->vm_mm, 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(); } static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, struct mm_struct *mm, unsigned long start, unsigned long end) { __flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3); } #endif #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H #ifndef __ASSEMBLY__ static inline void cpu_relax(void) { asm volatile("yield" ::: "memory"); } #endif /* __ASSEMBLY__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ |
| 72 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_INTERNAL_H #define _LINUX_HIGHMEM_INTERNAL_H /* * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft. */ #ifdef CONFIG_KMAP_LOCAL void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot); void *__kmap_local_page_prot(struct page *page, pgprot_t prot); void kunmap_local_indexed(const void *vaddr); void kmap_local_fork(struct task_struct *tsk); void __kmap_local_sched_out(void); void __kmap_local_sched_in(void); static inline void kmap_assert_nomap(void) { DEBUG_LOCKS_WARN_ON(current->kmap_ctrl.idx); } #else static inline void kmap_local_fork(struct task_struct *tsk) { } static inline void kmap_assert_nomap(void) { } #endif #ifdef CONFIG_HIGHMEM #include <asm/highmem.h> #ifndef ARCH_HAS_KMAP_FLUSH_TLB static inline void kmap_flush_tlb(unsigned long addr) { } #endif #ifndef kmap_prot #define kmap_prot PAGE_KERNEL #endif void *kmap_high(struct page *page); void kunmap_high(struct page *page); void __kmap_flush_unused(void); struct page *__kmap_to_page(void *addr); static inline void *kmap(struct page *page) { void *addr; might_sleep(); if (!PageHighMem(page)) addr = page_address(page); else addr = kmap_high(page); kmap_flush_tlb((unsigned long)addr); return addr; } static inline void kunmap(struct page *page) { might_sleep(); if (!PageHighMem(page)) return; kunmap_high(page); } static inline struct page *kmap_to_page(void *addr) { return __kmap_to_page(addr); } static inline void kmap_flush_unused(void) { __kmap_flush_unused(); } static inline void *kmap_local_page(struct page *page) { return __kmap_local_page_prot(page, kmap_prot); } static inline void *kmap_local_page_try_from_panic(struct page *page) { if (!PageHighMem(page)) return page_address(page); /* If the page is in HighMem, it's not safe to kmap it.*/ return NULL; } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { struct page *page = folio_page(folio, offset / PAGE_SIZE); return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); } static inline void *kmap_local_pfn(unsigned long pfn) { return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_local(const void *vaddr) { kunmap_local_indexed(vaddr); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_page_prot(page, prot); } static inline void *kmap_atomic(struct page *page) { return kmap_atomic_prot(page, kmap_prot); } static inline void *kmap_atomic_pfn(unsigned long pfn) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_atomic(const void *addr) { kunmap_local_indexed(addr); pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } unsigned long __nr_free_highpages(void); unsigned long __totalhigh_pages(void); static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) { unsigned long addr = (unsigned long)x; return (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) || (addr >= __fix_to_virt(FIX_KMAP_END) && addr < __fix_to_virt(FIX_KMAP_BEGIN)); } #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) { return virt_to_page(addr); } static inline void *kmap(struct page *page) { might_sleep(); return page_address(page); } static inline void kunmap_high(struct page *page) { } static inline void kmap_flush_unused(void) { } static inline void kunmap(struct page *page) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(page_address(page)); #endif } static inline void *kmap_local_page(struct page *page) { return page_address(page); } static inline void *kmap_local_page_try_from_panic(struct page *page) { return page_address(page); } static inline void *kmap_local_folio(struct folio *folio, size_t offset) { return folio_address(folio) + offset; } static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return kmap_local_page(page); } static inline void *kmap_local_pfn(unsigned long pfn) { return kmap_local_page(pfn_to_page(pfn)); } static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } static inline void *kmap_atomic(struct page *page) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return page_address(page); } static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { return kmap_atomic(page); } static inline void *kmap_atomic_pfn(unsigned long pfn) { return kmap_atomic(pfn_to_page(pfn)); } static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } static inline unsigned long nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { return false; } #endif /* CONFIG_HIGHMEM */ /** * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! * @__addr: Virtual address to be unmapped * * Unmaps an address previously mapped by kmap_atomic() and re-enables * pagefaults. Depending on PREEMP_RT configuration, re-enables also * migration and preemption. Users should not count on these side effects. * * Mappings should be unmapped in the reverse order that they were mapped. * See kmap_local_page() for details on nesting. * * @__addr can be any address within the mapped page, so there is no need * to subtract any offset that has been added. In contrast to kunmap(), * this function takes the address returned from kmap_atomic(), not the * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_atomic(__addr); \ } while (0) /** * kunmap_local - Unmap a page mapped via kmap_local_page(). * @__addr: An address within the page mapped * * @__addr can be any address within the mapped page. Commonly it is the * address return from kmap_local_page(), but it can also include offsets. * * Unmapping should be done in the reverse order of the mapping. See * kmap_local_page() for details. */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_local(__addr); \ } while (0) #endif |
| 209 | 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 |
| 58 59 58 29 29 29 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/stat.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/compat.h> #include <linux/iversion.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <trace/events/timestamp.h> #include "internal.h" #include "mount.h" /** * fill_mg_cmtime - Fill in the mtime and ctime and flag ctime as QUERIED * @stat: where to store the resulting values * @request_mask: STATX_* values requested * @inode: inode from which to grab the c/mtime * * Given @inode, grab the ctime and mtime out if it and store the result * in @stat. When fetching the value, flag it as QUERIED (if not already) * so the next write will record a distinct timestamp. * * NB: The QUERIED flag is tracked in the ctime, but we set it there even * if only the mtime was requested, as that ensures that the next mtime * change will be distinct. */ void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode) { atomic_t *pcn = (atomic_t *)&inode->i_ctime_nsec; /* If neither time was requested, then don't report them */ if (!(request_mask & (STATX_CTIME|STATX_MTIME))) { stat->result_mask &= ~(STATX_CTIME|STATX_MTIME); return; } stat->mtime = inode_get_mtime(inode); stat->ctime.tv_sec = inode->i_ctime_sec; stat->ctime.tv_nsec = (u32)atomic_read(pcn); if (!(stat->ctime.tv_nsec & I_CTIME_QUERIED)) stat->ctime.tv_nsec = ((u32)atomic_fetch_or(I_CTIME_QUERIED, pcn)); stat->ctime.tv_nsec &= ~I_CTIME_QUERIED; trace_fill_mg_cmtime(inode, &stat->ctime, &stat->mtime); } EXPORT_SYMBOL(fill_mg_cmtime); /** * generic_fillattr - Fill in the basic attributes from the inode struct * @idmap: idmap of the mount the inode was found from * @request_mask: statx request_mask * @inode: Inode to use as the source * @stat: Where to fill in the attributes * * Fill in the basic attributes in the kstat structure from data that's to be * found on the VFS inode structure. This is the default if no getattr inode * operation is supplied. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before filling in the * uid and gid filds. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask, struct inode *inode, struct kstat *stat) { vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); stat->dev = inode->i_sb->s_dev; stat->ino = inode->i_ino; stat->mode = inode->i_mode; stat->nlink = inode->i_nlink; stat->uid = vfsuid_into_kuid(vfsuid); stat->gid = vfsgid_into_kgid(vfsgid); stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode_get_atime(inode); if (is_mgtime(inode)) { fill_mg_cmtime(stat, request_mask, inode); } else { stat->ctime = inode_get_ctime(inode); stat->mtime = inode_get_mtime(inode); } stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) { stat->result_mask |= STATX_CHANGE_COOKIE; stat->change_cookie = inode_query_iversion(inode); } } EXPORT_SYMBOL(generic_fillattr); /** * generic_fill_statx_attr - Fill in the statx attributes from the inode flags * @inode: Inode to use as the source * @stat: Where to fill in the attribute flags * * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the * inode that are published on i_flags and enforced by the VFS. */ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) { if (inode->i_flags & S_IMMUTABLE) stat->attributes |= STATX_ATTR_IMMUTABLE; if (inode->i_flags & S_APPEND) stat->attributes |= STATX_ATTR_APPEND; stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS; } EXPORT_SYMBOL(generic_fill_statx_attr); /** * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes * @stat: Where to fill in the attribute flags * @unit_min: Minimum supported atomic write length in bytes * @unit_max: Maximum supported atomic write length in bytes * @unit_max_opt: Optimised maximum supported atomic write length in bytes * * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from * atomic write unit_min and unit_max values. */ void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, unsigned int unit_max, unsigned int unit_max_opt) { /* Confirm that the request type is known */ stat->result_mask |= STATX_WRITE_ATOMIC; /* Confirm that the file attribute type is known */ stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC; if (unit_min) { stat->atomic_write_unit_min = unit_min; stat->atomic_write_unit_max = unit_max; stat->atomic_write_unit_max_opt = unit_max_opt; /* Initially only allow 1x segment */ stat->atomic_write_segments_max = 1; /* Confirm atomic writes are actually supported */ stat->attributes |= STATX_ATTR_WRITE_ATOMIC; } } EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes); /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from * @stat: structure to return attributes in * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Get attributes without calling security_inode_getattr. * * Currently the only caller other than vfs_getattr is internal to the * filehandle lookup code, which uses only the inode number and returns no * attributes to any user. Any other code probably wants vfs_getattr. */ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct mnt_idmap *idmap; struct inode *inode = d_backing_inode(path->dentry); memset(stat, 0, sizeof(*stat)); stat->result_mask |= STATX_BASIC_STATS; query_flags &= AT_STATX_SYNC_TYPE; /* allow the fs to override these if it really wants to */ /* SB_NOATIME means filesystem supplies dummy atime value */ if (inode->i_sb->s_flags & SB_NOATIME) stat->result_mask &= ~STATX_ATIME; /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. */ if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; if (IS_DAX(inode)) stat->attributes |= STATX_ATTR_DAX; stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT | STATX_ATTR_DAX); idmap = mnt_idmap(path->mnt); if (inode->i_op->getattr) { int ret; ret = inode->i_op->getattr(idmap, path, stat, request_mask, query_flags); if (ret) return ret; } else { generic_fillattr(idmap, request_mask, inode, stat); } /* * If this is a block device inode, override the filesystem attributes * with the block device specific parameters that need to be obtained * from the bdev backing inode. */ if (S_ISBLK(stat->mode)) bdev_statx(path, stat, request_mask); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); /* * vfs_getattr - Get the enhanced basic attributes of a file * @path: The file of interest * @stat: Where to return the statistics * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Ask the filesystem for a file's attributes. The caller must indicate in * request_mask and query_flags to indicate what they want. * * If the file is remote, the filesystem can be forced to update the attributes * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can * suppress the update by passing AT_STATX_DONT_SYNC. * * Bits must have been set in request_mask to indicate which attributes the * caller wants retrieving. Any such attribute not requested may be returned * anyway, but the value may be approximate, and, if remote, may not have been * synchronised with the server. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { int retval; retval = security_inode_getattr(path); if (unlikely(retval)) return retval; return vfs_getattr_nosec(path, stat, request_mask, query_flags); } EXPORT_SYMBOL(vfs_getattr); /** * vfs_fstat - Get the basic attributes by file descriptor * @fd: The file descriptor referring to the file of interest * @stat: The result structure to fill in. * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a file descriptor to determine the file location. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_fstat(int fd, struct kstat *stat) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_getattr(&fd_file(f)->f_path, stat, STATX_BASIC_STATS, 0); } static int statx_lookup_flags(int flags) { int lookup_flags = 0; if (!(flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (!(flags & AT_NO_AUTOMOUNT)) lookup_flags |= LOOKUP_AUTOMOUNT; return lookup_flags; } static int vfs_statx_path(struct path *path, int flags, struct kstat *stat, u32 request_mask) { int error = vfs_getattr(path, stat, request_mask, flags); if (error) return error; if (request_mask & STATX_MNT_ID_UNIQUE) { stat->mnt_id = real_mount(path->mnt)->mnt_id_unique; stat->result_mask |= STATX_MNT_ID_UNIQUE; } else { stat->mnt_id = real_mount(path->mnt)->mnt_id; stat->result_mask |= STATX_MNT_ID; } if (path_mounted(path)) stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; return 0; } static int vfs_statx_fd(int fd, int flags, struct kstat *stat, u32 request_mask) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_statx_path(&fd_file(f)->f_path, flags, stat, request_mask); } /** * vfs_statx - Get basic and extra attributes by filename * @dfd: A file descriptor representing the base dir for a relative filename * @filename: The name of the file of interest * @flags: Flags to control the query * @stat: The result structure to fill in. * @request_mask: STATX_xxx flags indicating what the caller wants * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a filename and base directory to determine the file location. * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink * at the given name from being referenced. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ static int vfs_statx(int dfd, struct filename *filename, int flags, struct kstat *stat, u32 request_mask) { struct path path; unsigned int lookup_flags = statx_lookup_flags(flags); int error; if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH | AT_STATX_SYNC_TYPE)) return -EINVAL; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) return error; error = vfs_statx_path(&path, flags, stat, request_mask); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags) { int ret; int statx_flags = flags | AT_NO_AUTOMOUNT; struct filename *name = getname_maybe_null(filename, flags); if (!name && dfd >= 0) return vfs_fstat(dfd, stat); ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS); putname(name); return ret; } #ifdef __ARCH_WANT_OLD_STAT /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf) { static int warncount = 5; struct __old_kernel_stat tmp; if (warncount > 0) { warncount--; printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n", current->comm); } else if (warncount < 0) { /* it's laughable, but... */ warncount = 0; } memset(&tmp, 0, sizeof(struct __old_kernel_stat)); tmp.st_dev = old_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (unlikely(error)) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(lstat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (unlikely(error)) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_fstat(fd, &stat); if (unlikely(error)) return error; return cp_old_stat(&stat, statbuf); } #endif /* __ARCH_WANT_OLD_STAT */ #ifdef __ARCH_WANT_NEW_STAT #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif INIT_STRUCT_STAT_PADDING(tmp); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; #ifdef STAT_HAVE_NSEC tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; #endif tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(newstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (unlikely(error)) return error; return cp_new_stat(&stat, statbuf); } SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (unlikely(error)) return error; return cp_new_stat(&stat, statbuf); } #if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT) SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename, struct stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (unlikely(error)) return error; return cp_new_stat(&stat, statbuf); } #endif SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf) { struct kstat stat; int error; error = vfs_fstat(fd, &stat); if (unlikely(error)) return error; return cp_new_stat(&stat, statbuf); } #endif static int do_readlinkat(int dfd, const char __user *pathname, char __user *buf, int bufsiz) { struct path path; struct filename *name; int error; unsigned int lookup_flags = LOOKUP_EMPTY; if (bufsiz <= 0) return -EINVAL; retry: name = getname_flags(pathname, lookup_flags); error = filename_lookup(dfd, name, lookup_flags, &path, NULL); if (unlikely(error)) { putname(name); return error; } /* * AFS mountpoints allow readlink(2) but are not symlinks */ if (d_is_symlink(path.dentry) || d_backing_inode(path.dentry)->i_op->readlink) { error = security_inode_readlink(path.dentry); if (!error) { touch_atime(&path); error = vfs_readlink(path.dentry, buf, bufsiz); } } else { error = (name->name[0] == '\0') ? -ENOENT : -EINVAL; } path_put(&path); putname(name); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, char __user *, buf, int, bufsiz) { return do_readlinkat(dfd, pathname, buf, bufsiz); } SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, int, bufsiz) { return do_readlinkat(AT_FDCWD, path, buf, bufsiz); } /* ---------- LFS-64 ----------- */ #if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) #ifndef INIT_STRUCT_STAT64_PADDING # define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st)) #endif static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) { struct stat64 tmp; INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ tmp.st_dev = new_encode_dev(stat->dev); tmp.st_rdev = new_encode_dev(stat->rdev); #else tmp.st_dev = huge_encode_dev(stat->dev); tmp.st_rdev = huge_encode_dev(stat->rdev); #endif tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; #ifdef STAT64_HAS_BROKEN_ST_INO tmp.__st_ino = stat->ino; #endif tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_size = stat->size; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(lstat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_lstat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename, struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_new_stat64(&stat, statbuf); } #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */ static noinline_for_stack int cp_statx(const struct kstat *stat, struct statx __user *buffer) { struct statx tmp; memset(&tmp, 0, sizeof(tmp)); /* STATX_CHANGE_COOKIE is kernel-only for now */ tmp.stx_mask = stat->result_mask & ~STATX_CHANGE_COOKIE; tmp.stx_blksize = stat->blksize; /* STATX_ATTR_CHANGE_MONOTONIC is kernel-only for now */ tmp.stx_attributes = stat->attributes & ~STATX_ATTR_CHANGE_MONOTONIC; tmp.stx_nlink = stat->nlink; tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.stx_mode = stat->mode; tmp.stx_ino = stat->ino; tmp.stx_size = stat->size; tmp.stx_blocks = stat->blocks; tmp.stx_attributes_mask = stat->attributes_mask; tmp.stx_atime.tv_sec = stat->atime.tv_sec; tmp.stx_atime.tv_nsec = stat->atime.tv_nsec; tmp.stx_btime.tv_sec = stat->btime.tv_sec; tmp.stx_btime.tv_nsec = stat->btime.tv_nsec; tmp.stx_ctime.tv_sec = stat->ctime.tv_sec; tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec; tmp.stx_mtime.tv_sec = stat->mtime.tv_sec; tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec; tmp.stx_rdev_major = MAJOR(stat->rdev); tmp.stx_rdev_minor = MINOR(stat->rdev); tmp.stx_dev_major = MAJOR(stat->dev); tmp.stx_dev_minor = MINOR(stat->dev); tmp.stx_mnt_id = stat->mnt_id; tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; tmp.stx_dio_read_offset_align = stat->dio_read_offset_align; tmp.stx_subvol = stat->subvol; tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max; tmp.stx_atomic_write_unit_max_opt = stat->atomic_write_unit_max_opt; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer) { struct kstat stat; int error; if (mask & STATX__RESERVED) return -EINVAL; if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; /* * STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests * from userland. */ mask &= ~STATX_CHANGE_COOKIE; error = vfs_statx(dfd, filename, flags, &stat, mask); if (error) return error; return cp_statx(&stat, buffer); } int do_statx_fd(int fd, unsigned int flags, unsigned int mask, struct statx __user *buffer) { struct kstat stat; int error; if (mask & STATX__RESERVED) return -EINVAL; if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; /* * STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests * from userland. */ mask &= ~STATX_CHANGE_COOKIE; error = vfs_statx_fd(fd, flags, &stat, mask); if (error) return error; return cp_statx(&stat, buffer); } /** * sys_statx - System call to get enhanced stats * @dfd: Base directory to pathwalk from *or* fd to stat. * @filename: File to stat or either NULL or "" with AT_EMPTY_PATH * @flags: AT_* flags to control pathwalk. * @mask: Parts of statx struct actually required. * @buffer: Result buffer. * * Note that fstat() can be emulated by setting dfd to the fd of interest, * supplying "" (or preferably NULL) as the filename and setting AT_EMPTY_PATH * in the flags. */ SYSCALL_DEFINE5(statx, int, dfd, const char __user *, filename, unsigned, flags, unsigned int, mask, struct statx __user *, buffer) { int ret; struct filename *name = getname_maybe_null(filename, flags); if (!name && dfd >= 0) return do_statx_fd(dfd, flags & ~AT_NO_AUTOMOUNT, mask, buffer); ret = do_statx(dfd, name, flags, mask, buffer); putname(name); return ret; } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_STAT) static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; } COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } #ifndef __ARCH_WANT_STAT64 COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, const char __user *, filename, struct compat_stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_compat_stat(&stat, statbuf); } #endif COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct compat_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_compat_stat(&stat, statbuf); return error; } #endif /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */ void __inode_add_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks += bytes >> 9; bytes &= 511; inode->i_bytes += bytes; if (inode->i_bytes >= 512) { inode->i_blocks++; inode->i_bytes -= 512; } } EXPORT_SYMBOL(__inode_add_bytes); void inode_add_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_add_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_add_bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks -= bytes >> 9; bytes &= 511; if (inode->i_bytes < bytes) { inode->i_blocks--; inode->i_bytes += 512; } inode->i_bytes -= bytes; } EXPORT_SYMBOL(__inode_sub_bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_sub_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_sub_bytes); loff_t inode_get_bytes(struct inode *inode) { loff_t ret; spin_lock(&inode->i_lock); ret = __inode_get_bytes(inode); spin_unlock(&inode->i_lock); return ret; } EXPORT_SYMBOL(inode_get_bytes); void inode_set_bytes(struct inode *inode, loff_t bytes) { /* Caller is here responsible for sufficient locking * (ie. inode->i_lock) */ inode->i_blocks = bytes >> 9; inode->i_bytes = bytes & 511; } EXPORT_SYMBOL(inode_set_bytes); |
| 31 31 31 32 31 33 1 1 1 1 11 10 10 1 1 1 1 1 1 1 1 14 13 14 13 13 12 1 1 12 1 11 11 10 10 10 10 10 10 10 10 10 9 10 10 1 1 2 3 13 14 14 5 5 5 5 5 12 12 4 1 1 2 2 1 3 1 1 1 1 1 1 24 2 2 21 2 2 1 16 1 1 1 1 1 1 1 1 4 1 1 1 1 1 1 1 2 19 24 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TUN - Universal TUN/TAP device driver. * Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com> * * $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $ */ /* * Changes: * * Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14 * Add TUNSETLINK ioctl to set the link encapsulation * * Mark Smith <markzzzsmith@yahoo.com.au> * Use eth_random_addr() for tap MAC address. * * Harald Roelle <harald.roelle@ifi.lmu.de> 2004/04/20 * Fixes in packet dropping, queue length setting and queue wakeup. * Increased default tx queue length. * Added ethtool API. * Minor cleanups * * Daniel Podlejski <underley@underley.eu.org> * Modifications for 2.3.99-pre5 kernel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "tun" #define DRV_VERSION "1.6" #define DRV_DESCRIPTION "Universal TUN/TAP device driver" #define DRV_COPYRIGHT "(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>" #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/miscdevice.h> #include <linux/ethtool.h> #include <linux/rtnetlink.h> #include <linux/compat.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_tun.h> #include <linux/if_vlan.h> #include <linux/crc32.h> #include <linux/math.h> #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> #include <net/ip_tunnels.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/skb_array.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mutex.h> #include <linux/ieee802154.h> #include <uapi/linux/if_ltalk.h> #include <uapi/linux/if_fddi.h> #include <uapi/linux/if_hippi.h> #include <uapi/linux/if_fc.h> #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> #include <net/rps.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> #include "tun_vnet.h" static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd); #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* TUN device flags */ /* IFF_ATTACH_QUEUE is never stored in device flags, * overload it to mean fasync when stored there. */ #define TUN_FASYNC IFF_ATTACH_QUEUE #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS) #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 struct tap_filter { unsigned int count; /* Number of addrs. Zero means disabled */ u32 mask[2]; /* Mask of the hashed addrs */ unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; }; /* MAX_TAP_QUEUES 256 is chosen to allow rx/tx queues to be equal * to max number of VCPUs in guest. */ #define MAX_TAP_QUEUES 256 #define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) /* A tun_file connects an open character device to a tuntap netdevice. It * also contains all socket related structures (except sock_fprog and tap_filter) * to serve as one transmit queue for tuntap device. The sock_fprog and * tap_filter were kept in tun_struct since they were used for filtering for the * netdevice not for a specific queue (at least I didn't see the requirement for * this). * * RCU usage: * The tun_file and tun_struct are loosely coupled, the pointer from one to the * other can only be read while rcu_read_lock or rtnl_lock is held. */ struct tun_file { struct sock sk; struct socket socket; struct tun_struct __rcu *tun; struct fasync_struct *fasync; /* only used for fasnyc */ unsigned int flags; union { u16 queue_index; unsigned int ifindex; }; struct napi_struct napi; bool napi_enabled; bool napi_frags_enabled; struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; }; struct tun_page { struct page *page; int count; }; struct tun_flow_entry { struct hlist_node hash_link; struct rcu_head rcu; struct tun_struct *tun; u32 rxhash; u32 rps_rxhash; int queue_index; unsigned long updated ____cacheline_aligned_in_smp; }; #define TUN_NUM_FLOW_ENTRIES 1024 #define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1) struct tun_prog { struct rcu_head rcu; struct bpf_prog *prog; }; /* Since the socket were moved to tun_file, to preserve the behavior of persist * device, socket filter, sndbuf and vnet header size were restore when the * file were attached to a persist device. */ struct tun_struct { struct tun_file __rcu *tfiles[MAX_TAP_QUEUES]; unsigned int numqueues; unsigned int flags; kuid_t owner; kgid_t group; struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4 | \ NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM) int align; int vnet_hdr_sz; int sndbuf; struct tap_filter txflt; struct sock_fprog fprog; /* protected by rtnl lock */ bool filter_attached; u32 msg_enable; spinlock_t lock; struct hlist_head flows[TUN_NUM_FLOW_ENTRIES]; struct timer_list flow_gc_timer; unsigned long ageing_time; unsigned int numdisabled; struct list_head disabled; void *security; u32 flow_count; u32 rx_batched; atomic_long_t rx_frame_errors; struct bpf_prog __rcu *xdp_prog; struct tun_prog __rcu *steering_prog; struct tun_prog __rcu *filter_prog; struct ethtool_link_ksettings link_ksettings; /* init args */ struct file *file; struct ifreq *ifr; }; struct veth { __be16 h_vlan_proto; __be16 h_vlan_TCI; }; static void tun_flow_init(struct tun_struct *tun); static void tun_flow_uninit(struct tun_struct *tun); static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; struct sk_buff *skb; int received = 0; __skb_queue_head_init(&process_queue); spin_lock(&queue->lock); skb_queue_splice_tail_init(queue, &process_queue); spin_unlock(&queue->lock); while (received < budget && (skb = __skb_dequeue(&process_queue))) { napi_gro_receive(napi, skb); ++received; } if (!skb_queue_empty(&process_queue)) { spin_lock(&queue->lock); skb_queue_splice(&process_queue, queue); spin_unlock(&queue->lock); } return received; } static int tun_napi_poll(struct napi_struct *napi, int budget) { unsigned int received; received = tun_napi_receive(napi, budget); if (received < budget) napi_complete_done(napi, received); return received; } static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, bool napi_en, bool napi_frags) { tfile->napi_enabled = napi_en; tfile->napi_frags_enabled = napi_en && napi_frags; if (napi_en) { netif_napi_add_tx(tun->dev, &tfile->napi, tun_napi_poll); napi_enable(&tfile->napi); } } static void tun_napi_enable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_enable(&tfile->napi); } static void tun_napi_disable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_disable(&tfile->napi); } static void tun_napi_del(struct tun_file *tfile) { if (tfile->napi_enabled) netif_napi_del(&tfile->napi); } static bool tun_napi_frags_enabled(const struct tun_file *tfile) { return tfile->napi_frags_enabled; } static inline u32 tun_hashfn(u32 rxhash) { return rxhash & TUN_MASK_FLOW_ENTRIES; } static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) { struct tun_flow_entry *e; hlist_for_each_entry_rcu(e, head, hash_link) { if (e->rxhash == rxhash) return e; } return NULL; } static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun, struct hlist_head *head, u32 rxhash, u16 queue_index) { struct tun_flow_entry *e = kmalloc(sizeof(*e), GFP_ATOMIC); if (e) { netif_info(tun, tx_queued, tun->dev, "create flow: hash %u index %u\n", rxhash, queue_index); e->updated = jiffies; e->rxhash = rxhash; e->rps_rxhash = 0; e->queue_index = queue_index; e->tun = tun; hlist_add_head_rcu(&e->hash_link, head); ++tun->flow_count; } return e; } static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e) { netif_info(tun, tx_queued, tun->dev, "delete flow: hash %u index %u\n", e->rxhash, e->queue_index); hlist_del_rcu(&e->hash_link); kfree_rcu(e, rcu); --tun->flow_count; } static void tun_flow_flush(struct tun_struct *tun) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) tun_flow_delete(tun, e); } spin_unlock_bh(&tun->lock); } static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { if (e->queue_index == queue_index) tun_flow_delete(tun, e); } } spin_unlock_bh(&tun->lock); } static void tun_flow_cleanup(struct timer_list *t) { struct tun_struct *tun = timer_container_of(tun, t, flow_gc_timer); unsigned long delay = tun->ageing_time; unsigned long next_timer = jiffies + delay; unsigned long count = 0; int i; spin_lock(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { unsigned long this_timer; this_timer = e->updated + delay; if (time_before_eq(this_timer, jiffies)) { tun_flow_delete(tun, e); continue; } count++; if (time_before(this_timer, next_timer)) next_timer = this_timer; } } if (count) mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer)); spin_unlock(&tun->lock); } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, struct tun_file *tfile) { struct hlist_head *head; struct tun_flow_entry *e; unsigned long delay = tun->ageing_time; u16 queue_index = tfile->queue_index; head = &tun->flows[tun_hashfn(rxhash)]; rcu_read_lock(); e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ if (READ_ONCE(e->queue_index) != queue_index) WRITE_ONCE(e->queue_index, queue_index); if (e->updated != jiffies) e->updated = jiffies; sock_rps_record_flow_hash(e->rps_rxhash); } else { spin_lock_bh(&tun->lock); if (!tun_flow_find(head, rxhash) && tun->flow_count < MAX_TAP_FLOWS) tun_flow_create(tun, head, rxhash, queue_index); if (!timer_pending(&tun->flow_gc_timer)) mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + delay)); spin_unlock_bh(&tun->lock); } rcu_read_unlock(); } /* Save the hash received in the stack receive path and update the * flow_hash table accordingly. */ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) { if (unlikely(e->rps_rxhash != hash)) e->rps_rxhash = hash; } /* We try to identify a flow through its rxhash. The reason that * we do not check rxq no. is because some cards(e.g 82599), chooses * the rxq based on the txq where the last packet of the flow comes. As * the userspace application move between processors, we may get a * different rxq no. here. */ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_flow_entry *e; u32 txq, numqueues; numqueues = READ_ONCE(tun->numqueues); txq = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); if (e) { tun_flow_save_rps_rxhash(e, txq); txq = e->queue_index; } else { txq = reciprocal_scale(txq, numqueues); } return txq; } static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_prog *prog; u32 numqueues; u16 ret = 0; numqueues = READ_ONCE(tun->numqueues); if (!numqueues) return 0; prog = rcu_dereference(tun->steering_prog); if (prog) ret = bpf_prog_run_clear_cb(prog->prog, skb); return ret % numqueues; } static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct tun_struct *tun = netdev_priv(dev); u16 ret; rcu_read_lock(); if (rcu_dereference(tun->steering_prog)) ret = tun_ebpf_select_queue(tun, skb); else ret = tun_automq_select_queue(tun, skb); rcu_read_unlock(); return ret; } static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); struct net *net = dev_net(tun->dev); return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || (gid_valid(tun->group) && !in_egroup_p(tun->group))) && !ns_capable(net->user_ns, CAP_NET_ADMIN); } static void tun_set_real_num_queues(struct tun_struct *tun) { netif_set_real_num_tx_queues(tun->dev, tun->numqueues); netif_set_real_num_rx_queues(tun->dev, tun->numqueues); } static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile) { tfile->detached = tun; list_add_tail(&tfile->next, &tun->disabled); ++tun->numdisabled; } static struct tun_struct *tun_enable_queue(struct tun_file *tfile) { struct tun_struct *tun = tfile->detached; tfile->detached = NULL; list_del_init(&tfile->next); --tun->numdisabled; return tun; } void tun_ptr_free(void *ptr) { if (!ptr) return; if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); xdp_return_frame(xdpf); } else { __skb_array_destroy_skb(ptr); } } EXPORT_SYMBOL_GPL(tun_ptr_free); static void tun_queue_purge(struct tun_file *tfile) { void *ptr; while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL) tun_ptr_free(ptr); skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); } static void __tun_detach(struct tun_file *tfile, bool clean) { struct tun_file *ntfile; struct tun_struct *tun; tun = rtnl_dereference(tfile->tun); if (tun && clean) { if (!tfile->detached) tun_napi_disable(tfile); tun_napi_del(tfile); } if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; ntfile->xdp_rxq.queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL); --tun->numqueues; if (clean) { RCU_INIT_POINTER(tfile->tun, NULL); sock_put(&tfile->sk); } else { tun_disable_queue(tun, tfile); tun_napi_disable(tfile); } synchronize_net(); tun_flow_delete_by_queue(tun, tun->numqueues + 1); /* Drop read queue */ tun_queue_purge(tfile); tun_set_real_num_queues(tun); } else if (tfile->detached && clean) { tun = tun_enable_queue(tfile); sock_put(&tfile->sk); } if (clean) { if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { netif_carrier_off(tun->dev); if (!(tun->flags & IFF_PERSIST) && tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); } } static void tun_detach(struct tun_file *tfile, bool clean) { struct tun_struct *tun; struct net_device *dev; rtnl_lock(); tun = rtnl_dereference(tfile->tun); dev = tun ? tun->dev : NULL; __tun_detach(tfile, clean); if (dev) netdev_state_change(dev); rtnl_unlock(); if (clean) sock_put(&tfile->sk); } static void tun_detach_all(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile, *tmp; int i, n = tun->numqueues; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); tun_napi_disable(tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); --tun->numqueues; } list_for_each_entry(tfile, &tun->disabled, next) { tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); } BUG_ON(tun->numqueues != 0); synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tun_napi_del(tfile); /* Drop read queue */ tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_napi_del(tfile); tun_enable_queue(tfile); tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } BUG_ON(tun->numdisabled != 0); if (tun->flags & IFF_PERSIST) module_put(THIS_MODULE); } static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter, bool napi, bool napi_frags, bool publish_tun) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; int err; err = security_tun_dev_attach(tfile->socket.sk, tun->security); if (err < 0) goto out; err = -EINVAL; if (rtnl_dereference(tfile->tun) && !tfile->detached) goto out; err = -EBUSY; if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1) goto out; err = -E2BIG; if (!tfile->detached && tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES) goto out; err = 0; /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { lock_sock(tfile->socket.sk); err = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (!err) goto out; } if (!tfile->detached && ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free)) { err = -ENOMEM; goto out; } tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; if (tfile->detached) { /* Re-attach detached tfile, updating XDP queue_index */ WARN_ON(!xdp_rxq_info_is_reg(&tfile->xdp_rxq)); if (tfile->xdp_rxq.queue_index != tfile->queue_index) tfile->xdp_rxq.queue_index = tfile->queue_index; } else { /* Setup XDP RX-queue info, for new tfile getting attached */ err = xdp_rxq_info_reg(&tfile->xdp_rxq, tun->dev, tfile->queue_index, 0); if (err < 0) goto out; err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) { xdp_rxq_info_unreg(&tfile->xdp_rxq); goto out; } err = 0; } if (tfile->detached) { tun_enable_queue(tfile); tun_napi_enable(tfile); } else { sock_hold(&tfile->sk); tun_napi_init(tun, tfile, napi, napi_frags); } if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); /* device is allowed to go away first, so no need to hold extra * refcnt. */ /* Publish tfile->tun and tun->tfiles only after we've fully * initialized tfile; otherwise we risk using half-initialized * object. */ if (publish_tun) rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; tun_set_real_num_queues(tun); out: return err; } static struct tun_struct *tun_get(struct tun_file *tfile) { struct tun_struct *tun; rcu_read_lock(); tun = rcu_dereference(tfile->tun); if (tun) dev_hold(tun->dev); rcu_read_unlock(); return tun; } static void tun_put(struct tun_struct *tun) { dev_put(tun->dev); } /* TAP filtering */ static void addr_hash_set(u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; mask[n >> 5] |= (1 << (n & 31)); } static unsigned int addr_hash_test(const u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; return mask[n >> 5] & (1 << (n & 31)); } static int update_filter(struct tap_filter *filter, void __user *arg) { struct { u8 u[ETH_ALEN]; } *addr; struct tun_filter uf; int err, alen, n, nexact; if (copy_from_user(&uf, arg, sizeof(uf))) return -EFAULT; if (!uf.count) { /* Disabled */ filter->count = 0; return 0; } alen = ETH_ALEN * uf.count; addr = memdup_user(arg + sizeof(uf), alen); if (IS_ERR(addr)) return PTR_ERR(addr); /* The filter is updated without holding any locks. Which is * perfectly safe. We disable it first and in the worst * case we'll accept a few undesired packets. */ filter->count = 0; wmb(); /* Use first set of addresses as an exact filter */ for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++) memcpy(filter->addr[n], addr[n].u, ETH_ALEN); nexact = n; /* Remaining multicast addresses are hashed, * unicast will leave the filter disabled. */ memset(filter->mask, 0, sizeof(filter->mask)); for (; n < uf.count; n++) { if (!is_multicast_ether_addr(addr[n].u)) { err = 0; /* no filter */ goto free_addr; } addr_hash_set(filter->mask, addr[n].u); } /* For ALLMULTI just set the mask to all ones. * This overrides the mask populated above. */ if ((uf.flags & TUN_FLT_ALLMULTI)) memset(filter->mask, ~0, sizeof(filter->mask)); /* Now enable the filter */ wmb(); filter->count = nexact; /* Return the number of exact filters */ err = nexact; free_addr: kfree(addr); return err; } /* Returns: 0 - drop, !=0 - accept */ static int run_filter(struct tap_filter *filter, const struct sk_buff *skb) { /* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect * at this point. */ struct ethhdr *eh = (struct ethhdr *) skb->data; int i; /* Exact match */ for (i = 0; i < filter->count; i++) if (ether_addr_equal(eh->h_dest, filter->addr[i])) return 1; /* Inexact match (multicast only) */ if (is_multicast_ether_addr(eh->h_dest)) return addr_hash_test(filter->mask, eh->h_dest); return 0; } /* * Checks whether the packet is accepted or not. * Returns: 0 - drop, !=0 - accept */ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) { if (!filter->count) return 1; return run_filter(filter, skb); } /* Network device part of the driver */ static const struct ethtool_ops tun_ethtool_ops; static int tun_net_init(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct ifreq *ifr = tun->ifr; int err; spin_lock_init(&tun->lock); err = security_tun_dev_alloc_security(&tun->security); if (err < 0) return err; tun_flow_init(tun); dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->hw_enc_features = dev->hw_features; dev->features = dev->hw_features; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); dev->lltx = true; tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, tun->file, false, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, false); if (err < 0) { tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); return err; } return 0; } /* Net device detach from fd. */ static void tun_net_uninit(struct net_device *dev) { tun_detach_all(dev); } /* Net device open. */ static int tun_net_open(struct net_device *dev) { netif_tx_start_all_queues(dev); return 0; } /* Net device close. */ static int tun_net_close(struct net_device *dev) { netif_tx_stop_all_queues(dev); return 0; } /* Net device start xmit */ static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { #ifdef CONFIG_RPS if (tun->numqueues == 1 && static_branch_unlikely(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ struct tun_flow_entry *e; __u32 rxhash; rxhash = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], rxhash); if (e) tun_flow_save_rps_rxhash(e, rxhash); } #endif } static unsigned int run_ebpf_filter(struct tun_struct *tun, struct sk_buff *skb, int len) { struct tun_prog *prog = rcu_dereference(tun->filter_prog); if (prog) len = bpf_prog_run_clear_cb(prog->prog, skb); return len; } /* Net device start xmit */ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct tun_struct *tun = netdev_priv(dev); int txq = skb->queue_mapping; struct netdev_queue *queue; struct tun_file *tfile; int len = skb->len; rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); /* Drop packet if interface is not attached */ if (!tfile) { drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (!rcu_dereference(tun->steering_prog)) tun_automq_xmit(tun, skb); netif_info(tun, tx_queued, tun->dev, "%s %d\n", __func__, skb->len); /* Drop if the filter does not like it. * This is a noop if the filter is disabled. * Filter can be enabled only for the TAP devices. */ if (!check_filter(&tun->txflt, skb)) { drop_reason = SKB_DROP_REASON_TAP_TXFILTER; goto drop; } if (tfile->socket.sk->sk_filter && sk_filter_reason(tfile->socket.sk, skb, &drop_reason)) goto drop; len = run_ebpf_filter(tun, skb, len); if (len == 0) { drop_reason = SKB_DROP_REASON_TAP_FILTER; goto drop; } if (pskb_trim(skb, len)) { drop_reason = SKB_DROP_REASON_NOMEM; goto drop; } if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } skb_tx_timestamp(skb); /* Orphan the skb - required as we might hang on to it * for indefinite time. */ skb_orphan(skb); nf_reset_ct(skb); if (ptr_ring_produce(&tfile->tx_ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } /* dev->lltx requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); txq_trans_cond_update(queue); /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); rcu_read_unlock(); return NETDEV_TX_OK; drop: dev_core_stats_tx_dropped_inc(dev); skb_tx_error(skb); kfree_skb_reason(skb, drop_reason); rcu_read_unlock(); return NET_XMIT_DROP; } static void tun_net_mclist(struct net_device *dev) { /* * This callback is supposed to deal with mc filter in * _rx_ path and has nothing to do with the _tx_ path. * In rx path we always accept everything userspace gives us. */ } static netdev_features_t tun_net_fix_features(struct net_device *dev, netdev_features_t features) { struct tun_struct *tun = netdev_priv(dev); return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } static void tun_set_headroom(struct net_device *dev, int new_hr) { struct tun_struct *tun = netdev_priv(dev); if (new_hr < NET_SKB_PAD) new_hr = NET_SKB_PAD; tun->align = new_hr; } static void tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct tun_struct *tun = netdev_priv(dev); dev_get_tstats64(dev, stats); stats->rx_frame_errors += (unsigned long)atomic_long_read(&tun->rx_frame_errors); } static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; struct bpf_prog *old_prog; int i; old_prog = rtnl_dereference(tun->xdp_prog); rcu_assign_pointer(tun->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } list_for_each_entry(tfile, &tun->disabled, next) { if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } return 0; } static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return tun_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static int tun_net_change_carrier(struct net_device *dev, bool new_carrier) { if (new_carrier) { struct tun_struct *tun = netdev_priv(dev); if (!tun->numqueues) return -EPERM; netif_carrier_on(dev); } else { netif_carrier_off(dev); } return 0; } static const struct net_device_ops tun_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_select_queue = tun_select_queue, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, .ndo_change_carrier = tun_net_change_carrier, }; static void __tun_xdp_flush_tfile(struct tun_file *tfile) { /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); } static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; u32 numqueues; int nxmit = 0; int i; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); resample: numqueues = READ_ONCE(tun->numqueues); if (!numqueues) { rcu_read_unlock(); return -ENXIO; /* Caller will free/return all frames */ } tfile = rcu_dereference(tun->tfiles[smp_processor_id() % numqueues]); if (unlikely(!tfile)) goto resample; spin_lock(&tfile->tx_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *xdp = frames[i]; /* Encode the XDP flag into lowest bit for consumer to differ * XDP buffer from sk_buff. */ void *frame = tun_xdp_to_ptr(xdp); if (__ptr_ring_produce(&tfile->tx_ring, frame)) { dev_core_stats_tx_dropped_inc(dev); break; } nxmit++; } spin_unlock(&tfile->tx_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __tun_xdp_flush_tfile(tfile); rcu_read_unlock(); return nxmit; } static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); int nxmit; if (unlikely(!frame)) return -EOVERFLOW; nxmit = tun_xdp_xmit(dev, 1, &frame, XDP_XMIT_FLUSH); if (!nxmit) xdp_return_frame_rx_napi(frame); return nxmit; } static const struct net_device_ops tap_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_set_rx_mode = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_select_queue = tun_select_queue, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_bpf = tun_xdp, .ndo_xdp_xmit = tun_xdp_xmit, .ndo_change_carrier = tun_net_change_carrier, }; static void tun_flow_init(struct tun_struct *tun) { int i; for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) INIT_HLIST_HEAD(&tun->flows[i]); tun->ageing_time = TUN_FLOW_EXPIRE; timer_setup(&tun->flow_gc_timer, tun_flow_cleanup, 0); mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + tun->ageing_time)); } static void tun_flow_uninit(struct tun_struct *tun) { timer_delete_sync(&tun->flow_gc_timer); tun_flow_flush(tun); } #define MIN_MTU 68 #define MAX_MTU 65535 /* Initialize net device. */ static void tun_net_initialize(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: dev->netdev_ops = &tun_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; /* Point-to-Point TUN Device */ dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = 1500; /* Zero header length */ dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; break; case IFF_TAP: dev->netdev_ops = &tap_netdev_ops; /* Ethernet TAP Device */ ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; eth_hw_addr_random(dev); /* Currently tun does not support XDP, only tap does. */ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT; break; } dev->min_mtu = MIN_MTU; dev->max_mtu = MAX_MTU - dev->hard_header_len; } static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile) { struct sock *sk = tfile->socket.sk; return (tun->dev->flags & IFF_UP) && sock_writeable(sk); } /* Character device part */ /* Poll */ static __poll_t tun_chr_poll(struct file *file, poll_table *wait) { struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); struct sock *sk; __poll_t mask = 0; if (!tun) return EPOLLERR; sk = tfile->socket.sk; poll_wait(file, sk_sleep(sk), wait); if (!ptr_ring_empty(&tfile->tx_ring)) mask |= EPOLLIN | EPOLLRDNORM; /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to * guarantee EPOLLOUT to be raised by either here or * tun_sock_write_space(). Then process could get notification * after it writes to a down device and meets -EIO. */ if (tun_sock_writeable(tun, tfile) || (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && tun_sock_writeable(tun, tfile))) mask |= EPOLLOUT | EPOLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) mask = EPOLLERR; tun_put(tun); return mask; } static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, size_t len, const struct iov_iter *it) { struct sk_buff *skb; size_t linear; int err; int i; if (it->nr_segs > MAX_SKB_FRAGS + 1 || len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE); local_bh_disable(); skb = napi_get_frags(&tfile->napi); local_bh_enable(); if (!skb) return ERR_PTR(-ENOMEM); linear = iov_iter_single_seg_count(it); err = __skb_grow(skb, linear); if (err) goto free; skb->len = len; skb->data_len = len - linear; skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; if (fragsz == 0 || fragsz > PAGE_SIZE) { err = -EINVAL; goto free; } frag = netdev_alloc_frag(fragsz); if (!frag) { err = -ENOMEM; goto free; } page = virt_to_head_page(frag); skb_fill_page_desc(skb, i - 1, page, frag - page_address(page), fragsz); } return skb; free: /* frees skb and all frags allocated with napi_alloc_frag() */ napi_free_frags(&tfile->napi); return ERR_PTR(err); } /* prepad is the amount to reserve at front. len is length after that. * linear is a hint as to how much to copy (usually headers). */ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, size_t prepad, size_t len, size_t linear, int noblock) { struct sock *sk = tfile->socket.sk; struct sk_buff *skb; int err; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, &err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return ERR_PTR(err); skb_reserve(skb, prepad); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, int more) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; u32 rx_batched = tun->rx_batched; bool rcv = false; if (!rx_batched || (!more && skb_queue_empty(queue))) { local_bh_disable(); skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); return; } spin_lock(&queue->lock); if (!more || skb_queue_len(queue) == rx_batched) { __skb_queue_head_init(&process_queue); skb_queue_splice_tail_init(queue, &process_queue); rcv = true; } else { __skb_queue_tail(queue, skb); } spin_unlock(&queue->lock); if (rcv) { struct sk_buff *nskb; local_bh_disable(); while ((nskb = __skb_dequeue(&process_queue))) { skb_record_rx_queue(nskb, tfile->queue_index); netif_receive_skb(nskb); } skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); } } static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, int len, int noblock, bool zerocopy) { if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) return false; if (tfile->socket.sk->sk_sndbuf != INT_MAX) return false; if (!noblock) return false; if (zerocopy) return false; if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; return true; } static struct sk_buff *__tun_build_skb(struct tun_file *tfile, struct page_frag *alloc_frag, char *buf, int buflen, int len, int pad, int metasize) { struct sk_buff *skb = build_skb(buf, buflen); if (!skb) return ERR_PTR(-ENOMEM); skb_reserve(skb, pad); skb_put(skb, len); if (metasize) skb_metadata_set(skb, metasize); skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen; return skb; } static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, struct xdp_buff *xdp, u32 act) { int err; switch (act) { case XDP_REDIRECT: err = xdp_do_redirect(tun->dev, xdp, xdp_prog); if (err) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_TX: err = tun_xdp_tx(tun->dev, xdp); if (err < 0) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_PASS: break; default: bpf_warn_invalid_xdp_action(tun->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tun->dev, xdp_prog, act); fallthrough; case XDP_DROP: dev_core_stats_rx_dropped_inc(tun->dev); break; } return act; } static struct sk_buff *tun_build_skb(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *from, struct virtio_net_hdr *hdr, int len, int *skb_xdp) { struct page_frag *alloc_frag = ¤t->task_frag; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); char *buf; size_t copied; int pad = TUN_RX_PAD; int metasize = 0; int err = 0; rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) pad += XDP_PACKET_HEADROOM; buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) return ERR_PTR(-ENOMEM); buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; copied = copy_page_from_iter(alloc_frag->page, alloc_frag->offset + pad, len, from); if (copied != len) return ERR_PTR(-EFAULT); /* There's a small window that XDP may be set after the check * of xdp_prog above, this should be rare and for simplicity * we do XDP on skb in case the headroom is not enough. */ if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); } *skb_xdp = 0; local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { struct xdp_buff xdp; u32 act; xdp_init_buff(&xdp, buflen, &tfile->xdp_rxq); xdp_prepare_buff(&xdp, buf, pad, len, true); act = bpf_prog_run_xdp(xdp_prog, &xdp); if (act == XDP_REDIRECT || act == XDP_TX) { get_page(alloc_frag->page); alloc_frag->offset += buflen; } err = tun_xdp_act(tun, xdp_prog, &xdp, act); if (err < 0) { if (act == XDP_REDIRECT || act == XDP_TX) put_page(alloc_frag->page); goto out; } if (err == XDP_REDIRECT) xdp_do_flush(); if (err != XDP_PASS) goto out; pad = xdp.data - xdp.data_hard_start; len = xdp.data_end - xdp.data; /* It is known that the xdp_buff was prepared with metadata * support, so the metasize will never be negative. */ metasize = xdp.data - xdp.data_meta; } bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); out: bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return NULL; } /* Get packet from user space buffer */ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, void *msg_control, struct iov_iter *from, int noblock, bool more) { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; size_t total_len = iov_iter_count(from); size_t len = total_len, align = tun->align, linear; struct virtio_net_hdr_v1_hash_tunnel hdr; struct virtio_net_hdr *gso; int good_linear; int copylen; int hdr_len = 0; bool zerocopy = false; int err; u32 rxhash = 0; int skb_xdp = 1; bool frags = tun_napi_frags_enabled(tfile); enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; netdev_features_t features = 0; /* * Keep it easy and always zero the whole buffer, even if the * tunnel-related field will be touched only when the feature * is enabled and the hdr size id compatible. */ memset(&hdr, 0, sizeof(hdr)); gso = (struct virtio_net_hdr *)&hdr; if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; len -= sizeof(pi); if (!copy_from_iter_full(&pi, sizeof(pi), from)) return -EFAULT; } if (tun->flags & IFF_VNET_HDR) { int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); features = tun_vnet_hdr_guest_features(vnet_hdr_sz); hdr_len = __tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, features, from, gso); if (hdr_len < 0) return hdr_len; len -= vnet_hdr_sz; } if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) { align += NET_IP_ALIGN; if (unlikely(len < ETH_HLEN || (hdr_len && hdr_len < ETH_HLEN))) return -EINVAL; } good_linear = SKB_MAX_HEAD(align); if (msg_control) { struct iov_iter i = *from; /* There are 256 bytes to be copied in skb, so there is * enough room for skb expand head in case it is used. * The rest of the buffer is mapped from userspace. */ copylen = min(hdr_len ? hdr_len : GOODCOPY_LEN, good_linear); linear = copylen; iov_iter_advance(&i, copylen); if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS) zerocopy = true; } if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { /* For the packet that is not easy to be processed * (e.g gso or jumbo packet), we will do it at after * skb was created with generic XDP routine. */ skb = tun_build_skb(tun, tfile, from, gso, len, &skb_xdp); err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (!skb) return total_len; } else { if (!zerocopy) { copylen = len; linear = min(hdr_len, good_linear); } if (frags) { mutex_lock(&tfile->napi_mutex); skb = tun_napi_alloc_frags(tfile, copylen, from); /* tun_napi_alloc_frags() enforces a layout for the skb. * If zerocopy is enabled, then this layout will be * overwritten by zerocopy_sg_from_iter(). */ zerocopy = false; } else { if (!linear) linear = min_t(size_t, good_linear, copylen); skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); } err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (zerocopy) err = zerocopy_sg_from_iter(skb, from); else err = skb_copy_datagram_from_iter(skb, 0, from, len); if (err) { err = -EFAULT; drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } } if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) { atomic_long_inc(&tun->rx_frame_errors); err = -EINVAL; goto free_skb; } switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; switch (ip_version) { case 4: pi.proto = htons(ETH_P_IP); break; case 6: pi.proto = htons(ETH_P_IPV6); break; default: err = -EINVAL; goto drop; } } skb_reset_mac_header(skb); skb->protocol = pi.proto; skb->dev = tun->dev; break; case IFF_TAP: if (frags && !pskb_may_pull(skb, ETH_HLEN)) { err = -ENOMEM; drop_reason = SKB_DROP_REASON_HDR_TRUNC; goto drop; } skb->protocol = eth_type_trans(skb, tun->dev); break; } /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { skb_zcopy_init(skb, msg_control); } else if (msg_control) { struct ubuf_info *uarg = msg_control; uarg->ops->complete(NULL, uarg, false); } skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { struct bpf_prog *xdp_prog; int ret; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); goto unlock_frags; } } rcu_read_unlock(); local_bh_enable(); } /* Compute the costly rx hash only if needed for flow updates. * We may get a very small possibility of OOO during switching, not * worth to optimize. */ if (!rcu_access_pointer(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); rcu_read_lock(); if (unlikely(!(tun->dev->flags & IFF_UP))) { err = -EIO; rcu_read_unlock(); drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (frags) { u32 headlen; /* Exercise flow dissector code path. */ skb_push(skb, ETH_HLEN); headlen = eth_get_headlen(tun->dev, skb->data, skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { WARN_ON_ONCE(1); err = -ENOMEM; dev_core_stats_rx_dropped_inc(tun->dev); napi_busy: napi_free_frags(&tfile->napi); rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); return err; } if (likely(napi_schedule_prep(&tfile->napi))) { local_bh_disable(); napi_gro_frags(&tfile->napi); napi_complete(&tfile->napi); local_bh_enable(); } else { err = -EBUSY; goto napi_busy; } mutex_unlock(&tfile->napi_mutex); } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; int queue_len; spin_lock_bh(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock_bh(&queue->lock); rcu_read_unlock(); err = -EBUSY; goto free_skb; } __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); if (!more || queue_len > NAPI_POLL_WEIGHT) napi_schedule(&tfile->napi); local_bh_enable(); } else if (!IS_ENABLED(CONFIG_4KSTACKS)) { tun_rx_batched(tun, tfile, skb, more); } else { netif_rx(skb); } rcu_read_unlock(); preempt_disable(); dev_sw_netstats_rx_add(tun->dev, len); preempt_enable(); if (rxhash) tun_flow_update(tun, rxhash, tfile); return total_len; drop: if (err != -EAGAIN) dev_core_stats_rx_dropped_inc(tun->dev); free_skb: if (!IS_ERR_OR_NULL(skb)) kfree_skb_reason(skb, drop_reason); unlock_frags: if (frags) { tfile->napi.skb = NULL; mutex_unlock(&tfile->napi_mutex); } return err ?: total_len; } static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; result = tun_get_user(tun, tfile, NULL, from, noblock, false); tun_put(tun); return result; } static ssize_t tun_put_user_xdp(struct tun_struct *tun, struct tun_file *tfile, struct xdp_frame *xdp_frame, struct iov_iter *iter) { int vnet_hdr_sz = 0; size_t size = xdp_frame->len; ssize_t ret; if (tun->flags & IFF_VNET_HDR) { struct virtio_net_hdr gso = { 0 }; vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso); if (ret) return ret; } ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz; preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, ret); preempt_enable(); return ret; } /* Put packet to the user space buffer */ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, struct iov_iter *iter) { struct tun_pi pi = { 0, skb->protocol }; ssize_t total; int vlan_offset = 0; int vlan_hlen = 0; int vnet_hdr_sz = 0; int ret; if (skb_vlan_tag_present(skb)) vlan_hlen = VLAN_HLEN; if (tun->flags & IFF_VNET_HDR) vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); total = skb->len + vlan_hlen + vnet_hdr_sz; if (!(tun->flags & IFF_NO_PI)) { if (iov_iter_count(iter) < sizeof(pi)) return -EINVAL; total += sizeof(pi); if (iov_iter_count(iter) < total) { /* Packet will be striped */ pi.flags |= TUN_PKT_STRIP; } if (copy_to_iter(&pi, sizeof(pi), iter) != sizeof(pi)) return -EFAULT; } if (vnet_hdr_sz) { struct virtio_net_hdr_v1_hash_tunnel hdr; struct virtio_net_hdr *gso; ret = tun_vnet_hdr_tnl_from_skb(tun->flags, tun->dev, skb, &hdr); if (ret) return ret; /* * Drop the packet if the configured header size is too small * WRT the enabled offloads. */ gso = (struct virtio_net_hdr *)&hdr; ret = __tun_vnet_hdr_put(vnet_hdr_sz, tun->dev->features, iter, gso); if (ret) return ret; } if (vlan_hlen) { int ret; struct veth veth; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset); if (ret || !iov_iter_count(iter)) goto done; ret = copy_to_iter(&veth, sizeof(veth), iter); if (ret != sizeof(veth) || !iov_iter_count(iter)) goto done; } skb_copy_datagram_iter(skb, vlan_offset, iter, skb->len - vlan_offset); done: /* caller is in process context, */ preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, skb->len + vlan_hlen); preempt_enable(); return total; } static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) { DECLARE_WAITQUEUE(wait, current); void *ptr = NULL; int error = 0; ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) goto out; if (noblock) { error = -EAGAIN; goto out; } add_wait_queue(&tfile->socket.wq.wait, &wait); while (1) { set_current_state(TASK_INTERRUPTIBLE); ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) break; if (signal_pending(current)) { error = -ERESTARTSYS; break; } if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) { error = -EFAULT; break; } schedule(); } __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->socket.wq.wait, &wait); out: *err = error; return ptr; } static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, int noblock, void *ptr) { ssize_t ret; int err; if (!iov_iter_count(to)) { tun_ptr_free(ptr); return 0; } if (!ptr) { /* Read frames from ring */ ptr = tun_ring_recv(tfile, noblock, &err); if (!ptr) return err; } if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); ret = tun_put_user_xdp(tun, tfile, xdpf, to); xdp_return_frame(xdpf); } else { struct sk_buff *skb = ptr; ret = tun_put_user(tun, tfile, skb, to); if (unlikely(ret < 0)) kfree_skb(skb); else consume_skb(skb); } return ret; } static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; tun_put(tun); return ret; } static void tun_prog_free(struct rcu_head *rcu) { struct tun_prog *prog = container_of(rcu, struct tun_prog, rcu); bpf_prog_destroy(prog->prog); kfree(prog); } static int __tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, struct bpf_prog *prog) { struct tun_prog *old, *new = NULL; if (prog) { new = kmalloc(sizeof(*new), GFP_KERNEL); if (!new) return -ENOMEM; new->prog = prog; } spin_lock_bh(&tun->lock); old = rcu_dereference_protected(*prog_p, lockdep_is_held(&tun->lock)); rcu_assign_pointer(*prog_p, new); spin_unlock_bh(&tun->lock); if (old) call_rcu(&old->rcu, tun_prog_free); return 0; } static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); BUG_ON(!(list_empty(&tun->disabled))); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); __tun_set_ebpf(tun, &tun->filter_prog, NULL); } static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); tun->owner = INVALID_UID; tun->group = INVALID_GID; tun_default_link_ksettings(dev, &tun->link_ksettings); dev->ethtool_ops = &tun_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = tun_free_netdev; /* We prefer our own queue length */ dev->tx_queue_len = TUN_READQ_SIZE; } /* Trivial set of netlink ops to allow deleting tun or tap * device with netlink. */ static int tun_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "tun/tap creation via rtnetlink is not supported."); return -EOPNOTSUPP; } static size_t tun_get_size(const struct net_device *dev) { BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); return nla_total_size(sizeof(uid_t)) + /* OWNER */ nla_total_size(sizeof(gid_t)) + /* GROUP */ nla_total_size(sizeof(u8)) + /* TYPE */ nla_total_size(sizeof(u8)) + /* PI */ nla_total_size(sizeof(u8)) + /* VNET_HDR */ nla_total_size(sizeof(u8)) + /* PERSIST */ nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ 0; } static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) goto nla_put_failure; if (uid_valid(tun->owner) && nla_put_u32(skb, IFLA_TUN_OWNER, from_kuid_munged(current_user_ns(), tun->owner))) goto nla_put_failure; if (gid_valid(tun->group) && nla_put_u32(skb, IFLA_TUN_GROUP, from_kgid_munged(current_user_ns(), tun->group))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, !!(tun->flags & IFF_MULTI_QUEUE))) goto nla_put_failure; if (tun->flags & IFF_MULTI_QUEUE) { if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, tun->numdisabled)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops tun_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, .get_size = tun_get_size, .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) { struct tun_file *tfile; wait_queue_head_t *wqueue; if (!sock_writeable(sk)) return; if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) wake_up_interruptible_sync_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); tfile = container_of(sk, struct tun_file, sk); kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } static void tun_put_page(struct tun_page *tpage) { if (tpage->page) __page_frag_cache_drain(tpage->page, tpage->count); } static int tun_xdp_one(struct tun_struct *tun, struct tun_file *tfile, struct xdp_buff *xdp, int *flush, struct tun_page *tpage) { unsigned int datasize = xdp->data_end - xdp->data; struct virtio_net_hdr *gso = xdp->data_hard_start; struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr; struct bpf_prog *xdp_prog; struct sk_buff *skb = NULL; struct sk_buff_head *queue; netdev_features_t features; u32 rxhash = 0, act; int buflen = xdp->frame_sz; int metasize = 0; int ret = 0; bool skb_xdp = false; struct page *page; if (unlikely(datasize < ETH_HLEN)) return -EINVAL; xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { if (gso->gso_type) { skb_xdp = true; goto build; } xdp_init_buff(xdp, buflen, &tfile->xdp_rxq); act = bpf_prog_run_xdp(xdp_prog, xdp); ret = tun_xdp_act(tun, xdp_prog, xdp, act); if (ret < 0) { put_page(virt_to_head_page(xdp->data)); return ret; } switch (ret) { case XDP_REDIRECT: *flush = true; fallthrough; case XDP_TX: return 0; case XDP_PASS: break; default: page = virt_to_head_page(xdp->data); if (tpage->page == page) { ++tpage->count; } else { tun_put_page(tpage); tpage->page = page; tpage->count = 1; } return 0; } } build: skb = build_skb(xdp->data_hard_start, buflen); if (!skb) { ret = -ENOMEM; goto out; } skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); /* The externally provided xdp_buff may have no metadata support, which * is marked by xdp->data_meta being xdp->data + 1. This will lead to a * metasize of -1 and is the reason why the condition checks for > 0. */ metasize = xdp->data - xdp->data_meta; if (metasize > 0) skb_metadata_set(skb, metasize); features = tun_vnet_hdr_guest_features(READ_ONCE(tun->vnet_hdr_sz)); tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso; if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) { atomic_long_inc(&tun->rx_frame_errors); kfree_skb(skb); ret = -EINVAL; goto out; } skb->protocol = eth_type_trans(skb, tun->dev); skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { ret = 0; goto out; } } if (!rcu_dereference(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock(&queue->lock); kfree_skb(skb); return -EBUSY; } __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; } else { netif_receive_skb(skb); ret = 0; } /* No need to disable preemption here since this function is * always called with bh disabled */ dev_sw_netstats_rx_add(tun->dev, datasize); if (rxhash) tun_flow_update(tun, rxhash, tfile); out: return ret; } static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); struct tun_msg_ctl *ctl = m->msg_control; struct xdp_buff *xdp; if (!tun) return -EBADFD; if (m->msg_controllen == sizeof(struct tun_msg_ctl) && ctl && ctl->type == TUN_MSG_PTR) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct tun_page tpage; int n = ctl->num; int flush = 0, queued = 0; memset(&tpage, 0, sizeof(tpage)); local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); for (i = 0; i < n; i++) { xdp = &((struct xdp_buff *)ctl->ptr)[i]; ret = tun_xdp_one(tun, tfile, xdp, &flush, &tpage); if (ret > 0) queued += ret; } if (flush) xdp_do_flush(); if (tfile->napi_enabled && queued > 0) napi_schedule(&tfile->napi); bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); tun_put_page(&tpage); ret = total_len; goto out; } ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); out: tun_put(tun); return ret; } static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); void *ptr = m->msg_control; int ret; if (!tun) { ret = -EBADFD; goto out_free; } if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; goto out_put_tun; } if (flags & MSG_ERRQUEUE) { ret = sock_recv_errqueue(sock->sk, m, total_len, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, ptr); if (ret > (ssize_t)total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; } out: tun_put(tun); return ret; out_put_tun: tun_put(tun); out_free: tun_ptr_free(ptr); return ret; } static int tun_ptr_peek_len(void *ptr) { if (likely(ptr)) { if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); return xdpf->len; } return __skb_array_len_with_tag(ptr); } else { return 0; } } static int tun_peek_len(struct socket *sock) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun; int ret = 0; tun = tun_get(tfile); if (!tun) return 0; ret = PTR_RING_PEEK_CALL(&tfile->tx_ring, tun_ptr_peek_len); tun_put(tun); return ret; } /* Ops structure to mimic raw sockets with tun */ static const struct proto_ops tun_socket_ops = { .peek_len = tun_peek_len, .sendmsg = tun_sendmsg, .recvmsg = tun_recvmsg, }; static struct proto tun_proto = { .name = "tun", .owner = THIS_MODULE, .obj_size = sizeof(struct tun_file), }; static int tun_flags(struct tun_struct *tun) { return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP); } static ssize_t tun_flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return sysfs_emit(buf, "0x%x\n", tun_flags(tun)); } static ssize_t owner_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return uid_valid(tun->owner)? sysfs_emit(buf, "%u\n", from_kuid_munged(current_user_ns(), tun->owner)) : sysfs_emit(buf, "-1\n"); } static ssize_t group_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return gid_valid(tun->group) ? sysfs_emit(buf, "%u\n", from_kgid_munged(current_user_ns(), tun->group)) : sysfs_emit(buf, "-1\n"); } static DEVICE_ATTR_RO(tun_flags); static DEVICE_ATTR_RO(owner); static DEVICE_ATTR_RO(group); static struct attribute *tun_dev_attrs[] = { &dev_attr_tun_flags.attr, &dev_attr_owner.attr, &dev_attr_group.attr, NULL }; static const struct attribute_group tun_attr_group = { .attrs = tun_dev_attrs }; static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) { struct tun_struct *tun; struct tun_file *tfile = file->private_data; struct net_device *dev; int err; if (tfile->detached) return -EINVAL; if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) { if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!(ifr->ifr_flags & IFF_NAPI) || (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP) return -EINVAL; } dev = __dev_get_by_name(net, ifr->ifr_name); if (dev) { if (ifr->ifr_flags & IFF_TUN_EXCL) return -EBUSY; if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops) tun = netdev_priv(dev); else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops) tun = netdev_priv(dev); else return -EINVAL; if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) != !!(tun->flags & IFF_MULTI_QUEUE)) return -EINVAL; if (tun_not_capable(tun)) return -EPERM; err = security_tun_dev_open(tun->security); if (err < 0) return err; err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, true); if (err < 0) return err; if (tun->flags & IFF_MULTI_QUEUE && (tun->numqueues + tun->numdisabled > 1)) { /* One or more queue has already been attached, no need * to initialize the device again. */ netdev_state_change(dev); return 0; } tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); netdev_state_change(dev); } else { char *name; unsigned long flags = 0; int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = security_tun_dev_create(); if (err < 0) return err; /* Set dev type */ if (ifr->ifr_flags & IFF_TUN) { /* TUN device */ flags |= IFF_TUN; name = "tun%d"; } else if (ifr->ifr_flags & IFF_TAP) { /* TAP device */ flags |= IFF_TAP; name = "tap%d"; } else return -EINVAL; if (*ifr->ifr_name) name = ifr->ifr_name; dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, NET_NAME_UNKNOWN, tun_setup, queues, queues); if (!dev) return -ENOMEM; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; dev->ifindex = tfile->ifindex; dev->sysfs_groups[0] = &tun_attr_group; tun = netdev_priv(dev); tun->dev = dev; tun->flags = flags; tun->txflt.count = 0; tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); tun->align = NET_SKB_PAD; tun->filter_attached = false; tun->sndbuf = tfile->socket.sk->sk_sndbuf; tun->rx_batched = 0; RCU_INIT_POINTER(tun->steering_prog, NULL); tun->ifr = ifr; tun->file = file; tun_net_initialize(dev); err = register_netdevice(tun->dev); if (err < 0) { free_netdev(dev); return err; } /* free_netdev() won't check refcnt, to avoid race * with dev_put() we need publish tun after registration. */ rcu_assign_pointer(tfile->tun, tun); } if (ifr->ifr_flags & IFF_NO_CARRIER) netif_carrier_off(tun->dev); else netif_carrier_on(tun->dev); /* Make sure persistent devices do not get stuck in * xoff state. */ if (netif_running(tun->dev)) netif_tx_wake_all_queues(tun->dev); strcpy(ifr->ifr_name, tun->dev->name); return 0; } static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr) { strcpy(ifr->ifr_name, tun->dev->name); ifr->ifr_flags = tun_flags(tun); } #define PLAIN_GSO (NETIF_F_GSO_UDP_L4 | NETIF_F_TSO | NETIF_F_TSO6) /* This is like a cut-down ethtool ops, except done via tun fd so no * privs required. */ static int set_offload(struct tun_struct *tun, unsigned long arg) { netdev_features_t features = 0; if (arg & TUN_F_CSUM) { features |= NETIF_F_HW_CSUM; arg &= ~TUN_F_CSUM; if (arg & (TUN_F_TSO4|TUN_F_TSO6)) { if (arg & TUN_F_TSO_ECN) { features |= NETIF_F_TSO_ECN; arg &= ~TUN_F_TSO_ECN; } if (arg & TUN_F_TSO4) features |= NETIF_F_TSO; if (arg & TUN_F_TSO6) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } arg &= ~TUN_F_UFO; /* TODO: for now USO4 and USO6 should work simultaneously */ if (arg & TUN_F_USO4 && arg & TUN_F_USO6) { features |= NETIF_F_GSO_UDP_L4; arg &= ~(TUN_F_USO4 | TUN_F_USO6); } /* * Tunnel offload is allowed only if some plain offload is * available, too. */ if (features & PLAIN_GSO && arg & TUN_F_UDP_TUNNEL_GSO) { features |= NETIF_F_GSO_UDP_TUNNEL; if (arg & TUN_F_UDP_TUNNEL_GSO_CSUM) features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; arg &= ~(TUN_F_UDP_TUNNEL_GSO | TUN_F_UDP_TUNNEL_GSO_CSUM); } } /* This gives the user a way to test for new features in future by * trying to set them. */ if (arg) return -EINVAL; tun->set_features = features; tun->dev->wanted_features &= ~TUN_USER_FEATURES; tun->dev->wanted_features |= features; netdev_update_features(tun->dev); return 0; } static void tun_detach_filter(struct tun_struct *tun, int n) { int i; struct tun_file *tfile; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); sk_detach_filter(tfile->socket.sk); release_sock(tfile->socket.sk); } tun->filter_attached = false; } static int tun_attach_filter(struct tun_struct *tun) { int i, ret = 0; struct tun_file *tfile; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (ret) { tun_detach_filter(tun, i); return ret; } } tun->filter_attached = true; return ret; } static void tun_set_sndbuf(struct tun_struct *tun) { struct tun_file *tfile; int i; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_sndbuf = tun->sndbuf; } } static int tun_set_queue(struct file *file, struct ifreq *ifr) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; int ret = 0; rtnl_lock(); if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { tun = tfile->detached; if (!tun) { ret = -EINVAL; goto unlock; } ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI, tun->flags & IFF_NAPI_FRAGS, true); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) ret = -EINVAL; else __tun_detach(tfile, false); } else ret = -EINVAL; if (ret >= 0) netdev_state_change(tun->dev); unlock: rtnl_unlock(); return ret; } static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, void __user *data) { struct bpf_prog *prog; int fd; if (copy_from_user(&fd, data, sizeof(fd))) return -EFAULT; if (fd == -1) { prog = NULL; } else { prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) return PTR_ERR(prog); } return __tun_set_ebpf(tun, prog_p, prog); } /* Return correct value for tun->dev->addr_len based on tun->dev->type. */ static unsigned char tun_get_addr_len(unsigned short type) { switch (type) { case ARPHRD_IP6GRE: case ARPHRD_TUNNEL6: return sizeof(struct in6_addr); case ARPHRD_IPGRE: case ARPHRD_TUNNEL: case ARPHRD_SIT: return 4; case ARPHRD_ETHER: return ETH_ALEN; case ARPHRD_IEEE802154: case ARPHRD_IEEE802154_MONITOR: return IEEE802154_EXTENDED_ADDR_LEN; case ARPHRD_PHONET_PIPE: case ARPHRD_PPP: case ARPHRD_NONE: return 0; case ARPHRD_6LOWPAN: return EUI64_ADDR_LEN; case ARPHRD_FDDI: return FDDI_K_ALEN; case ARPHRD_HIPPI: return HIPPI_ALEN; case ARPHRD_IEEE802: return FC_ALEN; case ARPHRD_ROSE: return ROSE_ADDR_LEN; case ARPHRD_NETROM: return AX25_ADDR_LEN; case ARPHRD_LOCALTLK: return LTALK_ALEN; default: return 0; } } static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { struct tun_file *tfile = file->private_data; struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; unsigned int carrier; struct ifreq ifr; kuid_t owner; kgid_t group; int ifindex; int sndbuf; int ret; bool do_notify = false; if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { memset(&ifr, 0, sizeof(ifr)); } if (cmd == TUNGETFEATURES) { /* Currently this just means: "what IFF flags are valid?". * This is needed because we never checked for invalid flags on * TUNSETIFF. */ return put_user(IFF_TUN | IFF_TAP | IFF_NO_CARRIER | TUN_FEATURES, (unsigned int __user*)argp); } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); } else if (cmd == SIOCGSKNS) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; return open_related_ns(&net->ns, get_net_ns); } rtnl_lock(); tun = tun_get(tfile); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) goto unlock; ifr.ifr_name[IFNAMSIZ-1] = '\0'; ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; goto unlock; } if (cmd == TUNSETIFINDEX) { ret = -EPERM; if (tun) goto unlock; ret = -EFAULT; if (copy_from_user(&ifindex, argp, sizeof(ifindex))) goto unlock; ret = -EINVAL; if (ifindex < 0) goto unlock; ret = 0; tfile->ifindex = ifindex; goto unlock; } ret = -EBADFD; if (!tun) goto unlock; netif_info(tun, drv, tun->dev, "tun_chr_ioctl cmd %u\n", cmd); net = dev_net(tun->dev); ret = 0; switch (cmd) { case TUNGETIFF: tun_get_iff(tun, &ifr); if (tfile->detached) ifr.ifr_flags |= IFF_DETACH_QUEUE; if (!tfile->socket.sk->sk_filter) ifr.ifr_flags |= IFF_NOFILTER; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case TUNSETNOCSUM: /* Disable/Enable checksum */ /* [unimplemented] */ netif_info(tun, drv, tun->dev, "ignored: set checksum %s\n", arg ? "disabled" : "enabled"); break; case TUNSETPERSIST: /* Disable/Enable persist mode. Keep an extra reference to the * module to prevent the module being unprobed. */ if (arg && !(tun->flags & IFF_PERSIST)) { tun->flags |= IFF_PERSIST; __module_get(THIS_MODULE); do_notify = true; } if (!arg && (tun->flags & IFF_PERSIST)) { tun->flags &= ~IFF_PERSIST; module_put(THIS_MODULE); do_notify = true; } netif_info(tun, drv, tun->dev, "persist %s\n", arg ? "enabled" : "disabled"); break; case TUNSETOWNER: /* Set owner of the device */ owner = make_kuid(current_user_ns(), arg); if (!uid_valid(owner)) { ret = -EINVAL; break; } tun->owner = owner; do_notify = true; netif_info(tun, drv, tun->dev, "owner set to %u\n", from_kuid(&init_user_ns, tun->owner)); break; case TUNSETGROUP: /* Set group of the device */ group = make_kgid(current_user_ns(), arg); if (!gid_valid(group)) { ret = -EINVAL; break; } tun->group = group; do_notify = true; netif_info(tun, drv, tun->dev, "group set to %u\n", from_kgid(&init_user_ns, tun->group)); break; case TUNSETLINK: /* Only allow setting the type when the interface is down */ if (tun->dev->flags & IFF_UP) { netif_info(tun, drv, tun->dev, "Linktype set failed because interface is up\n"); ret = -EBUSY; } else { ret = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, tun->dev); ret = notifier_to_errno(ret); if (ret) { netif_info(tun, drv, tun->dev, "Refused to change device type\n"); break; } tun->dev->type = (int) arg; tun->dev->addr_len = tun_get_addr_len(tun->dev->type); netif_info(tun, drv, tun->dev, "linktype set to %d\n", tun->dev->type); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, tun->dev); } break; case TUNSETDEBUG: tun->msg_enable = (u32)arg; break; case TUNSETOFFLOAD: ret = set_offload(tun, arg); break; case TUNSETTXFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = update_filter(&tun->txflt, (void __user *)arg); break; case SIOCGIFHWADDR: /* Get hw address */ netif_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name); if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case SIOCSIFHWADDR: /* Set hw address */ if (tun->dev->addr_len > sizeof(ifr.ifr_hwaddr)) { ret = -EINVAL; break; } ret = dev_set_mac_address_user(tun->dev, (struct sockaddr_storage *)&ifr.ifr_hwaddr, NULL); break; case TUNGETSNDBUF: sndbuf = tfile->socket.sk->sk_sndbuf; if (copy_to_user(argp, &sndbuf, sizeof(sndbuf))) ret = -EFAULT; break; case TUNSETSNDBUF: if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) { ret = -EFAULT; break; } if (sndbuf <= 0) { ret = -EINVAL; break; } tun->sndbuf = sndbuf; tun_set_sndbuf(tun); break; case TUNATTACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog))) break; ret = tun_attach_filter(tun); break; case TUNDETACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = 0; tun_detach_filter(tun, tun->numqueues); break; case TUNGETFILTER: ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) break; ret = 0; break; case TUNSETSTEERINGEBPF: ret = tun_set_ebpf(tun, &tun->steering_prog, argp); break; case TUNSETFILTEREBPF: ret = tun_set_ebpf(tun, &tun->filter_prog, argp); break; case TUNSETCARRIER: ret = -EFAULT; if (copy_from_user(&carrier, argp, sizeof(carrier))) goto unlock; ret = tun_net_change_carrier(tun->dev, (bool)carrier); break; case TUNGETDEVNETNS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto unlock; ret = open_related_ns(&net->ns, get_net_ns); break; default: ret = tun_vnet_ioctl(&tun->vnet_hdr_sz, &tun->flags, cmd, argp); break; } if (do_notify) netdev_state_change(tun->dev); unlock: rtnl_unlock(); if (tun) tun_put(tun); return ret; } static long tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq)); } #ifdef CONFIG_COMPAT static long tun_chr_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { case TUNSETIFF: case TUNGETIFF: case TUNSETTXFILTER: case TUNGETSNDBUF: case TUNSETSNDBUF: case SIOCGIFHWADDR: case SIOCSIFHWADDR: arg = (unsigned long)compat_ptr(arg); break; default: arg = (compat_ulong_t)arg; break; } /* * compat_ifreq is shorter than ifreq, so we must not access beyond * the end of that structure. All fields that are used in this * driver are compatible though, we don't need to convert the * contents. */ return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq)); } #endif /* CONFIG_COMPAT */ static int tun_chr_fasync(int fd, struct file *file, int on) { struct tun_file *tfile = file->private_data; int ret; if (on) { ret = file_f_owner_allocate(file); if (ret) goto out; } if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) goto out; if (on) { __f_setown(file, task_pid(current), PIDTYPE_TGID, 0); tfile->flags |= TUN_FASYNC; } else tfile->flags &= ~TUN_FASYNC; ret = 0; out: return ret; } static int tun_chr_open(struct inode *inode, struct file * file) { struct net *net = current->nsproxy->net_ns; struct tun_file *tfile; tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto, 0); if (!tfile) return -ENOMEM; if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) { sk_free(&tfile->sk); return -ENOMEM; } mutex_init(&tfile->napi_mutex); RCU_INIT_POINTER(tfile->tun, NULL); tfile->flags = 0; tfile->ifindex = 0; init_waitqueue_head(&tfile->socket.wq.wait); tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; file->private_data = tfile; INIT_LIST_HEAD(&tfile->next); sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); /* tun groks IOCB_NOWAIT just fine, mark it as such */ file->f_mode |= FMODE_NOWAIT; return 0; } static int tun_chr_close(struct inode *inode, struct file *file) { struct tun_file *tfile = file->private_data; tun_detach(tfile, true); return 0; } #ifdef CONFIG_PROC_FS static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; struct ifreq ifr; memset(&ifr, 0, sizeof(ifr)); rtnl_lock(); tun = tun_get(tfile); if (tun) tun_get_iff(tun, &ifr); rtnl_unlock(); if (tun) tun_put(tun); seq_printf(m, "iff:\t%s\n", ifr.ifr_name); } #endif static const struct file_operations tun_fops = { .owner = THIS_MODULE, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, .unlocked_ioctl = tun_chr_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = tun_chr_compat_ioctl, #endif .open = tun_chr_open, .release = tun_chr_close, .fasync = tun_chr_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = tun_chr_show_fdinfo, #endif }; static struct miscdevice tun_miscdev = { .minor = TUN_MINOR, .name = "tun", .nodename = "net/tun", .fops = &tun_fops, }; /* ethtool interface */ static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { ethtool_link_ksettings_zero_link_mode(cmd, supported); ethtool_link_ksettings_zero_link_mode(cmd, advertising); cmd->base.speed = SPEED_10000; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.phy_address = 0; cmd->base.autoneg = AUTONEG_DISABLE; } static int tun_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(cmd, &tun->link_ksettings, sizeof(*cmd)); return 0; } static int tun_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(&tun->link_ksettings, cmd, sizeof(*cmd)); return 0; } static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct tun_struct *tun = netdev_priv(dev); strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: strscpy(info->bus_info, "tun", sizeof(info->bus_info)); break; case IFF_TAP: strscpy(info->bus_info, "tap", sizeof(info->bus_info)); break; } } static u32 tun_get_msglevel(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); return tun->msg_enable; } static void tun_set_msglevel(struct net_device *dev, u32 value) { struct tun_struct *tun = netdev_priv(dev); tun->msg_enable = value; } static int tun_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); ec->rx_max_coalesced_frames = tun->rx_batched; return 0; } static int tun_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT) tun->rx_batched = NAPI_POLL_WEIGHT; else tun->rx_batched = ec->rx_max_coalesced_frames; return 0; } static void tun_get_channels(struct net_device *dev, struct ethtool_channels *channels) { struct tun_struct *tun = netdev_priv(dev); channels->combined_count = tun->numqueues; channels->max_combined = tun->flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; } static const struct ethtool_ops tun_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, .get_channels = tun_get_channels, .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, .get_link_ksettings = tun_get_link_ksettings, .set_link_ksettings = tun_set_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) { struct net_device *dev = tun->dev; struct tun_file *tfile; struct ptr_ring **rings; int n = tun->numqueues + tun->numdisabled; int ret, i; rings = kmalloc_array(n, sizeof(*rings), GFP_KERNEL); if (!rings) return -ENOMEM; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); rings[i] = &tfile->tx_ring; } list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; ret = ptr_ring_resize_multiple_bh(rings, n, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free); kfree(rings); return ret; } static int tun_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tun_struct *tun = netdev_priv(dev); int i; if (dev->rtnl_link_ops != &tun_link_ops) return NOTIFY_DONE; switch (event) { case NETDEV_CHANGE_TX_QUEUE_LEN: if (tun_queue_resize(tun)) return NOTIFY_BAD; break; case NETDEV_UP: for (i = 0; i < tun->numqueues; i++) { struct tun_file *tfile; tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_write_space(tfile->socket.sk); } break; default: break; } return NOTIFY_DONE; } static struct notifier_block tun_notifier_block __read_mostly = { .notifier_call = tun_device_event, }; static int __init tun_init(void) { int ret = 0; pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); ret = rtnl_link_register(&tun_link_ops); if (ret) { pr_err("Can't register link_ops\n"); goto err_linkops; } ret = misc_register(&tun_miscdev); if (ret) { pr_err("Can't register misc device %d\n", TUN_MINOR); goto err_misc; } ret = register_netdevice_notifier(&tun_notifier_block); if (ret) { pr_err("Can't register netdevice notifier\n"); goto err_notifier; } return 0; err_notifier: misc_deregister(&tun_miscdev); err_misc: rtnl_link_unregister(&tun_link_ops); err_linkops: return ret; } static void __exit tun_cleanup(void) { misc_deregister(&tun_miscdev); rtnl_link_unregister(&tun_link_ops); unregister_netdevice_notifier(&tun_notifier_block); } /* Get an underlying socket object from tun file. Returns error unless file is * attached to a device. The returned object works like a packet socket, it * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for * holding a reference to the file for as long as the socket is in use. */ struct socket *tun_get_socket(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->socket; } EXPORT_SYMBOL_GPL(tun_get_socket); struct ptr_ring *tun_get_tx_ring(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->tx_ring; } EXPORT_SYMBOL_GPL(tun_get_tx_ring); module_init(tun_init); module_exit(tun_cleanup); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(TUN_MINOR); MODULE_ALIAS("devname:net/tun"); MODULE_IMPORT_NS("NETDEV_INTERNAL"); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 | // SPDX-License-Identifier: GPL-2.0-only /* * ARMv8 single-step debug support and mdscr context switching. * * Copyright (C) 2012 ARM Limited * * Author: Will Deacon <will.deacon@arm.com> */ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/ptrace.h> #include <linux/kprobes.h> #include <linux/stat.h> #include <linux/uaccess.h> #include <linux/sched/task_stack.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/exception.h> #include <asm/kgdb.h> #include <asm/kprobes.h> #include <asm/system_misc.h> #include <asm/traps.h> #include <asm/uprobes.h> /* Determine debug architecture. */ u8 debug_monitors_arch(void) { return cpuid_feature_extract_unsigned_field(read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1), ID_AA64DFR0_EL1_DebugVer_SHIFT); } /* * MDSCR access routines. */ static void mdscr_write(u64 mdscr) { unsigned long flags; flags = local_daif_save(); write_sysreg(mdscr, mdscr_el1); local_daif_restore(flags); } NOKPROBE_SYMBOL(mdscr_write); static u64 mdscr_read(void) { return read_sysreg(mdscr_el1); } NOKPROBE_SYMBOL(mdscr_read); /* * Allow root to disable self-hosted debug from userspace. * This is useful if you want to connect an external JTAG debugger. */ static bool debug_enabled = true; static int create_debug_debugfs_entry(void) { debugfs_create_bool("debug_enabled", 0644, NULL, &debug_enabled); return 0; } fs_initcall(create_debug_debugfs_entry); static int __init early_debug_disable(char *buf) { debug_enabled = false; return 0; } early_param("nodebugmon", early_debug_disable); /* * Keep track of debug users on each core. * The ref counts are per-cpu so we use a local_t type. */ static DEFINE_PER_CPU(int, mde_ref_count); static DEFINE_PER_CPU(int, kde_ref_count); void enable_debug_monitors(enum dbg_active_el el) { u64 mdscr, enable = 0; WARN_ON(preemptible()); if (this_cpu_inc_return(mde_ref_count) == 1) enable = MDSCR_EL1_MDE; if (el == DBG_ACTIVE_EL1 && this_cpu_inc_return(kde_ref_count) == 1) enable |= MDSCR_EL1_KDE; if (enable && debug_enabled) { mdscr = mdscr_read(); mdscr |= enable; mdscr_write(mdscr); } } NOKPROBE_SYMBOL(enable_debug_monitors); void disable_debug_monitors(enum dbg_active_el el) { u64 mdscr, disable = 0; WARN_ON(preemptible()); if (this_cpu_dec_return(mde_ref_count) == 0) disable = ~MDSCR_EL1_MDE; if (el == DBG_ACTIVE_EL1 && this_cpu_dec_return(kde_ref_count) == 0) disable &= ~MDSCR_EL1_KDE; if (disable) { mdscr = mdscr_read(); mdscr &= disable; mdscr_write(mdscr); } } NOKPROBE_SYMBOL(disable_debug_monitors); /* * OS lock clearing. */ static int clear_os_lock(unsigned int cpu) { write_sysreg(0, osdlr_el1); write_sysreg(0, oslar_el1); isb(); return 0; } static int __init debug_monitors_init(void) { return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, "arm64/debug_monitors:starting", clear_os_lock, NULL); } postcore_initcall(debug_monitors_init); /* * Single step API and exception handling. */ static void set_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate |= DBG_SPSR_SS; } NOKPROBE_SYMBOL(set_user_regs_spsr_ss); static void clear_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate &= ~DBG_SPSR_SS; } NOKPROBE_SYMBOL(clear_user_regs_spsr_ss); #define set_regs_spsr_ss(r) set_user_regs_spsr_ss(&(r)->user_regs) #define clear_regs_spsr_ss(r) clear_user_regs_spsr_ss(&(r)->user_regs) static void send_user_sigtrap(int si_code) { struct pt_regs *regs = current_pt_regs(); if (WARN_ON(!user_mode(regs))) return; if (interrupts_enabled(regs)) local_irq_enable(); arm64_force_sig_fault(SIGTRAP, si_code, instruction_pointer(regs), "User debug trap"); } /* * We have already unmasked interrupts and enabled preemption * when calling do_el0_softstep() from entry-common.c. */ void do_el0_softstep(unsigned long esr, struct pt_regs *regs) { if (uprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED) return; send_user_sigtrap(TRAP_TRACE); /* * ptrace will disable single step unless explicitly * asked to re-enable it. For other clients, it makes * sense to leave it enabled (i.e. rewind the controls * to the active-not-pending state). */ user_rewind_single_step(current); } void do_el1_softstep(unsigned long esr, struct pt_regs *regs) { if (kgdb_single_step_handler(regs, esr) == DBG_HOOK_HANDLED) return; pr_warn("Unexpected kernel single-step exception at EL1\n"); /* * Re-enable stepping since we know that we will be * returning to regs. */ set_regs_spsr_ss(regs); } NOKPROBE_SYMBOL(do_el1_softstep); static int call_el1_break_hook(struct pt_regs *regs, unsigned long esr) { if (esr_brk_comment(esr) == BUG_BRK_IMM) return bug_brk_handler(regs, esr); if (IS_ENABLED(CONFIG_CFI_CLANG) && esr_is_cfi_brk(esr)) return cfi_brk_handler(regs, esr); if (esr_brk_comment(esr) == FAULT_BRK_IMM) return reserved_fault_brk_handler(regs, esr); if (IS_ENABLED(CONFIG_KASAN_SW_TAGS) && (esr_brk_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM) return kasan_brk_handler(regs, esr); if (IS_ENABLED(CONFIG_UBSAN_TRAP) && esr_is_ubsan_brk(esr)) return ubsan_brk_handler(regs, esr); if (IS_ENABLED(CONFIG_KGDB)) { if (esr_brk_comment(esr) == KGDB_DYN_DBG_BRK_IMM) return kgdb_brk_handler(regs, esr); if (esr_brk_comment(esr) == KGDB_COMPILED_DBG_BRK_IMM) return kgdb_compiled_brk_handler(regs, esr); } if (IS_ENABLED(CONFIG_KPROBES)) { if (esr_brk_comment(esr) == KPROBES_BRK_IMM) return kprobe_brk_handler(regs, esr); if (esr_brk_comment(esr) == KPROBES_BRK_SS_IMM) return kprobe_ss_brk_handler(regs, esr); } if (IS_ENABLED(CONFIG_KRETPROBES) && esr_brk_comment(esr) == KRETPROBES_BRK_IMM) return kretprobe_brk_handler(regs, esr); return DBG_HOOK_ERROR; } NOKPROBE_SYMBOL(call_el1_break_hook); /* * We have already unmasked interrupts and enabled preemption * when calling do_el0_brk64() from entry-common.c. */ void do_el0_brk64(unsigned long esr, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_UPROBES) && esr_brk_comment(esr) == UPROBES_BRK_IMM && uprobe_brk_handler(regs, esr) == DBG_HOOK_HANDLED) return; send_user_sigtrap(TRAP_BRKPT); } void do_el1_brk64(unsigned long esr, struct pt_regs *regs) { if (call_el1_break_hook(regs, esr) == DBG_HOOK_HANDLED) return; die("Oops - BRK", regs, esr); } NOKPROBE_SYMBOL(do_el1_brk64); #ifdef CONFIG_COMPAT void do_bkpt32(unsigned long esr, struct pt_regs *regs) { arm64_notify_die("aarch32 BKPT", regs, SIGTRAP, TRAP_BRKPT, regs->pc, esr); } #endif /* CONFIG_COMPAT */ bool try_handle_aarch32_break(struct pt_regs *regs) { u32 arm_instr; u16 thumb_instr; bool bp = false; void __user *pc = (void __user *)instruction_pointer(regs); if (!compat_user_mode(regs)) return false; if (compat_thumb_mode(regs)) { /* get 16-bit Thumb instruction */ __le16 instr; get_user(instr, (__le16 __user *)pc); thumb_instr = le16_to_cpu(instr); if (thumb_instr == AARCH32_BREAK_THUMB2_LO) { /* get second half of 32-bit Thumb-2 instruction */ get_user(instr, (__le16 __user *)(pc + 2)); thumb_instr = le16_to_cpu(instr); bp = thumb_instr == AARCH32_BREAK_THUMB2_HI; } else { bp = thumb_instr == AARCH32_BREAK_THUMB; } } else { /* 32-bit ARM instruction */ __le32 instr; get_user(instr, (__le32 __user *)pc); arm_instr = le32_to_cpu(instr); bp = (arm_instr & ~0xf0000000) == AARCH32_BREAK_ARM; } if (!bp) return false; send_user_sigtrap(TRAP_BRKPT); return true; } NOKPROBE_SYMBOL(try_handle_aarch32_break); /* Re-enable single step for syscall restarting. */ void user_rewind_single_step(struct task_struct *task) { /* * If single step is active for this thread, then set SPSR.SS * to 1 to avoid returning to the active-pending state. */ if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) clear_regs_spsr_ss(task_pt_regs(task)); } void user_regs_reset_single_step(struct user_pt_regs *regs, struct task_struct *task) { if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_user_regs_spsr_ss(regs); else clear_user_regs_spsr_ss(regs); } /* Kernel API */ void kernel_enable_single_step(struct pt_regs *regs) { WARN_ON(!irqs_disabled()); set_regs_spsr_ss(regs); mdscr_write(mdscr_read() | MDSCR_EL1_SS); enable_debug_monitors(DBG_ACTIVE_EL1); } NOKPROBE_SYMBOL(kernel_enable_single_step); void kernel_disable_single_step(void) { WARN_ON(!irqs_disabled()); mdscr_write(mdscr_read() & ~MDSCR_EL1_SS); disable_debug_monitors(DBG_ACTIVE_EL1); } NOKPROBE_SYMBOL(kernel_disable_single_step); int kernel_active_single_step(void) { WARN_ON(!irqs_disabled()); return mdscr_read() & MDSCR_EL1_SS; } NOKPROBE_SYMBOL(kernel_active_single_step); void kernel_rewind_single_step(struct pt_regs *regs) { set_regs_spsr_ss(regs); } void kernel_fastforward_single_step(struct pt_regs *regs) { clear_regs_spsr_ss(regs); } /* ptrace API */ void user_enable_single_step(struct task_struct *task) { struct thread_info *ti = task_thread_info(task); if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_enable_single_step); void user_disable_single_step(struct task_struct *task) { clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); } NOKPROBE_SYMBOL(user_disable_single_step); |
| 1453 1455 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_IRQFLAGS_H #define __ASM_IRQFLAGS_H #include <asm/barrier.h> #include <asm/ptrace.h> #include <asm/sysreg.h> /* * Aarch64 has flags for masking: Debug, Asynchronous (serror), Interrupts and * FIQ exceptions, in the 'daif' register. We mask and unmask them in 'daif' * order: * Masking debug exceptions causes all other exceptions to be masked too/ * Masking SError masks IRQ/FIQ, but not debug exceptions. IRQ and FIQ are * always masked and unmasked together, and have no side effects for other * flags. Keeping to this order makes it easier for entry.S to know which * exceptions should be unmasked. */ static __always_inline void __daif_local_irq_enable(void) { barrier(); asm volatile("msr daifclr, #3"); barrier(); } static __always_inline void __pmr_local_irq_enable(void) { if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) { u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); } barrier(); write_sysreg_s(GIC_PRIO_IRQON, SYS_ICC_PMR_EL1); pmr_sync(); barrier(); } static inline void arch_local_irq_enable(void) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_enable(); } else { __daif_local_irq_enable(); } } static __always_inline void __daif_local_irq_disable(void) { barrier(); asm volatile("msr daifset, #3"); barrier(); } static __always_inline void __pmr_local_irq_disable(void) { if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) { u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); } barrier(); write_sysreg_s(GIC_PRIO_IRQOFF, SYS_ICC_PMR_EL1); barrier(); } static inline void arch_local_irq_disable(void) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_disable(); } else { __daif_local_irq_disable(); } } static __always_inline unsigned long __daif_local_save_flags(void) { return read_sysreg(daif); } static __always_inline unsigned long __pmr_local_save_flags(void) { return read_sysreg_s(SYS_ICC_PMR_EL1); } /* * Save the current interrupt enable state. */ static inline unsigned long arch_local_save_flags(void) { if (system_uses_irq_prio_masking()) { return __pmr_local_save_flags(); } else { return __daif_local_save_flags(); } } static __always_inline bool __daif_irqs_disabled_flags(unsigned long flags) { return flags & PSR_I_BIT; } static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags) { return flags != GIC_PRIO_IRQON; } static inline bool arch_irqs_disabled_flags(unsigned long flags) { if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled_flags(flags); } else { return __daif_irqs_disabled_flags(flags); } } static __always_inline bool __daif_irqs_disabled(void) { return __daif_irqs_disabled_flags(__daif_local_save_flags()); } static __always_inline bool __pmr_irqs_disabled(void) { return __pmr_irqs_disabled_flags(__pmr_local_save_flags()); } static inline bool arch_irqs_disabled(void) { if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled(); } else { return __daif_irqs_disabled(); } } static __always_inline unsigned long __daif_local_irq_save(void) { unsigned long flags = __daif_local_save_flags(); __daif_local_irq_disable(); return flags; } static __always_inline unsigned long __pmr_local_irq_save(void) { unsigned long flags = __pmr_local_save_flags(); /* * There are too many states with IRQs disabled, just keep the current * state if interrupts are already disabled/masked. */ if (!__pmr_irqs_disabled_flags(flags)) __pmr_local_irq_disable(); return flags; } static inline unsigned long arch_local_irq_save(void) { if (system_uses_irq_prio_masking()) { return __pmr_local_irq_save(); } else { return __daif_local_irq_save(); } } static __always_inline void __daif_local_irq_restore(unsigned long flags) { barrier(); write_sysreg(flags, daif); barrier(); } static __always_inline void __pmr_local_irq_restore(unsigned long flags) { barrier(); write_sysreg_s(flags, SYS_ICC_PMR_EL1); pmr_sync(); barrier(); } /* * restore saved IRQ state */ static inline void arch_local_irq_restore(unsigned long flags) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_restore(flags); } else { __daif_local_irq_restore(flags); } } #endif /* __ASM_IRQFLAGS_H */ |
| 1 1 10 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef TUN_VNET_H #define TUN_VNET_H /* High bits in flags field are unused. */ #define TUN_VNET_LE 0x80000000 #define TUN_VNET_BE 0x40000000 #define TUN_VNET_TNL_SIZE sizeof(struct virtio_net_hdr_v1_hash_tunnel) static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags) { bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) && (flags & TUN_VNET_BE); return !be && virtio_legacy_is_little_endian(); } static inline long tun_get_vnet_be(unsigned int flags, int __user *argp) { int be = !!(flags & TUN_VNET_BE); if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (put_user(be, argp)) return -EFAULT; return 0; } static inline long tun_set_vnet_be(unsigned int *flags, int __user *argp) { int be; if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (get_user(be, argp)) return -EFAULT; if (be) *flags |= TUN_VNET_BE; else *flags &= ~TUN_VNET_BE; return 0; } static inline bool tun_vnet_is_little_endian(unsigned int flags) { return flags & TUN_VNET_LE || tun_vnet_legacy_is_little_endian(flags); } static inline u16 tun_vnet16_to_cpu(unsigned int flags, __virtio16 val) { return __virtio16_to_cpu(tun_vnet_is_little_endian(flags), val); } static inline __virtio16 cpu_to_tun_vnet16(unsigned int flags, u16 val) { return __cpu_to_virtio16(tun_vnet_is_little_endian(flags), val); } static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags, unsigned int cmd, int __user *sp) { int s; switch (cmd) { case TUNGETVNETHDRSZ: s = *vnet_hdr_sz; if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETHDRSZ: if (get_user(s, sp)) return -EFAULT; if (s < (int)sizeof(struct virtio_net_hdr)) return -EINVAL; *vnet_hdr_sz = s; return 0; case TUNGETVNETLE: s = !!(*flags & TUN_VNET_LE); if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETLE: if (get_user(s, sp)) return -EFAULT; if (s) *flags |= TUN_VNET_LE; else *flags &= ~TUN_VNET_LE; return 0; case TUNGETVNETBE: return tun_get_vnet_be(*flags, sp); case TUNSETVNETBE: return tun_set_vnet_be(flags, sp); default: return -EINVAL; } } static inline unsigned int tun_vnet_parse_size(netdev_features_t features) { if (!(features & NETIF_F_GSO_UDP_TUNNEL)) return sizeof(struct virtio_net_hdr); return TUN_VNET_TNL_SIZE; } static inline int __tun_vnet_hdr_get(int sz, unsigned int flags, netdev_features_t features, struct iov_iter *from, struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); u16 hdr_len; if (iov_iter_count(from) < sz) return -EINVAL; if (!copy_from_iter_full(hdr, parsed_size, from)) return -EFAULT; hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { hdr_len = max(tun_vnet16_to_cpu(flags, hdr->csum_start) + tun_vnet16_to_cpu(flags, hdr->csum_offset) + 2, hdr_len); hdr->hdr_len = cpu_to_tun_vnet16(flags, hdr_len); } if (hdr_len > iov_iter_count(from)) return -EINVAL; iov_iter_advance(from, sz - parsed_size); return hdr_len; } static inline int tun_vnet_hdr_get(int sz, unsigned int flags, struct iov_iter *from, struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_get(sz, flags, 0, from, hdr); } static inline int __tun_vnet_hdr_put(int sz, netdev_features_t features, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); if (unlikely(iov_iter_count(iter) < sz)) return -EINVAL; if (unlikely(copy_to_iter(hdr, parsed_size, iter) != parsed_size)) return -EFAULT; if (iov_iter_zero(sz - parsed_size, iter) != sz - parsed_size) return -EFAULT; return 0; } static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_put(sz, 0, iter, hdr); } static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb, const struct virtio_net_hdr *hdr) { return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags)); } /* * Tun is not aware of the negotiated guest features, guess them from the * virtio net hdr size */ static inline netdev_features_t tun_vnet_hdr_guest_features(int vnet_hdr_sz) { if (vnet_hdr_sz >= TUN_VNET_TNL_SIZE) return NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; return 0; } static inline int tun_vnet_hdr_tnl_to_skb(unsigned int flags, netdev_features_t features, struct sk_buff *skb, const struct virtio_net_hdr_v1_hash_tunnel *hdr) { return virtio_net_hdr_tnl_to_skb(skb, hdr, features & NETIF_F_GSO_UDP_TUNNEL, features & NETIF_F_GSO_UDP_TUNNEL_CSUM, tun_vnet_is_little_endian(flags)); } static inline int tun_vnet_hdr_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr *hdr) { int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_from_skb(skb, hdr, tun_vnet_is_little_endian(flags), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } static inline int tun_vnet_hdr_tnl_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr) { bool has_tnl_offload = !!(dev->features & NETIF_F_GSO_UDP_TUNNEL); int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload, tun_vnet_is_little_endian(flags), vlan_hlen)) { struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr; struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { int hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(hdr_len, 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } #endif /* TUN_VNET_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2023 Arm Ltd. * * Based on arch/x86/include/asm/pkeys.h */ #ifndef _ASM_ARM64_PKEYS_H #define _ASM_ARM64_PKEYS_H #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2) #define arch_max_pkey() 8 int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { return system_supports_poe(); } static inline int vma_pkey(struct vm_area_struct *vma) { return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT; } static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { if (pkey != -1) return pkey; return vma_pkey(vma); } static inline int execute_only_pkey(struct mm_struct *mm) { // Execute-only mappings are handled by EPAN/FEAT_PAN3. return -1; } #define mm_pkey_allocation_map(mm) (mm)->context.pkey_allocation_map #define mm_set_pkey_allocated(mm, pkey) do { \ mm_pkey_allocation_map(mm) |= (1U << pkey); \ } while (0) #define mm_set_pkey_free(mm, pkey) do { \ mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ } while (0) static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned * from pkey_alloc() or pkey 0 which is allocated * implicitly when the mm is created. */ if (pkey < 0 || pkey >= arch_max_pkey()) return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } /* * Returns a positive, 3-bit key on success, or -1 on failure. */ static inline int mm_pkey_alloc(struct mm_struct *mm) { /* * Note: this is the one and only place we make sure * that the pkey is valid as far as the hardware is * concerned. The rest of the kernel trusts that * only good, valid pkeys come out of here. */ u8 all_pkeys_mask = GENMASK(arch_max_pkey() - 1, 0); int ret; if (!arch_pkeys_enabled()) return -1; /* * Are we out of pkeys? We must handle this specially * because ffz() behavior is undefined if there are no * zeros. */ if (mm_pkey_allocation_map(mm) == all_pkeys_mask) return -1; ret = ffz(mm_pkey_allocation_map(mm)); mm_set_pkey_allocated(mm, ret); return ret; } static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; mm_set_pkey_free(mm, pkey); return 0; } #endif /* _ASM_ARM64_PKEYS_H */ |
| 325 325 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/blkdev.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/kthread.h> #include <linux/backing-dev.h> #include <linux/blk-cgroup.h> #include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> #include <trace/events/writeback.h> #include "internal.h" struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); static u64 bdi_id_cursor; static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> struct wb_stats { unsigned long nr_dirty; unsigned long nr_io; unsigned long nr_more_io; unsigned long nr_dirty_time; unsigned long nr_writeback; unsigned long nr_reclaimable; unsigned long nr_dirtied; unsigned long nr_written; unsigned long dirty_thresh; unsigned long wb_thresh; }; static struct dentry *bdi_debug_root; static void bdi_debug_init(void) { bdi_debug_root = debugfs_create_dir("bdi", NULL); } static void collect_wb_stats(struct wb_stats *stats, struct bdi_writeback *wb) { struct inode *inode; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) if (inode->i_state & I_DIRTY_TIME) stats->nr_dirty_time++; spin_unlock(&wb->list_lock); stats->nr_writeback += wb_stat(wb, WB_WRITEBACK); stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE); stats->nr_dirtied += wb_stat(wb, WB_DIRTIED); stats->nr_written += wb_stat(wb, WB_WRITTEN); stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh); } #ifdef CONFIG_CGROUP_WRITEBACK static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { struct bdi_writeback *wb; rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { if (!wb_tryget(wb)) continue; collect_wb_stats(stats, wb); wb_put(wb); } rcu_read_unlock(); } #else static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { collect_wb_stats(stats, &bdi->wb); } #endif static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct wb_stats stats; unsigned long tot_bw; global_dirty_limits(&background_thresh, &dirty_thresh); memset(&stats, 0, sizeof(stats)); stats.dirty_thresh = dirty_thresh; bdi_collect_stats(bdi, &stats); tot_bw = atomic_long_read(&bdi->tot_write_bandwidth); seq_printf(m, "BdiWriteback: %10lu kB\n" "BdiReclaimable: %10lu kB\n" "BdiDirtyThresh: %10lu kB\n" "DirtyThresh: %10lu kB\n" "BackgroundThresh: %10lu kB\n" "BdiDirtied: %10lu kB\n" "BdiWritten: %10lu kB\n" "BdiWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", K(stats.nr_writeback), K(stats.nr_reclaimable), K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), K(stats.nr_dirtied), K(stats.nr_written), K(tot_bw), stats.nr_dirty, stats.nr_io, stats.nr_more_io, stats.nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, struct wb_stats *stats) { seq_printf(m, "WbCgIno: %10lu\n" "WbWriteback: %10lu kB\n" "WbReclaimable: %10lu kB\n" "WbDirtyThresh: %10lu kB\n" "WbDirtied: %10lu kB\n" "WbWritten: %10lu kB\n" "WbWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "state: %10lx\n\n", #ifdef CONFIG_CGROUP_WRITEBACK cgroup_ino(wb->memcg_css->cgroup), #else 1ul, #endif K(stats->nr_writeback), K(stats->nr_reclaimable), K(stats->wb_thresh), K(stats->nr_dirtied), K(stats->nr_written), K(wb->avg_write_bandwidth), stats->nr_dirty, stats->nr_io, stats->nr_more_io, stats->nr_dirty_time, wb->state); } static int cgwb_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct bdi_writeback *wb; global_dirty_limits(&background_thresh, &dirty_thresh); rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { struct wb_stats stats = { .dirty_thresh = dirty_thresh }; if (!wb_tryget(wb)) continue; collect_wb_stats(&stats, wb); /* * Calculate thresh of wb in writeback cgroup which is min of * thresh in global domain and thresh in cgroup domain. Drop * rcu lock because cgwb_calc_thresh may sleep in * cgroup_rstat_flush. We can do so here because we have a ref. */ if (mem_cgroup_wb_domain(wb)) { rcu_read_unlock(); stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); rcu_read_lock(); } wb_stats_show(m, wb, &stats); wb_put(wb); } rcu_read_unlock(); return 0; } DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, &cgwb_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } #else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } #endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned long read_ahead_kb; ssize_t ret; ret = kstrtoul(buf, 10, &read_ahead_kb); if (ret < 0) return ret; bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10); return count; } #define BDI_SHOW(name, expr) \ static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return sysfs_emit(buf, "%lld\n", (long long)expr); \ } \ static DEVICE_ATTR_RW(name); BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) static ssize_t min_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE) static ssize_t min_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio_fine, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE) static ssize_t max_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio_fine, bdi->max_ratio) static ssize_t min_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi)); } static ssize_t min_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_min_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(min_bytes); static ssize_t max_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi)); } static ssize_t max_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_max_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(max_bytes); static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, char *buf) { dev_warn_once(dev, "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); return sysfs_emit(buf, "%d\n", 0); } static DEVICE_ATTR_RO(stable_pages_required); static ssize_t strict_limit_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int strict_limit; ssize_t ret; ret = kstrtouint(buf, 10, &strict_limit); if (ret < 0) return ret; ret = bdi_set_strict_limit(bdi, strict_limit); if (!ret) ret = count; return ret; } static ssize_t strict_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%d\n", !!(bdi->capabilities & BDI_CAP_STRICTLIMIT)); } static DEVICE_ATTR_RW(strict_limit); static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, &dev_attr_min_ratio_fine.attr, &dev_attr_max_ratio.attr, &dev_attr_max_ratio_fine.attr, &dev_attr_min_bytes.attr, &dev_attr_max_bytes.attr, &dev_attr_stable_pages_required.attr, &dev_attr_strict_limit.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); static const struct class bdi_class = { .name = "bdi", .dev_groups = bdi_dev_groups, }; static __init int bdi_class_init(void) { int ret; ret = class_register(&bdi_class); if (ret) return ret; bdi_debug_init(); return 0; } postcore_initcall(bdi_class_init); static int __init default_bdi_init(void) { bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; return 0; } subsys_initcall(default_bdi_init); static void wb_update_bandwidth_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, bw_dwork); wb_update_bandwidth(wb); } /* * Initial write bandwidth: 100 MB/s */ #define INIT_BW (100 << (20 - PAGE_SHIFT)) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp) { int err; memset(wb, 0, sizeof(*wb)); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); atomic_set(&wb->writeback_inodes, 0); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; wb->write_bandwidth = INIT_BW; wb->avg_write_bandwidth = INIT_BW; spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); err = fprop_local_init_percpu(&wb->completions, gfp); if (err) return err; err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); if (err) fprop_local_destroy_percpu(&wb->completions); return err; } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); /* * Remove bdi from the global list and shutdown any threads we have running */ static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ spin_lock_irq(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_irq(&wb->work_lock); return; } spin_unlock_irq(&wb->work_lock); cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to * be drained no matter what. */ mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); flush_delayed_work(&wb->bw_dwork); } static void wb_exit(struct bdi_writeback *wb) { WARN_ON(delayed_work_pending(&wb->dwork)); percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/memcontrol.h> /* * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; static LIST_HEAD(offline_cgwbs); static void cleanup_offline_cgwbs_workfn(struct work_struct *work); static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); static void cgwb_free_rcu(struct rcu_head *rcu_head) { struct bdi_writeback *wb = container_of(rcu_head, struct bdi_writeback, rcu); percpu_ref_exit(&wb->refcnt); kfree(wb); } static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); /* triggers blkg destruction if no online users left */ blkcg_unpin_online(wb->blkcg_css); fprop_local_destroy_percpu(&wb->memcg_completions); spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); wb_exit(wb); bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) { lockdep_assert_held(&cgwb_lock); WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { spin_lock_irq(&cgwb_lock); list_del_rcu(&wb->bdi_node); spin_unlock_irq(&cgwb_lock); } static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; int ret = 0; memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); memcg_cgwb_list = &memcg->cgwb_list; blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb && wb->blkcg_css != blkcg_css) { cgwb_kill(wb); wb = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); if (wb) goto out_put; /* need to create a new one */ wb = kmalloc(sizeof(*wb), gfp); if (!wb) { ret = -ENOMEM; goto out_put; } ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); if (ret) goto err_wb_exit; ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); if (ret) goto err_ref_exit; wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate * whether they're still online. Don't link @wb if any is dead. * See wb_memcg_offline() and wb_blkcg_offline(). */ ret = -ENODEV; spin_lock_irqsave(&cgwb_lock, flags); if (test_bit(WB_registered, &bdi->wb.state) && blkcg_cgwb_list->next && memcg_cgwb_list->next) { /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } } spin_unlock_irqrestore(&cgwb_lock, flags); if (ret) { if (ret == -EEXIST) ret = 0; goto err_fprop_exit; } goto out_put; err_fprop_exit: bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); err_wb_exit: wb_exit(wb); err_free: kfree(wb); out_put: css_put(blkcg_css); return ret; } /** * wb_get_lookup - get wb for a given memcg * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * * Try to get the wb for @memcg_css on @bdi. The returned wb has its * refcount incremented. * * This function uses css_get() on @memcg_css and thus expects its refcnt * to be positive on invocation. IOW, rcu_read_lock() protection on * @memcg_css isn't enough. try_get it before calling this function. * * A wb is keyed by its associated memcg. As blkcg implicitly enables * memcg on the default hierarchy, memcg association is guaranteed to be * more specific (equal or descendant to the associated blkcg) and thus can * identify both the memcg and blkcg associations. * * Because the blkcg associated with a memcg may change as blkcg is enabled * and disabled closer to root in the hierarchy, each wb keeps track of * both the memcg and blkcg associated with it and verifies the blkcg on * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css) { struct bdi_writeback *wb; if (!memcg_css->parent) return &bdi->wb; rcu_read_lock(); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb) { struct cgroup_subsys_state *blkcg_css; /* see whether the blkcg association has changed */ blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) wb = NULL; css_put(blkcg_css); } rcu_read_unlock(); return wb; } /** * wb_get_create - get wb for a given memcg, create if necessary * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * @gfp: allocation mask to use * * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to * create one. See wb_get_lookup() for more details. */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct bdi_writeback *wb; might_alloc(gfp); do { wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; } static int cgwb_bdi_init(struct backing_dev_info *bdi) { int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; } return ret; } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; void **slot; struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); spin_unlock_irq(&cgwb_lock); mutex_lock(&bdi->cgwb_release_mutex); spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); mutex_unlock(&bdi->cgwb_release_mutex); } /* * cleanup_offline_cgwbs_workfn - try to release dying cgwbs * * Try to release dying cgwbs by switching attached inodes to the nearest * living ancestor's writeback. Processed wbs are placed at the end * of the list to guarantee the forward progress. */ static void cleanup_offline_cgwbs_workfn(struct work_struct *work) { struct bdi_writeback *wb; LIST_HEAD(processed); spin_lock_irq(&cgwb_lock); while (!list_empty(&offline_cgwbs)) { wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, offline_node); list_move(&wb->offline_node, &processed); /* * If wb is dirty, cleaning up the writeback by switching * attached inodes will result in an effective removal of any * bandwidth restrictions, which isn't the goal. Instead, * it can be postponed until the next time, when all io * will be likely completed. If in the meantime some inodes * will get re-dirtied, they should be eventually switched to * a new cgwb. */ if (wb_has_dirty_io(wb)) continue; if (!wb_tryget(wb)) continue; spin_unlock_irq(&cgwb_lock); while (cleanup_offline_cgwb(wb)) cond_resched(); spin_lock_irq(&cgwb_lock); wb_put(wb); } if (!list_empty(&processed)) list_splice_tail(&processed, &offline_cgwbs); spin_unlock_irq(&cgwb_lock); } /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined * * Also prevents creation of any new wb's associated with @memcg. */ void wb_memcg_offline(struct mem_cgroup *memcg) { struct list_head *memcg_cgwb_list = &memcg->cgwb_list; struct bdi_writeback *wb, *next; spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work); } /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } static void cgwb_bdi_register(struct backing_dev_info *bdi) { spin_lock_irq(&cgwb_lock); list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); spin_unlock_irq(&cgwb_lock); } static int __init cgwb_init(void) { /* * There can be many concurrent release work items overwhelming * system_wq. Put them in a separate wq and limit concurrency. * There's no point in executing many of these in parallel. */ cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); if (!cgwb_release_wq) return -ENOMEM; return 0; } subsys_initcall(cgwb_init); #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) { return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { list_del_rcu(&wb->bdi_node); } #endif /* CONFIG_CGROUP_WRITEBACK */ int bdi_init(struct backing_dev_info *bdi) { bdi->dev = NULL; kref_init(&bdi->refcnt); bdi->min_ratio = 0; bdi->max_ratio = 100 * BDI_RATIO_SCALE; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } struct backing_dev_info *bdi_alloc(int node_id) { struct backing_dev_info *bdi; bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL; if (bdi_init(bdi)) { kfree(bdi); return NULL; } bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); return bdi; } EXPORT_SYMBOL(bdi_alloc); static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) { struct rb_node **p = &bdi_tree.rb_node; struct rb_node *parent = NULL; struct backing_dev_info *bdi; lockdep_assert_held(&bdi_lock); while (*p) { parent = *p; bdi = rb_entry(parent, struct backing_dev_info, rb_node); if (bdi->id > id) p = &(*p)->rb_left; else if (bdi->id < id) p = &(*p)->rb_right; else break; } if (parentp) *parentp = parent; return p; } /** * bdi_get_by_id - lookup and get bdi from its id * @id: bdi id to lookup * * Find bdi matching @id and get it. Returns NULL if the matching bdi * doesn't exist or is already unregistered. */ struct backing_dev_info *bdi_get_by_id(u64 id) { struct backing_dev_info *bdi = NULL; struct rb_node **p; spin_lock_bh(&bdi_lock); p = bdi_lookup_rb_node(id, NULL); if (*p) { bdi = rb_entry(*p, struct backing_dev_info, rb_node); bdi_get(bdi); } spin_unlock_bh(&bdi_lock); return bdi; } int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); dev = device_create(&bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); bdi->id = ++bdi_id_cursor; p = bdi_lookup_rb_node(bdi->id, &parent); rb_link_node(&bdi->rb_node, parent, p); rb_insert_color(&bdi->rb_node, &bdi_tree); list_add_tail_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); return 0; } int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = bdi_register_va(bdi, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL(bdi_register); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) { WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner); } /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); } void bdi_unregister(struct backing_dev_info *bdi) { timer_delete_sync(&bdi->laptop_mode_wb_timer); /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); /* * If this BDI's min ratio has been set, use bdi_set_min_ratio() to * update the global bdi_min_ratio. */ if (bdi->min_ratio) bdi_set_min_ratio(bdi, 0); if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; } if (bdi->owner) { put_device(bdi->owner); bdi->owner = NULL; } } EXPORT_SYMBOL(bdi_unregister); static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi); } void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } EXPORT_SYMBOL(bdi_put); struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb; if (!inode) return &noop_backing_dev_info; sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return I_BDEV(inode)->bd_disk->bdi; #endif return sb->s_bdi; } EXPORT_SYMBOL(inode_to_bdi); const char *bdi_dev_name(struct backing_dev_info *bdi) { if (!bdi || !bdi->dev) return bdi_unknown_name; return bdi->dev_name; } EXPORT_SYMBOL_GPL(bdi_dev_name); |
| 5 5 5 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 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 | // SPDX-License-Identifier: GPL-2.0 /* net/sched/sch_taprio.c Time Aware Priority Scheduler * * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> * */ #include <linux/ethtool.h> #include <linux/ethtool_netlink.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/list.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/math64.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/time.h> #include <net/gso.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/sch_generic.h> #include <net/sock.h> #include <net/tcp.h> #define TAPRIO_STAT_NOT_SET (~0ULL) #include "sch_mqprio_lib.h" static LIST_HEAD(taprio_list); static struct static_key_false taprio_have_broken_mqprio; static struct static_key_false taprio_have_working_mqprio; #define TAPRIO_ALL_GATES_OPEN -1 #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) #define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) #define TAPRIO_SUPPORTED_FLAGS \ (TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) #define TAPRIO_FLAGS_INVALID U32_MAX /* Minimum value for picos_per_byte to ensure non-zero duration * for minimum-sized Ethernet frames (ETH_ZLEN = 60). * 60 * 17 > PSEC_PER_NSEC (1000) */ #define TAPRIO_PICOS_PER_BYTE_MIN 17 struct sched_entry { /* Durations between this GCL entry and the GCL entry where the * respective traffic class gate closes */ u64 gate_duration[TC_MAX_QUEUE]; atomic_t budget[TC_MAX_QUEUE]; /* The qdisc makes some effort so that no packet leaves * after this time */ ktime_t gate_close_time[TC_MAX_QUEUE]; struct list_head list; /* Used to calculate when to advance the schedule */ ktime_t end_time; ktime_t next_txtime; int index; u32 gate_mask; u32 interval; u8 command; }; struct sched_gate_list { /* Longest non-zero contiguous gate durations per traffic class, * or 0 if a traffic class gate never opens during the schedule. */ u64 max_open_gate_duration[TC_MAX_QUEUE]; u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ u32 max_sdu[TC_MAX_QUEUE]; /* for dump */ struct rcu_head rcu; struct list_head entries; size_t num_entries; ktime_t cycle_end_time; s64 cycle_time; s64 cycle_time_extension; s64 base_time; }; struct taprio_sched { struct Qdisc **qdiscs; struct Qdisc *root; u32 flags; enum tk_offsets tk_offset; int clockid; bool offloaded; bool detected_mqprio; bool broken_mqprio; atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ * speeds it's sub-nanoseconds per byte */ /* Protects the update side of the RCU protected current_entry */ spinlock_t current_entry_lock; struct sched_entry __rcu *current_entry; struct sched_gate_list __rcu *oper_sched; struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; int cur_txq[TC_MAX_QUEUE]; u32 max_sdu[TC_MAX_QUEUE]; /* save info from the user */ u32 fp[TC_QOPT_MAX_QUEUE]; /* only for dump and offloading */ u32 txtime_delay; }; struct __tc_taprio_qopt_offload { refcount_t users; struct tc_taprio_qopt_offload offload; }; static void taprio_calculate_gate_durations(struct taprio_sched *q, struct sched_gate_list *sched) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); struct sched_entry *entry, *cur; int tc; list_for_each_entry(entry, &sched->entries, list) { u32 gates_still_open = entry->gate_mask; /* For each traffic class, calculate each open gate duration, * starting at this schedule entry and ending at the schedule * entry containing a gate close event for that TC. */ cur = entry; do { if (!gates_still_open) break; for (tc = 0; tc < num_tc; tc++) { if (!(gates_still_open & BIT(tc))) continue; if (cur->gate_mask & BIT(tc)) entry->gate_duration[tc] += cur->interval; else gates_still_open &= ~BIT(tc); } cur = list_next_entry_circular(cur, &sched->entries, list); } while (cur != entry); /* Keep track of the maximum gate duration for each traffic * class, taking care to not confuse a traffic class which is * temporarily closed with one that is always closed. */ for (tc = 0; tc < num_tc; tc++) if (entry->gate_duration[tc] && sched->max_open_gate_duration[tc] < entry->gate_duration[tc]) sched->max_open_gate_duration[tc] = entry->gate_duration[tc]; } } static bool taprio_entry_allows_tx(ktime_t skb_end_time, struct sched_entry *entry, int tc) { return ktime_before(skb_end_time, entry->gate_close_time[tc]); } static ktime_t sched_base_time(const struct sched_gate_list *sched) { if (!sched) return KTIME_MAX; return ns_to_ktime(sched->base_time); } static ktime_t taprio_mono_to_any(const struct taprio_sched *q, ktime_t mono) { /* This pairs with WRITE_ONCE() in taprio_parse_clockid() */ enum tk_offsets tk_offset = READ_ONCE(q->tk_offset); switch (tk_offset) { case TK_OFFS_MAX: return mono; default: return ktime_mono_to_any(mono, tk_offset); } } static ktime_t taprio_get_time(const struct taprio_sched *q) { return taprio_mono_to_any(q, ktime_get()); } static void taprio_free_sched_cb(struct rcu_head *head) { struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu); struct sched_entry *entry, *n; list_for_each_entry_safe(entry, n, &sched->entries, list) { list_del(&entry->list); kfree(entry); } kfree(sched); } static void switch_schedules(struct taprio_sched *q, struct sched_gate_list **admin, struct sched_gate_list **oper) { rcu_assign_pointer(q->oper_sched, *admin); rcu_assign_pointer(q->admin_sched, NULL); if (*oper) call_rcu(&(*oper)->rcu, taprio_free_sched_cb); *oper = *admin; *admin = NULL; } /* Get how much time has been already elapsed in the current cycle. */ static s32 get_cycle_time_elapsed(struct sched_gate_list *sched, ktime_t time) { ktime_t time_since_sched_start; s32 time_elapsed; time_since_sched_start = ktime_sub(time, sched->base_time); div_s64_rem(time_since_sched_start, sched->cycle_time, &time_elapsed); return time_elapsed; } static ktime_t get_interval_end_time(struct sched_gate_list *sched, struct sched_gate_list *admin, struct sched_entry *entry, ktime_t intv_start) { s32 cycle_elapsed = get_cycle_time_elapsed(sched, intv_start); ktime_t intv_end, cycle_ext_end, cycle_end; cycle_end = ktime_add_ns(intv_start, sched->cycle_time - cycle_elapsed); intv_end = ktime_add_ns(intv_start, entry->interval); cycle_ext_end = ktime_add(cycle_end, sched->cycle_time_extension); if (ktime_before(intv_end, cycle_end)) return intv_end; else if (admin && admin != sched && ktime_after(admin->base_time, cycle_end) && ktime_before(admin->base_time, cycle_ext_end)) return admin->base_time; else return cycle_end; } static int length_to_duration(struct taprio_sched *q, int len) { return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC); } static int duration_to_length(struct taprio_sched *q, u64 duration) { return div_u64(duration * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); } /* Sets sched->max_sdu[] and sched->max_frm_len[] to the minimum between the * q->max_sdu[] requested by the user and the max_sdu dynamically determined by * the maximum open gate durations at the given link speed. */ static void taprio_update_queue_max_sdu(struct taprio_sched *q, struct sched_gate_list *sched, struct qdisc_size_table *stab) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); u32 max_sdu_from_user; u32 max_sdu_dynamic; u32 max_sdu; int tc; for (tc = 0; tc < num_tc; tc++) { max_sdu_from_user = q->max_sdu[tc] ?: U32_MAX; /* TC gate never closes => keep the queueMaxSDU * selected by the user */ if (sched->max_open_gate_duration[tc] == sched->cycle_time) { max_sdu_dynamic = U32_MAX; } else { u32 max_frm_len; max_frm_len = duration_to_length(q, sched->max_open_gate_duration[tc]); /* Compensate for L1 overhead from size table, * but don't let the frame size go negative */ if (stab) { max_frm_len -= stab->szopts.overhead; max_frm_len = max_t(int, max_frm_len, dev->hard_header_len + 1); } max_sdu_dynamic = max_frm_len - dev->hard_header_len; if (max_sdu_dynamic > dev->max_mtu) max_sdu_dynamic = U32_MAX; } max_sdu = min(max_sdu_dynamic, max_sdu_from_user); if (max_sdu != U32_MAX) { sched->max_frm_len[tc] = max_sdu + dev->hard_header_len; sched->max_sdu[tc] = max_sdu; } else { sched->max_frm_len[tc] = U32_MAX; /* never oversized */ sched->max_sdu[tc] = 0; } } } /* Returns the entry corresponding to next available interval. If * validate_interval is set, it only validates whether the timestamp occurs * when the gate corresponding to the skb's traffic class is open. */ static struct sched_entry *find_entry_to_transmit(struct sk_buff *skb, struct Qdisc *sch, struct sched_gate_list *sched, struct sched_gate_list *admin, ktime_t time, ktime_t *interval_start, ktime_t *interval_end, bool validate_interval) { ktime_t curr_intv_start, curr_intv_end, cycle_end, packet_transmit_time; ktime_t earliest_txtime = KTIME_MAX, txtime, cycle, transmit_end_time; struct sched_entry *entry = NULL, *entry_found = NULL; struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); bool entry_available = false; s32 cycle_elapsed; int tc, n; tc = netdev_get_prio_tc_map(dev, skb->priority); packet_transmit_time = length_to_duration(q, qdisc_pkt_len(skb)); *interval_start = 0; *interval_end = 0; if (!sched) return NULL; cycle = sched->cycle_time; cycle_elapsed = get_cycle_time_elapsed(sched, time); curr_intv_end = ktime_sub_ns(time, cycle_elapsed); cycle_end = ktime_add_ns(curr_intv_end, cycle); list_for_each_entry(entry, &sched->entries, list) { curr_intv_start = curr_intv_end; curr_intv_end = get_interval_end_time(sched, admin, entry, curr_intv_start); if (ktime_after(curr_intv_start, cycle_end)) break; if (!(entry->gate_mask & BIT(tc)) || packet_transmit_time > entry->interval) continue; txtime = entry->next_txtime; if (ktime_before(txtime, time) || validate_interval) { transmit_end_time = ktime_add_ns(time, packet_transmit_time); if ((ktime_before(curr_intv_start, time) && ktime_before(transmit_end_time, curr_intv_end)) || (ktime_after(curr_intv_start, time) && !validate_interval)) { entry_found = entry; *interval_start = curr_intv_start; *interval_end = curr_intv_end; break; } else if (!entry_available && !validate_interval) { /* Here, we are just trying to find out the * first available interval in the next cycle. */ entry_available = true; entry_found = entry; *interval_start = ktime_add_ns(curr_intv_start, cycle); *interval_end = ktime_add_ns(curr_intv_end, cycle); } } else if (ktime_before(txtime, earliest_txtime) && !entry_available) { earliest_txtime = txtime; entry_found = entry; n = div_s64(ktime_sub(txtime, curr_intv_start), cycle); *interval_start = ktime_add(curr_intv_start, n * cycle); *interval_end = ktime_add(curr_intv_end, n * cycle); } } return entry_found; } static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct sched_gate_list *sched, *admin; ktime_t interval_start, interval_end; struct sched_entry *entry; rcu_read_lock(); sched = rcu_dereference(q->oper_sched); admin = rcu_dereference(q->admin_sched); entry = find_entry_to_transmit(skb, sch, sched, admin, skb->tstamp, &interval_start, &interval_end, true); rcu_read_unlock(); return entry; } /* This returns the tstamp value set by TCP in terms of the set clock. */ static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb) { unsigned int offset = skb_network_offset(skb); const struct ipv6hdr *ipv6h; const struct iphdr *iph; struct ipv6hdr _ipv6h; ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h) return 0; if (ipv6h->version == 4) { iph = (struct iphdr *)ipv6h; offset += iph->ihl * 4; /* special-case 6in4 tunnelling, as that is a common way to get * v6 connectivity in the home */ if (iph->protocol == IPPROTO_IPV6) { ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP) return 0; } else if (iph->protocol != IPPROTO_TCP) { return 0; } } else if (ipv6h->version == 6 && ipv6h->nexthdr != IPPROTO_TCP) { return 0; } return taprio_mono_to_any(q, skb->skb_mstamp_ns); } /* There are a few scenarios where we will have to modify the txtime from * what is read from next_txtime in sched_entry. They are: * 1. If txtime is in the past, * a. The gate for the traffic class is currently open and packet can be * transmitted before it closes, schedule the packet right away. * b. If the gate corresponding to the traffic class is going to open later * in the cycle, set the txtime of packet to the interval start. * 2. If txtime is in the future, there are packets corresponding to the * current traffic class waiting to be transmitted. So, the following * possibilities exist: * a. We can transmit the packet before the window containing the txtime * closes. * b. The window might close before the transmission can be completed * successfully. So, schedule the packet in the next open window. */ static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch) { ktime_t transmit_end_time, interval_end, interval_start, tcp_tstamp; struct taprio_sched *q = qdisc_priv(sch); struct sched_gate_list *sched, *admin; ktime_t minimum_time, now, txtime; int len, packet_transmit_time; struct sched_entry *entry; bool sched_changed; now = taprio_get_time(q); minimum_time = ktime_add_ns(now, q->txtime_delay); tcp_tstamp = get_tcp_tstamp(q, skb); minimum_time = max_t(ktime_t, minimum_time, tcp_tstamp); rcu_read_lock(); admin = rcu_dereference(q->admin_sched); sched = rcu_dereference(q->oper_sched); if (admin && ktime_after(minimum_time, admin->base_time)) switch_schedules(q, &admin, &sched); /* Until the schedule starts, all the queues are open */ if (!sched || ktime_before(minimum_time, sched->base_time)) { txtime = minimum_time; goto done; } len = qdisc_pkt_len(skb); packet_transmit_time = length_to_duration(q, len); do { sched_changed = false; entry = find_entry_to_transmit(skb, sch, sched, admin, minimum_time, &interval_start, &interval_end, false); if (!entry) { txtime = 0; goto done; } txtime = entry->next_txtime; txtime = max_t(ktime_t, txtime, minimum_time); txtime = max_t(ktime_t, txtime, interval_start); if (admin && admin != sched && ktime_after(txtime, admin->base_time)) { sched = admin; sched_changed = true; continue; } transmit_end_time = ktime_add(txtime, packet_transmit_time); minimum_time = transmit_end_time; /* Update the txtime of current entry to the next time it's * interval starts. */ if (ktime_after(transmit_end_time, interval_end)) entry->next_txtime = ktime_add(interval_start, sched->cycle_time); } while (sched_changed || ktime_after(transmit_end_time, interval_end)); entry->next_txtime = transmit_end_time; done: rcu_read_unlock(); return txtime; } /* Devices with full offload are expected to honor this in hardware */ static bool taprio_skb_exceeds_queue_max_sdu(struct Qdisc *sch, struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct sched_gate_list *sched; int prio = skb->priority; bool exceeds = false; u8 tc; tc = netdev_get_prio_tc_map(dev, prio); rcu_read_lock(); sched = rcu_dereference(q->oper_sched); if (sched && skb->len > sched->max_frm_len[tc]) exceeds = true; rcu_read_unlock(); return exceeds; } static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child, struct sk_buff **to_free) { struct taprio_sched *q = qdisc_priv(sch); /* sk_flags are only safe to use on full sockets. */ if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) return qdisc_drop(skb, sch, to_free); } else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { skb->tstamp = get_packet_txtime(skb, sch); if (!skb->tstamp) return qdisc_drop(skb, sch, to_free); } qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return qdisc_enqueue(skb, child, to_free); } static int taprio_enqueue_segmented(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child, struct sk_buff **to_free) { unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); netdev_features_t features = netif_skb_features(skb); struct sk_buff *segs, *nskb; int ret; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; slen += segs->len; /* FIXME: we should be segmenting to a smaller size * rather than dropping these */ if (taprio_skb_exceeds_queue_max_sdu(sch, segs)) ret = qdisc_drop(segs, sch, to_free); else ret = taprio_enqueue_one(segs, sch, child, to_free); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) qdisc_qstats_drop(sch); } else { numsegs++; } } if (numsegs > 1) qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); consume_skb(skb); return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } /* Will not be called in the full offload case, since the TX queues are * attached to the Qdisc created using qdisc_create_dflt() */ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct taprio_sched *q = qdisc_priv(sch); struct Qdisc *child; int queue; queue = skb_get_queue_mapping(skb); child = q->qdiscs[queue]; if (unlikely(!child)) return qdisc_drop(skb, sch, to_free); if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { /* Large packets might not be transmitted when the transmission * duration exceeds any configured interval. Therefore, segment * the skb into smaller chunks. Drivers with full offload are * expected to handle this in hardware. */ if (skb_is_gso(skb)) return taprio_enqueue_segmented(skb, sch, child, to_free); return qdisc_drop(skb, sch, to_free); } return taprio_enqueue_one(skb, sch, child, to_free); } static struct sk_buff *taprio_peek(struct Qdisc *sch) { WARN_ONCE(1, "taprio only supports operating as root qdisc, peek() not implemented"); return NULL; } static void taprio_set_budgets(struct taprio_sched *q, struct sched_gate_list *sched, struct sched_entry *entry) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); int tc, budget; for (tc = 0; tc < num_tc; tc++) { /* Traffic classes which never close have infinite budget */ if (entry->gate_duration[tc] == sched->cycle_time) budget = INT_MAX; else budget = div64_u64((u64)entry->gate_duration[tc] * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); atomic_set(&entry->budget[tc], budget); } } /* When an skb is sent, it consumes from the budget of all traffic classes */ static int taprio_update_budgets(struct sched_entry *entry, size_t len, int tc_consumed, int num_tc) { int tc, budget, new_budget = 0; for (tc = 0; tc < num_tc; tc++) { budget = atomic_read(&entry->budget[tc]); /* Don't consume from infinite budget */ if (budget == INT_MAX) { if (tc == tc_consumed) new_budget = budget; continue; } if (tc == tc_consumed) new_budget = atomic_sub_return(len, &entry->budget[tc]); else atomic_sub(len, &entry->budget[tc]); } return new_budget; } static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, struct sched_entry *entry, u32 gate_mask) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct Qdisc *child = q->qdiscs[txq]; int num_tc = netdev_get_num_tc(dev); struct sk_buff *skb; ktime_t guard; int prio; int len; u8 tc; if (unlikely(!child)) return NULL; if (TXTIME_ASSIST_IS_ENABLED(q->flags)) goto skip_peek_checks; skb = child->ops->peek(child); if (!skb) return NULL; prio = skb->priority; tc = netdev_get_prio_tc_map(dev, prio); if (!(gate_mask & BIT(tc))) return NULL; len = qdisc_pkt_len(skb); guard = ktime_add_ns(taprio_get_time(q), length_to_duration(q, len)); /* In the case that there's no gate entry, there's no * guard band ... */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && !taprio_entry_allows_tx(guard, entry, tc)) return NULL; /* ... and no budget. */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && taprio_update_budgets(entry, len, tc, num_tc) < 0) return NULL; skip_peek_checks: skb = child->ops->dequeue(child); if (unlikely(!skb)) return NULL; qdisc_bstats_update(sch, skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; return skb; } static void taprio_next_tc_txq(struct net_device *dev, int tc, int *txq) { int offset = dev->tc_to_txq[tc].offset; int count = dev->tc_to_txq[tc].count; (*txq)++; if (*txq == offset + count) *txq = offset; } /* Prioritize higher traffic classes, and select among TXQs belonging to the * same TC using round robin */ static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch, struct sched_entry *entry, u32 gate_mask) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int num_tc = netdev_get_num_tc(dev); struct sk_buff *skb; int tc; for (tc = num_tc - 1; tc >= 0; tc--) { int first_txq = q->cur_txq[tc]; if (!(gate_mask & BIT(tc))) continue; do { skb = taprio_dequeue_from_txq(sch, q->cur_txq[tc], entry, gate_mask); taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]); if (q->cur_txq[tc] >= dev->num_tx_queues) q->cur_txq[tc] = first_txq; if (skb) return skb; } while (q->cur_txq[tc] != first_txq); } return NULL; } /* Broken way of prioritizing smaller TXQ indices and ignoring the traffic * class other than to determine whether the gate is open or not */ static struct sk_buff *taprio_dequeue_txq_priority(struct Qdisc *sch, struct sched_entry *entry, u32 gate_mask) { struct net_device *dev = qdisc_dev(sch); struct sk_buff *skb; int i; for (i = 0; i < dev->num_tx_queues; i++) { skb = taprio_dequeue_from_txq(sch, i, entry, gate_mask); if (skb) return skb; } return NULL; } /* Will not be called in the full offload case, since the TX queues are * attached to the Qdisc created using qdisc_create_dflt() */ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct sk_buff *skb = NULL; struct sched_entry *entry; u32 gate_mask; rcu_read_lock(); entry = rcu_dereference(q->current_entry); /* if there's no entry, it means that the schedule didn't * start yet, so force all gates to be open, this is in * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; if (!gate_mask) goto done; if (static_branch_unlikely(&taprio_have_broken_mqprio) && !static_branch_likely(&taprio_have_working_mqprio)) { /* Single NIC kind which is broken */ skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); } else if (static_branch_likely(&taprio_have_working_mqprio) && !static_branch_unlikely(&taprio_have_broken_mqprio)) { /* Single NIC kind which prioritizes properly */ skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); } else { /* Mixed NIC kinds present in system, need dynamic testing */ if (q->broken_mqprio) skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); else skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); } done: rcu_read_unlock(); return skb; } static bool should_restart_cycle(const struct sched_gate_list *oper, const struct sched_entry *entry) { if (list_is_last(&entry->list, &oper->entries)) return true; if (ktime_compare(entry->end_time, oper->cycle_end_time) == 0) return true; return false; } static bool should_change_schedules(const struct sched_gate_list *admin, const struct sched_gate_list *oper, ktime_t end_time) { ktime_t next_base_time, extension_time; if (!admin) return false; next_base_time = sched_base_time(admin); /* This is the simple case, the end_time would fall after * the next schedule base_time. */ if (ktime_compare(next_base_time, end_time) <= 0) return true; /* This is the cycle_time_extension case, if the end_time * plus the amount that can be extended would fall after the * next schedule base_time, we can extend the current schedule * for that amount. */ extension_time = ktime_add_ns(end_time, oper->cycle_time_extension); /* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about * how precisely the extension should be made. So after * conformance testing, this logic may change. */ if (ktime_compare(next_base_time, extension_time) <= 0) return true; return false; } static enum hrtimer_restart advance_sched(struct hrtimer *timer) { struct taprio_sched *q = container_of(timer, struct taprio_sched, advance_timer); struct net_device *dev = qdisc_dev(q->root); struct sched_gate_list *oper, *admin; int num_tc = netdev_get_num_tc(dev); struct sched_entry *entry, *next; struct Qdisc *sch = q->root; ktime_t end_time; int tc; spin_lock(&q->current_entry_lock); entry = rcu_dereference_protected(q->current_entry, lockdep_is_held(&q->current_entry_lock)); oper = rcu_dereference_protected(q->oper_sched, lockdep_is_held(&q->current_entry_lock)); admin = rcu_dereference_protected(q->admin_sched, lockdep_is_held(&q->current_entry_lock)); if (!oper) switch_schedules(q, &admin, &oper); /* This can happen in two cases: 1. this is the very first run * of this function (i.e. we weren't running any schedule * previously); 2. The previous schedule just ended. The first * entry of all schedules are pre-calculated during the * schedule initialization. */ if (unlikely(!entry || entry->end_time == oper->base_time)) { next = list_first_entry(&oper->entries, struct sched_entry, list); end_time = next->end_time; goto first_run; } if (should_restart_cycle(oper, entry)) { next = list_first_entry(&oper->entries, struct sched_entry, list); oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time, oper->cycle_time); } else { next = list_next_entry(entry, list); } end_time = ktime_add_ns(entry->end_time, next->interval); end_time = min_t(ktime_t, end_time, oper->cycle_end_time); for (tc = 0; tc < num_tc; tc++) { if (next->gate_duration[tc] == oper->cycle_time) next->gate_close_time[tc] = KTIME_MAX; else next->gate_close_time[tc] = ktime_add_ns(entry->end_time, next->gate_duration[tc]); } if (should_change_schedules(admin, oper, end_time)) { /* Set things so the next time this runs, the new * schedule runs. */ end_time = sched_base_time(admin); switch_schedules(q, &admin, &oper); } next->end_time = end_time; taprio_set_budgets(q, oper, next); first_run: rcu_assign_pointer(q->current_entry, next); spin_unlock(&q->current_entry_lock); hrtimer_set_expires(&q->advance_timer, end_time); rcu_read_lock(); __netif_schedule(sch); rcu_read_unlock(); return HRTIMER_RESTART; } static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { [TCA_TAPRIO_SCHED_ENTRY_INDEX] = { .type = NLA_U32 }, [TCA_TAPRIO_SCHED_ENTRY_CMD] = { .type = NLA_U8 }, [TCA_TAPRIO_SCHED_ENTRY_GATE_MASK] = { .type = NLA_U32 }, [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, }; static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { [TCA_TAPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, TC_QOPT_MAX_QUEUE - 1), [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, [TCA_TAPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32, TC_FP_EXPRESS, TC_FP_PREEMPTIBLE), }; static const struct netlink_range_validation_signed taprio_cycle_time_range = { .min = 0, .max = INT_MAX, }; static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) }, [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = NLA_POLICY_MASK(NLA_U32, TAPRIO_SUPPORTED_FLAGS), [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TC_ENTRY] = { .type = NLA_NESTED }, }; static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb, struct sched_entry *entry, struct netlink_ext_ack *extack) { int min_duration = length_to_duration(q, ETH_ZLEN); u32 interval = 0; if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) entry->command = nla_get_u8( tb[TCA_TAPRIO_SCHED_ENTRY_CMD]); if (tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]) entry->gate_mask = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]); if (tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]) interval = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); /* The interval should allow at least the minimum ethernet * frame to go out. */ if (interval < min_duration) { NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); return -EINVAL; } entry->interval = interval; return 0; } static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n, struct sched_entry *entry, int index, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; int err; err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n, entry_policy, NULL); if (err < 0) { NL_SET_ERR_MSG(extack, "Could not parse nested entry"); return -EINVAL; } entry->index = index; return fill_sched_entry(q, tb, entry, extack); } static int parse_sched_list(struct taprio_sched *q, struct nlattr *list, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { struct nlattr *n; int err, rem; int i = 0; if (!list) return -EINVAL; nla_for_each_nested(n, list, rem) { struct sched_entry *entry; if (nla_type(n) != TCA_TAPRIO_SCHED_ENTRY) { NL_SET_ERR_MSG(extack, "Attribute is not of type 'entry'"); continue; } entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { NL_SET_ERR_MSG(extack, "Not enough memory for entry"); return -ENOMEM; } err = parse_sched_entry(q, n, entry, i, extack); if (err < 0) { kfree(entry); return err; } list_add_tail(&entry->list, &sched->entries); i++; } sched->num_entries = i; return i; } static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, struct sched_gate_list *new, struct netlink_ext_ack *extack) { int err = 0; if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) { NL_SET_ERR_MSG(extack, "Adding a single entry is not supported"); return -ENOTSUPP; } if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]) new->base_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION]) new->cycle_time_extension = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION]); if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]) new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack); if (err < 0) return err; if (!new->cycle_time) { struct sched_entry *entry; ktime_t cycle = 0; list_for_each_entry(entry, &new->entries, list) cycle = ktime_add_ns(cycle, entry->interval); if (cycle < 0 || cycle > INT_MAX) { NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); return -EINVAL; } new->cycle_time = cycle; } if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) { NL_SET_ERR_MSG(extack, "'cycle_time' is too small"); return -EINVAL; } taprio_calculate_gate_durations(q, new); return 0; } static int taprio_parse_mqprio_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt, struct netlink_ext_ack *extack, u32 taprio_flags) { bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); if (!qopt) { if (!dev->num_tc) { NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); return -EINVAL; } return 0; } /* taprio imposes that traffic classes map 1:n to tx queues */ if (qopt->num_tc > dev->num_tx_queues) { NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); return -EINVAL; } /* For some reason, in txtime-assist mode, we allow TXQ ranges for * different TCs to overlap, and just validate the TXQ ranges. */ return mqprio_validate_qopt(dev, qopt, true, allow_overlapping_txqs, extack); } static int taprio_get_start_time(struct Qdisc *sch, struct sched_gate_list *sched, ktime_t *start) { struct taprio_sched *q = qdisc_priv(sch); ktime_t now, base, cycle; s64 n; base = sched_base_time(sched); now = taprio_get_time(q); if (ktime_after(base, now)) { *start = base; return 0; } cycle = sched->cycle_time; /* The qdisc is expected to have at least one sched_entry. Moreover, * any entry must have 'interval' > 0. Thus if the cycle time is zero, * something went really wrong. In that case, we should warn about this * inconsistent state and return error. */ if (WARN_ON(!cycle)) return -EFAULT; /* Schedule the start time for the beginning of the next * cycle. */ n = div64_s64(ktime_sub_ns(now, base), cycle); *start = ktime_add_ns(base, (n + 1) * cycle); return 0; } static void setup_first_end_time(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); struct sched_entry *first; ktime_t cycle; int tc; first = list_first_entry(&sched->entries, struct sched_entry, list); cycle = sched->cycle_time; /* FIXME: find a better place to do this */ sched->cycle_end_time = ktime_add_ns(base, cycle); first->end_time = ktime_add_ns(base, first->interval); taprio_set_budgets(q, sched, first); for (tc = 0; tc < num_tc; tc++) { if (first->gate_duration[tc] == sched->cycle_time) first->gate_close_time[tc] = KTIME_MAX; else first->gate_close_time[tc] = ktime_add_ns(base, first->gate_duration[tc]); } rcu_assign_pointer(q->current_entry, NULL); } static void taprio_start_sched(struct Qdisc *sch, ktime_t start, struct sched_gate_list *new) { struct taprio_sched *q = qdisc_priv(sch); ktime_t expires; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) return; expires = hrtimer_get_expires(&q->advance_timer); if (expires == 0) expires = KTIME_MAX; /* If the new schedule starts before the next expiration, we * reprogram it to the earliest one, so we change the admin * schedule to the operational one at the right time. */ start = min_t(ktime_t, start, expires); hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS); } static void taprio_set_picos_per_byte(struct net_device *dev, struct taprio_sched *q, struct netlink_ext_ack *extack) { struct ethtool_link_ksettings ecmd; int speed = SPEED_10; int picos_per_byte; int err; err = __ethtool_get_link_ksettings(dev, &ecmd); if (err < 0) goto skip; if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: picos_per_byte = (USEC_PER_SEC * 8) / speed; if (picos_per_byte < TAPRIO_PICOS_PER_BYTE_MIN) { if (!extack) pr_warn("Link speed %d is too high. Schedule may be inaccurate.\n", speed); NL_SET_ERR_MSG_FMT_MOD(extack, "Link speed %d is too high. Schedule may be inaccurate.", speed); picos_per_byte = TAPRIO_PICOS_PER_BYTE_MIN; } atomic64_set(&q->picos_per_byte, picos_per_byte); netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", dev->name, (long long)atomic64_read(&q->picos_per_byte), ecmd.base.speed); } static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct sched_gate_list *oper, *admin; struct qdisc_size_table *stab; struct taprio_sched *q; ASSERT_RTNL(); if (event != NETDEV_UP && event != NETDEV_CHANGE) return NOTIFY_DONE; list_for_each_entry(q, &taprio_list, taprio_list) { if (dev != qdisc_dev(q->root)) continue; taprio_set_picos_per_byte(dev, q, NULL); stab = rtnl_dereference(q->root->stab); rcu_read_lock(); oper = rcu_dereference(q->oper_sched); if (oper) taprio_update_queue_max_sdu(q, oper, stab); admin = rcu_dereference(q->admin_sched); if (admin) taprio_update_queue_max_sdu(q, admin, stab); rcu_read_unlock(); break; } return NOTIFY_DONE; } static void setup_txtime(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct sched_entry *entry; u64 interval = 0; list_for_each_entry(entry, &sched->entries, list) { entry->next_txtime = ktime_add_ns(base, interval); interval += entry->interval; } } static struct tc_taprio_qopt_offload *taprio_offload_alloc(int num_entries) { struct __tc_taprio_qopt_offload *__offload; __offload = kzalloc(struct_size(__offload, offload.entries, num_entries), GFP_KERNEL); if (!__offload) return NULL; refcount_set(&__offload->users, 1); return &__offload->offload; } struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload *offload) { struct __tc_taprio_qopt_offload *__offload; __offload = container_of(offload, struct __tc_taprio_qopt_offload, offload); refcount_inc(&__offload->users); return offload; } EXPORT_SYMBOL_GPL(taprio_offload_get); void taprio_offload_free(struct tc_taprio_qopt_offload *offload) { struct __tc_taprio_qopt_offload *__offload; __offload = container_of(offload, struct __tc_taprio_qopt_offload, offload); if (!refcount_dec_and_test(&__offload->users)) return; kfree(__offload); } EXPORT_SYMBOL_GPL(taprio_offload_free); /* The function will only serve to keep the pointers to the "oper" and "admin" * schedules valid in relation to their base times, so when calling dump() the * users looks at the right schedules. * When using full offload, the admin configuration is promoted to oper at the * base_time in the PHC time domain. But because the system time is not * necessarily in sync with that, we can't just trigger a hrtimer to call * switch_schedules at the right hardware time. * At the moment we call this by hand right away from taprio, but in the future * it will be useful to create a mechanism for drivers to notify taprio of the * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). * This is left as TODO. */ static void taprio_offload_config_changed(struct taprio_sched *q) { struct sched_gate_list *oper, *admin; oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); switch_schedules(q, &admin, &oper); } static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) { u32 i, queue_mask = 0; for (i = 0; i < dev->num_tc; i++) { u32 offset, count; if (!(tc_mask & BIT(i))) continue; offset = dev->tc_to_txq[i].offset; count = dev->tc_to_txq[i].count; queue_mask |= GENMASK(offset + count - 1, offset); } return queue_mask; } static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, struct tc_taprio_qopt_offload *offload, const struct tc_taprio_caps *caps) { struct sched_entry *entry; int i = 0; offload->base_time = sched->base_time; offload->cycle_time = sched->cycle_time; offload->cycle_time_extension = sched->cycle_time_extension; list_for_each_entry(entry, &sched->entries, list) { struct tc_taprio_sched_entry *e = &offload->entries[i]; e->command = entry->command; e->interval = entry->interval; if (caps->gate_mask_per_txq) e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); else e->gate_mask = entry->gate_mask; i++; } offload->num_entries = i; } static void taprio_detect_broken_mqprio(struct taprio_sched *q) { struct net_device *dev = qdisc_dev(q->root); struct tc_taprio_caps caps; qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, &caps, sizeof(caps)); q->broken_mqprio = caps.broken_mqprio; if (q->broken_mqprio) static_branch_inc(&taprio_have_broken_mqprio); else static_branch_inc(&taprio_have_working_mqprio); q->detected_mqprio = true; } static void taprio_cleanup_broken_mqprio(struct taprio_sched *q) { if (!q->detected_mqprio) return; if (q->broken_mqprio) static_branch_dec(&taprio_have_broken_mqprio); else static_branch_dec(&taprio_have_working_mqprio); } static int taprio_enable_offload(struct net_device *dev, struct taprio_sched *q, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_taprio_qopt_offload *offload; struct tc_taprio_caps caps; int tc, err = 0; if (!ops->ndo_setup_tc) { NL_SET_ERR_MSG(extack, "Device does not support taprio offload"); return -EOPNOTSUPP; } qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, &caps, sizeof(caps)); if (!caps.supports_queue_max_sdu) { for (tc = 0; tc < TC_MAX_QUEUE; tc++) { if (q->max_sdu[tc]) { NL_SET_ERR_MSG_MOD(extack, "Device does not handle queueMaxSDU"); return -EOPNOTSUPP; } } } offload = taprio_offload_alloc(sched->num_entries); if (!offload) { NL_SET_ERR_MSG(extack, "Not enough memory for enabling offload mode"); return -ENOMEM; } offload->cmd = TAPRIO_CMD_REPLACE; offload->extack = extack; mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt); offload->mqprio.extack = extack; taprio_sched_to_offload(dev, sched, offload, &caps); mqprio_fp_to_offload(q->fp, &offload->mqprio); for (tc = 0; tc < TC_MAX_QUEUE; tc++) offload->max_sdu[tc] = q->max_sdu[tc]; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to setup taprio offload"); goto done; } q->offloaded = true; done: /* The offload structure may linger around via a reference taken by the * device driver, so clear up the netlink extack pointer so that the * driver isn't tempted to dereference data which stopped being valid */ offload->extack = NULL; offload->mqprio.extack = NULL; taprio_offload_free(offload); return err; } static int taprio_disable_offload(struct net_device *dev, struct taprio_sched *q, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_taprio_qopt_offload *offload; int err; if (!q->offloaded) return 0; offload = taprio_offload_alloc(0); if (!offload) { NL_SET_ERR_MSG(extack, "Not enough memory to disable offload mode"); return -ENOMEM; } offload->cmd = TAPRIO_CMD_DESTROY; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { NL_SET_ERR_MSG(extack, "Device failed to disable offload"); goto out; } q->offloaded = false; out: taprio_offload_free(offload); return err; } /* If full offload is enabled, the only possible clockid is the net device's * PHC. For that reason, specifying a clockid through netlink is incorrect. * For txtime-assist, it is implicitly assumed that the device's PHC is kept * in sync with the specified clockid via a user space daemon such as phc2sys. * For both software taprio and txtime-assist, the clockid is used for the * hrtimer that advances the schedule and hence mandatory. */ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int err = -EINVAL; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { const struct ethtool_ops *ops = dev->ethtool_ops; struct kernel_ethtool_ts_info info = { .cmd = ETHTOOL_GET_TS_INFO, .phc_index = -1, }; if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { NL_SET_ERR_MSG(extack, "The 'clockid' cannot be specified for full offload"); goto out; } if (ops && ops->get_ts_info) err = ops->get_ts_info(dev, &info); if (err || info.phc_index < 0) { NL_SET_ERR_MSG(extack, "Device does not have a PTP clock"); err = -ENOTSUPP; goto out; } } else if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { int clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); enum tk_offsets tk_offset; /* We only support static clockids and we don't allow * for it to be modified after the first init. */ if (clockid < 0 || (q->clockid != -1 && q->clockid != clockid)) { NL_SET_ERR_MSG(extack, "Changing the 'clockid' of a running schedule is not supported"); err = -ENOTSUPP; goto out; } switch (clockid) { case CLOCK_REALTIME: tk_offset = TK_OFFS_REAL; break; case CLOCK_MONOTONIC: tk_offset = TK_OFFS_MAX; break; case CLOCK_BOOTTIME: tk_offset = TK_OFFS_BOOT; break; case CLOCK_TAI: tk_offset = TK_OFFS_TAI; break; default: NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); err = -EINVAL; goto out; } /* This pairs with READ_ONCE() in taprio_mono_to_any */ WRITE_ONCE(q->tk_offset, tk_offset); q->clockid = clockid; } else { NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); goto out; } /* Everything went ok, return success. */ err = 0; out: return err; } static int taprio_parse_tc_entry(struct Qdisc *sch, struct nlattr *opt, u32 max_sdu[TC_QOPT_MAX_QUEUE], u32 fp[TC_QOPT_MAX_QUEUE], unsigned long *seen_tcs, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { }; struct net_device *dev = qdisc_dev(sch); int err, tc; u32 val; err = nla_parse_nested(tb, TCA_TAPRIO_TC_ENTRY_MAX, opt, taprio_tc_policy, extack); if (err < 0) return err; if (NL_REQ_ATTR_CHECK(extack, opt, tb, TCA_TAPRIO_TC_ENTRY_INDEX)) { NL_SET_ERR_MSG_MOD(extack, "TC entry index missing"); return -EINVAL; } tc = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_INDEX]); if (*seen_tcs & BIT(tc)) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_TAPRIO_TC_ENTRY_INDEX], "Duplicate tc entry"); return -EINVAL; } *seen_tcs |= BIT(tc); if (tb[TCA_TAPRIO_TC_ENTRY_MAX_SDU]) { val = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_MAX_SDU]); if (val > dev->max_mtu) { NL_SET_ERR_MSG_MOD(extack, "TC max SDU exceeds device max MTU"); return -ERANGE; } max_sdu[tc] = val; } if (tb[TCA_TAPRIO_TC_ENTRY_FP]) fp[tc] = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_FP]); return 0; } static int taprio_parse_tc_entries(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); u32 max_sdu[TC_QOPT_MAX_QUEUE]; bool have_preemption = false; unsigned long seen_tcs = 0; u32 fp[TC_QOPT_MAX_QUEUE]; struct nlattr *n; int tc, rem; int err = 0; for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { max_sdu[tc] = q->max_sdu[tc]; fp[tc] = q->fp[tc]; } nla_for_each_nested_type(n, TCA_TAPRIO_ATTR_TC_ENTRY, opt, rem) { err = taprio_parse_tc_entry(sch, n, max_sdu, fp, &seen_tcs, extack); if (err) return err; } for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { q->max_sdu[tc] = max_sdu[tc]; q->fp[tc] = fp[tc]; if (fp[tc] != TC_FP_EXPRESS) have_preemption = true; } if (have_preemption) { if (!FULL_OFFLOAD_IS_ENABLED(q->flags)) { NL_SET_ERR_MSG(extack, "Preemption only supported with full offload"); return -EOPNOTSUPP; } if (!ethtool_dev_mm_supported(dev)) { NL_SET_ERR_MSG(extack, "Device does not support preemption"); return -EOPNOTSUPP; } } return err; } static int taprio_mqprio_cmp(const struct net_device *dev, const struct tc_mqprio_qopt *mqprio) { int i; if (!mqprio || mqprio->num_tc != dev->num_tc) return -1; for (i = 0; i < mqprio->num_tc; i++) if (dev->tc_to_txq[i].count != mqprio->count[i] || dev->tc_to_txq[i].offset != mqprio->offset[i]) return -1; for (i = 0; i <= TC_BITMASK; i++) if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i]) return -1; return 0; } static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct qdisc_size_table *stab = rtnl_dereference(sch->stab); struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; struct sched_gate_list *oper, *admin, *new_admin; struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_mqprio_qopt *mqprio = NULL; unsigned long flags; u32 taprio_flags; ktime_t start; int i, err; err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_ATTR_MAX, opt, taprio_policy, extack); if (err < 0) return err; if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); /* The semantics of the 'flags' argument in relation to 'change()' * requests, are interpreted following two rules (which are applied in * this order): (1) an omitted 'flags' argument is interpreted as * zero; (2) the 'flags' of a "running" taprio instance cannot be * changed. */ taprio_flags = nla_get_u32_default(tb[TCA_TAPRIO_ATTR_FLAGS], 0); /* txtime-assist and full offload are mutually exclusive */ if ((taprio_flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && (taprio_flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_TAPRIO_ATTR_FLAGS], "TXTIME_ASSIST and FULL_OFFLOAD are mutually exclusive"); return -EINVAL; } if (q->flags != TAPRIO_FLAGS_INVALID && q->flags != taprio_flags) { NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); return -EOPNOTSUPP; } q->flags = taprio_flags; /* Needed for length_to_duration() during netlink attribute parsing */ taprio_set_picos_per_byte(dev, q, extack); err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; err = taprio_parse_tc_entries(sch, opt, extack); if (err) return err; new_admin = kzalloc(sizeof(*new_admin), GFP_KERNEL); if (!new_admin) { NL_SET_ERR_MSG(extack, "Not enough memory for a new schedule"); return -ENOMEM; } INIT_LIST_HEAD(&new_admin->entries); oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); /* no changes - no new mqprio settings */ if (!taprio_mqprio_cmp(dev, mqprio)) mqprio = NULL; if (mqprio && (oper || admin)) { NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported"); err = -ENOTSUPP; goto free_sched; } if (mqprio) { err = netdev_set_num_tc(dev, mqprio->num_tc); if (err) goto free_sched; for (i = 0; i < mqprio->num_tc; i++) { netdev_set_tc_queue(dev, i, mqprio->count[i], mqprio->offset[i]); q->cur_txq[i] = mqprio->offset[i]; } /* Always use supplied priority mappings */ for (i = 0; i <= TC_BITMASK; i++) netdev_set_prio_tc_map(dev, i, mqprio->prio_tc_map[i]); } err = parse_taprio_schedule(q, tb, new_admin, extack); if (err < 0) goto free_sched; if (new_admin->num_entries == 0) { NL_SET_ERR_MSG(extack, "There should be at least one entry in the schedule"); err = -EINVAL; goto free_sched; } err = taprio_parse_clockid(sch, tb, extack); if (err < 0) goto free_sched; taprio_update_queue_max_sdu(q, new_admin, stab); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) err = taprio_enable_offload(dev, q, new_admin, extack); else err = taprio_disable_offload(dev, q, extack); if (err) goto free_sched; /* Protects against enqueue()/dequeue() */ spin_lock_bh(qdisc_lock(sch)); if (tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]) { if (!TXTIME_ASSIST_IS_ENABLED(q->flags)) { NL_SET_ERR_MSG_MOD(extack, "txtime-delay can only be set when txtime-assist mode is enabled"); err = -EINVAL; goto unlock; } q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]); } if (!TXTIME_ASSIST_IS_ENABLED(q->flags) && !FULL_OFFLOAD_IS_ENABLED(q->flags) && !hrtimer_active(&q->advance_timer)) { hrtimer_setup(&q->advance_timer, advance_sched, q->clockid, HRTIMER_MODE_ABS); } err = taprio_get_start_time(sch, new_admin, &start); if (err < 0) { NL_SET_ERR_MSG(extack, "Internal error: failed get start time"); goto unlock; } setup_txtime(q, new_admin, start); if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { if (!oper) { rcu_assign_pointer(q->oper_sched, new_admin); err = 0; new_admin = NULL; goto unlock; } /* Not going to race against advance_sched(), but still */ admin = rcu_replace_pointer(q->admin_sched, new_admin, lockdep_rtnl_is_held()); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); } else { setup_first_end_time(q, new_admin, start); /* Protects against advance_sched() */ spin_lock_irqsave(&q->current_entry_lock, flags); taprio_start_sched(sch, start, new_admin); admin = rcu_replace_pointer(q->admin_sched, new_admin, lockdep_rtnl_is_held()); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); spin_unlock_irqrestore(&q->current_entry_lock, flags); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) taprio_offload_config_changed(q); } new_admin = NULL; err = 0; if (!stab) NL_SET_ERR_MSG_MOD(extack, "Size table not specified, frame length estimations may be inaccurate"); unlock: spin_unlock_bh(qdisc_lock(sch)); free_sched: if (new_admin) call_rcu(&new_admin->rcu, taprio_free_sched_cb); return err; } static void taprio_reset(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int i; hrtimer_cancel(&q->advance_timer); if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues; i++) if (q->qdiscs[i]) qdisc_reset(q->qdiscs[i]); } } static void taprio_destroy(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct sched_gate_list *oper, *admin; unsigned int i; list_del(&q->taprio_list); /* Note that taprio_reset() might not be called if an error * happens in qdisc_create(), after taprio_init() has been called. */ hrtimer_cancel(&q->advance_timer); qdisc_synchronize(sch); taprio_disable_offload(dev, q, NULL); if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues; i++) qdisc_put(q->qdiscs[i]); kfree(q->qdiscs); } q->qdiscs = NULL; netdev_reset_tc(dev); oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); if (oper) call_rcu(&oper->rcu, taprio_free_sched_cb); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); taprio_cleanup_broken_mqprio(q); } static int taprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int i, tc; spin_lock_init(&q->current_entry_lock); hrtimer_setup(&q->advance_timer, advance_sched, CLOCK_TAI, HRTIMER_MODE_ABS); q->root = sch; /* We only support static clockids. Use an invalid value as default * and get the valid one on taprio_change(). */ q->clockid = -1; q->flags = TAPRIO_FLAGS_INVALID; list_add(&q->taprio_list, &taprio_list); if (sch->parent != TC_H_ROOT) { NL_SET_ERR_MSG_MOD(extack, "Can only be attached as root qdisc"); return -EOPNOTSUPP; } if (!netif_is_multiqueue(dev)) { NL_SET_ERR_MSG_MOD(extack, "Multi-queue device is required"); return -EOPNOTSUPP; } q->qdiscs = kcalloc(dev->num_tx_queues, sizeof(q->qdiscs[0]), GFP_KERNEL); if (!q->qdiscs) return -ENOMEM; if (!opt) return -EINVAL; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; struct Qdisc *qdisc; dev_queue = netdev_get_tx_queue(dev, i); qdisc = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(i + 1)), extack); if (!qdisc) return -ENOMEM; if (i < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); q->qdiscs[i] = qdisc; } for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) q->fp[tc] = TC_FP_EXPRESS; taprio_detect_broken_mqprio(q); return taprio_change(sch, opt, extack); } static void taprio_attach(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); unsigned int ntx; /* Attach underlying qdisc */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); struct Qdisc *old, *dev_queue_qdisc; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { struct Qdisc *qdisc = q->qdiscs[ntx]; /* In offload mode, the root taprio qdisc is bypassed * and the netdev TX queues see the children directly */ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; dev_queue_qdisc = qdisc; } else { /* In software mode, attach the root taprio qdisc * to all netdev TX queues, so that dev_qdisc_enqueue() * goes through taprio_enqueue(). */ dev_queue_qdisc = sch; } old = dev_graft_qdisc(dev_queue, dev_queue_qdisc); /* The qdisc's refcount requires to be elevated once * for each netdev TX queue it is grafted onto */ qdisc_refcount_inc(dev_queue_qdisc); if (old) qdisc_put(old); } } static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; return netdev_get_tx_queue(dev, ntx); } static int taprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); if (!dev_queue) return -EINVAL; if (dev->flags & IFF_UP) dev_deactivate(dev); /* In offload mode, the child Qdisc is directly attached to the netdev * TX queue, and thus, we need to keep its refcount elevated in order * to counteract qdisc_graft()'s call to qdisc_put() once per TX queue. * However, save the reference to the new qdisc in the private array in * both software and offload cases, to have an up-to-date reference to * our children. */ *old = q->qdiscs[cl - 1]; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old); if (new) qdisc_refcount_inc(new); if (*old) qdisc_put(*old); } q->qdiscs[cl - 1] = new; if (new) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); return 0; } static int dump_entry(struct sk_buff *msg, const struct sched_entry *entry) { struct nlattr *item; item = nla_nest_start_noflag(msg, TCA_TAPRIO_SCHED_ENTRY); if (!item) return -ENOSPC; if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INDEX, entry->index)) goto nla_put_failure; if (nla_put_u8(msg, TCA_TAPRIO_SCHED_ENTRY_CMD, entry->command)) goto nla_put_failure; if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, entry->gate_mask)) goto nla_put_failure; if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INTERVAL, entry->interval)) goto nla_put_failure; return nla_nest_end(msg, item); nla_put_failure: nla_nest_cancel(msg, item); return -1; } static int dump_schedule(struct sk_buff *msg, const struct sched_gate_list *root) { struct nlattr *entry_list; struct sched_entry *entry; if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_BASE_TIME, root->base_time, TCA_TAPRIO_PAD)) return -1; if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, root->cycle_time, TCA_TAPRIO_PAD)) return -1; if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, root->cycle_time_extension, TCA_TAPRIO_PAD)) return -1; entry_list = nla_nest_start_noflag(msg, TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); if (!entry_list) goto error_nest; list_for_each_entry(entry, &root->entries, list) { if (dump_entry(msg, entry) < 0) goto error_nest; } nla_nest_end(msg, entry_list); return 0; error_nest: nla_nest_cancel(msg, entry_list); return -1; } static int taprio_dump_tc_entries(struct sk_buff *skb, struct taprio_sched *q, struct sched_gate_list *sched) { struct nlattr *n; int tc; for (tc = 0; tc < TC_MAX_QUEUE; tc++) { n = nla_nest_start(skb, TCA_TAPRIO_ATTR_TC_ENTRY); if (!n) return -EMSGSIZE; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_INDEX, tc)) goto nla_put_failure; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_MAX_SDU, sched->max_sdu[tc])) goto nla_put_failure; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_FP, q->fp[tc])) goto nla_put_failure; nla_nest_end(skb, n); } return 0; nla_put_failure: nla_nest_cancel(skb, n); return -EMSGSIZE; } static int taprio_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) { if (val == TAPRIO_STAT_NOT_SET) return 0; if (nla_put_u64_64bit(skb, attrtype, val, TCA_TAPRIO_OFFLOAD_STATS_PAD)) return -EMSGSIZE; return 0; } static int taprio_dump_xstats(struct Qdisc *sch, struct gnet_dump *d, struct tc_taprio_qopt_offload *offload, struct tc_taprio_qopt_stats *stats) { struct net_device *dev = qdisc_dev(sch); const struct net_device_ops *ops; struct sk_buff *skb = d->skb; struct nlattr *xstats; int err; ops = qdisc_dev(sch)->netdev_ops; /* FIXME I could use qdisc_offload_dump_helper(), but that messes * with sch->flags depending on whether the device reports taprio * stats, and I'm not sure whether that's a good idea, considering * that stats are optional to the offload itself */ if (!ops->ndo_setup_tc) return 0; memset(stats, 0xff, sizeof(*stats)); err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err == -EOPNOTSUPP) return 0; if (err) return err; xstats = nla_nest_start(skb, TCA_STATS_APP); if (!xstats) goto err; if (taprio_put_stat(skb, stats->window_drops, TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS) || taprio_put_stat(skb, stats->tx_overruns, TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS)) goto err_cancel; nla_nest_end(skb, xstats); return 0; err_cancel: nla_nest_cancel(skb, xstats); err: return -EMSGSIZE; } static int taprio_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct tc_taprio_qopt_offload offload = { .cmd = TAPRIO_CMD_STATS, }; return taprio_dump_xstats(sch, d, &offload, &offload.stats); } static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct sched_gate_list *oper, *admin; struct tc_mqprio_qopt opt = { 0 }; struct nlattr *nest, *sched_nest; mqprio_qopt_reconstruct(dev, &opt); nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto start_error; if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) goto options_error; if (!FULL_OFFLOAD_IS_ENABLED(q->flags) && nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) goto options_error; if (q->flags && nla_put_u32(skb, TCA_TAPRIO_ATTR_FLAGS, q->flags)) goto options_error; if (q->txtime_delay && nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) goto options_error; rcu_read_lock(); oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); if (oper && taprio_dump_tc_entries(skb, q, oper)) goto options_error_rcu; if (oper && dump_schedule(skb, oper)) goto options_error_rcu; if (!admin) goto done; sched_nest = nla_nest_start_noflag(skb, TCA_TAPRIO_ATTR_ADMIN_SCHED); if (!sched_nest) goto options_error_rcu; if (dump_schedule(skb, admin)) goto admin_error; nla_nest_end(skb, sched_nest); done: rcu_read_unlock(); return nla_nest_end(skb, nest); admin_error: nla_nest_cancel(skb, sched_nest); options_error_rcu: rcu_read_unlock(); options_error: nla_nest_cancel(skb, nest); start_error: return -ENOSPC; } static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); unsigned int ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; return q->qdiscs[ntx]; } static unsigned long taprio_find(struct Qdisc *sch, u32 classid) { unsigned int ntx = TC_H_MIN(classid); if (!taprio_queue_get(sch, ntx)) return 0; return ntx; } static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct Qdisc *child = taprio_leaf(sch, cl); tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); tcm->tcm_info = child->handle; return 0; } static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) __releases(d->lock) __acquires(d->lock) { struct Qdisc *child = taprio_leaf(sch, cl); struct tc_taprio_qopt_offload offload = { .cmd = TAPRIO_CMD_QUEUE_STATS, .queue_stats = { .queue = cl - 1, }, }; if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 || qdisc_qstats_copy(d, child) < 0) return -1; return taprio_dump_xstats(sch, d, &offload, &offload.queue_stats.stats); } static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct net_device *dev = qdisc_dev(sch); unsigned long ntx; if (arg->stop) return; arg->count = arg->skip; for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { if (!tc_qdisc_stats_dump(sch, ntx + 1, arg)) break; } } static struct netdev_queue *taprio_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { return taprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static const struct Qdisc_class_ops taprio_class_ops = { .graft = taprio_graft, .leaf = taprio_leaf, .find = taprio_find, .walk = taprio_walk, .dump = taprio_dump_class, .dump_stats = taprio_dump_class_stats, .select_queue = taprio_select_queue, }; static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .cl_ops = &taprio_class_ops, .id = "taprio", .priv_size = sizeof(struct taprio_sched), .init = taprio_init, .change = taprio_change, .destroy = taprio_destroy, .reset = taprio_reset, .attach = taprio_attach, .peek = taprio_peek, .dequeue = taprio_dequeue, .enqueue = taprio_enqueue, .dump = taprio_dump, .dump_stats = taprio_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("taprio"); static struct notifier_block taprio_device_notifier = { .notifier_call = taprio_dev_notifier, }; static int __init taprio_module_init(void) { int err = register_netdevice_notifier(&taprio_device_notifier); if (err) return err; return register_qdisc(&taprio_qdisc_ops); } static void __exit taprio_module_exit(void) { unregister_qdisc(&taprio_qdisc_ops); unregister_netdevice_notifier(&taprio_device_notifier); } module_init(taprio_module_init); module_exit(taprio_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Time Aware Priority qdisc"); |
| 823 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/memory.h * * Copyright (C) 2000-2002 Russell King * Copyright (C) 2012 ARM Ltd. * * Note: this file should not be included by non-asm/.h files */ #ifndef __ASM_MEMORY_H #define __ASM_MEMORY_H #include <linux/const.h> #include <linux/sizes.h> #include <asm/page-def.h> /* * Size of the PCI I/O space. This must remain a power of two so that * IO_SPACE_LIMIT acts as a mask for the low bits of I/O addresses. */ #define PCI_IO_SIZE SZ_16M /* * VMEMMAP_SIZE - allows the whole linear region to be covered by * a struct page array * * If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE * needs to cover the memory region from the beginning of the 52-bit * PAGE_OFFSET all the way to PAGE_END for 48-bit. This allows us to * keep a constant PAGE_OFFSET and "fallback" to using the higher end * of the VMEMMAP where 52-bit support is not available in hardware. */ #define VMEMMAP_RANGE (_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) #define VMEMMAP_SIZE ((VMEMMAP_RANGE >> PAGE_SHIFT) * sizeof(struct page)) /* * PAGE_OFFSET - the virtual address of the start of the linear map, at the * start of the TTBR1 address space. * PAGE_END - the end of the linear map, where all other kernel mappings begin. * KIMAGE_VADDR - the virtual address of the start of the kernel image. * VA_BITS - the maximum number of bits for virtual addresses. */ #define VA_BITS (CONFIG_ARM64_VA_BITS) #define _PAGE_OFFSET(va) (-(UL(1) << (va))) #define PAGE_OFFSET (_PAGE_OFFSET(VA_BITS)) #define KIMAGE_VADDR (MODULES_END) #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (_PAGE_END(VA_BITS_MIN)) #define MODULES_VSIZE (SZ_2G) #define VMEMMAP_START (VMEMMAP_END - VMEMMAP_SIZE) #define VMEMMAP_END (-UL(SZ_1G)) #define PCI_IO_START (VMEMMAP_END + SZ_8M) #define PCI_IO_END (PCI_IO_START + PCI_IO_SIZE) #define FIXADDR_TOP (-UL(SZ_8M)) #if VA_BITS > 48 #ifdef CONFIG_ARM64_16K_PAGES #define VA_BITS_MIN (47) #else #define VA_BITS_MIN (48) #endif #else #define VA_BITS_MIN (VA_BITS) #endif #define _PAGE_END(va) (-(UL(1) << ((va) - 1))) #define KERNEL_START _text #define KERNEL_END _end /* * Generic and Software Tag-Based KASAN modes require 1/8th and 1/16th of the * kernel virtual address space for storing the shadow memory respectively. * * The mapping between a virtual memory address and its corresponding shadow * memory address is defined based on the formula: * * shadow_addr = (addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET * * where KASAN_SHADOW_SCALE_SHIFT is the order of the number of bits that map * to a single shadow byte and KASAN_SHADOW_OFFSET is a constant that offsets * the mapping. Note that KASAN_SHADOW_OFFSET does not point to the start of * the shadow memory region. * * Based on this mapping, we define two constants: * * KASAN_SHADOW_START: the start of the shadow memory region; * KASAN_SHADOW_END: the end of the shadow memory region. * * KASAN_SHADOW_END is defined first as the shadow address that corresponds to * the upper bound of possible virtual kernel memory addresses UL(1) << 64 * according to the mapping formula. * * KASAN_SHADOW_START is defined second based on KASAN_SHADOW_END. The shadow * memory start must map to the lowest possible kernel virtual memory address * and thus it depends on the actual bitness of the address space. * * As KASAN inserts redzones between stack variables, this increases the stack * memory usage significantly. Thus, we double the (minimum) stack size. */ #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) #define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) + KASAN_SHADOW_OFFSET) #define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (UL(1) << ((va) - KASAN_SHADOW_SCALE_SHIFT))) #define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual) #define PAGE_END KASAN_SHADOW_START #define KASAN_THREAD_SHIFT 1 #else #define KASAN_THREAD_SHIFT 0 #define PAGE_END (_PAGE_END(VA_BITS_MIN)) #endif /* CONFIG_KASAN */ #define DIRECT_MAP_PHYSMEM_END __pa(PAGE_END - 1) #define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) /* * VMAP'd stacks are allocated at page granularity, so we must ensure that such * stacks are a multiple of page size. */ #if (MIN_THREAD_SHIFT < PAGE_SHIFT) #define THREAD_SHIFT PAGE_SHIFT #else #define THREAD_SHIFT MIN_THREAD_SHIFT #endif #if THREAD_SHIFT >= PAGE_SHIFT #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) #endif #define THREAD_SIZE (UL(1) << THREAD_SHIFT) /* * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry * assembly. */ #define THREAD_ALIGN (2 * THREAD_SIZE) #define IRQ_STACK_SIZE THREAD_SIZE #define OVERFLOW_STACK_SIZE SZ_4K #define NVHE_STACK_SHIFT PAGE_SHIFT #define NVHE_STACK_SIZE (UL(1) << NVHE_STACK_SHIFT) /* * With the minimum frame size of [x29, x30], exactly half the combined * sizes of the hyp and overflow stacks is the maximum size needed to * save the unwinded stacktrace; plus an additional entry to delimit the * end. */ #define NVHE_STACKTRACE_SIZE ((OVERFLOW_STACK_SIZE + NVHE_STACK_SIZE) / 2 + sizeof(long)) /* * Alignment of kernel segments (e.g. .text, .data). * * 4 KB granule: 16 level 3 entries, with contiguous bit * 16 KB granule: 4 level 3 entries, without contiguous bit * 64 KB granule: 1 level 3 entry */ #define SEGMENT_ALIGN SZ_64K /* * Memory types available. * * IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in * the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note * that protection_map[] only contains MT_NORMAL attributes. */ #define MT_NORMAL 0 #define MT_NORMAL_TAGGED 1 #define MT_NORMAL_NC 2 #define MT_DEVICE_nGnRnE 3 #define MT_DEVICE_nGnRE 4 /* * Memory types for Stage-2 translation */ #define MT_S2_NORMAL 0xf #define MT_S2_NORMAL_NC 0x5 #define MT_S2_DEVICE_nGnRE 0x1 /* * Memory types for Stage-2 translation when ID_AA64MMFR2_EL1.FWB is 0001 * Stage-2 enforces Normal-WB and Device-nGnRE */ #define MT_S2_FWB_NORMAL 6 #define MT_S2_FWB_NORMAL_NC 5 #define MT_S2_FWB_DEVICE_nGnRE 1 #ifdef CONFIG_ARM64_4K_PAGES #define IOREMAP_MAX_ORDER (PUD_SHIFT) #else #define IOREMAP_MAX_ORDER (PMD_SHIFT) #endif /* * Open-coded (swapper_pg_dir - reserved_pg_dir) as this cannot be calculated * until link time. */ #define RESERVED_SWAPPER_OFFSET (PAGE_SIZE) /* * Open-coded (swapper_pg_dir - tramp_pg_dir) as this cannot be calculated * until link time. */ #define TRAMP_SWAPPER_OFFSET (2 * PAGE_SIZE) #ifndef __ASSEMBLY__ #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/mmdebug.h> #include <linux/types.h> #include <asm/boot.h> #include <asm/bug.h> #include <asm/sections.h> #include <asm/sysreg.h> static inline u64 __pure read_tcr(void) { u64 tcr; // read_sysreg() uses asm volatile, so avoid it here asm("mrs %0, tcr_el1" : "=r"(tcr)); return tcr; } #if VA_BITS > 48 // For reasons of #include hell, we can't use TCR_T1SZ_OFFSET/TCR_T1SZ_MASK here #define vabits_actual (64 - ((read_tcr() >> 16) & 63)) #else #define vabits_actual ((u64)VA_BITS) #endif extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ #define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) /* the offset between the kernel virtual and physical mappings */ extern u64 kimage_voffset; static inline unsigned long kaslr_offset(void) { return (u64)&_text - KIMAGE_VADDR; } #ifdef CONFIG_RANDOMIZE_BASE void kaslr_init(void); static inline bool kaslr_enabled(void) { extern bool __kaslr_is_enabled; return __kaslr_is_enabled; } #else static inline void kaslr_init(void) { } static inline bool kaslr_enabled(void) { return false; } #endif /* * Allow all memory at the discovery stage. We will clip it later. */ #define MIN_MEMBLOCK_ADDR 0 #define MAX_MEMBLOCK_ADDR U64_MAX /* * PFNs are used to describe any physical page; this means * PFN 0 == physical address 0. * * This is the PFN of the first RAM page in the kernel * direct-mapped view. We assume this is the first page * of RAM in the mem_map as well. */ #define PHYS_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT) /* * When dealing with data aborts, watchpoints, or instruction traps we may end * up with a tagged userland pointer. Clear the tag to get a sane pointer to * pass on to access_ok(), for instance. */ #define __untagged_addr(addr) \ ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #define untagged_addr(addr) ({ \ u64 __addr = (__force u64)(addr); \ __addr &= __untagged_addr(__addr); \ (__force __typeof__(addr))__addr; \ }) #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) #define __tag_shifted(tag) ((u64)(tag) << 56) #define __tag_reset(addr) __untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else #define __tag_shifted(tag) 0UL #define __tag_reset(addr) (addr) #define __tag_get(addr) 0 #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline const void *__tag_set(const void *addr, u8 tag) { u64 __addr = (u64)addr & ~__tag_shifted(0xff); return (const void *)(__addr | __tag_shifted(tag)); } #ifdef CONFIG_KASAN_HW_TAGS #define arch_enable_tag_checks_sync() mte_enable_kernel_sync() #define arch_enable_tag_checks_async() mte_enable_kernel_async() #define arch_enable_tag_checks_asymm() mte_enable_kernel_asymm() #define arch_suppress_tag_checks_start() mte_enable_tco() #define arch_suppress_tag_checks_stop() mte_disable_tco() #define arch_force_async_tag_fault() mte_check_tfsr_exit() #define arch_get_random_tag() mte_get_random_tag() #define arch_get_mem_tag(addr) mte_get_mem_tag(addr) #define arch_set_mem_tag_range(addr, size, tag, init) \ mte_set_mem_tag_range((addr), (size), (tag), (init)) #endif /* CONFIG_KASAN_HW_TAGS */ /* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. */ /* * Check whether an arbitrary address is within the linear map, which * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the * kernel's TTBR1 address range. */ #define __is_lm_address(addr) (((u64)(addr) - PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) #define __lm_to_phys(addr) (((addr) - PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ phys_addr_t __x = (phys_addr_t)(__tag_reset(x)); \ __is_lm_address(__x) ? __lm_to_phys(__x) : __kimg_to_phys(__x); \ }) #define __pa_symbol_nodebug(x) __kimg_to_phys((phys_addr_t)(x)) #ifdef CONFIG_DEBUG_VIRTUAL extern phys_addr_t __virt_to_phys(unsigned long x); extern phys_addr_t __phys_addr_symbol(unsigned long x); #else #define __virt_to_phys(x) __virt_to_phys_nodebug(x) #define __phys_addr_symbol(x) __pa_symbol_nodebug(x) #endif /* CONFIG_DEBUG_VIRTUAL */ #define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) #define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* * Note: Drivers should NOT use these. They are the wrong * translation for translating DMA addresses. Use the driver * DMA support - see dma-mapping.h. */ #define virt_to_phys virt_to_phys static inline phys_addr_t virt_to_phys(const volatile void *x) { return __virt_to_phys((unsigned long)(x)); } #define phys_to_virt phys_to_virt static inline void *phys_to_virt(phys_addr_t x) { return (void *)(__phys_to_virt(x)); } /* Needed already here for resolving __phys_to_pfn() in virt_to_pfn() */ #include <asm-generic/memory_model.h> static inline unsigned long virt_to_pfn(const void *kaddr) { return __phys_to_pfn(virt_to_phys(kaddr)); } /* * Drivers should NOT use these either. */ #define __pa(x) __virt_to_phys((unsigned long)(x)) #define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0)) #define __pa_nodebug(x) __virt_to_phys_nodebug((unsigned long)(x)) #define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) #define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) /* * virt_to_page(x) convert a _valid_ virtual address to struct page * * virt_addr_valid(x) indicates whether a virtual address is valid */ #define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET) #if defined(CONFIG_DEBUG_VIRTUAL) #define page_to_virt(x) ({ \ __typeof__(x) __page = x; \ void *__addr = __va(page_to_phys(__page)); \ (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\ }) #define virt_to_page(x) pfn_to_page(virt_to_pfn(x)) #else #define page_to_virt(x) ({ \ __typeof__(x) __page = x; \ u64 __idx = ((u64)__page - VMEMMAP_START) / sizeof(struct page);\ u64 __addr = PAGE_OFFSET + (__idx * PAGE_SIZE); \ (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\ }) #define virt_to_page(x) ({ \ u64 __idx = (__tag_reset((u64)x) - PAGE_OFFSET) / PAGE_SIZE; \ u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page)); \ (struct page *)__addr; \ }) #endif /* CONFIG_DEBUG_VIRTUAL */ #define virt_addr_valid(addr) ({ \ __typeof__(addr) __addr = __tag_reset(addr); \ __is_lm_address(__addr) && pfn_is_map_memory(virt_to_pfn(__addr)); \ }) void dump_mem_limit(void); #endif /* !ASSEMBLY */ /* * Given that the GIC architecture permits ITS implementations that can only be * configured with a LPI table address once, GICv3 systems with many CPUs may * end up reserving a lot of different regions after a kexec for their LPI * tables (one per CPU), as we are forced to reuse the same memory after kexec * (and thus reserve it persistently with EFI beforehand) */ #if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS) # define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1) #endif /* * memory regions which marked with flag MEMBLOCK_NOMAP(for example, the memory * of the EFI_UNUSABLE_MEMORY type) may divide a continuous memory block into * multiple parts. As a result, the number of memory regions is large. */ #ifdef CONFIG_EFI #define INIT_MEMBLOCK_MEMORY_REGIONS (INIT_MEMBLOCK_REGIONS * 8) #endif #endif /* __ASM_MEMORY_H */ |
| 201 202 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/madvise.c * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 2002 Christoph Hellwig */ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> #include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_context.h> #include <linux/string.h> #include <linux/uio.h> #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" #include "swap.h" #define __MADV_SET_ANON_VMA_NAME (-1) /* * Maximum number of attempts we make to install guard pages before we give up * and return -ERESTARTNOINTR to have userspace try again. */ #define MAX_MADVISE_GUARD_RETRIES 3 struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; }; enum madvise_lock_mode { MADVISE_NO_LOCK, MADVISE_MMAP_READ_LOCK, MADVISE_MMAP_WRITE_LOCK, MADVISE_VMA_READ_LOCK, }; struct madvise_behavior_range { unsigned long start; unsigned long end; }; struct madvise_behavior { struct mm_struct *mm; int behavior; struct mmu_gather *tlb; enum madvise_lock_mode lock_mode; struct anon_vma_name *anon_name; /* * The range over which the behaviour is currently being applied. If * traversing multiple VMAs, this is updated for each. */ struct madvise_behavior_range range; /* The VMA and VMA preceding it (if applicable) currently targeted. */ struct vm_area_struct *prev; struct vm_area_struct *vma; bool lock_dropped; }; #ifdef CONFIG_ANON_VMA_NAME static int madvise_walk_vmas(struct madvise_behavior *madv_behavior); struct anon_vma_name *anon_vma_name_alloc(const char *name) { struct anon_vma_name *anon_name; size_t count; /* Add 1 for NUL terminator at the end of the anon_name->name */ count = strlen(name) + 1; anon_name = kmalloc(struct_size(anon_name, name, count), GFP_KERNEL); if (anon_name) { kref_init(&anon_name->kref); memcpy(anon_name->name, name, count); } return anon_name; } void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name = container_of(kref, struct anon_vma_name, kref); kfree(anon_name); } struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { if (!rwsem_is_locked(&vma->vm_mm->mmap_lock)) vma_assert_locked(vma); return vma->anon_name; } /* mmap_lock should be write-locked */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { struct anon_vma_name *orig_name = anon_vma_name(vma); if (!anon_name) { vma->anon_name = NULL; anon_vma_name_put(orig_name); return 0; } if (anon_vma_name_eq(orig_name, anon_name)) return 0; vma->anon_name = anon_vma_name_reuse(anon_name); anon_vma_name_put(orig_name); return 0; } #else /* CONFIG_ANON_VMA_NAME */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { if (anon_name) return -EINVAL; return 0; } #endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags or anon_name on region of a vma, splitting it or merging * it as necessary. Must be called with mmap_lock held for writing. */ static int madvise_update_vma(vm_flags_t new_flags, struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct anon_vma_name *anon_name = madv_behavior->anon_name; bool set_new_anon_name = madv_behavior->behavior == __MADV_SET_ANON_VMA_NAME; VMA_ITERATOR(vmi, madv_behavior->mm, range->start); if (new_flags == vma->vm_flags && (!set_new_anon_name || anon_vma_name_eq(anon_vma_name(vma), anon_name))) return 0; if (set_new_anon_name) vma = vma_modify_name(&vmi, madv_behavior->prev, vma, range->start, range->end, anon_name); else vma = vma_modify_flags(&vmi, madv_behavior->prev, vma, range->start, range->end, new_flags); if (IS_ERR(vma)) return PTR_ERR(vma); madv_behavior->vma = vma; /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vm_flags_reset(vma, new_flags); if (set_new_anon_name) return replace_anon_vma_name(vma, anon_name); return 0; } #ifdef CONFIG_SWAP static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->private; struct swap_iocb *splug = NULL; pte_t *ptep = NULL; spinlock_t *ptl; unsigned long addr; for (addr = start; addr < end; addr += PAGE_SIZE) { pte_t pte; swp_entry_t entry; struct folio *folio; if (!ptep++) { ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!ptep) break; } pte = ptep_get(ptep); if (!is_swap_pte(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) continue; pte_unmap_unlock(ptep, ptl); ptep = NULL; folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma, addr, &splug); if (folio) folio_put(folio); } if (ptep) pte_unmap_unlock(ptep, ptl); swap_read_unplug(splug); cond_resched(); return 0; } static const struct mm_walk_ops swapin_walk_ops = { .pmd_entry = swapin_walk_pmd_entry, .walk_lock = PGWALK_RDLOCK, }; static void shmem_swapin_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); pgoff_t end_index = linear_page_index(vma, end) - 1; struct folio *folio; struct swap_iocb *splug = NULL; rcu_read_lock(); xas_for_each(&xas, folio, end_index) { unsigned long addr; swp_entry_t entry; if (!xa_is_value(folio)) continue; entry = radix_to_swp_entry(folio); /* There might be swapin error entries in shmem mapping. */ if (non_swap_entry(entry)) continue; addr = vma->vm_start + ((xas.xa_index - vma->vm_pgoff) << PAGE_SHIFT); xas_pause(&xas); rcu_read_unlock(); folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping), vma, addr, &splug); if (folio) folio_put(folio); rcu_read_lock(); } rcu_read_unlock(); swap_read_unplug(splug); } #endif /* CONFIG_SWAP */ static void mark_mmap_lock_dropped(struct madvise_behavior *madv_behavior) { VM_WARN_ON_ONCE(madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK); madv_behavior->lock_dropped = true; } /* * Schedule all required I/O operations. Do not wait for completion. */ static long madvise_willneed(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct mm_struct *mm = madv_behavior->mm; struct file *file = vma->vm_file; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; loff_t offset; #ifdef CONFIG_SWAP if (!file) { walk_page_range_vma(vma, start, end, &swapin_walk_ops, vma); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } if (shmem_mapping(file->f_mapping)) { shmem_swapin_range(vma, start, end, file->f_mapping); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } #else if (!file) return -EBADF; #endif if (IS_DAX(file_inode(file))) { /* no bad return value, but ignore advice */ return 0; } /* * Filesystem's fadvise may need to take various locks. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ mark_mmap_lock_dropped(madv_behavior); get_file(file); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); mmap_read_unlock(mm); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); mmap_read_lock(mm); return 0; } static inline bool can_do_file_pageout(struct vm_area_struct *vma) { if (!vma->vm_file) return false; /* * paging out pagecache only for non-anonymous mappings that correspond * to the files the calling process could (if tried) open for writing; * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ return inode_owner_or_capable(&nop_mnt_idmap, file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, struct folio *folio, pte_t *ptep, pte_t *ptentp) { int max_nr = (end - addr) / PAGE_SIZE; return folio_pte_batch_flags(folio, NULL, ptep, ptentp, max_nr, FPB_MERGE_YOUNG_DIRTY); } static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct madvise_walk_private *private = walk->private; struct mmu_gather *tlb = private->tlb; bool pageout = private->pageout; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; pte_t *start_pte, *pte, ptent; spinlock_t *ptl; struct folio *folio = NULL; LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; int nr; if (fatal_signal_pending(current)) return -EINTR; pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) && !can_do_file_pageout(vma); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; unsigned long next = pmd_addr_end(addr, end); tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto huge_unlock; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); goto huge_unlock; } folio = pmd_folio(orig_pmd); /* Do not interfere with other mappings of this folio */ if (folio_maybe_mapped_shared(folio)) goto huge_unlock; if (pageout_anon_only_filter && !folio_test_anon(folio)) goto huge_unlock; if (next - addr != HPAGE_PMD_SIZE) { int err; folio_get(folio); spin_unlock(ptl); folio_lock(folio); err = split_folio(folio); folio_unlock(folio); folio_put(folio); if (!err) goto regular_folio; return 0; } if (!pageout && pmd_young(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); huge_unlock: spin_unlock(ptl); if (pageout) reclaim_pages(&folio_list); return 0; } regular_folio: #endif tlb_change_page_size(tlb, PAGE_SIZE); restart: start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { nr = 1; ptent = ptep_get(pte); if (++batch_count == SWAP_CLUSTER_MAX) { batch_count = 0; if (need_resched()) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); cond_resched(); goto restart; } } if (pte_none(ptent)) continue; if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be swapped out whole. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { nr = madvise_folio_pte_batch(addr, end, folio, pte, &ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_maybe_mapped_shared(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; continue; } } /* * Do not interfere with other mappings of this folio and * non-LRU folio. If we have a large folio at this point, we * know it is fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (!folio_test_lru(folio) || folio_mapcount(folio) != folio_nr_pages(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!pageout && pte_young(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, CYDP_CLEAR_YOUNG); tlb_remove_tlb_entries(tlb, pte, nr, addr); } /* * We are deactivating a folio for accelerating reclaiming. * VM couldn't reclaim the folio unless we clear PG_young. * As a side effect, it makes confuse idle-page tracking * because they will miss recent referenced history. */ folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); } if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); } if (pageout) reclaim_pages(&folio_list); cond_resched(); return 0; } static const struct mm_walk_ops cold_walk_ops = { .pmd_entry = madvise_cold_or_pageout_pte_range, .walk_lock = PGWALK_RDLOCK, }; static void madvise_cold_page_range(struct mmu_gather *tlb, struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct madvise_walk_private walk_private = { .pageout = false, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range_vma(vma, range->start, range->end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP|VM_HUGETLB)); } static long madvise_cold(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct mmu_gather tlb; if (!can_madv_lru_vma(vma)) return -EINVAL; lru_add_drain(); tlb_gather_mmu(&tlb, madv_behavior->mm); madvise_cold_page_range(&tlb, madv_behavior); tlb_finish_mmu(&tlb); return 0; } static void madvise_pageout_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct madvise_behavior_range *range) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range_vma(vma, range->start, range->end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static long madvise_pageout(struct madvise_behavior *madv_behavior) { struct mmu_gather tlb; struct vm_area_struct *vma = madv_behavior->vma; if (!can_madv_lru_vma(vma)) return -EINVAL; /* * If the VMA belongs to a private file mapping, there can be private * dirty pages which can be paged out if even this process is neither * owner nor write capable of the file. We allow private file mappings * further to pageout dirty anon pages. */ if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) && (vma->vm_flags & VM_MAYSHARE))) return 0; lru_add_drain(); tlb_gather_mmu(&tlb, madv_behavior->mm); madvise_pageout_page_range(&tlb, vma, &madv_behavior->range); tlb_finish_mmu(&tlb); return 0; } static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY; struct mmu_gather *tlb = walk->private; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte, ptent; struct folio *folio; int nr_swap = 0; unsigned long next; int nr, max_nr; next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next)) return 0; tlb_change_page_size(tlb, PAGE_SIZE); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) { nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * If the pte has swp_entry, just clear page table to * prevent swap-in which is more expensive rather than * (page allocation + zeroing). */ if (!pte_present(ptent)) { swp_entry_t entry; entry = pte_to_swp_entry(ptent); if (!non_swap_entry(entry)) { max_nr = (end - addr) / PAGE_SIZE; nr = swap_pte_batch(pte, max_nr, ptent); nr_swap -= nr; free_swap_and_cache_nr(entry, nr); clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be marked as lazyfree. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { nr = madvise_folio_pte_batch(addr, end, folio, pte, &ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_maybe_mapped_shared(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); start_pte = pte; if (!start_pte) break; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; continue; } } if (folio_test_swapcache(folio) || folio_test_dirty(folio)) { if (!folio_trylock(folio)) continue; /* * If we have a large folio at this point, we know it is * fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (folio_mapcount(folio) != folio_nr_pages(folio)) { folio_unlock(folio); continue; } if (folio_test_swapcache(folio) && !folio_free_swap(folio)) { folio_unlock(folio); continue; } folio_clear_dirty(folio); folio_unlock(folio); } if (pte_young(ptent) || pte_dirty(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags); tlb_remove_tlb_entries(tlb, pte, nr, addr); } folio_mark_lazyfree(folio); } if (nr_swap) add_mm_counter(mm, MM_SWAPENTS, nr_swap); if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); } cond_resched(); return 0; } static inline enum page_walk_lock get_walk_lock(enum madvise_lock_mode mode) { switch (mode) { case MADVISE_VMA_READ_LOCK: return PGWALK_VMA_RDLOCK_VERIFY; case MADVISE_MMAP_READ_LOCK: return PGWALK_RDLOCK; default: /* Other modes don't require fixing up the walk_lock */ WARN_ON_ONCE(1); return PGWALK_RDLOCK; } } static int madvise_free_single_vma(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma = madv_behavior->vma; unsigned long start_addr = madv_behavior->range.start; unsigned long end_addr = madv_behavior->range.end; struct mmu_notifier_range range; struct mmu_gather *tlb = madv_behavior->tlb; struct mm_walk_ops walk_ops = { .pmd_entry = madvise_free_pte_range, }; /* MADV_FREE works for only anon vma at the moment */ if (!vma_is_anonymous(vma)) return -EINVAL; range.start = max(vma->vm_start, start_addr); if (range.start >= vma->vm_end) return -EINVAL; range.end = min(vma->vm_end, end_addr); if (range.end <= vma->vm_start) return -EINVAL; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, range.start, range.end); lru_add_drain(); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); tlb_start_vma(tlb, vma); walk_ops.walk_lock = get_walk_lock(madv_behavior->lock_mode); walk_page_range_vma(vma, range.start, range.end, &walk_ops, tlb); tlb_end_vma(tlb, vma); mmu_notifier_invalidate_range_end(&range); return 0; } /* * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The * zap_page_range_single call sets things up for shrink_active_list to actually * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * * NB: This interface discards data rather than pushes it out to swap, * as some implementations do. This has performance implications for * applications like large transactional databases which want to discard * pages in anonymous maps after committing to backing store the data * that was kept in them. There is no reason to write this data out to * the swap area if the application is discarding it. * * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ static long madvise_dontneed_single_vma(struct madvise_behavior *madv_behavior) { struct madvise_behavior_range *range = &madv_behavior->range; struct zap_details details = { .reclaim_pt = true, .even_cows = true, }; zap_page_range_single_batched( madv_behavior->tlb, madv_behavior->vma, range->start, range->end - range->start, &details); return 0; } static bool madvise_dontneed_free_valid_vma(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; int behavior = madv_behavior->behavior; struct madvise_behavior_range *range = &madv_behavior->range; if (!is_vm_hugetlb_page(vma)) { unsigned int forbidden = VM_PFNMAP; if (behavior != MADV_DONTNEED_LOCKED) forbidden |= VM_LOCKED; return !(vma->vm_flags & forbidden); } if (behavior != MADV_DONTNEED && behavior != MADV_DONTNEED_LOCKED) return false; if (range->start & ~huge_page_mask(hstate_vma(vma))) return false; /* * Madvise callers expect the length to be rounded up to PAGE_SIZE * boundaries, and may be unaware that this VMA uses huge pages. * Avoid unexpected data loss by rounding down the number of * huge pages freed. */ range->end = ALIGN_DOWN(range->end, huge_page_size(hstate_vma(vma))); return true; } static long madvise_dontneed_free(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct madvise_behavior_range *range = &madv_behavior->range; int behavior = madv_behavior->behavior; if (!madvise_dontneed_free_valid_vma(madv_behavior)) return -EINVAL; if (range->start == range->end) return 0; if (!userfaultfd_remove(madv_behavior->vma, range->start, range->end)) { struct vm_area_struct *vma; mark_mmap_lock_dropped(madv_behavior); mmap_read_lock(mm); madv_behavior->vma = vma = vma_lookup(mm, range->start); if (!vma) return -ENOMEM; /* * Potential end adjustment for hugetlb vma is OK as * the check below keeps end within vma. */ if (!madvise_dontneed_free_valid_vma(madv_behavior)) return -EINVAL; if (range->end > vma->vm_end) { /* * Don't fail if end > vma->vm_end. If the old * vma was split while the mmap_lock was * released the effect of the concurrent * operation may not cause madvise() to * have an undefined result. There may be an * adjacent next vma that we'll walk * next. userfaultfd_remove() will generate an * UFFD_EVENT_REMOVE repetition on the * end-vma->vm_end range, but the manager can * handle a repetition fine. */ range->end = vma->vm_end; } /* * If the memory region between start and end was * originally backed by 4kB pages and then remapped to * be backed by hugepages while mmap_lock was dropped, * the adjustment for hugetlb vma above may have rounded * end down to the start address. */ if (range->start == range->end) return 0; VM_WARN_ON(range->start > range->end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) return madvise_dontneed_single_vma(madv_behavior); else if (behavior == MADV_FREE) return madvise_free_single_vma(madv_behavior); else return -EINVAL; } static long madvise_populate(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; const bool write = madv_behavior->behavior == MADV_POPULATE_WRITE; int locked = 1; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; long pages; while (start < end) { /* Populate (prefault) page tables readable/writable. */ pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; } if (pages < 0) { switch (pages) { case -EINTR: return -EINTR; case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } start += pages * PAGE_SIZE; } return 0; } /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. */ static long madvise_remove(struct madvise_behavior *madv_behavior) { loff_t offset; int error; struct file *f; struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma = madv_behavior->vma; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; mark_mmap_lock_dropped(madv_behavior); if (vma->vm_flags & VM_LOCKED) return -EINVAL; f = vma->vm_file; if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } if (!vma_is_shared_maywrite(vma)) return -EACCES; offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* * Filesystem's fallocate may need to take i_rwsem. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); mmap_read_lock(mm); return error; } static bool is_valid_guard_vma(struct vm_area_struct *vma, bool allow_locked) { vm_flags_t disallowed = VM_SPECIAL | VM_HUGETLB; /* * A user could lock after setting a guard range but that's fine, as * they'd not be able to fault in. The issue arises when we try to zap * existing locked VMAs. We don't want to do that. */ if (!allow_locked) disallowed |= VM_LOCKED; return !(vma->vm_flags & disallowed); } static bool is_guard_pte_marker(pte_t ptent) { return is_pte_marker(ptent) && is_guard_swp_entry(pte_to_swp_entry(ptent)); } static int guard_install_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge return >0 so we abort the operation + zap. */ return pud_trans_huge(pudval); } static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge return >0 so we abort the operation + zap. */ return pmd_trans_huge(pmdval); } static int guard_install_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t pteval = ptep_get(pte); unsigned long *nr_pages = (unsigned long *)walk->private; /* If there is already a guard page marker, we have nothing to do. */ if (is_guard_pte_marker(pteval)) { (*nr_pages)++; return 0; } /* If populated return >0 so we abort the operation + zap. */ return 1; } static int guard_install_set_pte(unsigned long addr, unsigned long next, pte_t *ptep, struct mm_walk *walk) { unsigned long *nr_pages = (unsigned long *)walk->private; /* Simply install a PTE marker, this causes segfault on access. */ *ptep = make_pte_marker(PTE_MARKER_GUARD); (*nr_pages)++; return 0; } static const struct mm_walk_ops guard_install_walk_ops = { .pud_entry = guard_install_pud_entry, .pmd_entry = guard_install_pmd_entry, .pte_entry = guard_install_pte_entry, .install_pte = guard_install_set_pte, .walk_lock = PGWALK_RDLOCK, }; static long madvise_guard_install(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; long err; int i; if (!is_valid_guard_vma(vma, /* allow_locked = */false)) return -EINVAL; /* * If we install guard markers, then the range is no longer * empty from a page table perspective and therefore it's * appropriate to have an anon_vma. * * This ensures that on fork, we copy page tables correctly. */ err = anon_vma_prepare(vma); if (err) return err; /* * Optimistically try to install the guard marker pages first. If any * non-guard pages are encountered, give up and zap the range before * trying again. * * We try a few times before giving up and releasing back to userland to * loop around, releasing locks in the process to avoid contention. This * would only happen if there was a great many racing page faults. * * In most cases we should simply install the guard markers immediately * with no zap or looping. */ for (i = 0; i < MAX_MADVISE_GUARD_RETRIES; i++) { unsigned long nr_pages = 0; /* Returns < 0 on error, == 0 if success, > 0 if zap needed. */ err = walk_page_range_mm(vma->vm_mm, range->start, range->end, &guard_install_walk_ops, &nr_pages); if (err < 0) return err; if (err == 0) { unsigned long nr_expected_pages = PHYS_PFN(range->end - range->start); VM_WARN_ON(nr_pages != nr_expected_pages); return 0; } /* * OK some of the range have non-guard pages mapped, zap * them. This leaves existing guard pages in place. */ zap_page_range_single(vma, range->start, range->end - range->start, NULL); } /* * We were unable to install the guard pages due to being raced by page * faults. This should not happen ordinarily. We return to userspace and * immediately retry, relieving lock contention. */ return restart_syscall(); } static int guard_remove_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pud_trans_huge(pudval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pmd_trans_huge(pmdval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t ptent = ptep_get(pte); if (is_guard_pte_marker(ptent)) { /* Simply clear the PTE marker. */ pte_clear_not_present_full(walk->mm, addr, pte, false); update_mmu_cache(walk->vma, addr, pte); } return 0; } static const struct mm_walk_ops guard_remove_walk_ops = { .pud_entry = guard_remove_pud_entry, .pmd_entry = guard_remove_pmd_entry, .pte_entry = guard_remove_pte_entry, .walk_lock = PGWALK_RDLOCK, }; static long madvise_guard_remove(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; /* * We're ok with removing guards in mlock()'d ranges, as this is a * non-destructive action. */ if (!is_valid_guard_vma(vma, /* allow_locked = */true)) return -EINVAL; return walk_page_range_vma(vma, range->start, range->end, &guard_remove_walk_ops, NULL); } #ifdef CONFIG_64BIT /* Does the madvise operation result in discarding of mapped data? */ static bool is_discard(int behavior) { switch (behavior) { case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_REMOVE: case MADV_DONTFORK: case MADV_WIPEONFORK: case MADV_GUARD_INSTALL: return true; } return false; } /* * We are restricted from madvise()'ing mseal()'d VMAs only in very particular * circumstances - discarding of data from read-only anonymous SEALED mappings. * * This is because users cannot trivally discard data from these VMAs, and may * only do so via an appropriate madvise() call. */ static bool can_madvise_modify(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; /* If the VMA isn't sealed we're good. */ if (!vma_is_sealed(vma)) return true; /* For a sealed VMA, we only care about discard operations. */ if (!is_discard(madv_behavior->behavior)) return true; /* * We explicitly permit all file-backed mappings, whether MAP_SHARED or * MAP_PRIVATE. * * The latter causes some complications. Because now, one can mmap() * read/write a MAP_PRIVATE mapping, write to it, then mprotect() * read-only, mseal() and a discard will be permitted. * * However, in order to avoid issues with potential use of madvise(..., * MADV_DONTNEED) of mseal()'d .text mappings we, for the time being, * permit this. */ if (!vma_is_anonymous(vma)) return true; /* If the user could write to the mapping anyway, then this is fine. */ if ((vma->vm_flags & VM_WRITE) && arch_vma_access_permitted(vma, /* write= */ true, /* execute= */ false, /* foreign= */ false)) return true; /* Otherwise, we are not permitted to perform this operation. */ return false; } #else static bool can_madvise_modify(struct madvise_behavior *madv_behavior) { return true; } #endif /* * Apply an madvise behavior to a region of a vma. madvise_update_vma * will handle splitting a vm area into separate areas, each area with its own * behavior. */ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior) { int behavior = madv_behavior->behavior; struct vm_area_struct *vma = madv_behavior->vma; vm_flags_t new_flags = vma->vm_flags; struct madvise_behavior_range *range = &madv_behavior->range; int error; if (unlikely(!can_madvise_modify(madv_behavior))) return -EPERM; switch (behavior) { case MADV_REMOVE: return madvise_remove(madv_behavior); case MADV_WILLNEED: return madvise_willneed(madv_behavior); case MADV_COLD: return madvise_cold(madv_behavior); case MADV_PAGEOUT: return madvise_pageout(madv_behavior); case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: return madvise_dontneed_free(madv_behavior); case MADV_COLLAPSE: return madvise_collapse(vma, range->start, range->end, &madv_behavior->lock_dropped); case MADV_GUARD_INSTALL: return madvise_guard_install(madv_behavior); case MADV_GUARD_REMOVE: return madvise_guard_remove(madv_behavior); /* The below behaviours update VMAs via madvise_update_vma(). */ case MADV_NORMAL: new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; break; case MADV_SEQUENTIAL: new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ; break; case MADV_RANDOM: new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ; break; case MADV_DONTFORK: new_flags |= VM_DONTCOPY; break; case MADV_DOFORK: if (new_flags & VM_IO) return -EINVAL; new_flags &= ~VM_DONTCOPY; break; case MADV_WIPEONFORK: /* MADV_WIPEONFORK is only supported on anonymous memory. */ if (vma->vm_file || new_flags & VM_SHARED) return -EINVAL; new_flags |= VM_WIPEONFORK; break; case MADV_KEEPONFORK: if (new_flags & VM_DROPPABLE) return -EINVAL; new_flags &= ~VM_WIPEONFORK; break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: if ((!is_vm_hugetlb_page(vma) && (new_flags & VM_SPECIAL)) || (new_flags & VM_DROPPABLE)) return -EINVAL; new_flags &= ~VM_DONTDUMP; break; case MADV_MERGEABLE: case MADV_UNMERGEABLE: error = ksm_madvise(vma, range->start, range->end, behavior, &new_flags); if (error) goto out; break; case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: error = hugepage_madvise(vma, &new_flags, behavior); if (error) goto out; break; case __MADV_SET_ANON_VMA_NAME: /* Only anonymous mappings can be named */ if (vma->vm_file && !vma_is_anon_shmem(vma)) return -EBADF; break; } /* This is a write operation.*/ VM_WARN_ON_ONCE(madv_behavior->lock_mode != MADVISE_MMAP_WRITE_LOCK); error = madvise_update_vma(new_flags, madv_behavior); out: /* * madvise() returns EAGAIN if kernel resources, such as * slab, are temporarily unavailable. */ if (error == -ENOMEM) error = -EAGAIN; return error; } #ifdef CONFIG_MEMORY_FAILURE /* * Error injection support for memory error handling. */ static int madvise_inject_error(struct madvise_behavior *madv_behavior) { unsigned long size; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; if (!capable(CAP_SYS_ADMIN)) return -EPERM; for (; start < end; start += size) { unsigned long pfn; struct page *page; int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; pfn = page_to_pfn(page); /* * When soft offlining hugepages, after migrating the page * we dissolve it, therefore in the second loop "page" will * no longer be a compound page. */ size = page_size(compound_head(page)); if (madv_behavior->behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); ret = soft_offline_page(pfn, MF_COUNT_INCREASED); } else { pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", pfn, start); ret = memory_failure(pfn, MF_ACTION_REQUIRED | MF_COUNT_INCREASED | MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; } if (ret) return ret; } return 0; } static bool is_memory_failure(struct madvise_behavior *madv_behavior) { switch (madv_behavior->behavior) { case MADV_HWPOISON: case MADV_SOFT_OFFLINE: return true; default: return false; } } #else static int madvise_inject_error(struct madvise_behavior *madv_behavior) { return 0; } static bool is_memory_failure(struct madvise_behavior *madv_behavior) { return false; } #endif /* CONFIG_MEMORY_FAILURE */ static bool madvise_behavior_valid(int behavior) { switch (behavior) { case MADV_DOFORK: case MADV_DONTFORK: case MADV_NORMAL: case MADV_SEQUENTIAL: case MADV_RANDOM: case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: case MADV_COLLAPSE: #endif case MADV_DONTDUMP: case MADV_DODUMP: case MADV_WIPEONFORK: case MADV_KEEPONFORK: case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: #ifdef CONFIG_MEMORY_FAILURE case MADV_SOFT_OFFLINE: case MADV_HWPOISON: #endif return true; default: return false; } } /* Can we invoke process_madvise() on a remote mm for the specified behavior? */ static bool process_madvise_remote_valid(int behavior) { switch (behavior) { case MADV_COLD: case MADV_PAGEOUT: case MADV_WILLNEED: case MADV_COLLAPSE: return true; default: return false; } } /* * Try to acquire a VMA read lock if possible. * * We only support this lock over a single VMA, which the input range must * span either partially or fully. * * This function always returns with an appropriate lock held. If a VMA read * lock could be acquired, we return true and set madv_behavior state * accordingly. * * If a VMA read lock could not be acquired, we return false and expect caller to * fallback to mmap lock behaviour. */ static bool try_vma_read_lock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma; vma = lock_vma_under_rcu(mm, madv_behavior->range.start); if (!vma) goto take_mmap_read_lock; /* * Must span only a single VMA; uffd and remote processes are * unsupported. */ if (madv_behavior->range.end > vma->vm_end || current->mm != mm || userfaultfd_armed(vma)) { vma_end_read(vma); goto take_mmap_read_lock; } madv_behavior->vma = vma; return true; take_mmap_read_lock: mmap_read_lock(mm); madv_behavior->lock_mode = MADVISE_MMAP_READ_LOCK; return false; } /* * Walk the vmas in range [start,end), and call the madvise_vma_behavior * function on each one. The function will get start and end parameters that * cover the overlap between the current vma and the original range. Any * unmapped regions in the original range will result in this function returning * -ENOMEM while still calling the madvise_vma_behavior function on all of the * existing vmas in the range. Must be called with the mmap_lock held for * reading or writing. */ static int madvise_walk_vmas(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct madvise_behavior_range *range = &madv_behavior->range; /* range is updated to span each VMA, so store end of entire range. */ unsigned long last_end = range->end; int unmapped_error = 0; int error; struct vm_area_struct *prev, *vma; /* * If VMA read lock is supported, apply madvise to a single VMA * tentatively, avoiding walking VMAs. */ if (madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK && try_vma_read_lock(madv_behavior)) { error = madvise_vma_behavior(madv_behavior); vma_end_read(madv_behavior->vma); return error; } vma = find_vma_prev(mm, range->start, &prev); if (vma && range->start > vma->vm_start) prev = vma; for (;;) { /* Still start < end. */ if (!vma) return -ENOMEM; /* Here start < (last_end|vma->vm_end). */ if (range->start < vma->vm_start) { /* * This indicates a gap between VMAs in the input * range. This does not cause the operation to abort, * rather we simply return -ENOMEM to indicate that this * has happened, but carry on. */ unmapped_error = -ENOMEM; range->start = vma->vm_start; if (range->start >= last_end) break; } /* Here vma->vm_start <= range->start < (last_end|vma->vm_end) */ range->end = min(vma->vm_end, last_end); /* Here vma->vm_start <= range->start < range->end <= (last_end|vma->vm_end). */ madv_behavior->prev = prev; madv_behavior->vma = vma; error = madvise_vma_behavior(madv_behavior); if (error) return error; if (madv_behavior->lock_dropped) { /* We dropped the mmap lock, we can't ref the VMA. */ prev = NULL; vma = NULL; madv_behavior->lock_dropped = false; } else { vma = madv_behavior->vma; prev = vma; } if (vma && range->end < vma->vm_end) range->end = vma->vm_end; if (range->end >= last_end) break; vma = find_vma(mm, vma ? vma->vm_end : range->end); range->start = range->end; } return unmapped_error; } /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_lock for writing. Others, which simply traverse vmas, need * to only take it for reading. */ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavior) { if (is_memory_failure(madv_behavior)) return MADVISE_NO_LOCK; switch (madv_behavior->behavior) { case MADV_REMOVE: case MADV_WILLNEED: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: case MADV_COLLAPSE: case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: return MADVISE_MMAP_READ_LOCK; case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: return MADVISE_VMA_READ_LOCK; default: return MADVISE_MMAP_WRITE_LOCK; } } static int madvise_lock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; enum madvise_lock_mode lock_mode = get_lock_mode(madv_behavior); switch (lock_mode) { case MADVISE_NO_LOCK: break; case MADVISE_MMAP_WRITE_LOCK: if (mmap_write_lock_killable(mm)) return -EINTR; break; case MADVISE_MMAP_READ_LOCK: mmap_read_lock(mm); break; case MADVISE_VMA_READ_LOCK: /* We will acquire the lock per-VMA in madvise_walk_vmas(). */ break; } madv_behavior->lock_mode = lock_mode; return 0; } static void madvise_unlock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; switch (madv_behavior->lock_mode) { case MADVISE_NO_LOCK: return; case MADVISE_MMAP_WRITE_LOCK: mmap_write_unlock(mm); break; case MADVISE_MMAP_READ_LOCK: mmap_read_unlock(mm); break; case MADVISE_VMA_READ_LOCK: /* We will drop the lock per-VMA in madvise_walk_vmas(). */ break; } madv_behavior->lock_mode = MADVISE_NO_LOCK; } static bool madvise_batch_tlb_flush(int behavior) { switch (behavior) { case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: return true; default: return false; } } static void madvise_init_tlb(struct madvise_behavior *madv_behavior) { if (madvise_batch_tlb_flush(madv_behavior->behavior)) tlb_gather_mmu(madv_behavior->tlb, madv_behavior->mm); } static void madvise_finish_tlb(struct madvise_behavior *madv_behavior) { if (madvise_batch_tlb_flush(madv_behavior->behavior)) tlb_finish_mmu(madv_behavior->tlb); } static bool is_valid_madvise(unsigned long start, size_t len_in, int behavior) { size_t len; if (!madvise_behavior_valid(behavior)) return false; if (!PAGE_ALIGNED(start)) return false; len = PAGE_ALIGN(len_in); /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return false; if (start + len < start) return false; return true; } /* * madvise_should_skip() - Return if the request is invalid or nothing. * @start: Start address of madvise-requested address range. * @len_in: Length of madvise-requested address range. * @behavior: Requested madvise behavor. * @err: Pointer to store an error code from the check. * * If the specified behaviour is invalid or nothing would occur, we skip the * operation. This function returns true in the cases, otherwise false. In * the former case we store an error on @err. */ static bool madvise_should_skip(unsigned long start, size_t len_in, int behavior, int *err) { if (!is_valid_madvise(start, len_in, behavior)) { *err = -EINVAL; return true; } if (start + PAGE_ALIGN(len_in) == start) { *err = 0; return true; } return false; } static bool is_madvise_populate(struct madvise_behavior *madv_behavior) { switch (madv_behavior->behavior) { case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: return true; default: return false; } } /* * untagged_addr_remote() assumes mmap_lock is already held. On * architectures like x86 and RISC-V, tagging is tricky because each * mm may have a different tagging mask. However, we might only hold * the per-VMA lock (currently only local processes are supported), * so untagged_addr is used to avoid the mmap_lock assertion for * local processes. */ static inline unsigned long get_untagged_addr(struct mm_struct *mm, unsigned long start) { return current->mm == mm ? untagged_addr(start) : untagged_addr_remote(mm, start); } static int madvise_do_behavior(unsigned long start, size_t len_in, struct madvise_behavior *madv_behavior) { struct blk_plug plug; int error; struct madvise_behavior_range *range = &madv_behavior->range; if (is_memory_failure(madv_behavior)) { range->start = start; range->end = start + len_in; return madvise_inject_error(madv_behavior); } range->start = get_untagged_addr(madv_behavior->mm, start); range->end = range->start + PAGE_ALIGN(len_in); blk_start_plug(&plug); if (is_madvise_populate(madv_behavior)) error = madvise_populate(madv_behavior); else error = madvise_walk_vmas(madv_behavior); blk_finish_plug(&plug); return error; } /* * The madvise(2) system call. * * Applications can use madvise() to advise the kernel how it should * handle paging I/O in this VM area. The idea is to help the kernel * use appropriate read-ahead and caching techniques. The information * provided is advisory only, and can be safely disregarded by the * kernel without affecting the correct operation of the application. * * behavior values: * MADV_NORMAL - the default behavior is to read clusters. This * results in some read-ahead and read-behind. * MADV_RANDOM - the system should read the minimum amount of data * on any access, since it is unlikely that the appli- * cation will need more than what it asks for. * MADV_SEQUENTIAL - pages in the given range will probably be accessed * once, so they can be aggressively read ahead, and * can be freed soon after they are accessed. * MADV_WILLNEED - the application is notifying the system to read * some pages ahead. * MADV_DONTNEED - the application is finished with the given range, * so the kernel can free resources associated with it. * MADV_FREE - the application marks pages in the given range as lazy free, * where actual purges are postponed until memory pressure happens. * MADV_REMOVE - the application wants to free up the given range of * pages and associated backing store. * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. * MADV_WIPEONFORK - present the child process with zero-filled memory in this * range after a fork. * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. * MADV_MERGEABLE - the application recommends that KSM try to merge pages in * this area with pages of identical content from other such areas. * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. * MADV_HUGEPAGE - the application wants to back the given range by transparent * huge pages in the future. Existing pages might be coalesced and * new pages might be allocated as THP. * MADV_NOHUGEPAGE - mark the given range as not worth being backed by * transparent huge pages so the existing pages will not be * coalesced into THP and new pages will not be allocated as THP. * MADV_COLLAPSE - synchronously coalesce pages into new THP. * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. * MADV_COLD - the application is not expected to use this memory soon, * deactivate pages in this range so that they can be reclaimed * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. * MADV_POPULATE_READ - populate (prefault) page tables readable by * triggering read faults if required * MADV_POPULATE_WRITE - populate (prefault) page tables writable by * triggering write faults if required * * return values: * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application * is attempting to release locked or shared pages, * or the specified address range includes file, Huge TLB, * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { int error; struct mmu_gather tlb; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = behavior, .tlb = &tlb, }; if (madvise_should_skip(start, len_in, behavior, &error)) return error; error = madvise_lock(&madv_behavior); if (error) return error; madvise_init_tlb(&madv_behavior); error = madvise_do_behavior(start, len_in, &madv_behavior); madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { return do_madvise(current->mm, start, len_in, behavior); } /* Perform an madvise operation over a vector of addresses and lengths. */ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter, int behavior) { ssize_t ret = 0; size_t total_len; struct mmu_gather tlb; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = behavior, .tlb = &tlb, }; total_len = iov_iter_count(iter); ret = madvise_lock(&madv_behavior); if (ret) return ret; madvise_init_tlb(&madv_behavior); while (iov_iter_count(iter)) { unsigned long start = (unsigned long)iter_iov_addr(iter); size_t len_in = iter_iov_len(iter); int error; if (madvise_should_skip(start, len_in, behavior, &error)) ret = error; else ret = madvise_do_behavior(start, len_in, &madv_behavior); /* * An madvise operation is attempting to restart the syscall, * but we cannot proceed as it would not be correct to repeat * the operation in aggregate, and would be surprising to the * user. * * We drop and reacquire locks so it is safe to just loop and * try again. We check for fatal signals in case we need exit * early anyway. */ if (ret == -ERESTARTNOINTR) { if (fatal_signal_pending(current)) { ret = -EINTR; break; } /* Drop and reacquire lock to unwind race. */ madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); ret = madvise_lock(&madv_behavior); if (ret) goto out; madvise_init_tlb(&madv_behavior); continue; } if (ret < 0) break; iov_iter_advance(iter, iter_iov_len(iter)); } madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); out: ret = (total_len - iov_iter_count(iter)) ? : ret; return ret; } SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, size_t, vlen, int, behavior, unsigned int, flags) { ssize_t ret; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; struct task_struct *task; struct mm_struct *mm; unsigned int f_flags; if (flags != 0) { ret = -EINVAL; goto out; } ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) goto out; task = pidfd_get_task(pidfd, &f_flags); if (IS_ERR(task)) { ret = PTR_ERR(task); goto free_iov; } /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) { ret = PTR_ERR(mm); goto release_task; } /* * We need only perform this check if we are attempting to manipulate a * remote process's address space. */ if (mm != current->mm && !process_madvise_remote_valid(behavior)) { ret = -EINVAL; goto release_mm; } /* * Require CAP_SYS_NICE for influencing process performance. Note that * only non-destructive hints are currently supported for remote * processes. */ if (mm != current->mm && !capable(CAP_SYS_NICE)) { ret = -EPERM; goto release_mm; } ret = vector_madvise(mm, &iter, behavior); release_mm: mmput(mm); release_task: put_task_struct(task); free_iov: kfree(iov); out: return ret; } #ifdef CONFIG_ANON_VMA_NAME #define ANON_VMA_NAME_MAX_LEN 80 #define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" static inline bool is_valid_name_char(char ch) { /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ return ch > 0x1f && ch < 0x7f && !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); } static int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { unsigned long end; unsigned long len; int error; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = __MADV_SET_ANON_VMA_NAME, .anon_name = anon_name, }; if (start & ~PAGE_MASK) return -EINVAL; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; madv_behavior.range.start = start; madv_behavior.range.end = end; error = madvise_lock(&madv_behavior); if (error) return error; error = madvise_walk_vmas(&madv_behavior); madvise_unlock(&madv_behavior); return error; } int set_anon_vma_name(unsigned long addr, unsigned long size, const char __user *uname) { struct anon_vma_name *anon_name = NULL; struct mm_struct *mm = current->mm; int error; if (uname) { char *name, *pch; name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); if (IS_ERR(name)) return PTR_ERR(name); for (pch = name; *pch != '\0'; pch++) { if (!is_valid_name_char(*pch)) { kfree(name); return -EINVAL; } } /* anon_vma has its own copy */ anon_name = anon_vma_name_alloc(name); kfree(name); if (!anon_name) return -ENOMEM; } error = madvise_set_anon_name(mm, addr, size, anon_name); anon_vma_name_put(anon_name); return error; } #endif |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2009 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/module.h> #include <linux/init.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/vmalloc.h> #include <linux/rhashtable.h> #include <linux/audit.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/net_namespace.h> #include <net/sock.h> #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) #define NFT_SET_MAX_ANONLEN 16 /* limit compaction to avoid huge kmalloc/krealloc sizes. */ #define NFT_MAX_SET_NELEMS ((2048 - sizeof(struct nft_trans_elem)) / sizeof(struct nft_trans_one_elem)) unsigned int nf_tables_net_id __read_mostly; static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); static DEFINE_SPINLOCK(nf_tables_gc_list_lock); enum { NFT_VALIDATE_SKIP = 0, NFT_VALIDATE_NEED, NFT_VALIDATE_DO, }; static struct rhltable nft_objname_ht; static u32 nft_chain_hash(const void *data, u32 len, u32 seed); static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed); static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *); static u32 nft_objname_hash(const void *data, u32 len, u32 seed); static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed); static int nft_objname_hash_cmp(struct rhashtable_compare_arg *, const void *); static const struct rhashtable_params nft_chain_ht_params = { .head_offset = offsetof(struct nft_chain, rhlhead), .key_offset = offsetof(struct nft_chain, name), .hashfn = nft_chain_hash, .obj_hashfn = nft_chain_hash_obj, .obj_cmpfn = nft_chain_hash_cmp, .automatic_shrinking = true, }; static const struct rhashtable_params nft_objname_ht_params = { .head_offset = offsetof(struct nft_object, rhlhead), .key_offset = offsetof(struct nft_object, key), .hashfn = nft_objname_hash, .obj_hashfn = nft_objname_hash_obj, .obj_cmpfn = nft_objname_hash_cmp, .automatic_shrinking = true, }; struct nft_audit_data { struct nft_table *table; int entries; int op; struct list_head list; }; static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types [NFT_MSG_NEWTABLE] = AUDIT_NFT_OP_TABLE_REGISTER, [NFT_MSG_GETTABLE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELTABLE] = AUDIT_NFT_OP_TABLE_UNREGISTER, [NFT_MSG_NEWCHAIN] = AUDIT_NFT_OP_CHAIN_REGISTER, [NFT_MSG_GETCHAIN] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELCHAIN] = AUDIT_NFT_OP_CHAIN_UNREGISTER, [NFT_MSG_NEWRULE] = AUDIT_NFT_OP_RULE_REGISTER, [NFT_MSG_GETRULE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELRULE] = AUDIT_NFT_OP_RULE_UNREGISTER, [NFT_MSG_NEWSET] = AUDIT_NFT_OP_SET_REGISTER, [NFT_MSG_GETSET] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELSET] = AUDIT_NFT_OP_SET_UNREGISTER, [NFT_MSG_NEWSETELEM] = AUDIT_NFT_OP_SETELEM_REGISTER, [NFT_MSG_GETSETELEM] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELSETELEM] = AUDIT_NFT_OP_SETELEM_UNREGISTER, [NFT_MSG_NEWGEN] = AUDIT_NFT_OP_GEN_REGISTER, [NFT_MSG_GETGEN] = AUDIT_NFT_OP_INVALID, [NFT_MSG_TRACE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_NEWOBJ] = AUDIT_NFT_OP_OBJ_REGISTER, [NFT_MSG_GETOBJ] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELOBJ] = AUDIT_NFT_OP_OBJ_UNREGISTER, [NFT_MSG_GETOBJ_RESET] = AUDIT_NFT_OP_OBJ_RESET, [NFT_MSG_NEWFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_REGISTER, [NFT_MSG_GETFLOWTABLE] = AUDIT_NFT_OP_INVALID, [NFT_MSG_DELFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, [NFT_MSG_GETSETELEM_RESET] = AUDIT_NFT_OP_SETELEM_RESET, }; static void nft_validate_state_update(struct nft_table *table, u8 new_validate_state) { switch (table->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; case NFT_VALIDATE_NEED: break; case NFT_VALIDATE_DO: if (new_validate_state == NFT_VALIDATE_NEED) return; } table->validate_state = new_validate_state; } static void nf_tables_trans_destroy_work(struct work_struct *w); static void nft_trans_gc_work(struct work_struct *work); static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, u8 family, struct nft_table *table, struct nft_chain *chain, const struct nlattr * const *nla) { ctx->net = net; ctx->family = family; ctx->level = 0; ctx->table = table; ctx->chain = chain; ctx->nla = nla; ctx->portid = NETLINK_CB(skb).portid; ctx->report = nlmsg_report(nlh); ctx->flags = nlh->nlmsg_flags; ctx->seq = nlh->nlmsg_seq; bitmap_zero(ctx->reg_inited, NFT_REG32_NUM); } static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, int msg_type, u32 size, gfp_t gfp) { struct nft_trans *trans; trans = kzalloc(size, gfp); if (trans == NULL) return NULL; INIT_LIST_HEAD(&trans->list); trans->msg_type = msg_type; trans->net = ctx->net; trans->table = ctx->table; trans->seq = ctx->seq; trans->flags = ctx->flags; trans->report = ctx->report; return trans; } static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx, int msg_type, u32 size) { return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL); } static struct nft_trans_binding *nft_trans_get_binding(struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: case NFT_MSG_NEWSET: return container_of(trans, struct nft_trans_binding, nft_trans); } return NULL; } static void nft_trans_list_del(struct nft_trans *trans) { struct nft_trans_binding *trans_binding; list_del(&trans->list); trans_binding = nft_trans_get_binding(trans); if (trans_binding) list_del(&trans_binding->binding_list); } static void nft_trans_destroy(struct nft_trans *trans) { nft_trans_list_del(trans); kfree(trans); } static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set, bool bind) { struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_set_is_anonymous(set)) return; nft_net = nft_pernet(net); list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) nft_trans_set_bound(trans) = bind; break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set(trans) == set) nft_trans_elem_set_bound(trans) = bind; break; } } } static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) { return __nft_set_trans_bind(ctx, set, true); } static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set) { return __nft_set_trans_bind(ctx, set, false); } static void __nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *chain, bool bind) { struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_chain_binding(chain)) return; nft_net = nft_pernet(net); list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (nft_trans_chain(trans) == chain) nft_trans_chain_bound(trans) = bind; break; case NFT_MSG_NEWRULE: if (nft_trans_rule_chain(trans) == chain) nft_trans_rule_bound(trans) = bind; break; } } } static void nft_chain_trans_bind(const struct nft_ctx *ctx, struct nft_chain *chain) { __nft_chain_trans_bind(ctx, chain, true); } int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) { if (!nft_chain_binding(chain)) return 0; if (nft_chain_binding(ctx->chain)) return -EOPNOTSUPP; if (chain->bound) return -EBUSY; if (!nft_use_inc(&chain->use)) return -EMFILE; chain->bound = true; nft_chain_trans_bind(ctx, chain); return 0; } void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) { __nft_chain_trans_bind(ctx, chain, false); } static int nft_netdev_register_hooks(struct net *net, struct list_head *hook_list) { struct nf_hook_ops *ops; struct nft_hook *hook; int err, j; j = 0; list_for_each_entry(hook, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { err = nf_register_net_hook(net, ops); if (err < 0) goto err_register; j++; } } return 0; err_register: list_for_each_entry(hook, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (j-- <= 0) break; nf_unregister_net_hook(net, ops); } } return err; } static void nft_netdev_hook_free_ops(struct nft_hook *hook) { struct nf_hook_ops *ops, *next; list_for_each_entry_safe(ops, next, &hook->ops_list, list) { list_del(&ops->list); kfree(ops); } } static void nft_netdev_hook_free(struct nft_hook *hook) { nft_netdev_hook_free_ops(hook); kfree(hook); } static void __nft_netdev_hook_free_rcu(struct rcu_head *rcu) { struct nft_hook *hook = container_of(rcu, struct nft_hook, rcu); nft_netdev_hook_free(hook); } static void nft_netdev_hook_free_rcu(struct nft_hook *hook) { call_rcu(&hook->rcu, __nft_netdev_hook_free_rcu); } static void nft_netdev_unregister_hooks(struct net *net, struct list_head *hook_list, bool release_netdev) { struct nft_hook *hook, *next; struct nf_hook_ops *ops; list_for_each_entry_safe(hook, next, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) nf_unregister_net_hook(net, ops); if (release_netdev) { list_del(&hook->list); nft_netdev_hook_free_rcu(hook); } } } static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { struct nft_base_chain *basechain; const struct nf_hook_ops *ops; if (table->flags & NFT_TABLE_F_DORMANT || !nft_is_base_chain(chain)) return 0; basechain = nft_base_chain(chain); ops = &basechain->ops; if (basechain->type->ops_register) return basechain->type->ops_register(net, ops); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) return nft_netdev_register_hooks(net, &basechain->hook_list); return nf_register_net_hook(net, &basechain->ops); } static void __nf_tables_unregister_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain, bool release_netdev) { struct nft_base_chain *basechain; const struct nf_hook_ops *ops; if (table->flags & NFT_TABLE_F_DORMANT || !nft_is_base_chain(chain)) return; basechain = nft_base_chain(chain); ops = &basechain->ops; if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) nft_netdev_unregister_hooks(net, &basechain->hook_list, release_netdev); else nf_unregister_net_hook(net, &basechain->ops); } static void nf_tables_unregister_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { return __nf_tables_unregister_hook(net, table, chain, false); } static bool nft_trans_collapse_set_elem_allowed(const struct nft_trans_elem *a, const struct nft_trans_elem *b) { /* NB: the ->bound equality check is defensive, at this time we only merge * a new nft_trans_elem transaction request with the transaction tail * element, but a->bound != b->bound would imply a NEWRULE transaction * is queued in-between. * * The set check is mandatory, the NFT_MAX_SET_NELEMS check prevents * huge krealloc() requests. */ return a->set == b->set && a->bound == b->bound && a->nelems < NFT_MAX_SET_NELEMS; } static bool nft_trans_collapse_set_elem(struct nftables_pernet *nft_net, struct nft_trans_elem *tail, struct nft_trans_elem *trans, gfp_t gfp) { unsigned int nelems, old_nelems = tail->nelems; struct nft_trans_elem *new_trans; if (!nft_trans_collapse_set_elem_allowed(tail, trans)) return false; /* "cannot happen", at this time userspace element add * requests always allocate a new transaction element. * * This serves as a reminder to adjust the list_add_tail * logic below in case this ever changes. */ if (WARN_ON_ONCE(trans->nelems != 1)) return false; if (check_add_overflow(old_nelems, trans->nelems, &nelems)) return false; /* krealloc might free tail which invalidates list pointers */ list_del_init(&tail->nft_trans.list); new_trans = krealloc(tail, struct_size(tail, elems, nelems), gfp); if (!new_trans) { list_add_tail(&tail->nft_trans.list, &nft_net->commit_list); return false; } /* * new_trans->nft_trans.list contains garbage, but * list_add_tail() doesn't care. */ new_trans->nelems = nelems; new_trans->elems[old_nelems] = trans->elems[0]; list_add_tail(&new_trans->nft_trans.list, &nft_net->commit_list); return true; } static bool nft_trans_try_collapse(struct nftables_pernet *nft_net, struct nft_trans *trans, gfp_t gfp) { struct nft_trans *tail; if (list_empty(&nft_net->commit_list)) return false; tail = list_last_entry(&nft_net->commit_list, struct nft_trans, list); if (tail->msg_type != trans->msg_type) return false; switch (trans->msg_type) { case NFT_MSG_NEWSETELEM: case NFT_MSG_DELSETELEM: return nft_trans_collapse_set_elem(nft_net, nft_trans_container_elem(tail), nft_trans_container_elem(trans), gfp); } return false; } static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans_binding *binding; struct nft_trans_set *trans_set; list_add_tail(&trans->list, &nft_net->commit_list); binding = nft_trans_get_binding(trans); if (!binding) return; switch (trans->msg_type) { case NFT_MSG_NEWSET: trans_set = nft_trans_container_set(trans); if (!nft_trans_set_update(trans) && nft_set_is_anonymous(nft_trans_set(trans))) list_add_tail(&binding->binding_list, &nft_net->binding_list); list_add_tail(&trans_set->list_trans_newset, &nft_net->commit_set_list); break; case NFT_MSG_NEWCHAIN: if (!nft_trans_chain_update(trans) && nft_chain_binding(nft_trans_chain(trans))) list_add_tail(&binding->binding_list, &nft_net->binding_list); break; } } static void nft_trans_commit_list_add_elem(struct net *net, struct nft_trans *trans, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); WARN_ON_ONCE(trans->msg_type != NFT_MSG_NEWSETELEM && trans->msg_type != NFT_MSG_DELSETELEM); might_alloc(gfp); if (nft_trans_try_collapse(nft_net, trans, gfp)) { kfree(trans); return; } nft_trans_commit_list_add_tail(net, trans); } static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_table)); if (trans == NULL) return -ENOMEM; if (msg_type == NFT_MSG_NEWTABLE) nft_activate_next(ctx->net, ctx->table); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int nft_deltable(struct nft_ctx *ctx) { int err; err = nft_trans_table_add(ctx, NFT_MSG_DELTABLE); if (err < 0) return err; nft_deactivate_next(ctx->net, ctx->table); return err; } static struct nft_trans * nft_trans_alloc_chain(const struct nft_ctx *ctx, int msg_type) { struct nft_trans_chain *trans_chain; struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_chain)); if (!trans) return NULL; trans_chain = nft_trans_container_chain(trans); INIT_LIST_HEAD(&trans_chain->nft_trans_binding.binding_list); trans_chain->chain = ctx->chain; return trans; } static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; trans = nft_trans_alloc_chain(ctx, msg_type); if (trans == NULL) return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWCHAIN) { nft_activate_next(ctx->net, ctx->chain); if (ctx->nla[NFTA_CHAIN_ID]) { nft_trans_chain_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); } } nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } static int nft_delchain(struct nft_ctx *ctx) { struct nft_trans *trans; trans = nft_trans_chain_add(ctx, NFT_MSG_DELCHAIN); if (IS_ERR(trans)) return PTR_ERR(trans); nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return 0; } void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->activate) expr->ops->activate(ctx, expr); expr = nft_expr_next(expr); } } void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->deactivate) expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } } static int nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) { /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; } static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, struct nft_rule *rule) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_rule)); if (trans == NULL) return NULL; if (msg_type == NFT_MSG_NEWRULE && ctx->nla[NFTA_RULE_ID] != NULL) { nft_trans_rule_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; nft_trans_rule_chain(trans) = ctx->chain; nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_flow_rule *flow; struct nft_trans *trans; int err; trans = nft_trans_rule_add(ctx, NFT_MSG_DELRULE, rule); if (trans == NULL) return -ENOMEM; if (ctx->chain->flags & NFT_CHAIN_HW_OFFLOAD) { flow = nft_flow_rule_create(ctx->net, rule); if (IS_ERR(flow)) { nft_trans_destroy(trans); return PTR_ERR(flow); } nft_trans_flow_rule(trans) = flow; } err = nf_tables_delrule_deactivate(ctx, rule); if (err < 0) { nft_trans_destroy(trans); return err; } nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } static int nft_delrule_by_chain(struct nft_ctx *ctx) { struct nft_rule *rule; int err; list_for_each_entry(rule, &ctx->chain->rules, list) { if (!nft_is_active_next(ctx->net, rule)) continue; err = nft_delrule(ctx, rule); if (err < 0) return err; } return 0; } static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, struct nft_set *set, const struct nft_set_desc *desc) { struct nft_trans_set *trans_set; struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set)); if (trans == NULL) return -ENOMEM; trans_set = nft_trans_container_set(trans); INIT_LIST_HEAD(&trans_set->nft_trans_binding.binding_list); INIT_LIST_HEAD(&trans_set->list_trans_newset); if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) { nft_trans_set_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID])); nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; if (desc) { nft_trans_set_update(trans) = true; nft_trans_set_gc_int(trans) = desc->gc_int; nft_trans_set_timeout(trans) = desc->timeout; nft_trans_set_size(trans) = desc->size; } nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, struct nft_set *set) { return __nft_trans_set_add(ctx, msg_type, set, NULL); } static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (!nft_set_elem_active(ext, iter->genmask)) return 0; nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; } struct nft_set_elem_catchall { struct list_head list; struct rcu_head rcu; struct nft_elem_priv *elem; }; static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } } static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), .type = NFT_ITER_UPDATE, .fn = nft_mapelem_deactivate, }; set->ops->walk(ctx, set, &iter); WARN_ON_ONCE(iter.err); nft_map_catchall_deactivate(ctx, set); } static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; err = nft_trans_set_add(ctx, NFT_MSG_DELSET, set); if (err < 0) return err; if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); nft_use_dec(&ctx->table->use); return err; } static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, struct nft_object *obj) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_obj)); if (trans == NULL) return -ENOMEM; if (msg_type == NFT_MSG_NEWOBJ) nft_activate_next(ctx->net, obj); nft_trans_obj(trans) = obj; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) { int err; err = nft_trans_obj_add(ctx, NFT_MSG_DELOBJ, obj); if (err < 0) return err; nft_deactivate_next(ctx->net, obj); nft_use_dec(&ctx->table->use); return err; } static struct nft_trans * nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_flowtable)); if (trans == NULL) return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } static int nft_delflowtable(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); if (IS_ERR(trans)) return PTR_ERR(trans); nft_deactivate_next(ctx->net, flowtable); nft_use_dec(&ctx->table->use); return 0; } static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) { int i; for (i = track->regs[dreg].num_reg; i > 0; i--) __nft_reg_track_cancel(track, dreg - i); } static void __nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 num_reg) { track->regs[dreg].selector = expr; track->regs[dreg].bitwise = NULL; track->regs[dreg].num_reg = num_reg; } void nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 len) { unsigned int regcount; int i; __nft_reg_track_clobber(track, dreg); regcount = DIV_ROUND_UP(len, NFT_REG32_SIZE); for (i = 0; i < regcount; i++, dreg++) __nft_reg_track_update(track, expr, dreg, i); } EXPORT_SYMBOL_GPL(nft_reg_track_update); void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len) { unsigned int regcount; int i; __nft_reg_track_clobber(track, dreg); regcount = DIV_ROUND_UP(len, NFT_REG32_SIZE); for (i = 0; i < regcount; i++, dreg++) __nft_reg_track_cancel(track, dreg); } EXPORT_SYMBOL_GPL(nft_reg_track_cancel); void __nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg) { track->regs[dreg].selector = NULL; track->regs[dreg].bitwise = NULL; track->regs[dreg].num_reg = 0; } EXPORT_SYMBOL_GPL(__nft_reg_track_cancel); /* * Tables */ static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, u8 family, u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); nft_net = nft_pernet(net); list_for_each_entry_rcu(table, &nft_net->tables, list, lockdep_is_held(&nft_net->commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && nlpid && table->nlpid != nlpid) return ERR_PTR(-EPERM); return table; } } return ERR_PTR(-ENOENT); } static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, int family, u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && nlpid && table->nlpid != nlpid) return ERR_PTR(-EPERM); return table; } } return ERR_PTR(-ENOENT); } static inline u64 nf_tables_alloc_handle(struct nft_table *table) { return ++table->hgenerator; } static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; static const struct nft_chain_type * __nft_chain_type_get(u8 family, enum nft_chain_types type) { if (family >= NFPROTO_NUMPROTO || type >= NFT_CHAIN_T_MAX) return NULL; return chain_type[family][type]; } static const struct nft_chain_type * __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) { const struct nft_chain_type *type; int i; for (i = 0; i < NFT_CHAIN_T_MAX; i++) { type = __nft_chain_type_get(family, i); if (!type) continue; if (!nla_strcmp(nla, type->name)) return type; } return NULL; } struct nft_module_request { struct list_head list; char module[MODULE_NAME_LEN]; bool done; }; #ifdef CONFIG_MODULES __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; struct nftables_pernet *nft_net; struct nft_module_request *req; va_list args; int ret; va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) return 0; nft_net = nft_pernet(net); list_for_each_entry(req, &nft_net->module_list, list) { if (!strcmp(req->module, module_name)) { if (req->done) return 0; /* A request to load this module already exists. */ return -EAGAIN; } } req = kmalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; req->done = false; strscpy(req->module, module_name, MODULE_NAME_LEN); list_add_tail(&req->list, &nft_net->module_list); return -EAGAIN; } EXPORT_SYMBOL_GPL(nft_request_module); #endif static void lockdep_nfnl_nft_mutex_not_held(void) { #ifdef CONFIG_PROVE_LOCKING if (debug_locks) WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); #endif } static const struct nft_chain_type * nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, u8 family, bool autoload) { const struct nft_chain_type *type; type = __nf_tables_chain_type_lookup(nla, family); if (type != NULL) return type; lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (autoload) { if (nft_request_module(net, "nft-chain-%u-%.*s", family, nla_len(nla), (const char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } static __be16 nft_base_seq(const struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); return htons(nft_net->base_seq & 0xffff); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { [NFTA_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, [NFTA_TABLE_HANDLE] = { .type = NLA_U64 }, [NFTA_TABLE_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN } }; static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table) { struct nlmsghdr *nlh; nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) || nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle), NFTA_TABLE_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELTABLE || event == NFT_MSG_DESTROYTABLE) { nlmsg_end(skb, nlh); return 0; } if (nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags & NFT_TABLE_F_MASK))) goto nla_put_failure; if (nft_table_has_owner(table) && nla_put_be32(skb, NFTA_TABLE_OWNER, htonl(table->nlpid))) goto nla_put_failure; if (table->udata) { if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata)) goto nla_put_failure; } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } struct nftnl_skb_parms { bool report; }; #define NFT_CB(skb) (*(struct nftnl_skb_parms*)&((skb)->cb)) static void nft_notify_enqueue(struct sk_buff *skb, bool report, struct list_head *notify_list) { NFT_CB(skb).report = report; list_add_tail(&skb->list, notify_list); } static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table); if (err < 0) { kfree_skb(skb); goto err; } nft_net = nft_pernet(ctx->net); nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_dump_tables(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; if (idx < s_idx) goto cont; if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (!nft_is_active(net, table)) continue; if (nf_tables_fill_table_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWTABLE, NLM_F_MULTI, table->family, table) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } done: rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *c) { int err; if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); err = netlink_dump_start(nlsk, skb, nlh, c); rcu_read_lock(); module_put(THIS_MODULE); return err; } /* called with rcu_read_lock held */ static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_tables, .module = THIS_MODULE, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]); return PTR_ERR(table); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; err = nf_tables_fill_table_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0, family, table); if (err < 0) goto err_fill_table_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_table_info: kfree_skb(skb2); return err; } static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt) { struct nft_chain *chain; u32 i = 0; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; if (!nft_is_base_chain(chain)) continue; if (cnt && i++ == cnt) break; nf_tables_unregister_hook(net, table, chain); } } static int nf_tables_table_enable(struct net *net, struct nft_table *table) { struct nft_chain *chain; int err, i = 0; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; if (!nft_is_base_chain(chain)) continue; err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err_register_hooks; i++; } return 0; err_register_hooks: if (i) nft_table_disable(net, table, i); return err; } static void nf_tables_table_disable(struct net *net, struct nft_table *table) { table->flags &= ~NFT_TABLE_F_DORMANT; nft_table_disable(net, table, 0); table->flags |= NFT_TABLE_F_DORMANT; } #define __NFT_TABLE_F_INTERNAL (NFT_TABLE_F_MASK + 1) #define __NFT_TABLE_F_WAS_DORMANT (__NFT_TABLE_F_INTERNAL << 0) #define __NFT_TABLE_F_WAS_AWAKEN (__NFT_TABLE_F_INTERNAL << 1) #define __NFT_TABLE_F_WAS_ORPHAN (__NFT_TABLE_F_INTERNAL << 2) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN | \ __NFT_TABLE_F_WAS_ORPHAN) static bool nft_table_pending_update(const struct nft_ctx *ctx) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_trans *trans; if (ctx->table->flags & __NFT_TABLE_F_UPDATE) return true; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->table == ctx->table && ((trans->msg_type == NFT_MSG_NEWCHAIN && nft_trans_chain_update(trans)) || (trans->msg_type == NFT_MSG_DELCHAIN && nft_is_base_chain(nft_trans_chain(trans))))) return true; } return false; } static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; u32 flags; int ret; if (!ctx->nla[NFTA_TABLE_FLAGS]) return 0; flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS])); if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; if ((nft_table_has_owner(ctx->table) && !(flags & NFT_TABLE_F_OWNER)) || (flags & NFT_TABLE_F_OWNER && !nft_table_is_orphan(ctx->table))) return -EOPNOTSUPP; if ((flags ^ ctx->table->flags) & NFT_TABLE_F_PERSIST) return -EOPNOTSUPP; /* No dormant off/on/off/on games in single transaction */ if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) return -ENOMEM; if ((flags & NFT_TABLE_F_DORMANT) && !(ctx->table->flags & NFT_TABLE_F_DORMANT)) { ctx->table->flags |= NFT_TABLE_F_DORMANT; if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) ctx->table->flags |= __NFT_TABLE_F_WAS_AWAKEN; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { ctx->table->flags &= ~NFT_TABLE_F_DORMANT; if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) { ret = nf_tables_table_enable(ctx->net, ctx->table); if (ret < 0) goto err_register_hooks; ctx->table->flags |= __NFT_TABLE_F_WAS_DORMANT; } } if ((flags & NFT_TABLE_F_OWNER) && !nft_table_has_owner(ctx->table)) { ctx->table->nlpid = ctx->portid; ctx->table->flags |= NFT_TABLE_F_OWNER | __NFT_TABLE_F_WAS_ORPHAN; } nft_trans_table_update(trans) = true; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_register_hooks: ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } static u32 nft_chain_hash(const void *data, u32 len, u32 seed) { const char *name = data; return jhash(name, strlen(name), seed); } static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed) { const struct nft_chain *chain = data; return nft_chain_hash(chain->name, 0, seed); } static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct nft_chain *chain = ptr; const char *name = arg->key; return strcmp(chain->name, name); } static u32 nft_objname_hash(const void *data, u32 len, u32 seed) { const struct nft_object_hash_key *k = data; seed ^= hash_ptr(k->table, 32); return jhash(k->name, strlen(k->name), seed); } static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed) { const struct nft_object *obj = data; return nft_objname_hash(&obj->key, 0, seed); } static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct nft_object_hash_key *k = arg->key; const struct nft_object *obj = ptr; if (obj->key.table != k->table) return -1; return strcmp(obj->key.name, k->name); } static bool nft_supported_family(u8 family) { return false #ifdef CONFIG_NF_TABLES_INET || family == NFPROTO_INET #endif #ifdef CONFIG_NF_TABLES_IPV4 || family == NFPROTO_IPV4 #endif #ifdef CONFIG_NF_TABLES_ARP || family == NFPROTO_ARP #endif #ifdef CONFIG_NF_TABLES_NETDEV || family == NFPROTO_NETDEV #endif #if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) || family == NFPROTO_BRIDGE #endif #ifdef CONFIG_NF_TABLES_IPV6 || family == NFPROTO_IPV6 #endif ; } static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; u32 flags = 0; int err; if (!nft_supported_family(family)) return -EOPNOTSUPP; lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); } else { if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nf_tables_updtable(&ctx); } if (nla[NFTA_TABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; } err = -ENOMEM; table = kzalloc(sizeof(*table), GFP_KERNEL_ACCOUNT); if (table == NULL) goto err_kzalloc; table->validate_state = nft_net->validate_state; table->name = nla_strdup(attr, GFP_KERNEL_ACCOUNT); if (table->name == NULL) goto err_strdup; if (nla[NFTA_TABLE_USERDATA]) { table->udata = nla_memdup(nla[NFTA_TABLE_USERDATA], GFP_KERNEL_ACCOUNT); if (table->udata == NULL) goto err_table_udata; table->udlen = nla_len(nla[NFTA_TABLE_USERDATA]); } err = rhltable_init(&table->chains_ht, &nft_chain_ht_params); if (err) goto err_chain_ht; INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); INIT_LIST_HEAD(&table->flowtables); table->family = family; table->flags = flags; table->handle = ++nft_net->table_handle; if (table->flags & NFT_TABLE_F_OWNER) table->nlpid = NETLINK_CB(skb).portid; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) goto err_trans; list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: rhltable_destroy(&table->chains_ht); err_chain_ht: kfree(table->udata); err_table_udata: kfree(table->name); err_strdup: kfree(table); err_kzalloc: return err; } static int nft_flush_table(struct nft_ctx *ctx) { struct nft_flowtable *flowtable, *nft; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_set *set, *ns; int err; list_for_each_entry(chain, &ctx->table->chains, list) { if (!nft_is_active_next(ctx->net, chain)) continue; if (nft_chain_binding(chain)) continue; ctx->chain = chain; err = nft_delrule_by_chain(ctx); if (err < 0) goto out; } list_for_each_entry_safe(set, ns, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, set)) continue; if (nft_set_is_anonymous(set)) continue; err = nft_delset(ctx, set); if (err < 0) goto out; } list_for_each_entry_safe(flowtable, nft, &ctx->table->flowtables, list) { if (!nft_is_active_next(ctx->net, flowtable)) continue; err = nft_delflowtable(ctx, flowtable); if (err < 0) goto out; } list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) { if (!nft_is_active_next(ctx->net, obj)) continue; err = nft_delobj(ctx, obj); if (err < 0) goto out; } list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) { if (!nft_is_active_next(ctx->net, chain)) continue; if (nft_chain_binding(chain)) continue; ctx->chain = chain; err = nft_delchain(ctx); if (err < 0) goto out; } err = nft_deltable(ctx); out: return err; } static int nft_flush(struct nft_ctx *ctx, int family) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nlattr * const *nla = ctx->nla; struct nft_table *table, *nt; int err = 0; list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (family != AF_UNSPEC && table->family != family) continue; ctx->family = table->family; if (!nft_is_active_next(ctx->net, table)) continue; if (nft_table_has_owner(table) && table->nlpid != ctx->portid) continue; if (nla[NFTA_TABLE_NAME] && nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0) continue; ctx->table = table; err = nft_flush_table(ctx); if (err < 0) goto out; } out: return err; } static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; nft_ctx_init(&ctx, net, skb, info->nlh, 0, NULL, NULL, nla); if (family == AF_UNSPEC || (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE])) return nft_flush(&ctx, family); if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; table = nft_table_lookup_byhandle(net, attr, family, genmask, NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, NETLINK_CB(skb).portid); } if (IS_ERR(table)) { if (PTR_ERR(table) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYTABLE) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(table); } if (info->nlh->nlmsg_flags & NLM_F_NONREC && table->use > 0) return -EBUSY; ctx.family = family; ctx.table = table; return nft_flush_table(&ctx); } static void nf_tables_table_destroy(struct nft_table *table) { if (WARN_ON(table->use > 0)) return; rhltable_destroy(&table->chains_ht); kfree(table->name); kfree(table->udata); kfree(table); } void nft_register_chain_type(const struct nft_chain_type *ctype) { nfnl_lock(NFNL_SUBSYS_NFTABLES); if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); return; } chain_type[ctype->family][ctype->type] = ctype; nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_register_chain_type); void nft_unregister_chain_type(const struct nft_chain_type *ctype) { nfnl_lock(NFNL_SUBSYS_NFTABLES); chain_type[ctype->family][ctype->type] = NULL; nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_chain_type); /* * Chains */ static struct nft_chain * nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) { struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) { if (chain->handle == handle && nft_active_genmask(chain, genmask)) return chain; } return ERR_PTR(-ENOENT); } static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING struct nftables_pernet *nft_net = nft_pernet(net); return lockdep_is_held(&nft_net->commit_mutex); #else return true; #endif } static struct nft_chain *nft_chain_lookup(struct net *net, struct nft_table *table, const struct nlattr *nla, u8 genmask) { char search[NFT_CHAIN_MAXNAMELEN + 1]; struct rhlist_head *tmp, *list; struct nft_chain *chain; if (nla == NULL) return ERR_PTR(-EINVAL); nla_strscpy(search, nla, sizeof(search)); WARN_ON(!rcu_read_lock_held() && !lockdep_commit_lock_is_held(net)); chain = ERR_PTR(-ENOENT); rcu_read_lock(); list = rhltable_lookup(&table->chains_ht, search, nft_chain_ht_params); if (!list) goto out_unlock; rhl_for_each_entry_rcu(chain, tmp, list, rhlhead) { if (nft_active_genmask(chain, genmask)) goto out_unlock; } chain = ERR_PTR(-ENOENT); out_unlock: rcu_read_unlock(); return chain; } static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { [NFTA_CHAIN_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_CHAIN_HANDLE] = { .type = NLA_U64 }, [NFTA_CHAIN_NAME] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_CHAIN_HOOK] = { .type = NLA_NESTED }, [NFTA_CHAIN_POLICY] = { .type = NLA_U32 }, [NFTA_CHAIN_TYPE] = { .type = NLA_STRING, .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED }, [NFTA_CHAIN_FLAGS] = { .type = NLA_U32 }, [NFTA_CHAIN_ID] = { .type = NLA_U32 }, [NFTA_CHAIN_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, }; static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = { [NFTA_HOOK_HOOKNUM] = { .type = NLA_U32 }, [NFTA_HOOK_PRIORITY] = { .type = NLA_U32 }, [NFTA_HOOK_DEV] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) { struct nft_stats *cpu_stats, total; struct nlattr *nest; unsigned int seq; u64 pkts, bytes; int cpu; if (!stats) return 0; memset(&total, 0, sizeof(total)); for_each_possible_cpu(cpu) { cpu_stats = per_cpu_ptr(stats, cpu); do { seq = u64_stats_fetch_begin(&cpu_stats->syncp); pkts = cpu_stats->pkts; bytes = cpu_stats->bytes; } while (u64_stats_fetch_retry(&cpu_stats->syncp, seq)); total.pkts += pkts; total.bytes += bytes; } nest = nla_nest_start_noflag(skb, NFTA_CHAIN_COUNTERS); if (nest == NULL) goto nla_put_failure; if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.pkts), NFTA_COUNTER_PAD) || nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes), NFTA_COUNTER_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: return -ENOSPC; } static int nft_dump_basechain_hook(struct sk_buff *skb, const struct net *net, int family, const struct nft_base_chain *basechain, const struct list_head *hook_list) { const struct nf_hook_ops *ops = &basechain->ops; struct nft_hook *hook, *first = NULL; struct nlattr *nest, *nest_devs; int n = 0; nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK); if (nest == NULL) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority))) goto nla_put_failure; if (nft_base_chain_netdev(family, ops->hooknum)) { nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS); if (!nest_devs) goto nla_put_failure; if (!hook_list) hook_list = &basechain->hook_list; list_for_each_entry_rcu(hook, hook_list, list, lockdep_commit_lock_is_held(net)) { if (!first) first = hook; if (nla_put(skb, NFTA_DEVICE_NAME, hook->ifnamelen, hook->ifname)) goto nla_put_failure; n++; } nla_nest_end(skb, nest_devs); if (n == 1 && nla_put(skb, NFTA_HOOK_DEV, first->ifnamelen, first->ifname)) goto nla_put_failure; } nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, const struct list_head *hook_list) { struct nlmsghdr *nlh; nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name) || nla_put_string(skb, NFTA_CHAIN_NAME, chain->name) || nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle), NFTA_CHAIN_PAD)) goto nla_put_failure; if (!hook_list && (event == NFT_MSG_DELCHAIN || event == NFT_MSG_DESTROYCHAIN)) { nlmsg_end(skb, nlh); return 0; } if (nft_is_base_chain(chain)) { const struct nft_base_chain *basechain = nft_base_chain(chain); struct nft_stats __percpu *stats; if (nft_dump_basechain_hook(skb, net, family, basechain, hook_list)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CHAIN_POLICY, htonl(basechain->policy))) goto nla_put_failure; if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; stats = rcu_dereference_check(basechain->stats, lockdep_commit_lock_is_held(net)); if (nft_dump_stats(skb, stats)) goto nla_put_failure; } if (chain->flags && nla_put_be32(skb, NFTA_CHAIN_FLAGS, htonl(chain->flags))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) goto nla_put_failure; if (chain->udata && nla_put(skb, NFTA_CHAIN_USERDATA, chain->udlen, chain->udata)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event, const struct list_head *hook_list) { struct nftables_pernet *nft_net; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, ctx->chain, hook_list); if (err < 0) { kfree_skb(skb); goto err; } nft_net = nft_pernet(ctx->net); nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_dump_chains(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; const struct nft_table *table; const struct nft_chain *chain; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; list_for_each_entry_rcu(chain, &table->chains, list) { if (idx < s_idx) goto cont; if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (!nft_is_active(net, chain)) continue; if (nf_tables_fill_chain_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, NLM_F_MULTI, table->family, table, chain, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } } done: rcu_read_unlock(); cb->args[0] = idx; return skb->len; } /* called with rcu_read_lock held */ static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_chains, .module = THIS_MODULE, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); } chain = nft_chain_lookup(net, table, nla[NFTA_CHAIN_NAME], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return PTR_ERR(chain); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0, family, table, chain, NULL); if (err < 0) goto err_fill_chain_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_chain_info: kfree_skb(skb2); return err; } static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = { [NFTA_COUNTER_PACKETS] = { .type = NLA_U64 }, [NFTA_COUNTER_BYTES] = { .type = NLA_U64 }, }; static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) { struct nlattr *tb[NFTA_COUNTER_MAX+1]; struct nft_stats __percpu *newstats; struct nft_stats *stats; int err; err = nla_parse_nested_deprecated(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy, NULL); if (err < 0) return ERR_PTR_PCPU(err); if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS]) return ERR_PTR_PCPU(-EINVAL); newstats = netdev_alloc_pcpu_stats(struct nft_stats); if (newstats == NULL) return ERR_PTR_PCPU(-ENOMEM); /* Restore old counters on this cpu, no problem. Per-cpu statistics * are not exposed to userspace. */ preempt_disable(); stats = this_cpu_ptr(newstats); stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); preempt_enable(); return newstats; } static void nft_chain_stats_replace(struct nft_trans_chain *trans) { const struct nft_trans *t = &trans->nft_trans_binding.nft_trans; struct nft_base_chain *chain = nft_base_chain(trans->chain); if (!trans->stats) return; trans->stats = rcu_replace_pointer(chain->stats, trans->stats, lockdep_commit_lock_is_held(t->net)); if (!trans->stats) static_branch_inc(&nft_counters_enabled); } static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) { struct nft_rule_blob *g0 = rcu_dereference_raw(chain->blob_gen_0); struct nft_rule_blob *g1 = rcu_dereference_raw(chain->blob_gen_1); if (g0 != g1) kvfree(g1); kvfree(g0); /* should be NULL either via abort or via successful commit */ WARN_ON_ONCE(chain->blob_next); kvfree(chain->blob_next); } void nf_tables_chain_destroy(struct nft_chain *chain) { const struct nft_table *table = chain->table; struct nft_hook *hook, *next; if (WARN_ON(chain->use > 0)) return; /* no concurrent access possible anymore */ nf_tables_chain_free_chain_rules(chain); if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, &basechain->hook_list, list) { list_del_rcu(&hook->list); nft_netdev_hook_free_rcu(hook); } } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { static_branch_dec(&nft_counters_enabled); free_percpu(rcu_dereference_raw(basechain->stats)); } kfree(chain->name); kfree(chain->udata); kfree(basechain); } else { kfree(chain->name); kfree(chain->udata); kfree(chain); } } static struct nft_hook *nft_netdev_hook_alloc(struct net *net, const struct nlattr *attr) { struct nf_hook_ops *ops; struct net_device *dev; struct nft_hook *hook; int err; hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&hook->ops_list); err = nla_strscpy(hook->ifname, attr, IFNAMSIZ); if (err < 0) goto err_hook_free; hook->ifnamelen = nla_len(attr); /* nf_tables_netdev_event() is called under rtnl_mutex, this is * indirectly serializing all the other holders of the commit_mutex with * the rtnl_mutex. */ for_each_netdev(net, dev) { if (strncmp(dev->name, hook->ifname, hook->ifnamelen)) continue; ops = kzalloc(sizeof(struct nf_hook_ops), GFP_KERNEL_ACCOUNT); if (!ops) { err = -ENOMEM; goto err_hook_free; } ops->dev = dev; list_add_tail(&ops->list, &hook->ops_list); } return hook; err_hook_free: nft_netdev_hook_free(hook); return ERR_PTR(err); } static struct nft_hook *nft_hook_list_find(struct list_head *hook_list, const struct nft_hook *this) { struct nft_hook *hook; list_for_each_entry(hook, hook_list, list) { if (!strncmp(hook->ifname, this->ifname, min(hook->ifnamelen, this->ifnamelen))) return hook; } return NULL; } static int nf_tables_parse_netdev_hooks(struct net *net, const struct nlattr *attr, struct list_head *hook_list, struct netlink_ext_ack *extack) { struct nft_hook *hook, *next; const struct nlattr *tmp; int rem, n = 0, err; nla_for_each_nested(tmp, attr, rem) { if (nla_type(tmp) != NFTA_DEVICE_NAME) { err = -EINVAL; goto err_hook; } hook = nft_netdev_hook_alloc(net, tmp); if (IS_ERR(hook)) { NL_SET_BAD_ATTR(extack, tmp); err = PTR_ERR(hook); goto err_hook; } if (nft_hook_list_find(hook_list, hook)) { NL_SET_BAD_ATTR(extack, tmp); nft_netdev_hook_free(hook); err = -EEXIST; goto err_hook; } list_add_tail(&hook->list, hook_list); n++; if (n == NFT_NETDEVICE_MAX) { err = -EFBIG; goto err_hook; } } return 0; err_hook: list_for_each_entry_safe(hook, next, hook_list, list) { list_del(&hook->list); nft_netdev_hook_free(hook); } return err; } struct nft_chain_hook { u32 num; s32 priority; const struct nft_chain_type *type; struct list_head list; }; static int nft_chain_parse_netdev(struct net *net, struct nlattr *tb[], struct list_head *hook_list, struct netlink_ext_ack *extack, u32 flags) { struct nft_hook *hook; int err; if (tb[NFTA_HOOK_DEV]) { hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV]); if (IS_ERR(hook)) { NL_SET_BAD_ATTR(extack, tb[NFTA_HOOK_DEV]); return PTR_ERR(hook); } list_add_tail(&hook->list, hook_list); } else if (tb[NFTA_HOOK_DEVS]) { err = nf_tables_parse_netdev_hooks(net, tb[NFTA_HOOK_DEVS], hook_list, extack); if (err < 0) return err; } if (flags & NFT_CHAIN_HW_OFFLOAD && list_empty(hook_list)) return -EINVAL; return 0; } static int nft_chain_parse_hook(struct net *net, struct nft_base_chain *basechain, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, u32 flags, struct netlink_ext_ack *extack) { struct nftables_pernet *nft_net = nft_pernet(net); struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; int err; lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); err = nla_parse_nested_deprecated(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK], nft_hook_policy, NULL); if (err < 0) return err; if (!basechain) { if (!ha[NFTA_HOOK_HOOKNUM] || !ha[NFTA_HOOK_PRIORITY]) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return -ENOENT; } hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); if (!type) return -EOPNOTSUPP; if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, true); if (IS_ERR(type)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return PTR_ERR(type); } } if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && hook->priority <= NF_IP_PRI_CONNTRACK) return -EOPNOTSUPP; } else { if (ha[NFTA_HOOK_HOOKNUM]) { hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); if (hook->num != basechain->ops.hooknum) return -EOPNOTSUPP; } if (ha[NFTA_HOOK_PRIORITY]) { hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); if (hook->priority != basechain->ops.priority) return -EOPNOTSUPP; } if (nla[NFTA_CHAIN_TYPE]) { type = __nf_tables_chain_type_lookup(nla[NFTA_CHAIN_TYPE], family); if (!type) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return -ENOENT; } } else { type = basechain->type; } } if (!try_module_get(type->owner)) { if (nla[NFTA_CHAIN_TYPE]) NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return -ENOENT; } hook->type = type; INIT_LIST_HEAD(&hook->list); if (nft_base_chain_netdev(family, hook->num)) { err = nft_chain_parse_netdev(net, ha, &hook->list, extack, flags); if (err < 0) { module_put(type->owner); return err; } } else if (ha[NFTA_HOOK_DEV] || ha[NFTA_HOOK_DEVS]) { module_put(type->owner); return -EOPNOTSUPP; } return 0; } static void nft_chain_release_hook(struct nft_chain_hook *hook) { struct nft_hook *h, *next; list_for_each_entry_safe(h, next, &hook->list, list) { list_del(&h->list); nft_netdev_hook_free(h); } module_put(hook->type->owner); } static void nft_last_rule(const struct nft_chain *chain, const void *ptr) { struct nft_rule_dp_last *lrule; BUILD_BUG_ON(offsetof(struct nft_rule_dp_last, end) != 0); lrule = (struct nft_rule_dp_last *)ptr; lrule->end.is_last = 1; lrule->chain = chain; /* blob size does not include the trailer rule */ } static struct nft_rule_blob *nf_tables_chain_alloc_rules(const struct nft_chain *chain, unsigned int size) { struct nft_rule_blob *blob; if (size > INT_MAX) return NULL; size += sizeof(struct nft_rule_blob) + sizeof(struct nft_rule_dp_last); blob = kvmalloc(size, GFP_KERNEL_ACCOUNT); if (!blob) return NULL; blob->size = 0; nft_last_rule(chain, blob->data); return blob; } static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family, const struct nft_chain_hook *hook, struct nft_chain *chain) { ops->pf = family; ops->hooknum = hook->num; ops->priority = hook->priority; ops->priv = chain; ops->hook = hook->type->hooks[ops->hooknum]; ops->hook_ops_type = NF_HOOK_OP_NF_TABLES; } static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, struct nft_chain_hook *hook, u32 flags) { struct nft_chain *chain; struct nf_hook_ops *ops; struct nft_hook *h; basechain->type = hook->type; INIT_LIST_HEAD(&basechain->hook_list); chain = &basechain->chain; if (nft_base_chain_netdev(family, hook->num)) { list_splice_init(&hook->list, &basechain->hook_list); list_for_each_entry(h, &basechain->hook_list, list) { list_for_each_entry(ops, &h->ops_list, list) nft_basechain_hook_init(ops, family, hook, chain); } } nft_basechain_hook_init(&basechain->ops, family, hook, chain); chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; if (chain->flags & NFT_CHAIN_HW_OFFLOAD && !nft_chain_offload_support(basechain)) { list_splice_init(&basechain->hook_list, &hook->list); return -EOPNOTSUPP; } flow_block_init(&basechain->flow_block); return 0; } int nft_chain_add(struct nft_table *table, struct nft_chain *chain) { int err; err = rhltable_insert_key(&table->chains_ht, chain->name, &chain->rhlhead, nft_chain_ht_params); if (err) return err; list_add_tail_rcu(&chain->list, &table->chains); return 0; } static u64 chain_id; static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 policy, u32 flags, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; struct nft_base_chain *basechain; struct net *net = ctx->net; char name[NFT_NAME_MAXLEN]; struct nft_rule_blob *blob; struct nft_trans *trans; struct nft_chain *chain; int err; if (nla[NFTA_CHAIN_HOOK]) { struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook = {}; if (table->flags & __NFT_TABLE_F_UPDATE) return -EINVAL; if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; err = nft_chain_parse_hook(net, NULL, nla, &hook, family, flags, extack); if (err < 0) return err; basechain = kzalloc(sizeof(*basechain), GFP_KERNEL_ACCOUNT); if (basechain == NULL) { nft_chain_release_hook(&hook); return -ENOMEM; } chain = &basechain->chain; if (nla[NFTA_CHAIN_COUNTERS]) { stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); if (IS_ERR_PCPU(stats)) { nft_chain_release_hook(&hook); kfree(basechain); return PTR_ERR_PCPU(stats); } rcu_assign_pointer(basechain->stats, stats); } err = nft_basechain_init(basechain, family, &hook, flags); if (err < 0) { nft_chain_release_hook(&hook); kfree(basechain); free_percpu(stats); return err; } if (stats) static_branch_inc(&nft_counters_enabled); } else { if (flags & NFT_CHAIN_BASE) return -EINVAL; if (flags & NFT_CHAIN_HW_OFFLOAD) return -EOPNOTSUPP; chain = kzalloc(sizeof(*chain), GFP_KERNEL_ACCOUNT); if (chain == NULL) return -ENOMEM; chain->flags = flags; } ctx->chain = chain; INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); chain->table = table; if (nla[NFTA_CHAIN_NAME]) { chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT); } else { if (!(flags & NFT_CHAIN_BINDING)) { err = -EINVAL; goto err_destroy_chain; } snprintf(name, sizeof(name), "__chain%llu", ++chain_id); chain->name = kstrdup(name, GFP_KERNEL_ACCOUNT); } if (!chain->name) { err = -ENOMEM; goto err_destroy_chain; } if (nla[NFTA_CHAIN_USERDATA]) { chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL_ACCOUNT); if (chain->udata == NULL) { err = -ENOMEM; goto err_destroy_chain; } chain->udlen = nla_len(nla[NFTA_CHAIN_USERDATA]); } blob = nf_tables_chain_alloc_rules(chain, 0); if (!blob) { err = -ENOMEM; goto err_destroy_chain; } RCU_INIT_POINTER(chain->blob_gen_0, blob); RCU_INIT_POINTER(chain->blob_gen_1, blob); if (!nft_use_inc(&table->use)) { err = -EMFILE; goto err_destroy_chain; } trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto err_trans; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; if (nft_is_base_chain(chain)) nft_trans_chain_policy(trans) = policy; err = nft_chain_add(table, chain); if (err < 0) goto err_chain_add; /* This must be LAST to ensure no packets are walking over this chain. */ err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err_register_hook; return 0; err_register_hook: nft_chain_del(chain); err_chain_add: nft_trans_destroy(trans); err_trans: nft_use_dec_restore(&table->use); err_destroy_chain: nf_tables_chain_destroy(chain); return err; } static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, u32 flags, const struct nlattr *attr, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_base_chain *basechain = NULL; struct nft_table *table = ctx->table; struct nft_chain *chain = ctx->chain; struct nft_chain_hook hook = {}; struct nft_stats __percpu *stats = NULL; struct nftables_pernet *nft_net; struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; bool unregister = false; int err; if (chain->flags ^ flags) return -EOPNOTSUPP; INIT_LIST_HEAD(&hook.list); if (nla[NFTA_CHAIN_HOOK]) { if (!nft_is_base_chain(chain)) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } basechain = nft_base_chain(chain); err = nft_chain_parse_hook(ctx->net, basechain, nla, &hook, ctx->family, flags, extack); if (err < 0) return err; if (basechain->type != hook.type) { nft_chain_release_hook(&hook); NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { list_for_each_entry_safe(h, next, &hook.list, list) { list_for_each_entry(ops, &h->ops_list, list) { ops->pf = basechain->ops.pf; ops->hooknum = basechain->ops.hooknum; ops->priority = basechain->ops.priority; ops->priv = basechain->ops.priv; ops->hook = basechain->ops.hook; } if (nft_hook_list_find(&basechain->hook_list, h)) { list_del(&h->list); nft_netdev_hook_free(h); continue; } nft_net = nft_pernet(ctx->net); list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type != NFT_MSG_NEWCHAIN || trans->table != ctx->table || !nft_trans_chain_update(trans)) continue; if (nft_hook_list_find(&nft_trans_chain_hooks(trans), h)) { nft_chain_release_hook(&hook); return -EEXIST; } } } } else { ops = &basechain->ops; if (ops->hooknum != hook.num || ops->priority != hook.priority) { nft_chain_release_hook(&hook); NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } } } if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { struct nft_chain *chain2; chain2 = nft_chain_lookup(ctx->net, table, nla[NFTA_CHAIN_NAME], genmask); if (!IS_ERR(chain2)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); err = -EEXIST; goto err_hooks; } } if (table->flags & __NFT_TABLE_F_UPDATE && !list_empty(&hook.list)) { NL_SET_BAD_ATTR(extack, attr); err = -EOPNOTSUPP; goto err_hooks; } if (!(table->flags & NFT_TABLE_F_DORMANT) && nft_is_base_chain(chain) && !list_empty(&hook.list)) { basechain = nft_base_chain(chain); ops = &basechain->ops; if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { err = nft_netdev_register_hooks(ctx->net, &hook.list); if (err < 0) goto err_hooks; unregister = true; } } if (nla[NFTA_CHAIN_COUNTERS]) { if (!nft_is_base_chain(chain)) { err = -EOPNOTSUPP; goto err_hooks; } stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); if (IS_ERR_PCPU(stats)) { err = PTR_ERR_PCPU(stats); goto err_hooks; } } err = -ENOMEM; trans = nft_trans_alloc_chain(ctx, NFT_MSG_NEWCHAIN); if (trans == NULL) goto err_trans; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; if (nla[NFTA_CHAIN_POLICY]) nft_trans_chain_policy(trans) = policy; else nft_trans_chain_policy(trans) = -1; if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_trans *tmp; char *name; err = -ENOMEM; name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT); if (!name) goto err_trans; err = -EEXIST; list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && tmp->table == table && nft_trans_chain_update(tmp) && nft_trans_chain_name(tmp) && strcmp(name, nft_trans_chain_name(tmp)) == 0) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); kfree(name); goto err_trans; } } nft_trans_chain_name(trans) = name; } nft_trans_basechain(trans) = basechain; INIT_LIST_HEAD(&nft_trans_chain_hooks(trans)); list_splice(&hook.list, &nft_trans_chain_hooks(trans)); if (nla[NFTA_CHAIN_HOOK]) module_put(hook.type->owner); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_trans: free_percpu(stats); kfree(trans); err_hooks: if (nla[NFTA_CHAIN_HOOK]) { list_for_each_entry_safe(h, next, &hook.list, list) { if (unregister) { list_for_each_entry(ops, &h->ops_list, list) nf_unregister_net_hook(ctx->net, ops); } list_del(&h->list); nft_netdev_hook_free_rcu(h); } module_put(hook.type->owner); } return err; } static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWCHAIN && nft_trans_chain(trans)->table == table && id == nft_trans_chain_id(trans) && nft_active_genmask(nft_trans_chain(trans), genmask)) return nft_trans_chain(trans); } return ERR_PTR(-ENOENT); } static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; u8 policy = NF_ACCEPT; struct nft_ctx ctx; u64 handle = 0; u32 flags = 0; lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); } chain = NULL; attr = nla[NFTA_CHAIN_NAME]; if (nla[NFTA_CHAIN_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); chain = nft_chain_lookup_byhandle(table, handle, genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_HANDLE]); return PTR_ERR(chain); } attr = nla[NFTA_CHAIN_HANDLE]; } else if (nla[NFTA_CHAIN_NAME]) { chain = nft_chain_lookup(net, table, attr, genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) != -ENOENT) { NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); } chain = NULL; } } else if (!nla[NFTA_CHAIN_ID]) { return -EINVAL; } if (nla[NFTA_CHAIN_POLICY]) { if (chain != NULL && !nft_is_base_chain(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; } if (chain == NULL && nla[NFTA_CHAIN_HOOK] == NULL) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; } policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY])); switch (policy) { case NF_DROP: case NF_ACCEPT: break; default: return -EINVAL; } } if (nla[NFTA_CHAIN_FLAGS]) flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS])); else if (chain) flags = chain->flags; if (flags & ~NFT_CHAIN_FLAGS) return -EOPNOTSUPP; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain != NULL) { if (chain->flags & NFT_CHAIN_BINDING) return -EINVAL; if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; flags |= chain->flags & NFT_CHAIN_BASE; return nf_tables_updchain(&ctx, genmask, policy, flags, attr, extack); } return nf_tables_addchain(&ctx, family, policy, flags, extack); } static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { const struct nft_chain *chain = &basechain->chain; const struct nlattr * const *nla = ctx->nla; struct nft_chain_hook chain_hook = {}; struct nft_hook *this, *hook; LIST_HEAD(chain_del_list); struct nft_trans *trans; int err; if (ctx->table->flags & __NFT_TABLE_F_UPDATE) return -EOPNOTSUPP; err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook, ctx->family, chain->flags, extack); if (err < 0) return err; list_for_each_entry(this, &chain_hook.list, list) { hook = nft_hook_list_find(&basechain->hook_list, this); if (!hook) { err = -ENOENT; goto err_chain_del_hook; } list_move(&hook->list, &chain_del_list); } trans = nft_trans_alloc_chain(ctx, NFT_MSG_DELCHAIN); if (!trans) { err = -ENOMEM; goto err_chain_del_hook; } nft_trans_basechain(trans) = basechain; nft_trans_chain_update(trans) = true; INIT_LIST_HEAD(&nft_trans_chain_hooks(trans)); list_splice(&chain_del_list, &nft_trans_chain_hooks(trans)); nft_chain_release_hook(&chain_hook); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_chain_del_hook: list_splice(&chain_del_list, &basechain->hook_list); nft_chain_release_hook(&chain_hook); return err; } static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule; struct nft_ctx ctx; u64 handle; u32 use; int err; table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); } if (nla[NFTA_CHAIN_HANDLE]) { attr = nla[NFTA_CHAIN_HANDLE]; handle = be64_to_cpu(nla_get_be64(attr)); chain = nft_chain_lookup_byhandle(table, handle, genmask); } else { attr = nla[NFTA_CHAIN_NAME]; chain = nft_chain_lookup(net, table, attr, genmask); } if (IS_ERR(chain)) { if (PTR_ERR(chain) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); } if (nft_chain_binding(chain)) return -EOPNOTSUPP; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (nla[NFTA_CHAIN_HOOK]) { if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN || chain->flags & NFT_CHAIN_HW_OFFLOAD) return -EOPNOTSUPP; if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) return nft_delchain_hook(&ctx, basechain, extack); } } if (info->nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; use = chain->use; list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(net, rule)) continue; use--; err = nft_delrule(&ctx, rule); if (err < 0) return err; } /* There are rules and elements that are still holding references to us, * we cannot do a recursive removal in this case. */ if (use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } return nft_delchain(&ctx); } /* * Expressions */ /** * nft_register_expr - register nf_tables expr type * @type: expr type * * Registers the expr type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. */ int nft_register_expr(struct nft_expr_type *type) { if (WARN_ON_ONCE(type->maxattr > NFT_EXPR_MAXATTR)) return -ENOMEM; nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); else list_add_rcu(&type->list, &nf_tables_expressions); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } EXPORT_SYMBOL_GPL(nft_register_expr); /** * nft_unregister_expr - unregister nf_tables expr type * @type: expr type * * Unregisters the expr typefor use with nf_tables. */ void nft_unregister_expr(struct nft_expr_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_expr); static const struct nft_expr_type *__nft_expr_type_get(u8 family, struct nlattr *nla) { const struct nft_expr_type *type, *candidate = NULL; list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; else if (type->family == family) candidate = type; } } return candidate; } #ifdef CONFIG_MODULES static int nft_expr_type_request_module(struct net *net, u8 family, struct nlattr *nla) { if (nft_request_module(net, "nft-expr-%u-%.*s", family, nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) return -EAGAIN; return 0; } #endif static const struct nft_expr_type *nft_expr_type_get(struct net *net, u8 family, struct nlattr *nla) { const struct nft_expr_type *type; if (nla == NULL) return ERR_PTR(-EINVAL); rcu_read_lock(); type = __nft_expr_type_get(family, nla); if (type != NULL && try_module_get(type->owner)) { rcu_read_unlock(); return type; } rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { if (nft_expr_type_request_module(net, family, nla) == -EAGAIN) return ERR_PTR(-EAGAIN); if (nft_request_module(net, "nft-expr-%.*s", nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = { [NFTA_EXPR_NAME] = { .type = NLA_STRING, .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_EXPR_DATA] = { .type = NLA_NESTED }, }; static int nf_tables_fill_expr_info(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->type->name)) goto nla_put_failure; if (expr->ops->dump) { struct nlattr *data = nla_nest_start_noflag(skb, NFTA_EXPR_DATA); if (data == NULL) goto nla_put_failure; if (expr->ops->dump(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, data); } return skb->len; nla_put_failure: return -1; }; int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr, bool reset) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; if (nf_tables_fill_expr_info(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } struct nft_expr_info { const struct nft_expr_ops *ops; const struct nlattr *attr; struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; }; static int nf_tables_expr_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info) { const struct nft_expr_type *type; const struct nft_expr_ops *ops; struct nlattr *tb[NFTA_EXPR_MAX + 1]; int err; err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla, nft_expr_policy, NULL); if (err < 0) return err; type = nft_expr_type_get(ctx->net, ctx->family, tb[NFTA_EXPR_NAME]); if (IS_ERR(type)) return PTR_ERR(type); if (tb[NFTA_EXPR_DATA]) { err = nla_parse_nested_deprecated(info->tb, type->maxattr, tb[NFTA_EXPR_DATA], type->policy, NULL); if (err < 0) goto err1; } else memset(info->tb, 0, sizeof(info->tb[0]) * (type->maxattr + 1)); if (type->select_ops != NULL) { ops = type->select_ops(ctx, (const struct nlattr * const *)info->tb); if (IS_ERR(ops)) { err = PTR_ERR(ops); #ifdef CONFIG_MODULES if (err == -EAGAIN) if (nft_expr_type_request_module(ctx->net, ctx->family, tb[NFTA_EXPR_NAME]) != -EAGAIN) err = -ENOENT; #endif goto err1; } } else ops = type->ops; info->attr = nla; info->ops = ops; return 0; err1: module_put(type->owner); return err; } int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info) { struct nlattr *tb[NFTA_EXPR_MAX + 1]; const struct nft_expr_type *type; int err; err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla, nft_expr_policy, NULL); if (err < 0) return err; if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME]) return -EINVAL; rcu_read_lock(); type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); if (!type) { err = -ENOENT; goto out_unlock; } if (!type->inner_ops) { err = -EOPNOTSUPP; goto out_unlock; } err = nla_parse_nested_deprecated(info->tb, type->maxattr, tb[NFTA_EXPR_DATA], type->policy, NULL); if (err < 0) goto out_unlock; info->attr = nla; info->ops = type->inner_ops; /* No module reference will be taken on type->owner. * Presence of type->inner_ops implies that the expression * is builtin, so it cannot go away. */ rcu_read_unlock(); return 0; out_unlock: rcu_read_unlock(); return err; } static int nf_tables_newexpr(const struct nft_ctx *ctx, const struct nft_expr_info *expr_info, struct nft_expr *expr) { const struct nft_expr_ops *ops = expr_info->ops; int err; expr->ops = ops; if (ops->init) { err = ops->init(ctx, expr, (const struct nlattr **)expr_info->tb); if (err < 0) goto err1; } return 0; err1: expr->ops = NULL; return err; } static void nf_tables_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { const struct nft_expr_type *type = expr->ops->type; if (expr->ops->destroy) expr->ops->destroy(ctx, expr); module_put(type->owner); } static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, const struct nlattr *nla) { struct nft_expr_info expr_info; struct nft_expr *expr; struct module *owner; int err; err = nf_tables_expr_parse(ctx, nla, &expr_info); if (err < 0) goto err_expr_parse; err = -EOPNOTSUPP; if (!(expr_info.ops->type->flags & NFT_EXPR_STATEFUL)) goto err_expr_stateful; err = -ENOMEM; expr = kzalloc(expr_info.ops->size, GFP_KERNEL_ACCOUNT); if (expr == NULL) goto err_expr_stateful; err = nf_tables_newexpr(ctx, &expr_info, expr); if (err < 0) goto err_expr_new; return expr; err_expr_new: kfree(expr); err_expr_stateful: owner = expr_info.ops->type->owner; if (expr_info.ops->type->release_ops) expr_info.ops->type->release_ops(expr_info.ops); module_put(owner); err_expr_parse: return ERR_PTR(err); } int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp) { int err; if (WARN_ON_ONCE(!src->ops->clone)) return -EINVAL; dst->ops = src->ops; err = src->ops->clone(dst, src, gfp); if (err < 0) return err; __module_get(src->ops->type->owner); return 0; } void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { nf_tables_expr_destroy(ctx, expr); kfree(expr); } /* * Rules */ static struct nft_rule *__nft_rule_lookup(const struct net *net, const struct nft_chain *chain, u64 handle) { struct nft_rule *rule; // FIXME: this sucks list_for_each_entry_rcu(rule, &chain->rules, list, lockdep_commit_lock_is_held(net)) { if (handle == rule->handle) return rule; } return ERR_PTR(-ENOENT); } static struct nft_rule *nft_rule_lookup(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla) { if (nla == NULL) return ERR_PTR(-EINVAL); return __nft_rule_lookup(net, chain, be64_to_cpu(nla_get_be64(nla))); } static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { [NFTA_RULE_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_RULE_CHAIN] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_RULE_HANDLE] = { .type = NLA_U64 }, [NFTA_RULE_EXPRESSIONS] = NLA_POLICY_NESTED_ARRAY(nft_expr_policy), [NFTA_RULE_COMPAT] = { .type = NLA_NESTED }, [NFTA_RULE_POSITION] = { .type = NLA_U64 }, [NFTA_RULE_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, [NFTA_RULE_ID] = { .type = NLA_U32 }, [NFTA_RULE_POSITION_ID] = { .type = NLA_U32 }, [NFTA_RULE_CHAIN_ID] = { .type = NLA_U32 }, }; static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, const struct nft_rule *rule, u64 handle, bool reset) { struct nlmsghdr *nlh; const struct nft_expr *expr, *next; struct nlattr *list; u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_RULE_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_RULE_HANDLE, cpu_to_be64(rule->handle), NFTA_RULE_PAD)) goto nla_put_failure; if (event != NFT_MSG_DELRULE && handle) { if (nla_put_be64(skb, NFTA_RULE_POSITION, cpu_to_be64(handle), NFTA_RULE_PAD)) goto nla_put_failure; } if (chain->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_stats(chain, rule); list = nla_nest_start_noflag(skb, NFTA_RULE_EXPRESSIONS); if (list == NULL) goto nla_put_failure; nft_rule_for_each_expr(expr, next, rule) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, list); if (rule->udata) { struct nft_userdata *udata = nft_userdata(rule); if (nla_put(skb, NFTA_RULE_USERDATA, udata->len + 1, udata->data) < 0) goto nla_put_failure; } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_rule *prule; struct sk_buff *skb; u64 handle = 0; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (event == NFT_MSG_NEWRULE && !list_is_first(&rule->list, &ctx->chain->rules) && !list_is_last(&rule->list, &ctx->chain->rules)) { prule = list_prev_entry(rule, list); handle = prule->handle; } if (ctx->flags & (NLM_F_APPEND | NLM_F_REPLACE)) flags |= NLM_F_APPEND; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, ctx->chain, rule, handle, false); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static void audit_log_rule_reset(const struct nft_table *table, unsigned int base_seq, unsigned int nentries) { char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); audit_log_nfcfg(buf, table->family, nentries, AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); kfree(buf); } struct nft_rule_dump_ctx { unsigned int s_idx; char *table; char *chain; bool reset; }; static int __nf_tables_dump_rules(struct sk_buff *skb, unsigned int *idx, struct netlink_callback *cb, const struct nft_table *table, const struct nft_chain *chain) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int entries = 0; int ret = 0; u64 handle; prule = NULL; list_for_each_entry_rcu(rule, &chain->rules, list) { if (!nft_is_active(net, rule)) goto cont_skip; if (*idx < ctx->s_idx) goto cont; if (prule) handle = prule->handle; else handle = 0; if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, table, chain, rule, handle, ctx->reset) < 0) { ret = 1; break; } entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: prule = rule; cont_skip: (*idx)++; } if (ctx->reset && entries) audit_log_rule_reset(table, cb->seq, entries); return ret; } static int nf_tables_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; struct nft_table *table; const struct nft_chain *chain; unsigned int idx = 0; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; if (ctx->table && strcmp(ctx->table, table->name) != 0) continue; if (ctx->table && ctx->chain) { struct rhlist_head *list, *tmp; list = rhltable_lookup(&table->chains_ht, ctx->chain, nft_chain_ht_params); if (!list) goto done; rhl_for_each_entry_rcu(chain, tmp, list, rhlhead) { if (!nft_is_active(net, chain)) continue; __nf_tables_dump_rules(skb, &idx, cb, table, chain); break; } goto done; } list_for_each_entry_rcu(chain, &table->chains, list) { if (__nf_tables_dump_rules(skb, &idx, cb, table, chain)) goto done; } if (ctx->table) break; } done: rcu_read_unlock(); ctx->s_idx = idx; return skb->len; } static int nf_tables_dumpreset_rules(struct sk_buff *skb, struct netlink_callback *cb) { struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); int ret; /* Mutex is held is to prevent that two concurrent dump-and-reset calls * do not underrun counters and quotas. The commit_mutex is used for * the lack a better lock, this is not transaction path. */ mutex_lock(&nft_net->commit_mutex); ret = nf_tables_dump_rules(skb, cb); mutex_unlock(&nft_net->commit_mutex); return ret; } static int nf_tables_dump_rules_start(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; const struct nlattr * const *nla = cb->data; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); if (nla[NFTA_RULE_TABLE]) { ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], GFP_ATOMIC); if (!ctx->table) return -ENOMEM; } if (nla[NFTA_RULE_CHAIN]) { ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], GFP_ATOMIC); if (!ctx->chain) { kfree(ctx->table); return -ENOMEM; } } return 0; } static int nf_tables_dumpreset_rules_start(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; ctx->reset = true; return nf_tables_dump_rules_start(cb); } static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; kfree(ctx->table); kfree(ctx->chain); return 0; } /* Caller must hold rcu read lock or transaction mutex */ static struct sk_buff * nf_tables_getrule_single(u32 portid, const struct nfnl_info *info, const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; const struct nft_rule *rule; struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; int err; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return ERR_CAST(table); } chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return ERR_CAST(chain); } rule = nft_rule_lookup(net, chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return ERR_CAST(rule); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); err = nf_tables_fill_rule_info(skb2, net, portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, 0, reset); if (err < 0) { kfree_skb(skb2); return ERR_PTR(err); } return skb2; } static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { u32 portid = NETLINK_CB(skb).portid; struct net *net = info->net; struct sk_buff *skb2; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } skb2 = nf_tables_getrule_single(portid, info, nla, false); if (IS_ERR(skb2)) return PTR_ERR(skb2); return nfnetlink_unicast(skb2, net, portid); } static int nf_tables_getrule_reset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); u32 portid = NETLINK_CB(skb).portid; struct net *net = info->net; struct sk_buff *skb2; char *buf; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start= nf_tables_dumpreset_rules_start, .dump = nf_tables_dumpreset_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); mutex_lock(&nft_net->commit_mutex); skb2 = nf_tables_getrule_single(portid, info, nla, true); mutex_unlock(&nft_net->commit_mutex); rcu_read_lock(); module_put(THIS_MODULE); if (IS_ERR(skb2)) return PTR_ERR(skb2); buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_RULE_TABLE]), (char *)nla_data(nla[NFTA_RULE_TABLE]), nft_net->base_seq); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); kfree(buf); return nfnetlink_unicast(skb2, net, portid); } void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr, *next; /* * Careful: some expressions might not be initialized in case this * is called on error from nf_tables_newrule(). */ expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); expr = next; } kfree(rule); } /* can only be used if rule is no longer visible to dumps */ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { WARN_ON_ONCE(!lockdep_commit_lock_is_held(ctx->net)); nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } /** nft_chain_validate - loop detection and hook validation * * @ctx: context containing call depth and base chain * @chain: chain to validate * * Walk through the rules of the given chain and chase all jumps/gotos * and set lookups until either the jump limit is hit or all reachable * chains have been validated. */ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) { struct nft_expr *expr, *last; struct nft_rule *rule; int err; if (ctx->level == NFT_JUMP_STACK_SIZE) return -EMLINK; list_for_each_entry(rule, &chain->rules, list) { if (fatal_signal_pending(current)) return -EINTR; if (!nft_is_active_next(ctx->net, rule)) continue; nft_rule_for_each_expr(expr, last, rule) { if (!expr->ops->validate) continue; /* This may call nft_chain_validate() recursively, * callers that do so must increment ctx->level. */ err = expr->ops->validate(ctx, expr); if (err < 0) return err; } } return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate); static int nft_table_validate(struct net *net, const struct nft_table *table) { struct nft_chain *chain; struct nft_ctx ctx = { .net = net, .family = table->family, }; int err; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain)) continue; ctx.chain = chain; err = nft_chain_validate(&ctx, chain); if (err < 0) return err; cond_resched(); } return 0; } int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; if (!nft_set_elem_active(ext, iter->genmask)) return 0; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; data = nft_set_ext_data(ext); switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; pctx->level--; break; default: break; } return 0; } int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter dummy_iter = { .genmask = nft_genmask_next(ctx->net), }; struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list, lockdep_commit_lock_is_held(ctx->net)) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, dummy_iter.genmask)) continue; ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem); if (ret < 0) return ret; } return ret; } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla); #define NFT_RULE_MAXEXPRS 128 static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; unsigned int size, i, n, ulen = 0, usize = 0; u8 genmask = nft_genmask_next(info->net); struct nft_rule *rule, *old_rule = NULL; struct nft_expr_info *expr_info = NULL; u8 family = info->nfmsg->nfgen_family; struct nft_flow_rule *flow = NULL; struct net *net = info->net; struct nft_userdata *udata; struct nft_table *table; struct nft_chain *chain; struct nft_trans *trans; u64 handle, pos_handle; struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; int err, rem; lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); } if (nla[NFTA_RULE_CHAIN]) { chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } } else if (nla[NFTA_RULE_CHAIN_ID]) { chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]); return PTR_ERR(chain); } } else { return -EINVAL; } if (nft_chain_is_bound(chain)) return -EOPNOTSUPP; if (nla[NFTA_RULE_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE])); rule = __nft_rule_lookup(net, chain, handle); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); } if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) old_rule = rule; else return -EOPNOTSUPP; } else { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE) || info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EINVAL; handle = nf_tables_alloc_handle(table); if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(net, chain, pos_handle); if (IS_ERR(old_rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); return PTR_ERR(old_rule); } } else if (nla[NFTA_RULE_POSITION_ID]) { old_rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_POSITION_ID]); if (IS_ERR(old_rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION_ID]); return PTR_ERR(old_rule); } } } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); n = 0; size = 0; if (nla[NFTA_RULE_EXPRESSIONS]) { expr_info = kvmalloc_array(NFT_RULE_MAXEXPRS, sizeof(struct nft_expr_info), GFP_KERNEL); if (!expr_info) return -ENOMEM; nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) { err = -EINVAL; if (nla_type(tmp) != NFTA_LIST_ELEM) goto err_release_expr; if (n == NFT_RULE_MAXEXPRS) goto err_release_expr; err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); if (err < 0) { NL_SET_BAD_ATTR(extack, tmp); goto err_release_expr; } size += expr_info[n].ops->size; n++; } } /* Check for overflow of dlen field */ err = -EFBIG; if (size >= 1 << 12) goto err_release_expr; if (nla[NFTA_RULE_USERDATA]) { ulen = nla_len(nla[NFTA_RULE_USERDATA]); if (ulen > 0) usize = sizeof(struct nft_userdata) + ulen; } err = -ENOMEM; rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL_ACCOUNT); if (rule == NULL) goto err_release_expr; nft_activate_next(net, rule); rule->handle = handle; rule->dlen = size; rule->udata = ulen ? 1 : 0; if (ulen) { udata = nft_userdata(rule); udata->len = ulen - 1; nla_memcpy(udata->data, nla[NFTA_RULE_USERDATA], ulen); } expr = nft_expr_first(rule); for (i = 0; i < n; i++) { err = nf_tables_newexpr(&ctx, &expr_info[i], expr); if (err < 0) { NL_SET_BAD_ATTR(extack, expr_info[i].attr); goto err_release_rule; } if (expr_info[i].ops->validate) nft_validate_state_update(table, NFT_VALIDATE_NEED); expr_info[i].ops = NULL; expr = nft_expr_next(expr); } if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { flow = nft_flow_rule_create(net, rule); if (IS_ERR(flow)) { err = PTR_ERR(flow); goto err_release_rule; } } if (!nft_use_inc(&chain->use)) { err = -EMFILE; goto err_release_rule; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { if (nft_chain_binding(chain)) { err = -EOPNOTSUPP; goto err_destroy_flow_rule; } err = nft_delrule(&ctx, old_rule); if (err < 0) goto err_destroy_flow_rule; trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; goto err_destroy_flow_rule; } list_add_tail_rcu(&rule->list, &old_rule->list); } else { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (!trans) { err = -ENOMEM; goto err_destroy_flow_rule; } if (info->nlh->nlmsg_flags & NLM_F_APPEND) { if (old_rule) list_add_rcu(&rule->list, &old_rule->list); else list_add_tail_rcu(&rule->list, &chain->rules); } else { if (old_rule) list_add_tail_rcu(&rule->list, &old_rule->list); else list_add_rcu(&rule->list, &chain->rules); } } kvfree(expr_info); if (flow) nft_trans_flow_rule(trans) = flow; if (table->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); return 0; err_destroy_flow_rule: nft_use_dec_restore(&chain->use); if (flow) nft_flow_rule_destroy(flow); err_release_rule: nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR); nf_tables_rule_destroy(&ctx, rule); err_release_expr: for (i = 0; i < n; i++) { if (expr_info[i].ops) { module_put(expr_info[i].ops->type->owner); if (expr_info[i].ops->type->release_ops) expr_info[i].ops->type->release_ops(expr_info[i].ops); } } kvfree(expr_info); return err; } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWRULE && nft_trans_rule_chain(trans) == chain && id == nft_trans_rule_id(trans)) return nft_trans_rule(trans); } return ERR_PTR(-ENOENT); } static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; struct nft_table *table; struct nft_rule *rule; struct nft_ctx ctx; int err = 0; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); } if (nla[NFTA_RULE_CHAIN]) { chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) return 0; NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } if (nft_chain_binding(chain)) return -EOPNOTSUPP; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { rule = nft_rule_lookup(info->net, chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { if (PTR_ERR(rule) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) return 0; NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); } err = nft_delrule(&ctx, rule); } else if (nla[NFTA_RULE_ID]) { rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_ID]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]); return PTR_ERR(rule); } err = nft_delrule(&ctx, rule); } else { err = nft_delrule_by_chain(&ctx); } } else { list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; if (nft_chain_binding(chain)) continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); if (err < 0) break; } } return err; } /* * Sets */ static const struct nft_set_type *nft_set_types[] = { &nft_set_hash_fast_type, &nft_set_hash_type, &nft_set_rhash_type, &nft_set_bitmap_type, &nft_set_rbtree_type, #if defined(CONFIG_X86_64) && !defined(CONFIG_UML) &nft_set_pipapo_avx2_type, #endif &nft_set_pipapo_type, }; #define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ NFT_SET_TIMEOUT | NFT_SET_OBJECT | \ NFT_SET_EVAL) static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags) { return (flags & type->features) == (flags & NFT_SET_FEATURES); } /* * Select a set implementation based on the data characteristics and the * given policy. The total memory use might not be known if no size is * given, in that case the amount of memory per element is used. */ static const struct nft_set_ops * nft_select_set_ops(const struct nft_ctx *ctx, u32 flags, const struct nft_set_desc *desc) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; int i; lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); bops = NULL; best.size = ~0; best.lookup = ~0; best.space = ~0; for (i = 0; i < ARRAY_SIZE(nft_set_types); i++) { type = nft_set_types[i]; ops = &type->ops; if (!nft_set_ops_candidate(type, flags)) continue; if (!ops->estimate(desc, flags, &est)) continue; switch (desc->policy) { case NFT_SET_POL_PERFORMANCE: if (est.lookup < best.lookup) break; if (est.lookup == best.lookup && est.space < best.space) break; continue; case NFT_SET_POL_MEMORY: if (!desc->size) { if (est.space < best.space) break; if (est.space == best.space && est.lookup < best.lookup) break; } else if (est.size < best.size || !bops) { break; } continue; default: break; } bops = ops; best = est; } if (bops != NULL) return bops; return ERR_PTR(-EOPNOTSUPP); } static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_SET_NAME] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_SET_FLAGS] = { .type = NLA_U32 }, [NFTA_SET_KEY_TYPE] = { .type = NLA_U32 }, [NFTA_SET_KEY_LEN] = { .type = NLA_U32 }, [NFTA_SET_DATA_TYPE] = { .type = NLA_U32 }, [NFTA_SET_DATA_LEN] = { .type = NLA_U32 }, [NFTA_SET_POLICY] = { .type = NLA_U32 }, [NFTA_SET_DESC] = { .type = NLA_NESTED }, [NFTA_SET_ID] = { .type = NLA_U32 }, [NFTA_SET_TIMEOUT] = { .type = NLA_U64 }, [NFTA_SET_GC_INTERVAL] = { .type = NLA_U32 }, [NFTA_SET_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, [NFTA_SET_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_SET_HANDLE] = { .type = NLA_U64 }, [NFTA_SET_EXPR] = { .type = NLA_NESTED }, [NFTA_SET_EXPRESSIONS] = NLA_POLICY_NESTED_ARRAY(nft_expr_policy), [NFTA_SET_TYPE] = { .type = NLA_REJECT }, [NFTA_SET_COUNT] = { .type = NLA_REJECT }, }; static const struct nla_policy nft_concat_policy[NFTA_SET_FIELD_MAX + 1] = { [NFTA_SET_FIELD_LEN] = { .type = NLA_U32 }, }; static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_SIZE] = { .type = NLA_U32 }, [NFTA_SET_DESC_CONCAT] = NLA_POLICY_NESTED_ARRAY(nft_concat_policy), }; static struct nft_set *nft_set_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_set *set; if (nla == NULL) return ERR_PTR(-EINVAL); list_for_each_entry_rcu(set, &table->sets, list, lockdep_commit_lock_is_held(net)) { if (!nla_strcmp(nla, set->name) && nft_active_genmask(set, genmask)) return set; } return ERR_PTR(-ENOENT); } static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_set *set; list_for_each_entry(set, &table->sets, list) { if (be64_to_cpu(nla_get_be64(nla)) == set->handle && nft_active_genmask(set, genmask)) return set; } return ERR_PTR(-ENOENT); } static struct nft_set *nft_set_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans_set *trans; /* its likely the id we need is at the tail, not at start */ list_for_each_entry_reverse(trans, &nft_net->commit_set_list, list_trans_newset) { struct nft_set *set = trans->set; if (id == trans->set_id && set->table == table && nft_active_genmask(set, genmask)) return set; } return ERR_PTR(-ENOENT); } struct nft_set *nft_set_lookup_global(const struct net *net, const struct nft_table *table, const struct nlattr *nla_set_name, const struct nlattr *nla_set_id, u8 genmask) { struct nft_set *set; set = nft_set_lookup(net, table, nla_set_name, genmask); if (IS_ERR(set)) { if (!nla_set_id) return set; set = nft_set_lookup_byid(net, table, nla_set_id, genmask); } return set; } EXPORT_SYMBOL_GPL(nft_set_lookup_global); static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, const char *name) { const struct nft_set *i; const char *p; unsigned long *inuse; unsigned int n = 0, min = 0; p = strchr(name, '%'); if (p != NULL) { if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN) return -EINVAL; inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM; cont: list_for_each_entry(i, &ctx->table->sets, list) { int tmp; if (!nft_is_active_next(ctx->net, i)) continue; if (!sscanf(i->name, name, &tmp)) continue; if (tmp < min || tmp >= min + BITS_PER_BYTE * PAGE_SIZE) continue; set_bit(tmp - min, inuse); } n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE); if (n >= BITS_PER_BYTE * PAGE_SIZE) { min += BITS_PER_BYTE * PAGE_SIZE; memset(inuse, 0, PAGE_SIZE); goto cont; } free_page((unsigned long)inuse); } set->name = kasprintf(GFP_KERNEL_ACCOUNT, name, min + n); if (!set->name) return -ENOMEM; list_for_each_entry(i, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, i)) continue; if (!strcmp(set->name, i->name)) { kfree(set->name); set->name = NULL; return -ENFILE; } } return 0; } int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) { u64 ms = be64_to_cpu(nla_get_be64(nla)); u64 max = (u64)(~((u64)0)); max = div_u64(max, NSEC_PER_MSEC); if (ms >= max) return -ERANGE; ms *= NSEC_PER_MSEC; *result = nsecs_to_jiffies64(ms) ? : !!ms; return 0; } __be64 nf_jiffies64_to_msecs(u64 input) { return cpu_to_be64(jiffies64_to_msecs(input)); } static int nf_tables_fill_set_concat(struct sk_buff *skb, const struct nft_set *set) { struct nlattr *concat, *field; int i; concat = nla_nest_start_noflag(skb, NFTA_SET_DESC_CONCAT); if (!concat) return -ENOMEM; for (i = 0; i < set->field_count; i++) { field = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (!field) return -ENOMEM; if (nla_put_be32(skb, NFTA_SET_FIELD_LEN, htonl(set->field_len[i]))) return -ENOMEM; nla_nest_end(skb, field); } nla_nest_end(skb, concat); return 0; } static u32 nft_set_userspace_size(const struct nft_set_ops *ops, u32 size) { if (ops->usize) return ops->usize(size); return size; } static noinline_for_stack int nf_tables_fill_set_info(struct sk_buff *skb, const struct nft_set *set) { unsigned int nelems; char str[40]; int ret; ret = snprintf(str, sizeof(str), "%ps", set->ops); /* Not expected to happen and harmless: NFTA_SET_TYPE is dumped * to userspace purely for informational/debug purposes. */ DEBUG_NET_WARN_ON_ONCE(ret >= sizeof(str)); if (nla_put_string(skb, NFTA_SET_TYPE, str)) return -EMSGSIZE; nelems = nft_set_userspace_size(set->ops, atomic_read(&set->nelems)); return nla_put_be32(skb, NFTA_SET_COUNT, htonl(nelems)); } static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { u64 timeout = READ_ONCE(set->timeout); u32 gc_int = READ_ONCE(set->gc_int); u32 portid = ctx->portid; struct nlmsghdr *nlh; struct nlattr *nest; u32 seq = ctx->seq; int i; nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, ctx->family, NFNETLINK_V0, nft_base_seq(ctx->net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_SET_HANDLE, cpu_to_be64(set->handle), NFTA_SET_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELSET || event == NFT_MSG_DESTROYSET) { nlmsg_end(skb, nlh); return 0; } if (set->flags != 0) if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_SET_KEY_TYPE, htonl(set->ktype))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_SET_KEY_LEN, htonl(set->klen))) goto nla_put_failure; if (set->flags & NFT_SET_MAP) { if (nla_put_be32(skb, NFTA_SET_DATA_TYPE, htonl(set->dtype))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_SET_DATA_LEN, htonl(set->dlen))) goto nla_put_failure; } if (set->flags & NFT_SET_OBJECT && nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype))) goto nla_put_failure; if (timeout && nla_put_be64(skb, NFTA_SET_TIMEOUT, nf_jiffies64_to_msecs(timeout), NFTA_SET_PAD)) goto nla_put_failure; if (gc_int && nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(gc_int))) goto nla_put_failure; if (set->policy != NFT_SET_POL_PERFORMANCE) { if (nla_put_be32(skb, NFTA_SET_POLICY, htonl(set->policy))) goto nla_put_failure; } if (set->udata && nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_DESC); if (!nest) goto nla_put_failure; if (set->size && nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(nft_set_userspace_size(set->ops, set->size)))) goto nla_put_failure; if (set->field_count > 1 && nf_tables_fill_set_concat(skb, set)) goto nla_put_failure; nla_nest_end(skb, nest); if (nf_tables_fill_set_info(skb, set)) goto nla_put_failure; if (set->num_exprs == 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR); if (nf_tables_fill_expr_info(skb, set->exprs[0], false) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (set->num_exprs > 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPRESSIONS); if (nest == NULL) goto nla_put_failure; for (i = 0; i < set->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, set->exprs[i], false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void nf_tables_set_notify(const struct nft_ctx *ctx, const struct nft_set *set, int event, gfp_t gfp_flags) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); u32 portid = ctx->portid; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, gfp_flags); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_set(skb, ctx, set, event, flags); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) { const struct nft_set *set; unsigned int idx, s_idx = cb->args[0]; struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); struct nft_ctx *ctx = cb->data, ctx_set; struct nftables_pernet *nft_net; if (cb->args[1]) return skb->len; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && ctx->family != table->family) continue; if (ctx->table && ctx->table != table) continue; if (cur_table) { if (cur_table != table) continue; cur_table = NULL; } idx = 0; list_for_each_entry_rcu(set, &table->sets, list) { if (idx < s_idx) goto cont; if (!nft_is_active(net, set)) goto cont; ctx_set = *ctx; ctx_set.table = table; ctx_set.family = table->family; if (nf_tables_fill_set(skb, &ctx_set, set, NFT_MSG_NEWSET, NLM_F_MULTI) < 0) { cb->args[0] = idx; cb->args[2] = (unsigned long) table; goto done; } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } if (s_idx) s_idx = 0; } cb->args[1] = 1; done: rcu_read_unlock(); return skb->len; } static int nf_tables_dump_sets_start(struct netlink_callback *cb) { struct nft_ctx *ctx_dump = NULL; ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC); if (ctx_dump == NULL) return -ENOMEM; cb->data = ctx_dump; return 0; } static int nf_tables_dump_sets_done(struct netlink_callback *cb) { kfree(cb->data); return 0; } /* called with rcu_read_lock held */ static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_table *table = NULL; struct net *net = info->net; const struct nft_set *set; struct sk_buff *skb2; struct nft_ctx ctx; int err; if (nla[NFTA_SET_TABLE]) { table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); } } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, .data = &ctx, .module = THIS_MODULE, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } /* Only accept unspec with dump */ if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; if (!nla[NFTA_SET_TABLE]) return -EINVAL; set = nft_set_lookup(net, table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return PTR_ERR(set); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb2 == NULL) return -ENOMEM; err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0); if (err < 0) goto err_fill_set_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_set_info: kfree_skb(skb2); return err; } static int nft_set_desc_concat_parse(const struct nlattr *attr, struct nft_set_desc *desc) { struct nlattr *tb[NFTA_SET_FIELD_MAX + 1]; u32 len; int err; if (desc->field_count >= ARRAY_SIZE(desc->field_len)) return -E2BIG; err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, nft_concat_policy, NULL); if (err < 0) return err; if (!tb[NFTA_SET_FIELD_LEN]) return -EINVAL; len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); if (!len || len > U8_MAX) return -EINVAL; desc->field_len[desc->field_count++] = len; return 0; } static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { u32 len = 0, num_regs; struct nlattr *attr; int rem, err, i; nla_for_each_nested(attr, nla, rem) { if (nla_type(attr) != NFTA_LIST_ELEM) return -EINVAL; err = nft_set_desc_concat_parse(attr, desc); if (err < 0) return err; } for (i = 0; i < desc->field_count; i++) len += round_up(desc->field_len[i], sizeof(u32)); if (len != desc->klen) return -EINVAL; num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); if (num_regs > NFT_REG32_COUNT) return -E2BIG; return 0; } static int nf_tables_set_desc_parse(struct nft_set_desc *desc, const struct nlattr *nla) { struct nlattr *da[NFTA_SET_DESC_MAX + 1]; int err; err = nla_parse_nested_deprecated(da, NFTA_SET_DESC_MAX, nla, nft_set_desc_policy, NULL); if (err < 0) return err; if (da[NFTA_SET_DESC_SIZE] != NULL) desc->size = ntohl(nla_get_be32(da[NFTA_SET_DESC_SIZE])); if (da[NFTA_SET_DESC_CONCAT]) err = nft_set_desc_concat(desc, da[NFTA_SET_DESC_CONCAT]); return err; } static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr * const *nla, struct nft_expr **exprs, int *num_exprs, u32 flags) { struct nft_expr *expr; int err, i; if (nla[NFTA_SET_EXPR]) { expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_EXPR]); if (IS_ERR(expr)) { err = PTR_ERR(expr); goto err_set_expr_alloc; } exprs[0] = expr; (*num_exprs)++; } else if (nla[NFTA_SET_EXPRESSIONS]) { struct nlattr *tmp; int left; if (!(flags & NFT_SET_EXPR)) { err = -EINVAL; goto err_set_expr_alloc; } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { err = -E2BIG; goto err_set_expr_alloc; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; goto err_set_expr_alloc; } expr = nft_set_elem_expr_alloc(ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); goto err_set_expr_alloc; } exprs[i++] = expr; (*num_exprs)++; } } return 0; err_set_expr_alloc: for (i = 0; i < *num_exprs; i++) nft_expr_destroy(ctx, exprs[i]); return err; } static bool nft_set_is_same(const struct nft_set *set, const struct nft_set_desc *desc, struct nft_expr *exprs[], u32 num_exprs, u32 flags) { int i; if (set->ktype != desc->ktype || set->dtype != desc->dtype || set->flags != flags || set->klen != desc->klen || set->dlen != desc->dlen || set->field_count != desc->field_count || set->num_exprs != num_exprs) return false; for (i = 0; i < desc->field_count; i++) { if (set->field_len[i] != desc->field_len[i]) return false; } for (i = 0; i < num_exprs; i++) { if (set->exprs[i]->ops != exprs[i]->ops) return false; } return true; } static u32 nft_set_kernel_size(const struct nft_set_ops *ops, const struct nft_set_desc *desc) { if (ops->ksize) return ops->ksize(desc->size); return desc->size; } static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_set_ops *ops; struct net *net = info->net; struct nft_set_desc desc; struct nft_table *table; unsigned char *udata; struct nft_set *set; struct nft_ctx ctx; size_t alloc_size; int num_exprs = 0; char *name; int err, i; u16 udlen; u32 flags; u64 size; if (nla[NFTA_SET_TABLE] == NULL || nla[NFTA_SET_NAME] == NULL || nla[NFTA_SET_KEY_LEN] == NULL || nla[NFTA_SET_ID] == NULL) return -EINVAL; memset(&desc, 0, sizeof(desc)); desc.ktype = NFT_DATA_VALUE; if (nla[NFTA_SET_KEY_TYPE] != NULL) { desc.ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE])); if ((desc.ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK) return -EINVAL; } desc.klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); if (desc.klen == 0 || desc.klen > NFT_DATA_VALUE_MAXLEN) return -EINVAL; flags = 0; if (nla[NFTA_SET_FLAGS] != NULL) { flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR)) return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == (NFT_SET_MAP | NFT_SET_OBJECT)) return -EOPNOTSUPP; if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) return -EOPNOTSUPP; if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) return -EOPNOTSUPP; } desc.dtype = 0; if (nla[NFTA_SET_DATA_TYPE] != NULL) { if (!(flags & NFT_SET_MAP)) return -EINVAL; desc.dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE])); if ((desc.dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK && desc.dtype != NFT_DATA_VERDICT) return -EINVAL; if (desc.dtype != NFT_DATA_VERDICT) { if (nla[NFTA_SET_DATA_LEN] == NULL) return -EINVAL; desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN])); if (desc.dlen == 0 || desc.dlen > NFT_DATA_VALUE_MAXLEN) return -EINVAL; } else desc.dlen = sizeof(struct nft_verdict); } else if (flags & NFT_SET_MAP) return -EINVAL; if (nla[NFTA_SET_OBJ_TYPE] != NULL) { if (!(flags & NFT_SET_OBJECT)) return -EINVAL; desc.objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); if (desc.objtype == NFT_OBJECT_UNSPEC || desc.objtype > NFT_OBJECT_MAX) return -EOPNOTSUPP; } else if (flags & NFT_SET_OBJECT) return -EINVAL; else desc.objtype = NFT_OBJECT_UNSPEC; desc.timeout = 0; if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; if (flags & NFT_SET_ANONYMOUS) return -EOPNOTSUPP; err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout); if (err) return err; } desc.gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; if (flags & NFT_SET_ANONYMOUS) return -EOPNOTSUPP; desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } desc.policy = NFT_SET_POL_PERFORMANCE; if (nla[NFTA_SET_POLICY] != NULL) { desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); switch (desc.policy) { case NFT_SET_POL_PERFORMANCE: case NFT_SET_POL_MEMORY: break; default: return -EOPNOTSUPP; } } if (nla[NFTA_SET_DESC] != NULL) { err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); if (err < 0) return err; if (desc.field_count > 1) { if (!(flags & NFT_SET_CONCAT)) return -EINVAL; } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS]) desc.expr = true; table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); set = nft_set_lookup(net, table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { if (PTR_ERR(set) != -ENOENT) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return PTR_ERR(set); } } else { struct nft_expr *exprs[NFT_SET_EXPR_MAX] = {}; if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (nft_set_is_anonymous(set)) return -EOPNOTSUPP; err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags); if (err < 0) return err; if (desc.size) desc.size = nft_set_kernel_size(set->ops, &desc); err = 0; if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); err = -EEXIST; } for (i = 0; i < num_exprs; i++) nft_expr_destroy(&ctx, exprs[i]); if (err < 0) return err; return __nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set, &desc); } if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; ops = nft_select_set_ops(&ctx, flags, &desc); if (IS_ERR(ops)) return PTR_ERR(ops); if (desc.size) desc.size = nft_set_kernel_size(ops, &desc); udlen = 0; if (nla[NFTA_SET_USERDATA]) udlen = nla_len(nla[NFTA_SET_USERDATA]); size = 0; if (ops->privsize != NULL) size = ops->privsize(nla, &desc); alloc_size = sizeof(*set) + size + udlen; if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; if (!nft_use_inc(&table->use)) return -EMFILE; set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); if (!set) { err = -ENOMEM; goto err_alloc; } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { err = -ENOMEM; goto err_set_name; } err = nf_tables_set_alloc_name(&ctx, set, name); kfree(name); if (err < 0) goto err_set_name; udata = NULL; if (udlen) { udata = set->data + size; nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); } INIT_LIST_HEAD(&set->bindings); INIT_LIST_HEAD(&set->catchall_list); refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; set->ktype = desc.ktype; set->klen = desc.klen; set->dtype = desc.dtype; set->objtype = desc.objtype; set->dlen = desc.dlen; set->flags = flags; set->size = desc.size; set->policy = desc.policy; set->udlen = udlen; set->udata = udata; set->timeout = desc.timeout; set->gc_int = desc.gc_int; set->field_count = desc.field_count; for (i = 0; i < desc.field_count; i++) set->field_len[i] = desc.field_len[i]; err = ops->init(set, &desc, nla); if (err < 0) goto err_set_init; err = nft_set_expr_alloc(&ctx, set, nla, set->exprs, &num_exprs, flags); if (err < 0) goto err_set_destroy; set->num_exprs = num_exprs; set->handle = nf_tables_alloc_handle(table); INIT_LIST_HEAD(&set->pending_update); err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); return 0; err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); err_set_destroy: ops->destroy(&ctx, set); err_set_init: kfree(set->name); err_set_name: kvfree(set); err_alloc: nft_use_dec_restore(&table->use); return err; } static void nft_set_catchall_destroy(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_elem_catchall *next, *catchall; list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { list_del_rcu(&catchall->list); nf_tables_set_elem_destroy(ctx, set, catchall->elem); kfree_rcu(catchall, rcu); } } static void nft_set_put(struct nft_set *set) { if (refcount_dec_and_test(&set->refs)) { kfree(set->name); kvfree(set); } } static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; if (WARN_ON(set->use > 0)) return; for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(ctx, set->exprs[i]); set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); nft_set_put(set); } static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); } if (nla[NFTA_SET_HANDLE]) { attr = nla[NFTA_SET_HANDLE]; set = nft_set_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_SET_NAME]; set = nft_set_lookup(net, table, attr, genmask); } if (IS_ERR(set)) { if (PTR_ERR(set) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSET) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(set); } if (set->use || (info->nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_delset(&ctx, set); } static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, enum nft_data_types type, unsigned int len); static int nft_setelem_data_validate(const struct nft_ctx *ctx, struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); enum nft_registers dreg; dreg = nft_type_to_reg(set->dtype); return nft_validate_register_store(ctx, dreg, nft_set_ext_data(ext), set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, set->dlen); } static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (!nft_set_elem_active(ext, iter->genmask)) return 0; return nft_setelem_data_validate(ctx, set, elem_priv); } static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list, lockdep_commit_lock_is_held(ctx->net)) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; ret = nft_setelem_data_validate(ctx, set, catchall->elem); if (ret < 0) break; } return ret; } int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding) { struct nft_set_binding *i; struct nft_set_iter iter; if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; if (binding->flags & NFT_SET_MAP) { /* If the set is already bound to the same chain all * jumps are already validated for that chain. */ list_for_each_entry(i, &set->bindings, list) { if (i->flags & NFT_SET_MAP && i->chain == binding->chain) goto bind; } iter.genmask = nft_genmask_next(ctx->net); iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; iter.fn = nf_tables_bind_check_setelem; set->ops->walk(ctx, set, &iter); if (!iter.err) iter.err = nft_set_catchall_bind_check(ctx, set); if (iter.err < 0) return iter.err; } bind: if (!nft_use_inc(&set->use)) return -EMFILE; binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); } } static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); static int nft_mapelem_activate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); /* called from abort path, reverse check to undo changes. */ if (nft_set_elem_active(ext, iter->genmask)) return 0; nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; } static void nft_map_catchall_activate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } } static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), .type = NFT_ITER_UPDATE, .fn = nft_mapelem_activate, }; set->ops->walk(ctx, set, &iter); WARN_ON_ONCE(iter.err); nft_map_catchall_activate(ctx, set); } void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) { if (nft_set_is_anonymous(set)) { if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(ctx, set); nft_clear(ctx->net, set); } nft_use_inc_restore(&set->use); } EXPORT_SYMBOL_GPL(nf_tables_activate_set); void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { WARN_ON_ONCE(!lockdep_commit_lock_is_held(ctx->net)); switch (phase) { case NFT_TRANS_PREPARE_ERROR: nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); else list_del_rcu(&binding->list); nft_use_dec(&set->use); break; case NFT_TRANS_PREPARE: if (nft_set_is_anonymous(set)) { if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); nft_deactivate_next(ctx->net, set); } nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: if (nft_set_is_anonymous(set) && set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(ctx, set); nft_use_dec(&set->use); fallthrough; default: nf_tables_unbind_set(ctx, set, binding, phase == NFT_TRANS_COMMIT); } } EXPORT_SYMBOL_GPL(nf_tables_deactivate_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) nft_set_destroy(ctx, set); } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); const struct nft_set_ext_type nft_set_ext_types[] = { [NFT_SET_EXT_KEY] = { .align = __alignof__(u32), }, [NFT_SET_EXT_DATA] = { .align = __alignof__(u32), }, [NFT_SET_EXT_EXPRESSIONS] = { .align = __alignof__(struct nft_set_elem_expr), }, [NFT_SET_EXT_OBJREF] = { .len = sizeof(struct nft_object *), .align = __alignof__(struct nft_object *), }, [NFT_SET_EXT_FLAGS] = { .len = sizeof(u8), .align = __alignof__(u8), }, [NFT_SET_EXT_TIMEOUT] = { .len = sizeof(struct nft_timeout), .align = __alignof__(struct nft_timeout), }, [NFT_SET_EXT_USERDATA] = { .len = sizeof(struct nft_userdata), .align = __alignof__(struct nft_userdata), }, [NFT_SET_EXT_KEY_END] = { .align = __alignof__(u32), }, }; /* * Set elements */ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { [NFTA_SET_ELEM_KEY] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_DATA] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_FLAGS] = { .type = NLA_U32 }, [NFTA_SET_ELEM_TIMEOUT] = { .type = NLA_U64 }, [NFTA_SET_ELEM_EXPIRATION] = { .type = NLA_U64 }, [NFTA_SET_ELEM_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, [NFTA_SET_ELEM_EXPR] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_KEY_END] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_EXPRESSIONS] = NLA_POLICY_NESTED_ARRAY(nft_expr_policy), }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_LIST_ELEMENTS] = NLA_POLICY_NESTED_ARRAY(nft_set_elem_policy), [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; static int nft_set_elem_expr_dump(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_ext *ext, bool reset) { struct nft_set_elem_expr *elem_expr; u32 size, num_exprs = 0; struct nft_expr *expr; struct nlattr *nest; elem_expr = nft_set_ext_expr(ext); nft_setelem_expr_foreach(expr, elem_expr, size) num_exprs++; if (num_exprs == 1) { expr = nft_setelem_expr_at(elem_expr, 0); if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, reset) < 0) return -1; return 0; } else if (num_exprs > 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_EXPRESSIONS); if (nest == NULL) goto nla_put_failure; nft_setelem_expr_foreach(expr, elem_expr, size) { expr = nft_setelem_expr_at(elem_expr, size); if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); } return 0; nla_put_failure: return -1; } static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool reset) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (nest == NULL) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) && nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) && nft_data_dump(skb, NFTA_SET_ELEM_KEY_END, nft_set_ext_key_end(ext), NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), nft_set_datatype(set), set->dlen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && nft_set_elem_expr_dump(skb, set, ext, reset)) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nla_put_string(skb, NFTA_SET_ELEM_OBJREF, (*nft_set_ext_obj(ext))->key.name) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(*nft_set_ext_flags(ext)))) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { u64 timeout = READ_ONCE(nft_set_ext_timeout(ext)->timeout); u64 set_timeout = READ_ONCE(set->timeout); __be64 msecs = 0; if (set_timeout != timeout) { msecs = nf_jiffies64_to_msecs(timeout); if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, msecs, NFTA_SET_ELEM_PAD)) goto nla_put_failure; } if (timeout > 0) { u64 expires, now = get_jiffies_64(); expires = READ_ONCE(nft_set_ext_timeout(ext)->expiration); if (time_before64(now, expires)) expires -= now; else expires = 0; if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION, nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; } } if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { struct nft_userdata *udata; udata = nft_set_ext_userdata(ext); if (nla_put(skb, NFTA_SET_ELEM_USERDATA, udata->len + 1, udata->data)) goto nla_put_failure; } nla_nest_end(skb, nest); return 0; nla_put_failure: nlmsg_trim(skb, b); return -EMSGSIZE; } struct nft_set_dump_args { const struct netlink_callback *cb; struct nft_set_iter iter; struct sk_buff *skb; bool reset; }; static int nf_tables_dump_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; if (!nft_set_elem_active(ext, iter->genmask)) return 0; if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); return nf_tables_fill_setelem(args->skb, set, elem_priv, args->reset); } static void audit_log_nft_set_reset(const struct nft_table *table, unsigned int base_seq, unsigned int nentries) { char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); audit_log_nfcfg(buf, table->family, nentries, AUDIT_NFT_OP_SETELEM_RESET, GFP_ATOMIC); kfree(buf); } struct nft_set_dump_ctx { const struct nft_set *set; struct nft_ctx ctx; bool reset; }; static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, const struct nft_set *set, bool reset, unsigned int base_seq) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask) || nft_set_elem_expired(ext)) continue; ret = nf_tables_fill_setelem(skb, set, catchall->elem, reset); if (reset && !ret) audit_log_nft_set_reset(set->table, base_seq, 1); break; } return ret; } static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; struct net *net = sock_net(skb->sk); struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; struct nft_set_dump_args args; bool set_found = false; struct nlmsghdr *nlh; struct nlattr *nest; u32 portid, seq; int event; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) continue; if (table != dump_ctx->ctx.table) continue; list_for_each_entry_rcu(set, &table->sets, list) { if (set == dump_ctx->set) { set_found = true; break; } } break; } if (!set_found) { rcu_read_unlock(); return -ENOENT; } event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWSETELEM); portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, table->family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS); if (nest == NULL) goto nla_put_failure; args.cb = cb; args.skb = skb; args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); args.iter.type = NFT_ITER_READ; args.iter.skip = cb->args[0]; args.iter.count = 0; args.iter.err = 0; args.iter.fn = nf_tables_dump_setelem; set->ops->walk(&dump_ctx->ctx, set, &args.iter); if (!args.iter.err && args.iter.count == cb->args[0]) args.iter.err = nft_set_catchall_dump(net, skb, set, dump_ctx->reset, cb->seq); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); rcu_read_unlock(); if (args.iter.err && args.iter.err != -EMSGSIZE) return args.iter.err; if (args.iter.count == cb->args[0]) return 0; cb->args[0] = args.iter.count; return skb->len; nla_put_failure: rcu_read_unlock(); return -ENOSPC; } static int nf_tables_dumpreset_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); struct nft_set_dump_ctx *dump_ctx = cb->data; int ret, skip = cb->args[0]; mutex_lock(&nft_net->commit_mutex); ret = nf_tables_dump_set(skb, cb); if (cb->args[0] > skip) audit_log_nft_set_reset(dump_ctx->ctx.table, cb->seq, cb->args[0] - skip); mutex_unlock(&nft_net->commit_mutex); return ret; } static int nf_tables_dump_set_start(struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC); return cb->data ? 0 : -ENOMEM; } static int nf_tables_dump_set_done(struct netlink_callback *cb) { kfree(cb->data); return 0; } static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_ctx *ctx, u32 seq, u32 portid, int event, u16 flags, const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool reset) { struct nlmsghdr *nlh; struct nlattr *nest; int err; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, NFNETLINK_V0, nft_base_seq(ctx->net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS); if (nest == NULL) goto nla_put_failure; err = nf_tables_fill_setelem(skb, set, elem_priv, reset); if (err < 0) goto nla_put_failure; nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static int nft_setelem_parse_flags(const struct nft_set *set, const struct nlattr *attr, u32 *flags) { if (attr == NULL) return 0; *flags = ntohl(nla_get_be32(attr)); if (*flags & ~(NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) return -EOPNOTSUPP; if (!(set->flags & NFT_SET_INTERVAL) && *flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; if ((*flags & (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) == (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) return -EINVAL; return 0; } static int nft_setelem_parse_key(struct nft_ctx *ctx, const struct nft_set *set, struct nft_data *key, struct nlattr *attr) { struct nft_data_desc desc = { .type = NFT_DATA_VALUE, .size = NFT_DATA_VALUE_MAXLEN, .len = set->klen, }; return nft_data_init(ctx, key, &desc, attr); } static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc *desc, struct nft_data *data, struct nlattr *attr) { u32 dtype; if (set->dtype == NFT_DATA_VERDICT) dtype = NFT_DATA_VERDICT; else dtype = NFT_DATA_VALUE; desc->type = dtype; desc->size = NFT_DATA_VALUE_MAXLEN; desc->len = set->dlen; desc->flags = NFT_DATA_DESC_SETELEM; return nft_data_init(ctx, data, desc, attr); } static void *nft_setelem_catchall_get(const struct net *net, const struct nft_set *set) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); struct nft_set_ext *ext; void *priv = NULL; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask) || nft_set_elem_expired(ext)) continue; priv = catchall->elem; break; } return priv; } static int nft_setelem_get(struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_elem *elem, u32 flags) { void *priv; if (!(flags & NFT_SET_ELEM_CATCHALL)) { priv = set->ops->get(ctx->net, set, elem, flags); if (IS_ERR(priv)) return PTR_ERR(priv); } else { priv = nft_setelem_catchall_get(ctx->net, set); if (!priv) return -ENOENT; } elem->priv = priv; return 0; } static int nft_get_set_elem(struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr, bool reset) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_elem elem; struct sk_buff *skb; uint32_t flags = 0; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) return err; err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, nla[NFTA_SET_ELEM_KEY]); if (err < 0) return err; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) return err; } err = nft_setelem_get(ctx, set, &elem, flags); if (err < 0) return err; err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, NFT_MSG_NEWSETELEM, 0, set, elem.priv, reset); if (err < 0) goto err_fill_setelem; return nfnetlink_unicast(skb, ctx->net, ctx->portid); err_fill_setelem: kfree_skb(skb); return err; } static int nft_set_dump_ctx_init(struct nft_set_dump_ctx *dump_ctx, const struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; struct nft_table *table; struct nft_set *set; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); } set = nft_set_lookup(net, table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); } nft_ctx_init(&dump_ctx->ctx, net, skb, info->nlh, family, table, NULL, nla); dump_ctx->set = set; dump_ctx->reset = reset; return 0; } /* called with rcu_read_lock held */ static int nf_tables_getsetelem(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; struct nft_set_dump_ctx dump_ctx; struct nlattr *attr; int rem, err = 0; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, false); if (err) return err; c.data = &dump_ctx; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return -EINVAL; err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, false); if (err) return err; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&dump_ctx.ctx, dump_ctx.set, attr, false); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); break; } } return err; } static int nf_tables_getsetelem_reset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; struct nft_set_dump_ctx dump_ctx; int rem, err = 0, nelems = 0; struct nlattr *attr; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, .dump = nf_tables_dumpreset_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, true); if (err) return err; c.data = &dump_ctx; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return -EINVAL; if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); mutex_lock(&nft_net->commit_mutex); rcu_read_lock(); err = nft_set_dump_ctx_init(&dump_ctx, skb, info, nla, true); if (err) goto out_unlock; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&dump_ctx.ctx, dump_ctx.set, attr, true); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); break; } nelems++; } audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems); out_unlock: rcu_read_unlock(); mutex_unlock(&nft_net->commit_mutex); rcu_read_lock(); module_put(THIS_MODULE); return err; } static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_elem_priv *elem_priv, int event) { struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, set, elem_priv, false); if (err < 0) { kfree_skb(skb); goto err; } nft_net = nft_pernet(net); nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } static struct nft_trans *nft_trans_elem_alloc(const struct nft_ctx *ctx, int msg_type, struct nft_set *set) { struct nft_trans_elem *te; struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, struct_size(te, elems, 1)); if (trans == NULL) return NULL; te = nft_trans_container_elem(trans); te->nelems = 1; te->set = set; return trans; } struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr) { struct nft_expr *expr; int err; expr = nft_expr_init(ctx, attr); if (IS_ERR(expr)) return expr; err = -EOPNOTSUPP; if (expr->ops->type->flags & NFT_EXPR_GC) { if (set->flags & NFT_SET_TIMEOUT) goto err_set_elem_expr; if (!set->ops->gc_init) goto err_set_elem_expr; set->ops->gc_init(set); } return expr; err_set_elem_expr: nft_expr_destroy(ctx, expr); return ERR_PTR(err); } static int nft_set_ext_check(const struct nft_set_ext_tmpl *tmpl, u8 id, u32 len) { len += nft_set_ext_types[id].len; if (len > tmpl->ext_len[id] || len > U8_MAX) return -1; return 0; } static int nft_set_ext_memcpy(const struct nft_set_ext_tmpl *tmpl, u8 id, void *to, const void *from, u32 len) { if (nft_set_ext_check(tmpl, id, len) < 0) return -1; memcpy(to, from, len); return 0; } struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *key_end, const u32 *data, u64 timeout, u64 expiration, gfp_t gfp) { struct nft_set_ext *ext; void *elem; elem = kzalloc(set->ops->elemsize + tmpl->len, gfp); if (elem == NULL) return ERR_PTR(-ENOMEM); ext = nft_set_elem_ext(set, elem); nft_set_ext_init(ext, tmpl); if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) && nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY, nft_set_ext_key(ext), key, set->klen) < 0) goto err_ext_check; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) && nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY_END, nft_set_ext_key_end(ext), key_end, set->klen) < 0) goto err_ext_check; if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_memcpy(tmpl, NFT_SET_EXT_DATA, nft_set_ext_data(ext), data, set->dlen) < 0) goto err_ext_check; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { nft_set_ext_timeout(ext)->timeout = timeout; if (expiration == 0) expiration = timeout; nft_set_ext_timeout(ext)->expiration = get_jiffies_64() + expiration; } return elem; err_ext_check: kfree(elem); return ERR_PTR(-EINVAL); } static void __nft_set_elem_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { if (expr->ops->destroy_clone) { expr->ops->destroy_clone(ctx, expr); module_put(expr->ops->type->owner); } else { nf_tables_expr_destroy(ctx, expr); } } static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, struct nft_set_elem_expr *elem_expr) { struct nft_expr *expr; u32 size; nft_setelem_expr_foreach(expr, elem_expr, size) __nft_set_elem_expr_destroy(ctx, expr); } /* Drop references and destroy. Called from gc, dynset and abort path. */ static void __nft_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool destroy_expr) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext)); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem_priv); } /* Drop references and destroy. Called from gc and dynset. */ void nft_set_elem_destroy(const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool destroy_expr) { struct nft_ctx ctx = { .net = read_pnet(&set->net), .family = set->table->family, }; __nft_set_elem_destroy(&ctx, set, elem_priv, destroy_expr); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); /* Drop references and destroy. Called from abort path. */ static void nft_trans_set_elem_destroy(const struct nft_ctx *ctx, struct nft_trans_elem *te) { int i; for (i = 0; i < te->nelems; i++) { /* skip update request, see nft_trans_elems_new_abort() */ if (!te->elems[i].priv) continue; __nft_set_elem_destroy(ctx, te->set, te->elems[i].priv, true); } } /* Destroy element. References have been already dropped in the preparation * path via nft_setelem_data_deactivate(). */ void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext)); kfree(elem_priv); } static void nft_trans_elems_destroy(const struct nft_ctx *ctx, const struct nft_trans_elem *te) { int i; for (i = 0; i < te->nelems; i++) nf_tables_set_elem_destroy(ctx, te->set, te->elems[i].priv); } int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]) { struct nft_expr *expr; int err, i, k; for (i = 0; i < set->num_exprs; i++) { expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT); if (!expr) goto err_expr; err = nft_expr_clone(expr, set->exprs[i], GFP_KERNEL_ACCOUNT); if (err < 0) { kfree(expr); goto err_expr; } expr_array[i] = expr; } return 0; err_expr: for (k = i - 1; k >= 0; k--) nft_expr_destroy(ctx, expr_array[k]); return -ENOMEM; } static int nft_set_elem_expr_setup(struct nft_ctx *ctx, const struct nft_set_ext_tmpl *tmpl, const struct nft_set_ext *ext, struct nft_expr *expr_array[], u32 num_exprs) { struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext); u32 len = sizeof(struct nft_set_elem_expr); struct nft_expr *expr; int i, err; if (num_exprs == 0) return 0; for (i = 0; i < num_exprs; i++) len += expr_array[i]->ops->size; if (nft_set_ext_check(tmpl, NFT_SET_EXT_EXPRESSIONS, len) < 0) return -EINVAL; for (i = 0; i < num_exprs; i++) { expr = nft_setelem_expr_at(elem_expr, elem_expr->size); err = nft_expr_clone(expr, expr_array[i], GFP_KERNEL_ACCOUNT); if (err < 0) goto err_elem_expr_setup; elem_expr->size += expr_array[i]->ops->size; nft_expr_destroy(ctx, expr_array[i]); expr_array[i] = NULL; } return 0; err_elem_expr_setup: for (; i < num_exprs; i++) { nft_expr_destroy(ctx, expr_array[i]); expr_array[i] = NULL; } return -ENOMEM; } struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); struct nft_set_ext *ext; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask) && !nft_set_elem_expired(ext) && !nft_set_elem_is_dead(ext)) return ext; } return NULL; } EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **priv) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_next(net); struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask)) { *priv = catchall->elem; return -EEXIST; } } catchall = kmalloc(sizeof(*catchall), GFP_KERNEL_ACCOUNT); if (!catchall) return -ENOMEM; catchall->elem = elem->priv; list_add_tail_rcu(&catchall->list, &set->catchall_list); return 0; } static int nft_setelem_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **elem_priv, unsigned int flags) { int ret; if (flags & NFT_SET_ELEM_CATCHALL) ret = nft_setelem_catchall_insert(net, set, elem, elem_priv); else ret = set->ops->insert(net, set, elem, elem_priv); return ret; } static bool nft_setelem_is_catchall(const struct nft_set *set, const struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_CATCHALL) return true; return false; } static void nft_setelem_activate(struct net *net, struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_setelem_is_catchall(set, elem_priv)) { nft_clear(net, ext); } else { set->ops->activate(net, set, elem_priv); } } static void nft_trans_elem_update(const struct nft_set *set, const struct nft_trans_one_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); const struct nft_elem_update *update = elem->update; if (update->flags & NFT_TRANS_UPD_TIMEOUT) WRITE_ONCE(nft_set_ext_timeout(ext)->timeout, update->timeout); if (update->flags & NFT_TRANS_UPD_EXPIRATION) WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + update->expiration); } static void nft_trans_elems_add(const struct nft_ctx *ctx, struct nft_trans_elem *te) { int i; for (i = 0; i < te->nelems; i++) { struct nft_trans_one_elem *elem = &te->elems[i]; if (elem->update) nft_trans_elem_update(te->set, elem); else nft_setelem_activate(ctx->net, te->set, elem->priv); nf_tables_setelem_notify(ctx, te->set, elem->priv, NFT_MSG_NEWSETELEM); kfree(elem->update); } } static int nft_setelem_catchall_deactivate(const struct net *net, struct nft_set *set, struct nft_set_elem *elem) { struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_is_active_next(net, ext)) continue; kfree(elem->priv); elem->priv = catchall->elem; nft_set_elem_change_active(net, set, ext); return 0; } return -ENOENT; } static int __nft_setelem_deactivate(const struct net *net, struct nft_set *set, struct nft_set_elem *elem) { void *priv; priv = set->ops->deactivate(net, set, elem); if (!priv) return -ENOENT; kfree(elem->priv); elem->priv = priv; set->ndeact++; return 0; } static int nft_setelem_deactivate(const struct net *net, struct nft_set *set, struct nft_set_elem *elem, u32 flags) { int ret; if (flags & NFT_SET_ELEM_CATCHALL) ret = nft_setelem_catchall_deactivate(net, set, elem); else ret = __nft_setelem_deactivate(net, set, elem); return ret; } static void nft_setelem_catchall_destroy(struct nft_set_elem_catchall *catchall) { list_del_rcu(&catchall->list); kfree_rcu(catchall, rcu); } static void nft_setelem_catchall_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_set_elem_catchall *catchall, *next; list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { if (catchall->elem == elem_priv) { nft_setelem_catchall_destroy(catchall); break; } } } static void nft_setelem_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { if (nft_setelem_is_catchall(set, elem_priv)) nft_setelem_catchall_remove(net, set, elem_priv); else set->ops->remove(net, set, elem_priv); } static void nft_trans_elems_remove(const struct nft_ctx *ctx, const struct nft_trans_elem *te) { int i; for (i = 0; i < te->nelems; i++) { WARN_ON_ONCE(te->elems[i].update); nf_tables_setelem_notify(ctx, te->set, te->elems[i].priv, te->nft_trans.msg_type); nft_setelem_remove(ctx->net, te->set, te->elems[i].priv); if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) { atomic_dec(&te->set->nelems); te->set->ndeact--; } } } static bool nft_setelem_valid_key_end(const struct nft_set *set, struct nlattr **nla, u32 flags) { if ((set->flags & (NFT_SET_CONCAT | NFT_SET_INTERVAL)) == (NFT_SET_CONCAT | NFT_SET_INTERVAL)) { if (flags & NFT_SET_ELEM_INTERVAL_END) return false; if (nla[NFTA_SET_ELEM_KEY_END] && flags & NFT_SET_ELEM_CATCHALL) return false; } else { if (nla[NFTA_SET_ELEM_KEY_END]) return false; } return true; } static u32 nft_set_maxsize(const struct nft_set *set) { u32 maxsize, delta; if (!set->size) return UINT_MAX; if (set->ops->adjust_maxsize) delta = set->ops->adjust_maxsize(set); else delta = 0; if (check_add_overflow(set->size, set->ndeact, &maxsize)) return UINT_MAX; if (check_add_overflow(maxsize, delta, &maxsize)) return UINT_MAX; return maxsize; } static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { struct nft_expr *expr_array[NFT_SET_EXPR_MAX] = {}; struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; u8 genmask = nft_genmask_next(ctx->net); u32 flags = 0, size = 0, num_exprs = 0; struct nft_set_ext_tmpl tmpl; struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; struct nft_elem_priv *elem_priv; struct nft_object *obj = NULL; struct nft_userdata *udata; struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; u64 expiration; u64 timeout; int err, i; u8 ulen; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) return err; nft_set_ext_prepare(&tmpl); err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; if (((flags & NFT_SET_ELEM_CATCHALL) && nla[NFTA_SET_ELEM_KEY]) || (!(flags & NFT_SET_ELEM_CATCHALL) && !nla[NFTA_SET_ELEM_KEY])) return -EINVAL; if (flags != 0) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); if (err < 0) return err; } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } if (set->flags & NFT_SET_OBJECT) { if (!nla[NFTA_SET_ELEM_OBJREF] && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; } else { if (nla[NFTA_SET_ELEM_OBJREF]) return -EINVAL; } if (!nft_setelem_valid_key_end(set, nla, flags)) return -EINVAL; if ((flags & NFT_SET_ELEM_INTERVAL_END) && (nla[NFTA_SET_ELEM_DATA] || nla[NFTA_SET_ELEM_OBJREF] || nla[NFTA_SET_ELEM_TIMEOUT] || nla[NFTA_SET_ELEM_EXPIRATION] || nla[NFTA_SET_ELEM_USERDATA] || nla[NFTA_SET_ELEM_EXPR] || nla[NFTA_SET_ELEM_KEY_END] || nla[NFTA_SET_ELEM_EXPRESSIONS])) return -EINVAL; timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_TIMEOUT], &timeout); if (err) return err; } else if (set->flags & NFT_SET_TIMEOUT && !(flags & NFT_SET_ELEM_INTERVAL_END)) { timeout = set->timeout; } expiration = 0; if (nla[NFTA_SET_ELEM_EXPIRATION] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; if (timeout == 0) return -EOPNOTSUPP; err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_EXPIRATION], &expiration); if (err) return err; if (expiration > timeout) return -ERANGE; } if (nla[NFTA_SET_ELEM_EXPR]) { struct nft_expr *expr; if (set->num_exprs && set->num_exprs != 1) return -EOPNOTSUPP; expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_ELEM_EXPR]); if (IS_ERR(expr)) return PTR_ERR(expr); expr_array[0] = expr; num_exprs = 1; if (set->num_exprs && set->exprs[0]->ops != expr->ops) { err = -EOPNOTSUPP; goto err_set_elem_expr; } } else if (nla[NFTA_SET_ELEM_EXPRESSIONS]) { struct nft_expr *expr; struct nlattr *tmp; int left; i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_ELEM_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX || (set->num_exprs && set->num_exprs == i)) { err = -E2BIG; goto err_set_elem_expr; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; goto err_set_elem_expr; } expr = nft_set_elem_expr_alloc(ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); goto err_set_elem_expr; } expr_array[i] = expr; num_exprs++; if (set->num_exprs && expr->ops != set->exprs[i]->ops) { err = -EOPNOTSUPP; goto err_set_elem_expr; } i++; } if (set->num_exprs && set->num_exprs != i) { err = -EOPNOTSUPP; goto err_set_elem_expr; } } else if (set->num_exprs > 0 && !(flags & NFT_SET_ELEM_INTERVAL_END)) { err = nft_set_elem_expr_clone(ctx, set, expr_array); if (err < 0) goto err_set_elem_expr_clone; num_exprs = set->num_exprs; } if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, nla[NFTA_SET_ELEM_KEY]); if (err < 0) goto err_set_elem_expr; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); if (err < 0) goto err_parse_key; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) goto err_parse_key; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); if (err < 0) goto err_parse_key_end; } if (set->flags & NFT_SET_TIMEOUT) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); if (err < 0) goto err_parse_key_end; } if (num_exprs) { for (i = 0; i < num_exprs; i++) size += expr_array[i]->ops->size; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, sizeof(struct nft_set_elem_expr) + size); if (err < 0) goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { obj = nft_obj_lookup(ctx->net, ctx->table, nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); obj = NULL; goto err_parse_key_end; } if (!nft_use_inc(&obj->use)) { err = -EMFILE; obj = NULL; goto err_parse_key_end; } err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); if (err < 0) goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_DATA] != NULL) { err = nft_setelem_parse_data(ctx, set, &desc, &elem.data.val, nla[NFTA_SET_ELEM_DATA]); if (err < 0) goto err_parse_key_end; dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { .net = ctx->net, .family = ctx->family, .table = ctx->table, .chain = (struct nft_chain *)binding->chain, }; if (!(binding->flags & NFT_SET_MAP)) continue; err = nft_validate_register_store(&bind_ctx, dreg, &elem.data.val, desc.type, desc.len); if (err < 0) goto err_parse_data; if (desc.type == NFT_DATA_VERDICT && (elem.data.val.verdict.code == NFT_GOTO || elem.data.val.verdict.code == NFT_JUMP)) nft_validate_state_update(ctx->table, NFT_VALIDATE_NEED); } err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); if (err < 0) goto err_parse_data; } /* The full maximum length of userdata can exceed the maximum * offset value (U8_MAX) for following extensions, therefor it * must be the last extension added. */ ulen = 0; if (nla[NFTA_SET_ELEM_USERDATA] != NULL) { ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]); if (ulen > 0) { err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, ulen); if (err < 0) goto err_parse_data; } } elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, elem.key_end.val.data, elem.data.val.data, timeout, expiration, GFP_KERNEL_ACCOUNT); if (IS_ERR(elem.priv)) { err = PTR_ERR(elem.priv); goto err_parse_data; } ext = nft_set_elem_ext(set, elem.priv); if (flags) *nft_set_ext_flags(ext) = flags; if (obj) *nft_set_ext_obj(ext) = obj; if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; goto err_elem_free; } udata = nft_set_ext_userdata(ext); udata->len = ulen - 1; nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen); } err = nft_set_elem_expr_setup(ctx, &tmpl, ext, expr_array, num_exprs); if (err < 0) goto err_elem_free; trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) { err = -ENOMEM; goto err_elem_free; } ext->genmask = nft_genmask_cur(ctx->net); err = nft_setelem_insert(ctx->net, set, &elem, &elem_priv, flags); if (err) { if (err == -EEXIST) { ext2 = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) goto err_element_clash; if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && memcmp(nft_set_ext_data(ext), nft_set_ext_data(ext2), set->dlen) != 0) || (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF) && *nft_set_ext_obj(ext) != *nft_set_ext_obj(ext2))) goto err_element_clash; else if (!(nlmsg_flags & NLM_F_EXCL)) { err = 0; if (nft_set_ext_exists(ext2, NFT_SET_EXT_TIMEOUT)) { struct nft_elem_update update = { }; if (timeout != nft_set_ext_timeout(ext2)->timeout) { update.timeout = timeout; if (expiration == 0) expiration = timeout; update.flags |= NFT_TRANS_UPD_TIMEOUT; } if (expiration) { update.expiration = expiration; update.flags |= NFT_TRANS_UPD_EXPIRATION; } if (update.flags) { struct nft_trans_one_elem *ue; ue = &nft_trans_container_elem(trans)->elems[0]; ue->update = kmemdup(&update, sizeof(update), GFP_KERNEL); if (!ue->update) { err = -ENOMEM; goto err_element_clash; } ue->priv = elem_priv; nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); goto err_elem_free; } } } } else if (err == -ENOTEMPTY) { /* ENOTEMPTY reports overlapping between this element * and an existing one. */ err = -EEXIST; } goto err_element_clash; } if (!(flags & NFT_SET_ELEM_CATCHALL)) { unsigned int max = nft_set_maxsize(set); if (!atomic_add_unless(&set->nelems, 1, max)) { err = -ENFILE; goto err_set_full; } } nft_trans_container_elem(trans)->elems[0].priv = elem.priv; nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); return 0; err_set_full: nft_setelem_remove(ctx->net, set, elem.priv); err_element_clash: kfree(trans); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); err_parse_key_end: if (obj) nft_use_dec_restore(&obj->use); nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); err_set_elem_expr: for (i = 0; i < num_exprs && expr_array[i]; i++) nft_expr_destroy(ctx, expr_array[i]); err_set_elem_expr_clone: return err; } static int nf_tables_newsetelem(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err; if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); } set = nft_set_lookup_global(net, table, nla[NFTA_SET_ELEM_LIST_SET], nla[NFTA_SET_ELEM_LIST_SET_ID], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); } if (!list_empty(&set->bindings) && (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); if (err < 0) { NL_SET_BAD_ATTR(extack, attr); return err; } } if (table->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); return 0; } /** * nft_data_hold - hold a nft_data item * * @data: struct nft_data to release * @type: type of data * * Hold a nft_data item. NFT_DATA_VALUE types can be silently discarded, * NFT_DATA_VERDICT bumps the reference to chains in case of NFT_JUMP and * NFT_GOTO verdicts. This function must be called on active data objects * from the second phase of the commit protocol. */ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { struct nft_chain *chain; if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; nft_use_inc_restore(&chain->use); break; } } } static int nft_setelem_active_next(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); u8 genmask = nft_genmask_next(net); return nft_set_elem_active(ext, genmask); } static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); } /* similar to nft_trans_elems_remove, but called from abort path to undo newsetelem. * No notifications and no ndeact changes. * * Returns true if set had been added to (i.e., elements need to be removed again). */ static bool nft_trans_elems_new_abort(const struct nft_ctx *ctx, struct nft_trans_elem *te) { bool removed = false; int i; for (i = 0; i < te->nelems; i++) { if (te->elems[i].update) { kfree(te->elems[i].update); te->elems[i].update = NULL; /* Update request, so do not release this element */ te->elems[i].priv = NULL; continue; } if (!te->set->ops->abort || nft_setelem_is_catchall(te->set, te->elems[i].priv)) nft_setelem_remove(ctx->net, te->set, te->elems[i].priv); if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) atomic_dec(&te->set->nelems); removed = true; } return removed; } /* Called from abort path to undo DELSETELEM/DESTROYSETELEM. */ static void nft_trans_elems_destroy_abort(const struct nft_ctx *ctx, const struct nft_trans_elem *te) { int i; for (i = 0; i < te->nelems; i++) { if (!nft_setelem_active_next(ctx->net, te->set, te->elems[i].priv)) { nft_setelem_data_activate(ctx->net, te->set, te->elems[i].priv); nft_setelem_activate(ctx->net, te->set, te->elems[i].priv); } if (!nft_setelem_is_catchall(te->set, te->elems[i].priv)) te->set->ndeact--; } } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_ext_tmpl tmpl; struct nft_set_elem elem; struct nft_set_ext *ext; struct nft_trans *trans; u32 flags = 0; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) return err; err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; if (!nft_setelem_valid_key_end(set, nla, flags)) return -EINVAL; nft_set_ext_prepare(&tmpl); if (flags != 0) { err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); if (err < 0) return err; } if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, nla[NFTA_SET_ELEM_KEY]); if (err < 0) return err; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); if (err < 0) goto fail_elem; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) goto fail_elem; err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); if (err < 0) goto fail_elem_key_end; } err = -ENOMEM; elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, elem.key_end.val.data, NULL, 0, 0, GFP_KERNEL_ACCOUNT); if (IS_ERR(elem.priv)) { err = PTR_ERR(elem.priv); goto fail_elem_key_end; } ext = nft_set_elem_ext(set, elem.priv); if (flags) *nft_set_ext_flags(ext) = flags; trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); if (trans == NULL) goto fail_trans; err = nft_setelem_deactivate(ctx->net, set, &elem, flags); if (err < 0) goto fail_ops; nft_setelem_data_deactivate(ctx->net, set, elem.priv); nft_trans_container_elem(trans)->elems[0].priv = elem.priv; nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); return 0; fail_ops: kfree(trans); fail_trans: kfree(elem.priv); fail_elem_key_end: nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); fail_elem: nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; } static int nft_setelem_flush(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_trans *trans; if (!nft_set_elem_active(ext, iter->genmask)) return 0; trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, struct_size_t(struct nft_trans_elem, elems, 1), GFP_ATOMIC); if (!trans) return -ENOMEM; set->ops->flush(ctx->net, set, elem_priv); set->ndeact++; nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; nft_trans_container_elem(trans)->nelems = 1; nft_trans_container_elem(trans)->elems[0].priv = elem_priv; nft_trans_commit_list_add_elem(ctx->net, trans, GFP_ATOMIC); return 0; } static int __nft_set_catchall_flush(const struct nft_ctx *ctx, struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_trans *trans; trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); if (!trans) return -ENOMEM; nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_container_elem(trans)->elems[0].priv = elem_priv; nft_trans_commit_list_add_elem(ctx->net, trans, GFP_KERNEL); return 0; } static int nft_set_catchall_flush(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list, lockdep_commit_lock_is_held(ctx->net)) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; ret = __nft_set_catchall_flush(ctx, set, catchall->elem); if (ret < 0) break; nft_set_elem_change_active(ctx->net, set, ext); } return ret; } static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { struct nft_set_iter iter = { .genmask = genmask, .type = NFT_ITER_UPDATE, .fn = nft_setelem_flush, }; set->ops->walk(ctx, set, &iter); if (!iter.err) iter.err = nft_set_catchall_flush(ctx, set); return iter.err; } static int nf_tables_delsetelem(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err = 0; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); } set = nft_set_lookup(net, table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); } if (nft_set_is_anonymous(set)) return -EOPNOTSUPP; if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return nft_set_flush(&ctx, set, genmask); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); if (err == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSETELEM) continue; if (err < 0) { NL_SET_BAD_ATTR(extack, attr); return err; } } return 0; } /* * Stateful objects */ /** * nft_register_obj- register nf_tables stateful object type * @obj_type: object type * * Registers the object type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. */ int nft_register_obj(struct nft_object_type *obj_type) { if (obj_type->type == NFT_OBJECT_UNSPEC) return -EINVAL; nfnl_lock(NFNL_SUBSYS_NFTABLES); list_add_rcu(&obj_type->list, &nf_tables_objects); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } EXPORT_SYMBOL_GPL(nft_register_obj); /** * nft_unregister_obj - unregister nf_tables object type * @obj_type: object type * * Unregisters the object type for use with nf_tables. */ void nft_unregister_obj(struct nft_object_type *obj_type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_del_rcu(&obj_type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_obj); struct nft_object *nft_obj_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { struct nft_object_hash_key k = { .table = table }; char search[NFT_OBJ_MAXNAMELEN]; struct rhlist_head *tmp, *list; struct nft_object *obj; nla_strscpy(search, nla, sizeof(search)); k.name = search; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_commit_lock_is_held(net)); rcu_read_lock(); list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params); if (!list) goto out; rhl_for_each_entry_rcu(obj, tmp, list, rhlhead) { if (objtype == obj->ops->type->type && nft_active_genmask(obj, genmask)) { rcu_read_unlock(); return obj; } } out: rcu_read_unlock(); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(nft_obj_lookup); static struct nft_object *nft_obj_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { struct nft_object *obj; list_for_each_entry(obj, &table->objects, list) { if (be64_to_cpu(nla_get_be64(nla)) == obj->handle && objtype == obj->ops->type->type && nft_active_genmask(obj, genmask)) return obj; } return ERR_PTR(-ENOENT); } static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { [NFTA_OBJ_TABLE] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_OBJ_NAME] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, [NFTA_OBJ_HANDLE] = { .type = NLA_U64}, [NFTA_OBJ_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, }; static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, const struct nft_object_type *type, const struct nlattr *attr) { struct nlattr **tb; const struct nft_object_ops *ops; struct nft_object *obj; int err = -ENOMEM; tb = kmalloc_array(type->maxattr + 1, sizeof(*tb), GFP_KERNEL); if (!tb) goto err1; if (attr) { err = nla_parse_nested_deprecated(tb, type->maxattr, attr, type->policy, NULL); if (err < 0) goto err2; } else { memset(tb, 0, sizeof(tb[0]) * (type->maxattr + 1)); } if (type->select_ops) { ops = type->select_ops(ctx, (const struct nlattr * const *)tb); if (IS_ERR(ops)) { err = PTR_ERR(ops); goto err2; } } else { ops = type->ops; } err = -ENOMEM; obj = kzalloc(sizeof(*obj) + ops->size, GFP_KERNEL_ACCOUNT); if (!obj) goto err2; err = ops->init(ctx, (const struct nlattr * const *)tb, obj); if (err < 0) goto err3; obj->ops = ops; kfree(tb); return obj; err3: kfree(obj); err2: kfree(tb); err1: return ERR_PTR(err); } static int nft_object_dump(struct sk_buff *skb, unsigned int attr, struct nft_object *obj, bool reset) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; if (obj->ops->dump(skb, obj, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; list_for_each_entry_rcu(type, &nf_tables_objects, list) { if (type->family != NFPROTO_UNSPEC && type->family != family) continue; if (objtype == type->type) return type; } return NULL; } static const struct nft_object_type * nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; rcu_read_lock(); type = __nft_obj_type_get(objtype, family); if (type != NULL && try_module_get(type->owner)) { rcu_read_unlock(); return type; } rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } static int nf_tables_updobj(const struct nft_ctx *ctx, const struct nft_object_type *type, const struct nlattr *attr, struct nft_object *obj) { struct nft_object *newobj; struct nft_trans *trans; int err = -ENOMEM; /* caller must have obtained type->owner reference. */ trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) goto err_trans; newobj = nft_obj_init(ctx, type, attr); if (IS_ERR(newobj)) { err = PTR_ERR(newobj); goto err_free_trans; } nft_trans_obj(trans) = obj; nft_trans_obj_update(trans) = true; nft_trans_obj_newobj(trans) = newobj; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_free_trans: kfree(trans); err_trans: module_put(type->owner); return err; } static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_object_type *type; struct net *net = info->net; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; u32 objtype; int err; if (!nla[NFTA_OBJ_TYPE] || !nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_DATA]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); if (err != -ENOENT) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return err; } } else { if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return -EEXIST; } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (!obj->ops->update) return 0; type = nft_obj_type_get(net, objtype, family); if (WARN_ON_ONCE(IS_ERR(type))) return PTR_ERR(type); nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); /* type->owner reference is put when transaction object is released. */ return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (!nft_use_inc(&table->use)) return -EMFILE; type = nft_obj_type_get(net, objtype, family); if (IS_ERR(type)) { err = PTR_ERR(type); goto err_type; } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { err = PTR_ERR(obj); goto err_init; } obj->key.table = table; obj->handle = nf_tables_alloc_handle(table); obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL_ACCOUNT); if (!obj->key.name) { err = -ENOMEM; goto err_strdup; } if (nla[NFTA_OBJ_USERDATA]) { obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL_ACCOUNT); if (obj->udata == NULL) goto err_userdata; obj->udlen = nla_len(nla[NFTA_OBJ_USERDATA]); } err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); if (err < 0) goto err_trans; err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); if (err < 0) goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); return 0; err_obj_ht: /* queued in transaction log */ INIT_LIST_HEAD(&obj->list); return err; err_trans: kfree(obj->udata); err_userdata: kfree(obj->key.name); err_strdup: if (obj->ops->destroy) obj->ops->destroy(&ctx, obj); kfree(obj); err_init: module_put(type->owner); err_type: nft_use_dec_restore(&table->use); return err; } static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, struct nft_object *obj, bool reset) { struct nlmsghdr *nlh; nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || nla_put_be64(skb, NFTA_OBJ_HANDLE, cpu_to_be64(obj->handle), NFTA_OBJ_PAD)) goto nla_put_failure; if (event == NFT_MSG_DELOBJ || event == NFT_MSG_DESTROYOBJ) { nlmsg_end(skb, nlh); return 0; } if (nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset)) goto nla_put_failure; if (obj->udata && nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } static void audit_log_obj_reset(const struct nft_table *table, unsigned int base_seq, unsigned int nentries) { char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); audit_log_nfcfg(buf, table->family, nentries, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); } struct nft_obj_dump_ctx { unsigned int s_idx; char *table; u32 type; bool reset; }; static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int entries = 0; struct nft_object *obj; unsigned int idx = 0; int rc = 0; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; entries = 0; list_for_each_entry_rcu(obj, &table->objects, list) { if (!nft_is_active(net, obj)) goto cont; if (idx < ctx->s_idx) goto cont; if (ctx->table && strcmp(ctx->table, table->name)) goto cont; if (ctx->type != NFT_OBJECT_UNSPEC && obj->ops->type->type != ctx->type) goto cont; rc = nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, NLM_F_MULTI | NLM_F_APPEND, table->family, table, obj, ctx->reset); if (rc < 0) break; entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } if (ctx->reset && entries) audit_log_obj_reset(table, nft_net->base_seq, entries); if (rc < 0) break; } rcu_read_unlock(); ctx->s_idx = idx; return skb->len; } static int nf_tables_dumpreset_obj(struct sk_buff *skb, struct netlink_callback *cb) { struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); int ret; mutex_lock(&nft_net->commit_mutex); ret = nf_tables_dump_obj(skb, cb); mutex_unlock(&nft_net->commit_mutex); return ret; } static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; const struct nlattr * const *nla = cb->data; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); if (nla[NFTA_OBJ_TABLE]) { ctx->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); if (!ctx->table) return -ENOMEM; } if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); return 0; } static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; ctx->reset = true; return nf_tables_dump_obj_start(cb); } static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; kfree(ctx->table); return 0; } /* Caller must hold rcu read lock or transaction mutex */ static struct sk_buff * nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; u32 objtype; int err; if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) return ERR_PTR(-EINVAL); table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return ERR_CAST(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return ERR_CAST(obj); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); err = nf_tables_fill_obj_info(skb2, net, portid, info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) { kfree_skb(skb2); return ERR_PTR(err); } return skb2; } static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { u32 portid = NETLINK_CB(skb).portid; struct sk_buff *skb2; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } skb2 = nf_tables_getobj_single(portid, info, nla, false); if (IS_ERR(skb2)) return PTR_ERR(skb2); return nfnetlink_unicast(skb2, info->net, portid); } static int nf_tables_getobj_reset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); u32 portid = NETLINK_CB(skb).portid; struct net *net = info->net; struct sk_buff *skb2; char *buf; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dumpreset_obj_start, .dump = nf_tables_dumpreset_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); mutex_lock(&nft_net->commit_mutex); skb2 = nf_tables_getobj_single(portid, info, nla, true); mutex_unlock(&nft_net->commit_mutex); rcu_read_lock(); module_put(THIS_MODULE); if (IS_ERR(skb2)) return PTR_ERR(skb2); buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_OBJ_TABLE]), (char *)nla_data(nla[NFTA_OBJ_TABLE]), nft_net->base_seq); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); return nfnetlink_unicast(skb2, net, portid); } static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { if (obj->ops->destroy) obj->ops->destroy(ctx, obj); module_put(obj->ops->type->owner); kfree(obj->key.name); kfree(obj->udata); kfree(obj); } static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; u32 objtype; if (!nla[NFTA_OBJ_TYPE] || (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE])) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); if (nla[NFTA_OBJ_HANDLE]) { attr = nla[NFTA_OBJ_HANDLE]; obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask); } else { attr = nla[NFTA_OBJ_NAME]; obj = nft_obj_lookup(net, table, attr, objtype, genmask); } if (IS_ERR(obj)) { if (PTR_ERR(obj) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYOBJ) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(obj); } if (obj->use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_delobj(&ctx, obj); } static void __nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, gfp); if (skb == NULL) goto err; err = nf_tables_fill_obj_info(skb, net, portid, seq, event, flags & (NLM_F_CREATE | NLM_F_EXCL), family, table, obj, false); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); char *buf = kasprintf(gfp, "%s:%u", table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, obj->handle, event == NFT_MSG_NEWOBJ ? AUDIT_NFT_OP_OBJ_REGISTER : AUDIT_NFT_OP_OBJ_UNREGISTER, gfp); kfree(buf); __nft_obj_notify(net, table, obj, portid, seq, event, flags, family, report, gfp); } EXPORT_SYMBOL_GPL(nft_obj_notify); static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { __nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, ctx->flags, ctx->family, ctx->report, GFP_KERNEL); } /* * Flow tables */ void nft_register_flowtable_type(struct nf_flowtable_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_add_tail_rcu(&type->list, &nf_tables_flowtables); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_register_flowtable_type); void nft_unregister_flowtable_type(struct nf_flowtable_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_flowtable_type); static const struct nla_policy nft_flowtable_policy[NFTA_FLOWTABLE_MAX + 1] = { [NFTA_FLOWTABLE_TABLE] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, [NFTA_FLOWTABLE_NAME] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, [NFTA_FLOWTABLE_HOOK] = { .type = NLA_NESTED }, [NFTA_FLOWTABLE_HANDLE] = { .type = NLA_U64 }, [NFTA_FLOWTABLE_FLAGS] = { .type = NLA_U32 }, }; struct nft_flowtable *nft_flowtable_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; list_for_each_entry_rcu(flowtable, &table->flowtables, list, lockdep_commit_lock_is_held(net)) { if (!nla_strcmp(nla, flowtable->name) && nft_active_genmask(flowtable, genmask)) return flowtable; } return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(nft_flowtable_lookup); void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, struct nft_flowtable *flowtable, enum nft_trans_phase phase) { switch (phase) { case NFT_TRANS_PREPARE_ERROR: case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: nft_use_dec(&flowtable->use); fallthrough; default: return; } } EXPORT_SYMBOL_GPL(nf_tables_deactivate_flowtable); static struct nft_flowtable * nft_flowtable_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; list_for_each_entry(flowtable, &table->flowtables, list) { if (be64_to_cpu(nla_get_be64(nla)) == flowtable->handle && nft_active_genmask(flowtable, genmask)) return flowtable; } return ERR_PTR(-ENOENT); } struct nft_flowtable_hook { u32 num; int priority; struct list_head list; }; static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = { [NFTA_FLOWTABLE_HOOK_NUM] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_PRIORITY] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_DEVS] = { .type = NLA_NESTED }, }; static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, const struct nlattr * const nla[], struct nft_flowtable_hook *flowtable_hook, struct nft_flowtable *flowtable, struct netlink_ext_ack *extack, bool add) { struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1]; struct nf_hook_ops *ops; struct nft_hook *hook; int hooknum, priority; int err; INIT_LIST_HEAD(&flowtable_hook->list); err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, nla[NFTA_FLOWTABLE_HOOK], nft_flowtable_hook_policy, NULL); if (err < 0) return err; if (add) { if (!tb[NFTA_FLOWTABLE_HOOK_NUM] || !tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -ENOENT; } hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); if (hooknum != NF_NETDEV_INGRESS) return -EOPNOTSUPP; priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); flowtable_hook->priority = priority; flowtable_hook->num = hooknum; } else { if (tb[NFTA_FLOWTABLE_HOOK_NUM]) { hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); if (hooknum != flowtable->hooknum) return -EOPNOTSUPP; } if (tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) { priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); if (priority != flowtable->data.priority) return -EOPNOTSUPP; } flowtable_hook->priority = flowtable->data.priority; flowtable_hook->num = flowtable->hooknum; } if (tb[NFTA_FLOWTABLE_HOOK_DEVS]) { err = nf_tables_parse_netdev_hooks(ctx->net, tb[NFTA_FLOWTABLE_HOOK_DEVS], &flowtable_hook->list, extack); if (err < 0) return err; } list_for_each_entry(hook, &flowtable_hook->list, list) { list_for_each_entry(ops, &hook->ops_list, list) { ops->pf = NFPROTO_NETDEV; ops->hooknum = flowtable_hook->num; ops->priority = flowtable_hook->priority; ops->priv = &flowtable->data; ops->hook = flowtable->data.type->hook; ops->hook_ops_type = NF_HOOK_OP_NFT_FT; } } return err; } /* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } return NULL; } static const struct nf_flowtable_type * nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; rcu_read_lock(); type = __nft_flowtable_type_get(family); if (type != NULL && try_module_get(type->owner)) { rcu_read_unlock(); return type; } rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif return ERR_PTR(-ENOENT); } /* Only called from error and netdev event paths. */ static void nft_unregister_flowtable_ops(struct net *net, struct nft_flowtable *flowtable, struct nf_hook_ops *ops) { nf_unregister_net_hook(net, ops); flowtable->data.type->setup(&flowtable->data, ops->dev, FLOW_BLOCK_UNBIND); } static void __nft_unregister_flowtable_net_hooks(struct net *net, struct nft_flowtable *flowtable, struct list_head *hook_list, bool release_netdev) { struct nft_hook *hook, *next; struct nf_hook_ops *ops; list_for_each_entry_safe(hook, next, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) nft_unregister_flowtable_ops(net, flowtable, ops); if (release_netdev) { list_del(&hook->list); nft_netdev_hook_free_rcu(hook); } } } static void nft_unregister_flowtable_net_hooks(struct net *net, struct nft_flowtable *flowtable, struct list_head *hook_list) { __nft_unregister_flowtable_net_hooks(net, flowtable, hook_list, false); } static int nft_register_flowtable_ops(struct net *net, struct nft_flowtable *flowtable, struct nf_hook_ops *ops) { int err; err = flowtable->data.type->setup(&flowtable->data, ops->dev, FLOW_BLOCK_BIND); if (err < 0) return err; err = nf_register_net_hook(net, ops); if (!err) return 0; flowtable->data.type->setup(&flowtable->data, ops->dev, FLOW_BLOCK_UNBIND); return err; } static int nft_register_flowtable_net_hooks(struct net *net, struct nft_table *table, struct list_head *hook_list, struct nft_flowtable *flowtable) { struct nft_hook *hook, *next; struct nft_flowtable *ft; struct nf_hook_ops *ops; int err, i = 0; list_for_each_entry(hook, hook_list, list) { list_for_each_entry(ft, &table->flowtables, list) { if (!nft_is_active_next(net, ft)) continue; if (nft_hook_list_find(&ft->hook_list, hook)) { err = -EEXIST; goto err_unregister_net_hooks; } } list_for_each_entry(ops, &hook->ops_list, list) { err = nft_register_flowtable_ops(net, flowtable, ops); if (err < 0) goto err_unregister_net_hooks; i++; } } return 0; err_unregister_net_hooks: list_for_each_entry_safe(hook, next, hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (i-- <= 0) break; nft_unregister_flowtable_ops(net, flowtable, ops); } list_del_rcu(&hook->list); nft_netdev_hook_free_rcu(hook); } return err; } static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; list_for_each_entry_safe(hook, next, hook_list, list) { list_del_rcu(&hook->list); nft_netdev_hook_free_rcu(hook); } } static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, struct nft_flowtable *flowtable, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; struct nftables_pernet *nft_net; struct nft_hook *hook, *next; struct nf_hook_ops *ops; struct nft_trans *trans; bool unregister = false; u32 flags; int err; err = nft_flowtable_parse_hook(ctx, nla, &flowtable_hook, flowtable, extack, false); if (err < 0) return err; list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { if (nft_hook_list_find(&flowtable->hook_list, hook)) { list_del(&hook->list); nft_netdev_hook_free(hook); continue; } nft_net = nft_pernet(ctx->net); list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type != NFT_MSG_NEWFLOWTABLE || trans->table != ctx->table || !nft_trans_flowtable_update(trans)) continue; if (nft_hook_list_find(&nft_trans_flowtable_hooks(trans), hook)) { err = -EEXIST; goto err_flowtable_update_hook; } } } if (nla[NFTA_FLOWTABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); if (flags & ~NFT_FLOWTABLE_MASK) { err = -EOPNOTSUPP; goto err_flowtable_update_hook; } if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^ (flags & NFT_FLOWTABLE_HW_OFFLOAD)) { err = -EOPNOTSUPP; goto err_flowtable_update_hook; } } else { flags = flowtable->data.flags; } err = nft_register_flowtable_net_hooks(ctx->net, ctx->table, &flowtable_hook.list, flowtable); if (err < 0) goto err_flowtable_update_hook; trans = nft_trans_alloc(ctx, NFT_MSG_NEWFLOWTABLE, sizeof(struct nft_trans_flowtable)); if (!trans) { unregister = true; err = -ENOMEM; goto err_flowtable_update_hook; } nft_trans_flowtable_flags(trans) = flags; nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans)); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_flowtable_update_hook: list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { if (unregister) { list_for_each_entry(ops, &hook->ops_list, list) nft_unregister_flowtable_ops(ctx->net, flowtable, ops); } list_del_rcu(&hook->list); nft_netdev_hook_free_rcu(hook); } return err; } static int nf_tables_newflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; struct nft_flowtable_hook flowtable_hook; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; struct nft_flowtable *flowtable; struct net *net = info->net; struct nft_table *table; struct nft_trans *trans; struct nft_ctx ctx; int err; if (!nla[NFTA_FLOWTABLE_TABLE] || !nla[NFTA_FLOWTABLE_NAME] || !nla[NFTA_FLOWTABLE_HOOK]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); } flowtable = nft_flowtable_lookup(net, table, nla[NFTA_FLOWTABLE_NAME], genmask); if (IS_ERR(flowtable)) { err = PTR_ERR(flowtable); if (err != -ENOENT) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return err; } } else { if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -EEXIST; } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_flowtable_update(&ctx, info->nlh, flowtable, extack); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (!nft_use_inc(&table->use)) return -EMFILE; flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); if (!flowtable) { err = -ENOMEM; goto flowtable_alloc; } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); INIT_LIST_HEAD(&flowtable->hook_list); flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL_ACCOUNT); if (!flowtable->name) { err = -ENOMEM; goto err1; } type = nft_flowtable_type_get(net, family); if (IS_ERR(type)) { err = PTR_ERR(type); goto err2; } if (nla[NFTA_FLOWTABLE_FLAGS]) { flowtable->data.flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK) { err = -EOPNOTSUPP; goto err3; } } write_pnet(&flowtable->data.net, net); flowtable->data.type = type; err = type->init(&flowtable->data); if (err < 0) goto err3; err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable, extack, true); if (err < 0) goto err_flowtable_parse_hooks; list_splice(&flowtable_hook.list, &flowtable->hook_list); flowtable->data.priority = flowtable_hook.priority; flowtable->hooknum = flowtable_hook.num; trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto err_flowtable_trans; } /* This must be LAST to ensure no packets are walking over this flowtable. */ err = nft_register_flowtable_net_hooks(ctx.net, table, &flowtable->hook_list, flowtable); if (err < 0) goto err_flowtable_hooks; list_add_tail_rcu(&flowtable->list, &table->flowtables); return 0; err_flowtable_hooks: nft_trans_destroy(trans); err_flowtable_trans: nft_hooks_destroy(&flowtable->hook_list); err_flowtable_parse_hooks: flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); err2: kfree(flowtable->name); err1: kfree(flowtable); flowtable_alloc: nft_use_dec_restore(&table->use); return err; } static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook) { struct nft_hook *this, *next; list_for_each_entry_safe(this, next, &flowtable_hook->list, list) { list_del(&this->list); nft_netdev_hook_free(this); } } static int nft_delflowtable_hook(struct nft_ctx *ctx, struct nft_flowtable *flowtable, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; LIST_HEAD(flowtable_del_list); struct nft_hook *this, *hook; struct nft_trans *trans; int err; err = nft_flowtable_parse_hook(ctx, nla, &flowtable_hook, flowtable, extack, false); if (err < 0) return err; list_for_each_entry(this, &flowtable_hook.list, list) { hook = nft_hook_list_find(&flowtable->hook_list, this); if (!hook) { err = -ENOENT; goto err_flowtable_del_hook; } list_move(&hook->list, &flowtable_del_list); } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, sizeof(struct nft_trans_flowtable)); if (!trans) { err = -ENOMEM; goto err_flowtable_del_hook; } nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); list_splice(&flowtable_del_list, &nft_trans_flowtable_hooks(trans)); nft_flowtable_hook_release(&flowtable_hook); nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_flowtable_del_hook: list_splice(&flowtable_del_list, &flowtable->hook_list); nft_flowtable_hook_release(&flowtable_hook); return err; } static int nf_tables_delflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; if (!nla[NFTA_FLOWTABLE_TABLE] || (!nla[NFTA_FLOWTABLE_NAME] && !nla[NFTA_FLOWTABLE_HANDLE])) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); } if (nla[NFTA_FLOWTABLE_HANDLE]) { attr = nla[NFTA_FLOWTABLE_HANDLE]; flowtable = nft_flowtable_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_FLOWTABLE_NAME]; flowtable = nft_flowtable_lookup(net, table, attr, genmask); } if (IS_ERR(flowtable)) { if (PTR_ERR(flowtable) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYFLOWTABLE) return 0; NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(flowtable); } nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (nla[NFTA_FLOWTABLE_HOOK]) return nft_delflowtable_hook(&ctx, flowtable, extack); if (flowtable->use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } return nft_delflowtable(&ctx, flowtable); } static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, struct nft_flowtable *flowtable, struct list_head *hook_list) { struct nlattr *nest, *nest_devs; struct nft_hook *hook; struct nlmsghdr *nlh; nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, family, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) || nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) || nla_put_be64(skb, NFTA_FLOWTABLE_HANDLE, cpu_to_be64(flowtable->handle), NFTA_FLOWTABLE_PAD)) goto nla_put_failure; if (!hook_list && (event == NFT_MSG_DELFLOWTABLE || event == NFT_MSG_DESTROYFLOWTABLE)) { nlmsg_end(skb, nlh); return 0; } if (nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) || nla_put_be32(skb, NFTA_FLOWTABLE_FLAGS, htonl(flowtable->data.flags))) goto nla_put_failure; nest = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK); if (!nest) goto nla_put_failure; if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) || nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->data.priority))) goto nla_put_failure; nest_devs = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK_DEVS); if (!nest_devs) goto nla_put_failure; if (!hook_list) hook_list = &flowtable->hook_list; list_for_each_entry_rcu(hook, hook_list, list, lockdep_commit_lock_is_held(net)) { if (nla_put(skb, NFTA_DEVICE_NAME, hook->ifnamelen, hook->ifname)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -1; } struct nft_flowtable_filter { char *table; }; static int nf_tables_dump_flowtable(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nft_flowtable_filter *filter = cb->data; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct nftables_pernet *nft_net; const struct nft_table *table; rcu_read_lock(); nft_net = nft_pernet(net); cb->seq = READ_ONCE(nft_net->base_seq); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; list_for_each_entry_rcu(flowtable, &table->flowtables, list) { if (!nft_is_active(net, flowtable)) goto cont; if (idx < s_idx) goto cont; if (idx > s_idx) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (filter && filter->table && strcmp(filter->table, table->name)) goto cont; if (nf_tables_fill_flowtable_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, NLM_F_MULTI | NLM_F_APPEND, table->family, flowtable, NULL) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } } done: rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static int nf_tables_dump_flowtable_start(struct netlink_callback *cb) { const struct nlattr * const *nla = cb->data; struct nft_flowtable_filter *filter = NULL; if (nla[NFTA_FLOWTABLE_TABLE]) { filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) return -ENOMEM; filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], GFP_ATOMIC); if (!filter->table) { kfree(filter); return -ENOMEM; } } cb->data = filter; return 0; } static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) { struct nft_flowtable_filter *filter = cb->data; if (!filter) return 0; kfree(filter->table); kfree(filter); return 0; } /* called with rcu_read_lock held */ static int nf_tables_getflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; const struct nft_table *table; struct net *net = info->net; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, .module = THIS_MODULE, .data = (void *)nla, }; return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_FLOWTABLE_NAME]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); } flowtable = nft_flowtable_lookup(net, table, nla[NFTA_FLOWTABLE_NAME], genmask); if (IS_ERR(flowtable)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return PTR_ERR(flowtable); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, 0, family, flowtable, NULL); if (err < 0) goto err_fill_flowtable_info; return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); err_fill_flowtable_info: kfree_skb(skb2); return err; } static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct nft_flowtable *flowtable, struct list_head *hook_list, int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) goto err; if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, flowtable, hook_list); if (err < 0) { kfree_skb(skb); goto err; } nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { struct nft_hook *hook, *next; flowtable->data.type->free(&flowtable->data); list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { list_del_rcu(&hook->list); nft_netdev_hook_free_rcu(hook); } kfree(flowtable->name); module_put(flowtable->data.type->owner); kfree(flowtable); } static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { struct nftables_pernet *nft_net = nft_pernet(net); struct nlmsghdr *nlh; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, NFNETLINK_V0, nft_base_seq(net)); if (!nlh) goto nla_put_failure; if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_trim(skb, nlh); return -EMSGSIZE; } struct nf_hook_ops *nft_hook_find_ops(const struct nft_hook *hook, const struct net_device *dev) { struct nf_hook_ops *ops; list_for_each_entry(ops, &hook->ops_list, list) { if (ops->dev == dev) return ops; } return NULL; } EXPORT_SYMBOL_GPL(nft_hook_find_ops); struct nf_hook_ops *nft_hook_find_ops_rcu(const struct nft_hook *hook, const struct net_device *dev) { struct nf_hook_ops *ops; list_for_each_entry_rcu(ops, &hook->ops_list, list) { if (ops->dev == dev) return ops; } return NULL; } EXPORT_SYMBOL_GPL(nft_hook_find_ops_rcu); static int nft_flowtable_event(unsigned long event, struct net_device *dev, struct nft_flowtable *flowtable, bool changename) { struct nf_hook_ops *ops; struct nft_hook *hook; bool match; list_for_each_entry(hook, &flowtable->hook_list, list) { ops = nft_hook_find_ops(hook, dev); match = !strncmp(hook->ifname, dev->name, hook->ifnamelen); switch (event) { case NETDEV_UNREGISTER: /* NOP if not found or new name still matching */ if (!ops || (changename && match)) continue; /* flow_offload_netdev_event() cleans up entries for us. */ nft_unregister_flowtable_ops(dev_net(dev), flowtable, ops); list_del_rcu(&ops->list); kfree_rcu(ops, rcu); break; case NETDEV_REGISTER: /* NOP if not matching or already registered */ if (!match || (changename && ops)) continue; ops = kzalloc(sizeof(struct nf_hook_ops), GFP_KERNEL_ACCOUNT); if (!ops) return 1; ops->pf = NFPROTO_NETDEV; ops->hooknum = flowtable->hooknum; ops->priority = flowtable->data.priority; ops->priv = &flowtable->data; ops->hook = flowtable->data.type->hook; ops->hook_ops_type = NF_HOOK_OP_NFT_FT; ops->dev = dev; if (nft_register_flowtable_ops(dev_net(dev), flowtable, ops)) { kfree(ops); return 1; } list_add_tail_rcu(&ops->list, &hook->ops_list); break; } break; } return 0; } static int __nf_tables_flowtable_event(unsigned long event, struct net_device *dev, bool changename) { struct nftables_pernet *nft_net = nft_pernet(dev_net(dev)); struct nft_flowtable *flowtable; struct nft_table *table; list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { if (nft_flowtable_event(event, dev, flowtable, changename)) return 1; } } return 0; } static int nf_tables_flowtable_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; int ret = NOTIFY_DONE; struct net *net; if (event != NETDEV_REGISTER && event != NETDEV_UNREGISTER && event != NETDEV_CHANGENAME) return NOTIFY_DONE; net = dev_net(dev); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); if (event == NETDEV_CHANGENAME) { if (__nf_tables_flowtable_event(NETDEV_REGISTER, dev, true)) { ret = NOTIFY_BAD; goto out_unlock; } __nf_tables_flowtable_event(NETDEV_UNREGISTER, dev, true); } else if (__nf_tables_flowtable_event(event, dev, false)) { ret = NOTIFY_BAD; } out_unlock: mutex_unlock(&nft_net->commit_mutex); return ret; } static struct notifier_block nf_tables_flowtable_notifier = { .notifier_call = nf_tables_flowtable_event, }; static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb, int event) { struct nlmsghdr *nlh = nlmsg_hdr(skb); struct sk_buff *skb2; int err; if (!nlmsg_report(nlh) && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; skb2 = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb2 == NULL) goto err; err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq); if (err < 0) { kfree_skb(skb2); goto err; } nfnetlink_send(skb2, net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES, nlmsg_report(nlh), GFP_KERNEL); return; err: nfnetlink_set_err(net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES, -ENOBUFS); } static int nf_tables_getgen(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct sk_buff *skb2; int err; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb2 == NULL) return -ENOMEM; err = nf_tables_fill_gen_info(skb2, info->net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq); if (err < 0) goto err_fill_gen_info; return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); err_fill_gen_info: kfree_skb(skb2); return err; } static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { [NFT_MSG_NEWTABLE] = { .call = nf_tables_newtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_GETTABLE] = { .call = nf_tables_gettable, .type = NFNL_CB_RCU, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_DELTABLE] = { .call = nf_tables_deltable, .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_DESTROYTABLE] = { .call = nf_tables_deltable, .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_NEWCHAIN] = { .call = nf_tables_newchain, .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_GETCHAIN] = { .call = nf_tables_getchain, .type = NFNL_CB_RCU, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_DELCHAIN] = { .call = nf_tables_delchain, .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_DESTROYCHAIN] = { .call = nf_tables_delchain, .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_NEWRULE] = { .call = nf_tables_newrule, .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_GETRULE] = { .call = nf_tables_getrule, .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_GETRULE_RESET] = { .call = nf_tables_getrule_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_DELRULE] = { .call = nf_tables_delrule, .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_DESTROYRULE] = { .call = nf_tables_delrule, .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_NEWSET] = { .call = nf_tables_newset, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_GETSET] = { .call = nf_tables_getset, .type = NFNL_CB_RCU, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_DELSET] = { .call = nf_tables_delset, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_DESTROYSET] = { .call = nf_tables_delset, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_NEWSETELEM] = { .call = nf_tables_newsetelem, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETSETELEM] = { .call = nf_tables_getsetelem, .type = NFNL_CB_RCU, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETSETELEM_RESET] = { .call = nf_tables_getsetelem_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_DELSETELEM] = { .call = nf_tables_delsetelem, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_DESTROYSETELEM] = { .call = nf_tables_delsetelem, .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETGEN] = { .call = nf_tables_getgen, .type = NFNL_CB_RCU, }, [NFT_MSG_NEWOBJ] = { .call = nf_tables_newobj, .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ] = { .call = nf_tables_getobj, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_DELOBJ] = { .call = nf_tables_delobj, .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_DESTROYOBJ] = { .call = nf_tables_delobj, .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_NEWFLOWTABLE] = { .call = nf_tables_newflowtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_GETFLOWTABLE] = { .call = nf_tables_getflowtable, .type = NFNL_CB_RCU, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_DELFLOWTABLE] = { .call = nf_tables_delflowtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_DESTROYFLOWTABLE] = { .call = nf_tables_delflowtable, .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, }; static int nf_tables_validate(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; list_for_each_entry(table, &nft_net->tables, list) { switch (table->validate_state) { case NFT_VALIDATE_SKIP: continue; case NFT_VALIDATE_NEED: nft_validate_state_update(table, NFT_VALIDATE_DO); fallthrough; case NFT_VALIDATE_DO: if (nft_table_validate(net, table) < 0) return -EAGAIN; nft_validate_state_update(table, NFT_VALIDATE_SKIP); break; } } return 0; } /* a drop policy has to be deferred until all rules have been activated, * otherwise a large ruleset that contains a drop-policy base chain will * cause all packets to get dropped until the full transaction has been * processed. * * We defer the drop policy until the transaction has been finalized. */ static void nft_chain_commit_drop_policy(struct nft_trans_chain *trans) { struct nft_base_chain *basechain; if (trans->policy != NF_DROP) return; if (!nft_is_base_chain(trans->chain)) return; basechain = nft_base_chain(trans->chain); basechain->policy = NF_DROP; } static void nft_chain_commit_update(struct nft_trans_chain *trans) { struct nft_table *table = trans->nft_trans_binding.nft_trans.table; struct nft_base_chain *basechain; if (trans->name) { rhltable_remove(&table->chains_ht, &trans->chain->rhlhead, nft_chain_ht_params); swap(trans->chain->name, trans->name); rhltable_insert_key(&table->chains_ht, trans->chain->name, &trans->chain->rhlhead, nft_chain_ht_params); } if (!nft_is_base_chain(trans->chain)) return; nft_chain_stats_replace(trans); basechain = nft_base_chain(trans->chain); switch (trans->policy) { case NF_DROP: case NF_ACCEPT: basechain->policy = trans->policy; break; } } static void nft_obj_commit_update(const struct nft_ctx *ctx, struct nft_trans *trans) { struct nft_object *newobj; struct nft_object *obj; obj = nft_trans_obj(trans); newobj = nft_trans_obj_newobj(trans); if (WARN_ON_ONCE(!obj->ops->update)) return; obj->ops->update(obj, newobj); nft_obj_destroy(ctx, newobj); } static void nft_commit_release(struct nft_trans *trans) { struct nft_ctx ctx = { .net = trans->net, }; nft_ctx_update(&ctx, trans); switch (trans->msg_type) { case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: nf_tables_table_destroy(trans->table); break; case NFT_MSG_NEWCHAIN: free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) nft_hooks_destroy(&nft_trans_chain_hooks(trans)); else nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: nf_tables_rule_destroy(&ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: nft_set_destroy(&ctx, nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: nft_trans_elems_destroy(&ctx, nft_trans_container_elem(trans)); break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: nft_obj_destroy(&ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } if (trans->put_net) put_net(trans->net); kfree(trans); } static void nf_tables_trans_destroy_work(struct work_struct *w) { struct nftables_pernet *nft_net = container_of(w, struct nftables_pernet, destroy_work); struct nft_trans *trans, *next; LIST_HEAD(head); spin_lock(&nf_tables_destroy_list_lock); list_splice_init(&nft_net->destroy_list, &head); spin_unlock(&nf_tables_destroy_list_lock); if (list_empty(&head)) return; synchronize_rcu(); list_for_each_entry_safe(trans, next, &head, list) { nft_trans_list_del(trans); nft_commit_release(trans); } } void nf_tables_trans_destroy_flush_work(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); flush_work(&nft_net->destroy_work); } EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); static bool nft_expr_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { return false; } static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) { const struct nft_expr *expr, *last; struct nft_regs_track track = {}; unsigned int size, data_size; void *data, *data_boundary; struct nft_rule_dp *prule; struct nft_rule *rule; /* already handled or inactive chain? */ if (chain->blob_next || !nft_is_active_next(net, chain)) return 0; data_size = 0; list_for_each_entry(rule, &chain->rules, list) { if (nft_is_active_next(net, rule)) { data_size += sizeof(*prule) + rule->dlen; if (data_size > INT_MAX) return -ENOMEM; } } chain->blob_next = nf_tables_chain_alloc_rules(chain, data_size); if (!chain->blob_next) return -ENOMEM; data = (void *)chain->blob_next->data; data_boundary = data + data_size; size = 0; list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(net, rule)) continue; prule = (struct nft_rule_dp *)data; data += offsetof(struct nft_rule_dp, data); if (WARN_ON_ONCE(data > data_boundary)) return -ENOMEM; size = 0; track.last = nft_expr_last(rule); nft_rule_for_each_expr(expr, last, rule) { track.cur = expr; if (nft_expr_reduce(&track, expr)) { expr = track.cur; continue; } if (WARN_ON_ONCE(data + size + expr->ops->size > data_boundary)) return -ENOMEM; memcpy(data + size, expr, expr->ops->size); size += expr->ops->size; } if (WARN_ON_ONCE(size >= 1 << 12)) return -ENOMEM; prule->handle = rule->handle; prule->dlen = size; prule->is_last = 0; data += size; size = 0; chain->blob_next->size += (unsigned long)(data - (void *)prule); } if (WARN_ON_ONCE(data > data_boundary)) return -ENOMEM; prule = (struct nft_rule_dp *)data; nft_last_rule(chain, prule); return 0; } static void nf_tables_commit_chain_prepare_cancel(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { struct nft_chain *chain = nft_trans_rule_chain(trans); kvfree(chain->blob_next); chain->blob_next = NULL; } } } static void __nf_tables_commit_chain_free_rules(struct rcu_head *h) { struct nft_rule_dp_last *l = container_of(h, struct nft_rule_dp_last, h); kvfree(l->blob); } static void nf_tables_commit_chain_free_rules_old(struct nft_rule_blob *blob) { struct nft_rule_dp_last *last; /* last rule trailer is after end marker */ last = (void *)blob + sizeof(*blob) + blob->size; last->blob = blob; call_rcu(&last->h, __nf_tables_commit_chain_free_rules); } static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) { struct nft_rule_blob *g0, *g1; bool next_genbit; next_genbit = nft_gencursor_next(net); g0 = rcu_dereference_protected(chain->blob_gen_0, lockdep_commit_lock_is_held(net)); g1 = rcu_dereference_protected(chain->blob_gen_1, lockdep_commit_lock_is_held(net)); /* No changes to this chain? */ if (chain->blob_next == NULL) { /* chain had no change in last or next generation */ if (g0 == g1) return; /* * chain had no change in this generation; make sure next * one uses same rules as current generation. */ if (next_genbit) { rcu_assign_pointer(chain->blob_gen_1, g0); nf_tables_commit_chain_free_rules_old(g1); } else { rcu_assign_pointer(chain->blob_gen_0, g1); nf_tables_commit_chain_free_rules_old(g0); } return; } if (next_genbit) rcu_assign_pointer(chain->blob_gen_1, chain->blob_next); else rcu_assign_pointer(chain->blob_gen_0, chain->blob_next); chain->blob_next = NULL; if (g0 == g1) return; if (next_genbit) nf_tables_commit_chain_free_rules_old(g1); else nf_tables_commit_chain_free_rules_old(g0); } static void nft_obj_del(struct nft_object *obj) { rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); list_del_rcu(&obj->list); } void nft_chain_del(struct nft_chain *chain) { struct nft_table *table = chain->table; WARN_ON_ONCE(rhltable_remove(&table->chains_ht, &chain->rhlhead, nft_chain_ht_params)); list_del_rcu(&chain->list); } static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, struct nft_trans_gc *trans) { struct nft_elem_priv **priv = trans->priv; unsigned int i; for (i = 0; i < trans->count; i++) { nft_setelem_data_deactivate(ctx->net, trans->set, priv[i]); nft_setelem_remove(ctx->net, trans->set, priv[i]); } } void nft_trans_gc_destroy(struct nft_trans_gc *trans) { nft_set_put(trans->set); put_net(trans->net); kfree(trans); } static void nft_trans_gc_trans_free(struct rcu_head *rcu) { struct nft_elem_priv *elem_priv; struct nft_trans_gc *trans; struct nft_ctx ctx = {}; unsigned int i; trans = container_of(rcu, struct nft_trans_gc, rcu); ctx.net = read_pnet(&trans->set->net); for (i = 0; i < trans->count; i++) { elem_priv = trans->priv[i]; if (!nft_setelem_is_catchall(trans->set, elem_priv)) atomic_dec(&trans->set->nelems); nf_tables_set_elem_destroy(&ctx, trans->set, elem_priv); } nft_trans_gc_destroy(trans); } static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) { struct nftables_pernet *nft_net; struct nft_ctx ctx = {}; nft_net = nft_pernet(trans->net); mutex_lock(&nft_net->commit_mutex); /* Check for race with transaction, otherwise this batch refers to * stale objects that might not be there anymore. Skip transaction if * set has been destroyed from control plane transaction in case gc * worker loses race. */ if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { mutex_unlock(&nft_net->commit_mutex); return false; } ctx.net = trans->net; ctx.table = trans->set->table; nft_trans_gc_setelem_remove(&ctx, trans); mutex_unlock(&nft_net->commit_mutex); return true; } static void nft_trans_gc_work(struct work_struct *work) { struct nft_trans_gc *trans, *next; LIST_HEAD(trans_gc_list); spin_lock(&nf_tables_gc_list_lock); list_splice_init(&nf_tables_gc_list, &trans_gc_list); spin_unlock(&nf_tables_gc_list_lock); list_for_each_entry_safe(trans, next, &trans_gc_list, list) { list_del(&trans->list); if (!nft_trans_gc_work_done(trans)) { nft_trans_gc_destroy(trans); continue; } call_rcu(&trans->rcu, nft_trans_gc_trans_free); } } struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, unsigned int gc_seq, gfp_t gfp) { struct net *net = read_pnet(&set->net); struct nft_trans_gc *trans; trans = kzalloc(sizeof(*trans), gfp); if (!trans) return NULL; trans->net = maybe_get_net(net); if (!trans->net) { kfree(trans); return NULL; } refcount_inc(&set->refs); trans->set = set; trans->seq = gc_seq; return trans; } void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) { trans->priv[trans->count++] = priv; } static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) { spin_lock(&nf_tables_gc_list_lock); list_add_tail(&trans->list, &nf_tables_gc_list); spin_unlock(&nf_tables_gc_list_lock); schedule_work(&trans_gc_work); } static int nft_trans_gc_space(struct nft_trans_gc *trans) { return NFT_TRANS_GC_BATCHCOUNT - trans->count; } struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { struct nft_set *set; if (nft_trans_gc_space(gc)) return gc; set = gc->set; nft_trans_gc_queue_work(gc); return nft_trans_gc_alloc(set, gc_seq, gfp); } void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) { if (trans->count == 0) { nft_trans_gc_destroy(trans); return; } nft_trans_gc_queue_work(trans); } struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) { struct nft_set *set; if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) return NULL; if (nft_trans_gc_space(gc)) return gc; set = gc->set; call_rcu(&gc->rcu, nft_trans_gc_trans_free); return nft_trans_gc_alloc(set, 0, gfp); } void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) { WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); if (trans->count == 0) { nft_trans_gc_destroy(trans); return; } call_rcu(&trans->rcu, nft_trans_gc_trans_free); } struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, unsigned int gc_seq) { struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; struct nft_set_ext *ext; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_expired(ext)) continue; if (nft_set_elem_is_dead(ext)) goto dead_elem; nft_set_elem_dead(ext); dead_elem: gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); if (!gc) return NULL; nft_trans_gc_elem_add(gc, catchall->elem); } return gc; } struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) { struct nft_set_elem_catchall *catchall, *next; u64 tstamp = nft_net_tstamp(gc->net); const struct nft_set *set = gc->set; struct nft_elem_priv *elem_priv; struct nft_set_ext *ext; WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net)); list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (!__nft_set_elem_expired(ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) return NULL; elem_priv = catchall->elem; nft_setelem_data_deactivate(gc->net, gc->set, elem_priv); nft_setelem_catchall_destroy(catchall); nft_trans_gc_elem_add(gc, elem_priv); } return gc; } static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); list_for_each_entry_safe(req, next, &nft_net->module_list, list) { WARN_ON_ONCE(!req->done); list_del(&req->list); kfree(req); } } static void nf_tables_commit_release(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; /* all side effects have to be made visible. * For example, if a chain named 'foo' has been deleted, a * new transaction must not find it anymore. * * Memory reclaim happens asynchronously from work queue * to prevent expensive synchronize_rcu() in commit phase. */ if (list_empty(&nft_net->commit_list)) { nf_tables_module_autoload_cleanup(net); mutex_unlock(&nft_net->commit_mutex); return; } trans = list_last_entry(&nft_net->commit_list, struct nft_trans, list); get_net(trans->net); WARN_ON_ONCE(trans->put_net); trans->put_net = true; spin_lock(&nf_tables_destroy_list_lock); list_splice_tail_init(&nft_net->commit_list, &nft_net->destroy_list); spin_unlock(&nf_tables_destroy_list_lock); nf_tables_module_autoload_cleanup(net); schedule_work(&nft_net->destroy_work); mutex_unlock(&nft_net->commit_mutex); } static void nft_commit_notify(struct net *net, u32 portid) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *batch_skb = NULL, *nskb, *skb; unsigned char *data; int len; list_for_each_entry_safe(skb, nskb, &nft_net->notify_list, list) { if (!batch_skb) { new_batch: batch_skb = skb; len = NLMSG_GOODSIZE - skb->len; list_del(&skb->list); continue; } len -= skb->len; if (len > 0 && NFT_CB(skb).report == NFT_CB(batch_skb).report) { data = skb_put(batch_skb, skb->len); memcpy(data, skb->data, skb->len); list_del(&skb->list); kfree_skb(skb); continue; } nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, NFT_CB(batch_skb).report, GFP_KERNEL); goto new_batch; } if (batch_skb) { nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, NFT_CB(batch_skb).report, GFP_KERNEL); } WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static int nf_tables_commit_audit_alloc(struct list_head *adl, struct nft_table *table) { struct nft_audit_data *adp; list_for_each_entry(adp, adl, list) { if (adp->table == table) return 0; } adp = kzalloc(sizeof(*adp), GFP_KERNEL); if (!adp) return -ENOMEM; adp->table = table; list_add(&adp->list, adl); return 0; } static void nf_tables_commit_audit_free(struct list_head *adl) { struct nft_audit_data *adp, *adn; list_for_each_entry_safe(adp, adn, adl, list) { list_del(&adp->list); kfree(adp); } } /* nft audit emits the number of elements that get added/removed/updated, * so NEW/DELSETELEM needs to increment based on the total elem count. */ static unsigned int nf_tables_commit_audit_entrycount(const struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_NEWSETELEM: case NFT_MSG_DELSETELEM: return nft_trans_container_elem(trans)->nelems; } return 1; } static void nf_tables_commit_audit_collect(struct list_head *adl, const struct nft_trans *trans, u32 op) { const struct nft_table *table = trans->table; struct nft_audit_data *adp; list_for_each_entry(adp, adl, list) { if (adp->table == table) goto found; } WARN_ONCE(1, "table=%s not expected in commit list", table->name); return; found: adp->entries += nf_tables_commit_audit_entrycount(trans); if (!adp->op || adp->op > op) adp->op = op; } #define AUNFTABLENAMELEN (NFT_TABLE_MAXNAMELEN + 22) static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) { struct nft_audit_data *adp, *adn; char aubuf[AUNFTABLENAMELEN]; list_for_each_entry_safe(adp, adn, adl, list) { snprintf(aubuf, AUNFTABLENAMELEN, "%s:%u", adp->table->name, generation); audit_log_nfcfg(aubuf, adp->table->family, adp->entries, nft2audit_op[adp->op], GFP_KERNEL); list_del(&adp->list); kfree(adp); } } static void nft_set_commit_update(struct list_head *set_update_list) { struct nft_set *set, *next; list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); if (!set->ops->commit || set->dead) continue; set->ops->commit(set); } } static unsigned int nft_gc_seq_begin(struct nftables_pernet *nft_net) { unsigned int gc_seq; /* Bump gc counter, it becomes odd, this is the busy mark. */ gc_seq = READ_ONCE(nft_net->gc_seq); WRITE_ONCE(nft_net->gc_seq, ++gc_seq); return gc_seq; } static void nft_gc_seq_end(struct nftables_pernet *nft_net, unsigned int gc_seq) { WRITE_ONCE(nft_net->gc_seq, ++gc_seq); } static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); const struct nlmsghdr *nlh = nlmsg_hdr(skb); struct nft_trans_binding *trans_binding; struct nft_trans *trans, *next; unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; struct nft_ctx ctx; LIST_HEAD(adl); int err; if (list_empty(&nft_net->commit_list)) { mutex_unlock(&nft_net->commit_mutex); return 0; } nft_ctx_init(&ctx, net, skb, nlh, NFPROTO_UNSPEC, NULL, NULL, NULL); list_for_each_entry(trans_binding, &nft_net->binding_list, binding_list) { trans = &trans_binding->nft_trans; switch (trans->msg_type) { case NFT_MSG_NEWSET: if (!nft_trans_set_update(trans) && nft_set_is_anonymous(nft_trans_set(trans)) && !nft_trans_set_bound(trans)) { pr_warn_once("nftables ruleset with unbound set\n"); return -EINVAL; } break; case NFT_MSG_NEWCHAIN: if (!nft_trans_chain_update(trans) && nft_chain_binding(nft_trans_chain(trans)) && !nft_trans_chain_bound(trans)) { pr_warn_once("nftables ruleset with unbound chain\n"); return -EINVAL; } break; default: WARN_ONCE(1, "Unhandled bind type %d", trans->msg_type); break; } } /* 0. Validate ruleset, otherwise roll back for error reporting. */ if (nf_tables_validate(net) < 0) { nft_net->validate_state = NFT_VALIDATE_DO; return -EAGAIN; } err = nft_flow_rule_offload_commit(net); if (err < 0) return err; /* 1. Allocate space for next generation rules_gen_X[] */ list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_table *table = trans->table; int ret; ret = nf_tables_commit_audit_alloc(&adl, table); if (ret) { nf_tables_commit_chain_prepare_cancel(net); nf_tables_commit_audit_free(&adl); return ret; } if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { chain = nft_trans_rule_chain(trans); ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { nf_tables_commit_chain_prepare_cancel(net); nf_tables_commit_audit_free(&adl); return ret; } } } /* step 2. Make rules_gen_X visible to packet path */ list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_commit_chain(net, chain); } /* * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ base_seq = READ_ONCE(nft_net->base_seq); while (++base_seq == 0) ; WRITE_ONCE(nft_net->base_seq, base_seq); gc_seq = nft_gc_seq_begin(nft_net); /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_table *table = trans->table; nft_ctx_update(&ctx, trans); nf_tables_commit_audit_collect(&adl, trans, trans->msg_type); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { if (!(table->flags & __NFT_TABLE_F_UPDATE)) { nft_trans_destroy(trans); break; } if (table->flags & NFT_TABLE_F_DORMANT) nf_tables_table_disable(net, table); table->flags &= ~__NFT_TABLE_F_UPDATE; } else { nft_clear(net, table); } nf_tables_table_notify(&ctx, NFT_MSG_NEWTABLE); nft_trans_destroy(trans); break; case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: list_del_rcu(&table->list); nf_tables_table_notify(&ctx, trans->msg_type); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { nft_chain_commit_update(nft_trans_container_chain(trans)); nf_tables_chain_notify(&ctx, NFT_MSG_NEWCHAIN, &nft_trans_chain_hooks(trans)); list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); /* trans destroyed after rcu grace period */ } else { nft_chain_commit_drop_policy(nft_trans_container_chain(trans)); nft_clear(net, nft_trans_chain(trans)); nf_tables_chain_notify(&ctx, NFT_MSG_NEWCHAIN, NULL); nft_trans_destroy(trans); } break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) { nf_tables_chain_notify(&ctx, NFT_MSG_DELCHAIN, &nft_trans_chain_hooks(trans)); if (!(table->flags & NFT_TABLE_F_DORMANT)) { nft_netdev_unregister_hooks(net, &nft_trans_chain_hooks(trans), true); } } else { nft_chain_del(nft_trans_chain(trans)); nf_tables_chain_notify(&ctx, NFT_MSG_DELCHAIN, NULL); nf_tables_unregister_hook(ctx.net, ctx.table, nft_trans_chain(trans)); } break; case NFT_MSG_NEWRULE: nft_clear(net, nft_trans_rule(trans)); nf_tables_rule_notify(&ctx, nft_trans_rule(trans), NFT_MSG_NEWRULE); if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: list_del_rcu(&nft_trans_rule(trans)->list); nf_tables_rule_notify(&ctx, nft_trans_rule(trans), trans->msg_type); nft_rule_expr_deactivate(&ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { struct nft_set *set = nft_trans_set(trans); WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans)); WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans)); if (nft_trans_set_size(trans)) WRITE_ONCE(set->size, nft_trans_set_size(trans)); } else { nft_clear(net, nft_trans_set(trans)); /* This avoids hitting -EBUSY when deleting the table * from the transaction. */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) nft_use_dec(&table->use); } nf_tables_set_notify(&ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); nft_trans_destroy(trans); break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&ctx, nft_trans_set(trans), trans->msg_type, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: te = nft_trans_container_elem(trans); nft_trans_elems_add(&ctx, te); if (te->set->ops->commit && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: te = nft_trans_container_elem(trans); nft_trans_elems_remove(&ctx, te); if (te->set->ops->commit && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { nft_obj_commit_update(&ctx, trans); nf_tables_obj_notify(&ctx, nft_trans_obj(trans), NFT_MSG_NEWOBJ); } else { nft_clear(net, nft_trans_obj(trans)); nf_tables_obj_notify(&ctx, nft_trans_obj(trans), NFT_MSG_NEWOBJ); nft_trans_destroy(trans); } break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: nft_obj_del(nft_trans_obj(trans)); nf_tables_obj_notify(&ctx, nft_trans_obj(trans), trans->msg_type); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nft_trans_flowtable(trans)->data.flags = nft_trans_flowtable_flags(trans); nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), NFT_MSG_NEWFLOWTABLE); list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { nft_clear(net, nft_trans_flowtable(trans)); nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), NULL, NFT_MSG_NEWFLOWTABLE); } nft_trans_destroy(trans); break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), trans->msg_type); nft_unregister_flowtable_net_hooks(net, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans)); } else { list_del_rcu(&nft_trans_flowtable(trans)->list); nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), NULL, trans->msg_type); nft_unregister_flowtable_net_hooks(net, nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list); } break; } } nft_set_commit_update(&set_update_list); nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); nft_gc_seq_end(nft_net, gc_seq); nft_net->validate_state = NFT_VALIDATE_SKIP; nf_tables_commit_release(net); return 0; } static void nf_tables_module_autoload(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; LIST_HEAD(module_list); list_splice_init(&nft_net->module_list, &module_list); mutex_unlock(&nft_net->commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { request_module("%s", req->module); req->done = true; } mutex_lock(&nft_net->commit_mutex); list_splice(&module_list, &nft_net->module_list); } static void nf_tables_abort_release(struct nft_trans *trans) { struct nft_ctx ctx = { }; nft_ctx_update(&ctx, trans); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: nf_tables_table_destroy(trans->table); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) nft_hooks_destroy(&nft_trans_chain_hooks(trans)); else nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_NEWRULE: nf_tables_rule_destroy(&ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: nft_set_destroy(&ctx, nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_trans_set_elem_destroy(&ctx, nft_trans_container_elem(trans)); break; case NFT_MSG_NEWOBJ: nft_obj_destroy(&ctx, nft_trans_obj(trans)); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } kfree(trans); } static void nft_set_abort_update(struct list_head *set_update_list) { struct nft_set *set, *next; list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); if (!set->ops->abort) continue; set->ops->abort(set); } } static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_ctx ctx = { .net = net, }; int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { struct nft_table *table = trans->table; nft_ctx_update(&ctx, trans); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { if (!(table->flags & __NFT_TABLE_F_UPDATE)) { nft_trans_destroy(trans); break; } if (table->flags & __NFT_TABLE_F_WAS_DORMANT) { nf_tables_table_disable(net, table); table->flags |= NFT_TABLE_F_DORMANT; } else if (table->flags & __NFT_TABLE_F_WAS_AWAKEN) { table->flags &= ~NFT_TABLE_F_DORMANT; } if (table->flags & __NFT_TABLE_F_WAS_ORPHAN) { table->flags &= ~NFT_TABLE_F_OWNER; table->nlpid = 0; } table->flags &= ~__NFT_TABLE_F_UPDATE; nft_trans_destroy(trans); } else { list_del_rcu(&table->list); } break; case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: nft_clear(trans->net, table); nft_trans_destroy(trans); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { if (!(table->flags & NFT_TABLE_F_DORMANT)) { nft_netdev_unregister_hooks(net, &nft_trans_chain_hooks(trans), true); } free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { if (nft_trans_chain_bound(trans)) { nft_trans_destroy(trans); break; } nft_use_dec_restore(&table->use); nft_chain_del(nft_trans_chain(trans)); nf_tables_unregister_hook(trans->net, table, nft_trans_chain(trans)); } break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) { list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); } else { nft_use_inc_restore(&table->use); nft_clear(trans->net, nft_trans_chain(trans)); } nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: if (nft_trans_rule_bound(trans)) { nft_trans_destroy(trans); break; } nft_use_dec_restore(&nft_trans_rule_chain(trans)->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: nft_use_inc_restore(&nft_trans_rule_chain(trans)->use); nft_clear(trans->net, nft_trans_rule(trans)); nft_rule_expr_activate(&ctx, nft_trans_rule(trans)); if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { nft_trans_destroy(trans); break; } nft_use_dec_restore(&table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; } nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: nft_use_inc_restore(&table->use); nft_clear(trans->net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_activate(&ctx, nft_trans_set(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set_bound(trans)) { nft_trans_destroy(trans); break; } te = nft_trans_container_elem(trans); if (!nft_trans_elems_new_abort(&ctx, te)) { nft_trans_destroy(trans); break; } if (te->set->ops->abort && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: te = nft_trans_container_elem(trans); nft_trans_elems_destroy_abort(&ctx, te); if (te->set->ops->abort && list_empty(&te->set->pending_update)) { list_add_tail(&te->set->pending_update, &set_update_list); } nft_trans_destroy(trans); break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { nft_obj_destroy(&ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { nft_use_dec_restore(&table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: nft_use_inc_restore(&table->use); nft_clear(trans->net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nft_unregister_flowtable_net_hooks(net, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans)); } else { nft_use_dec_restore(&table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list); } break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { nft_use_inc_restore(&table->use); nft_clear(trans->net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); break; } } WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); nft_set_abort_update(&set_update_list); synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { nft_trans_list_del(trans); nf_tables_abort_release(trans); } return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { struct nftables_pernet *nft_net = nft_pernet(net); unsigned int gc_seq; int ret; gc_seq = nft_gc_seq_begin(nft_net); ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); /* module autoload needs to happen after GC sequence update because it * temporarily releases and grabs mutex again. */ if (action == NFNL_ABORT_AUTOLOAD) nf_tables_module_autoload(net); else nf_tables_module_autoload_cleanup(net); mutex_unlock(&nft_net->commit_mutex); return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { struct nftables_pernet *nft_net = nft_pernet(net); bool genid_ok; mutex_lock(&nft_net->commit_mutex); nft_net->tstamp = get_jiffies_64(); genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) mutex_unlock(&nft_net->commit_mutex); /* else, commit mutex has to be released by commit or abort function */ return genid_ok; } static const struct nfnetlink_subsystem nf_tables_subsys = { .name = "nf_tables", .subsys_id = NFNL_SUBSYS_NFTABLES, .cb_count = NFT_MSG_MAX, .cb = nf_tables_cb, .commit = nf_tables_commit, .abort = nf_tables_abort, .valid_genid = nf_tables_valid_genid, .owner = THIS_MODULE, }; int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_types type) { const struct nft_base_chain *basechain; if (nft_is_base_chain(chain)) { basechain = nft_base_chain(chain); if (basechain->type->type != type) return -EOPNOTSUPP; } return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate_dependency); int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags) { struct nft_base_chain *basechain; if (nft_is_base_chain(chain)) { basechain = nft_base_chain(chain); if ((1 << basechain->ops.hooknum) & hook_flags) return 0; return -EOPNOTSUPP; } return 0; } EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); /** * nft_parse_u32_check - fetch u32 attribute and check for maximum value * * @attr: netlink attribute to fetch value from * @max: maximum value to be stored in dest * @dest: pointer to the variable * * Parse, check and store a given u32 netlink attribute into variable. * This function returns -ERANGE if the value goes over maximum value. * Otherwise a 0 is returned and the attribute value is stored in the * destination variable. */ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) { u32 val; val = ntohl(nla_get_be32(attr)); if (val > max) return -ERANGE; *dest = val; return 0; } EXPORT_SYMBOL_GPL(nft_parse_u32_check); static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; reg = ntohl(nla_get_be32(attr)); switch (reg) { case NFT_REG_VERDICT...NFT_REG_4: *preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE; break; case NFT_REG32_00...NFT_REG32_15: *preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; break; default: return -ERANGE; } return 0; } /** * nft_dump_register - dump a register value to a netlink attribute * * @skb: socket buffer * @attr: attribute number * @reg: register number * * Construct a netlink attribute containing the register number. For * compatibility reasons, register numbers being a multiple of 4 are * translated to the corresponding 128 bit register numbers. */ int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg) { if (reg % (NFT_REG_SIZE / NFT_REG32_SIZE) == 0) reg = reg / (NFT_REG_SIZE / NFT_REG32_SIZE); else reg = reg - NFT_REG_SIZE / NFT_REG32_SIZE + NFT_REG32_00; return nla_put_be32(skb, attr, htonl(reg)); } EXPORT_SYMBOL_GPL(nft_dump_register); static int nft_validate_register_load(enum nft_registers reg, unsigned int len) { if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; return 0; } int nft_parse_register_load(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *sreg, u32 len) { int err, invalid_reg; u32 reg, next_register; err = nft_parse_register(attr, ®); if (err < 0) return err; err = nft_validate_register_load(reg, len); if (err < 0) return err; next_register = DIV_ROUND_UP(len, NFT_REG32_SIZE) + reg; /* Can't happen: nft_validate_register_load() should have failed */ if (WARN_ON_ONCE(next_register > NFT_REG32_NUM)) return -EINVAL; /* find first register that did not see an earlier store. */ invalid_reg = find_next_zero_bit(ctx->reg_inited, NFT_REG32_NUM, reg); /* invalid register within the range that we're loading from? */ if (invalid_reg < next_register) return -ENODATA; *sreg = reg; return 0; } EXPORT_SYMBOL_GPL(nft_parse_register_load); static void nft_saw_register_store(const struct nft_ctx *__ctx, int reg, unsigned int len) { unsigned int registers = DIV_ROUND_UP(len, NFT_REG32_SIZE); struct nft_ctx *ctx = (struct nft_ctx *)__ctx; if (WARN_ON_ONCE(len == 0 || reg < 0)) return; bitmap_set(ctx->reg_inited, reg, registers); } static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, enum nft_data_types type, unsigned int len) { int err; switch (reg) { case NFT_REG_VERDICT: if (type != NFT_DATA_VERDICT) return -EINVAL; if (data != NULL && (data->verdict.code == NFT_GOTO || data->verdict.code == NFT_JUMP)) { err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; } break; default: if (type != NFT_DATA_VALUE) return -EINVAL; if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; break; } nft_saw_register_store(ctx, reg, len); return 0; } int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, enum nft_data_types type, unsigned int len) { int err; u32 reg; err = nft_parse_register(attr, ®); if (err < 0) return err; err = nft_validate_register_store(ctx, reg, data, type, len); if (err < 0) return err; *dreg = reg; return 0; } EXPORT_SYMBOL_GPL(nft_parse_register_store); static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { [NFTA_VERDICT_CODE] = { .type = NLA_U32 }, [NFTA_VERDICT_CHAIN] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_VERDICT_CHAIN_ID] = { .type = NLA_U32 }, }; static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { u8 genmask = nft_genmask_next(ctx->net); struct nlattr *tb[NFTA_VERDICT_MAX + 1]; struct nft_chain *chain; int err; err = nla_parse_nested_deprecated(tb, NFTA_VERDICT_MAX, nla, nft_verdict_policy, NULL); if (err < 0) return err; if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; /* zero padding hole for memcmp */ memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { case NF_ACCEPT: case NF_DROP: case NF_QUEUE: break; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: break; case NFT_JUMP: case NFT_GOTO: if (tb[NFTA_VERDICT_CHAIN]) { chain = nft_chain_lookup(ctx->net, ctx->table, tb[NFTA_VERDICT_CHAIN], genmask); } else if (tb[NFTA_VERDICT_CHAIN_ID]) { chain = nft_chain_lookup_byid(ctx->net, ctx->table, tb[NFTA_VERDICT_CHAIN_ID], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); } else { return -EINVAL; } if (IS_ERR(chain)) return PTR_ERR(chain); if (nft_is_base_chain(chain)) return -EOPNOTSUPP; if (nft_chain_is_bound(chain)) return -EINVAL; if (desc->flags & NFT_DATA_DESC_SETELEM && chain->flags & NFT_CHAIN_BINDING) return -EINVAL; if (!nft_use_inc(&chain->use)) return -EMFILE; data->verdict.chain = chain; break; default: return -EINVAL; } desc->len = sizeof(data->verdict); return 0; } static void nft_verdict_uninit(const struct nft_data *data) { struct nft_chain *chain; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; nft_use_dec(&chain->use); break; } } int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, type); if (!nest) goto nla_put_failure; if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(v->code))) goto nla_put_failure; switch (v->code) { case NFT_JUMP: case NFT_GOTO: if (nla_put_string(skb, NFTA_VERDICT_CHAIN, v->chain->name)) goto nla_put_failure; } nla_nest_end(skb, nest); return 0; nla_put_failure: return -1; } static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { unsigned int len; len = nla_len(nla); if (len == 0) return -EINVAL; if (len > desc->size) return -EOVERFLOW; if (desc->len) { if (len != desc->len) return -EINVAL; } else { desc->len = len; } nla_memcpy(data->data, nla, len); return 0; } static int nft_value_dump(struct sk_buff *skb, const struct nft_data *data, unsigned int len) { return nla_put(skb, NFTA_DATA_VALUE, len, data->data); } static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = { [NFTA_DATA_VALUE] = { .type = NLA_BINARY }, [NFTA_DATA_VERDICT] = { .type = NLA_NESTED }, }; /** * nft_data_init - parse nf_tables data netlink attributes * * @ctx: context of the expression using the data * @data: destination struct nft_data * @desc: data description * @nla: netlink attribute containing data * * Parse the netlink data attributes and initialize a struct nft_data. * The type and length of data are returned in the data description. * * The caller can indicate that it only wants to accept data of type * NFT_DATA_VALUE by passing NULL for the ctx argument. */ int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { struct nlattr *tb[NFTA_DATA_MAX + 1]; int err; if (WARN_ON_ONCE(!desc->size)) return -EINVAL; err = nla_parse_nested_deprecated(tb, NFTA_DATA_MAX, nla, nft_data_policy, NULL); if (err < 0) return err; if (tb[NFTA_DATA_VALUE]) { if (desc->type != NFT_DATA_VALUE) return -EINVAL; err = nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]); } else if (tb[NFTA_DATA_VERDICT] && ctx != NULL) { if (desc->type != NFT_DATA_VERDICT) return -EINVAL; err = nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]); } else { err = -EINVAL; } return err; } EXPORT_SYMBOL_GPL(nft_data_init); /** * nft_data_release - release a nft_data item * * @data: struct nft_data to release * @type: type of data * * Release a nft_data item. NFT_DATA_VALUE types can be silently discarded, * all others need to be released by calling this function. */ void nft_data_release(const struct nft_data *data, enum nft_data_types type) { if (type < NFT_DATA_VERDICT) return; switch (type) { case NFT_DATA_VERDICT: return nft_verdict_uninit(data); default: WARN_ON(1); } } EXPORT_SYMBOL_GPL(nft_data_release); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, enum nft_data_types type, unsigned int len) { struct nlattr *nest; int err; nest = nla_nest_start_noflag(skb, attr); if (nest == NULL) return -1; switch (type) { case NFT_DATA_VALUE: err = nft_value_dump(skb, data, len); break; case NFT_DATA_VERDICT: err = nft_verdict_dump(skb, NFTA_DATA_VERDICT, &data->verdict); break; default: err = -EINVAL; WARN_ON(1); } nla_nest_end(skb, nest); return err; } EXPORT_SYMBOL_GPL(nft_data_dump); static void __nft_release_hook(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable; struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) __nf_tables_unregister_hook(net, table, chain, true); list_for_each_entry(flowtable, &table->flowtables, list) __nft_unregister_flowtable_net_hooks(net, flowtable, &flowtable->hook_list, true); } static void __nft_release_hooks(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table)) continue; __nft_release_hook(net, table); } } static void __nft_release_table(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable, *nf; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_rule *rule, *nr; struct nft_set *set, *ns; struct nft_ctx ctx = { .net = net, .family = NFPROTO_NETDEV, }; ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { if (nft_chain_binding(chain)) continue; ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); nft_use_dec(&chain->use); nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { list_del(&flowtable->list); nft_use_dec(&table->use); nf_tables_flowtable_destroy(flowtable); } list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); nft_use_dec(&table->use); if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) nft_map_deactivate(&ctx, set); nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { nft_obj_del(obj); nft_use_dec(&table->use); nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { nft_chain_del(chain); nft_use_dec(&table->use); nf_tables_chain_destroy(chain); } nf_tables_table_destroy(table); } static void __nft_release_tables(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table, *nt; list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (nft_table_has_owner(table)) continue; list_del(&table->list); __nft_release_table(net, table); } } static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct nft_table *table, *to_delete[8]; struct nftables_pernet *nft_net; struct netlink_notify *n = ptr; struct net *net = n->net; unsigned int deleted; bool restart = false; unsigned int gc_seq; if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; nft_net = nft_pernet(net); deleted = 0; mutex_lock(&nft_net->commit_mutex); gc_seq = nft_gc_seq_begin(nft_net); nf_tables_trans_destroy_flush_work(net); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { if (table->flags & NFT_TABLE_F_PERSIST) { table->flags &= ~NFT_TABLE_F_OWNER; continue; } __nft_release_hook(net, table); list_del_rcu(&table->list); to_delete[deleted++] = table; if (deleted >= ARRAY_SIZE(to_delete)) break; } } if (deleted) { restart = deleted >= ARRAY_SIZE(to_delete); synchronize_rcu(); while (deleted) __nft_release_table(net, to_delete[--deleted]); if (restart) goto again; } nft_gc_seq_end(nft_net, gc_seq); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_nl_notifier = { .notifier_call = nft_rcv_nl_event, }; static int __net_init nf_tables_init_net(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); INIT_LIST_HEAD(&nft_net->tables); INIT_LIST_HEAD(&nft_net->commit_list); INIT_LIST_HEAD(&nft_net->destroy_list); INIT_LIST_HEAD(&nft_net->commit_set_list); INIT_LIST_HEAD(&nft_net->binding_list); INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; nft_net->gc_seq = 0; nft_net->validate_state = NFT_VALIDATE_SKIP; INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work); return 0; } static void __net_exit nf_tables_pre_exit_net(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); __nft_release_hooks(net); mutex_unlock(&nft_net->commit_mutex); } static void __net_exit nf_tables_exit_net(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); unsigned int gc_seq; mutex_lock(&nft_net->commit_mutex); gc_seq = nft_gc_seq_begin(nft_net); WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); if (!list_empty(&nft_net->module_list)) nf_tables_module_autoload_cleanup(net); cancel_work_sync(&nft_net->destroy_work); __nft_release_tables(net); nft_gc_seq_end(nft_net, gc_seq); mutex_unlock(&nft_net->commit_mutex); WARN_ON_ONCE(!list_empty(&nft_net->tables)); WARN_ON_ONCE(!list_empty(&nft_net->module_list)); WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); WARN_ON_ONCE(!list_empty(&nft_net->destroy_list)); } static void nf_tables_exit_batch(struct list_head *net_exit_list) { flush_work(&trans_gc_work); } static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; static int __init nf_tables_module_init(void) { int err; BUILD_BUG_ON(offsetof(struct nft_trans_table, nft_trans) != 0); BUILD_BUG_ON(offsetof(struct nft_trans_chain, nft_trans_binding.nft_trans) != 0); BUILD_BUG_ON(offsetof(struct nft_trans_rule, nft_trans) != 0); BUILD_BUG_ON(offsetof(struct nft_trans_set, nft_trans_binding.nft_trans) != 0); BUILD_BUG_ON(offsetof(struct nft_trans_elem, nft_trans) != 0); BUILD_BUG_ON(offsetof(struct nft_trans_obj, nft_trans) != 0); BUILD_BUG_ON(offsetof(struct nft_trans_flowtable, nft_trans) != 0); err = register_pernet_subsys(&nf_tables_net_ops); if (err < 0) return err; err = nft_chain_filter_init(); if (err < 0) goto err_chain_filter; err = nf_tables_core_module_init(); if (err < 0) goto err_core_module; err = register_netdevice_notifier(&nf_tables_flowtable_notifier); if (err < 0) goto err_netdev_notifier; err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); if (err < 0) goto err_rht_objname; err = nft_offload_init(); if (err < 0) goto err_offload; err = netlink_register_notifier(&nft_nl_notifier); if (err < 0) goto err_netlink_notifier; /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) goto err_nfnl_subsys; nft_chain_route_init(); return err; err_nfnl_subsys: netlink_unregister_notifier(&nft_nl_notifier); err_netlink_notifier: nft_offload_exit(); err_offload: rhltable_destroy(&nft_objname_ht); err_rht_objname: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); err_netdev_notifier: nf_tables_core_module_exit(); err_core_module: nft_chain_filter_fini(); err_chain_filter: unregister_pernet_subsys(&nf_tables_net_ops); return err; } static void __exit nf_tables_module_exit(void) { nfnetlink_subsys_unregister(&nf_tables_subsys); netlink_unregister_notifier(&nft_nl_notifier); nft_offload_exit(); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); nf_tables_core_module_exit(); } module_init(nf_tables_module_init); module_exit(nf_tables_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Framework for packet filtering and classification"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFTABLES); |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2011-2014 Autronica Fire and Security AS * * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * include file for HSR and PRP. */ #ifndef __HSR_SLAVE_H #define __HSR_SLAVE_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include "hsr_main.h" int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type pt, struct netlink_ext_ack *extack); void hsr_del_port(struct hsr_port *port); bool hsr_port_exists(const struct net_device *dev); static inline struct hsr_port *hsr_port_get_rtnl(const struct net_device *dev) { ASSERT_RTNL(); return hsr_port_exists(dev) ? rtnl_dereference(dev->rx_handler_data) : NULL; } static inline struct hsr_port *hsr_port_get_rcu(const struct net_device *dev) { return hsr_port_exists(dev) ? rcu_dereference(dev->rx_handler_data) : NULL; } bool hsr_invalid_dan_ingress_frame(__be16 protocol); #endif /* __HSR_SLAVE_H */ |
| 209 209 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ASM_ESR_H #define __ASM_ESR_H #include <asm/memory.h> #include <asm/sysreg.h> #define ESR_ELx_EC_UNKNOWN UL(0x00) #define ESR_ELx_EC_WFx UL(0x01) /* Unallocated EC: 0x02 */ #define ESR_ELx_EC_CP15_32 UL(0x03) #define ESR_ELx_EC_CP15_64 UL(0x04) #define ESR_ELx_EC_CP14_MR UL(0x05) #define ESR_ELx_EC_CP14_LS UL(0x06) #define ESR_ELx_EC_FP_ASIMD UL(0x07) #define ESR_ELx_EC_CP10_ID UL(0x08) /* EL2 only */ #define ESR_ELx_EC_PAC UL(0x09) /* EL2 and above */ #define ESR_ELx_EC_OTHER UL(0x0A) /* Unallocated EC: 0x0B */ #define ESR_ELx_EC_CP14_64 UL(0x0C) #define ESR_ELx_EC_BTI UL(0x0D) #define ESR_ELx_EC_ILL UL(0x0E) /* Unallocated EC: 0x0F - 0x10 */ #define ESR_ELx_EC_SVC32 UL(0x11) #define ESR_ELx_EC_HVC32 UL(0x12) /* EL2 only */ #define ESR_ELx_EC_SMC32 UL(0x13) /* EL2 and above */ /* Unallocated EC: 0x14 */ #define ESR_ELx_EC_SVC64 UL(0x15) #define ESR_ELx_EC_HVC64 UL(0x16) /* EL2 and above */ #define ESR_ELx_EC_SMC64 UL(0x17) /* EL2 and above */ #define ESR_ELx_EC_SYS64 UL(0x18) #define ESR_ELx_EC_SVE UL(0x19) #define ESR_ELx_EC_ERET UL(0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ #define ESR_ELx_EC_FPAC UL(0x1C) /* EL1 and above */ #define ESR_ELx_EC_SME UL(0x1D) /* Unallocated EC: 0x1E */ #define ESR_ELx_EC_IMP_DEF UL(0x1f) /* EL3 only */ #define ESR_ELx_EC_IABT_LOW UL(0x20) #define ESR_ELx_EC_IABT_CUR UL(0x21) #define ESR_ELx_EC_PC_ALIGN UL(0x22) /* Unallocated EC: 0x23 */ #define ESR_ELx_EC_DABT_LOW UL(0x24) #define ESR_ELx_EC_DABT_CUR UL(0x25) #define ESR_ELx_EC_SP_ALIGN UL(0x26) #define ESR_ELx_EC_MOPS UL(0x27) #define ESR_ELx_EC_FP_EXC32 UL(0x28) /* Unallocated EC: 0x29 - 0x2B */ #define ESR_ELx_EC_FP_EXC64 UL(0x2C) #define ESR_ELx_EC_GCS UL(0x2D) /* Unallocated EC: 0x2E */ #define ESR_ELx_EC_SERROR UL(0x2F) #define ESR_ELx_EC_BREAKPT_LOW UL(0x30) #define ESR_ELx_EC_BREAKPT_CUR UL(0x31) #define ESR_ELx_EC_SOFTSTP_LOW UL(0x32) #define ESR_ELx_EC_SOFTSTP_CUR UL(0x33) #define ESR_ELx_EC_WATCHPT_LOW UL(0x34) #define ESR_ELx_EC_WATCHPT_CUR UL(0x35) /* Unallocated EC: 0x36 - 0x37 */ #define ESR_ELx_EC_BKPT32 UL(0x38) /* Unallocated EC: 0x39 */ #define ESR_ELx_EC_VECTOR32 UL(0x3A) /* EL2 only */ /* Unallocated EC: 0x3B */ #define ESR_ELx_EC_BRK64 UL(0x3C) /* Unallocated EC: 0x3D - 0x3F */ #define ESR_ELx_EC_MAX UL(0x3F) #define ESR_ELx_EC_SHIFT (26) #define ESR_ELx_EC_WIDTH (6) #define ESR_ELx_EC_MASK (UL(0x3F) << ESR_ELx_EC_SHIFT) #define ESR_ELx_EC(esr) (((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT) #define ESR_ELx_IL_SHIFT (25) #define ESR_ELx_IL (UL(1) << ESR_ELx_IL_SHIFT) #define ESR_ELx_ISS_MASK (GENMASK(24, 0)) #define ESR_ELx_ISS(esr) ((esr) & ESR_ELx_ISS_MASK) #define ESR_ELx_ISS2_SHIFT (32) #define ESR_ELx_ISS2_MASK (GENMASK_ULL(55, 32)) #define ESR_ELx_ISS2(esr) (((esr) & ESR_ELx_ISS2_MASK) >> ESR_ELx_ISS2_SHIFT) /* ISS field definitions shared by different classes */ #define ESR_ELx_WNR_SHIFT (6) #define ESR_ELx_WNR (UL(1) << ESR_ELx_WNR_SHIFT) /* Asynchronous Error Type */ #define ESR_ELx_IDS_SHIFT (24) #define ESR_ELx_IDS (UL(1) << ESR_ELx_IDS_SHIFT) #define ESR_ELx_AET_SHIFT (10) #define ESR_ELx_AET (UL(0x7) << ESR_ELx_AET_SHIFT) #define ESR_ELx_AET_UC (UL(0) << ESR_ELx_AET_SHIFT) #define ESR_ELx_AET_UEU (UL(1) << ESR_ELx_AET_SHIFT) #define ESR_ELx_AET_UEO (UL(2) << ESR_ELx_AET_SHIFT) #define ESR_ELx_AET_UER (UL(3) << ESR_ELx_AET_SHIFT) #define ESR_ELx_AET_CE (UL(6) << ESR_ELx_AET_SHIFT) /* Shared ISS field definitions for Data/Instruction aborts */ #define ESR_ELx_VNCR_SHIFT (13) #define ESR_ELx_VNCR (UL(1) << ESR_ELx_VNCR_SHIFT) #define ESR_ELx_SET_SHIFT (11) #define ESR_ELx_SET_MASK (UL(3) << ESR_ELx_SET_SHIFT) #define ESR_ELx_FnV_SHIFT (10) #define ESR_ELx_FnV (UL(1) << ESR_ELx_FnV_SHIFT) #define ESR_ELx_EA_SHIFT (9) #define ESR_ELx_EA (UL(1) << ESR_ELx_EA_SHIFT) #define ESR_ELx_S1PTW_SHIFT (7) #define ESR_ELx_S1PTW (UL(1) << ESR_ELx_S1PTW_SHIFT) /* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */ #define ESR_ELx_FSC (0x3F) #define ESR_ELx_FSC_TYPE (0x3C) #define ESR_ELx_FSC_LEVEL (0x03) #define ESR_ELx_FSC_EXTABT (0x10) #define ESR_ELx_FSC_MTE (0x11) #define ESR_ELx_FSC_SERROR (0x11) #define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) #define ESR_ELx_FSC_SEA_TTW(n) (0x14 + (n)) #define ESR_ELx_FSC_SECC (0x18) #define ESR_ELx_FSC_SECC_TTW(n) (0x1c + (n)) #define ESR_ELx_FSC_ADDRSZ (0x00) /* * Annoyingly, the negative levels for Address size faults aren't laid out * contiguously (or in the desired order) */ #define ESR_ELx_FSC_ADDRSZ_nL(n) ((n) == -1 ? 0x25 : 0x2C) #define ESR_ELx_FSC_ADDRSZ_L(n) ((n) < 0 ? ESR_ELx_FSC_ADDRSZ_nL(n) : \ (ESR_ELx_FSC_ADDRSZ + (n))) /* Status codes for individual page table levels */ #define ESR_ELx_FSC_ACCESS_L(n) (ESR_ELx_FSC_ACCESS + (n)) #define ESR_ELx_FSC_PERM_L(n) (ESR_ELx_FSC_PERM + (n)) #define ESR_ELx_FSC_FAULT_nL (0x2C) #define ESR_ELx_FSC_FAULT_L(n) (((n) < 0 ? ESR_ELx_FSC_FAULT_nL : \ ESR_ELx_FSC_FAULT) + (n)) /* ISS field definitions for Data Aborts */ #define ESR_ELx_ISV_SHIFT (24) #define ESR_ELx_ISV (UL(1) << ESR_ELx_ISV_SHIFT) #define ESR_ELx_SAS_SHIFT (22) #define ESR_ELx_SAS (UL(3) << ESR_ELx_SAS_SHIFT) #define ESR_ELx_SSE_SHIFT (21) #define ESR_ELx_SSE (UL(1) << ESR_ELx_SSE_SHIFT) #define ESR_ELx_SRT_SHIFT (16) #define ESR_ELx_SRT_MASK (UL(0x1F) << ESR_ELx_SRT_SHIFT) #define ESR_ELx_SF_SHIFT (15) #define ESR_ELx_SF (UL(1) << ESR_ELx_SF_SHIFT) #define ESR_ELx_AR_SHIFT (14) #define ESR_ELx_AR (UL(1) << ESR_ELx_AR_SHIFT) #define ESR_ELx_CM_SHIFT (8) #define ESR_ELx_CM (UL(1) << ESR_ELx_CM_SHIFT) /* ISS2 field definitions for Data Aborts */ #define ESR_ELx_TnD_SHIFT (10) #define ESR_ELx_TnD (UL(1) << ESR_ELx_TnD_SHIFT) #define ESR_ELx_TagAccess_SHIFT (9) #define ESR_ELx_TagAccess (UL(1) << ESR_ELx_TagAccess_SHIFT) #define ESR_ELx_GCS_SHIFT (8) #define ESR_ELx_GCS (UL(1) << ESR_ELx_GCS_SHIFT) #define ESR_ELx_Overlay_SHIFT (6) #define ESR_ELx_Overlay (UL(1) << ESR_ELx_Overlay_SHIFT) #define ESR_ELx_DirtyBit_SHIFT (5) #define ESR_ELx_DirtyBit (UL(1) << ESR_ELx_DirtyBit_SHIFT) #define ESR_ELx_Xs_SHIFT (0) #define ESR_ELx_Xs_MASK (GENMASK_ULL(4, 0)) /* ISS field definitions for exceptions taken in to Hyp */ #define ESR_ELx_CV (UL(1) << 24) #define ESR_ELx_COND_SHIFT (20) #define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT) #define ESR_ELx_WFx_ISS_RN (UL(0x1F) << 5) #define ESR_ELx_WFx_ISS_RV (UL(1) << 2) #define ESR_ELx_WFx_ISS_TI (UL(3) << 0) #define ESR_ELx_WFx_ISS_WFxT (UL(2) << 0) #define ESR_ELx_WFx_ISS_WFI (UL(0) << 0) #define ESR_ELx_WFx_ISS_WFE (UL(1) << 0) #define ESR_ELx_xVC_IMM_MASK ((UL(1) << 16) - 1) /* ISS definitions for LD64B/ST64B/{T,P}SBCSYNC instructions */ #define ESR_ELx_ISS_OTHER_ST64BV (0) #define ESR_ELx_ISS_OTHER_ST64BV0 (1) #define ESR_ELx_ISS_OTHER_LDST64B (2) #define ESR_ELx_ISS_OTHER_TSBCSYNC (3) #define ESR_ELx_ISS_OTHER_PSBCSYNC (4) #define DISR_EL1_IDS (UL(1) << 24) /* * DISR_EL1 and ESR_ELx share the bottom 13 bits, but the RES0 bits may mean * different things in the future... */ #define DISR_EL1_ESR_MASK (ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC) /* ESR value templates for specific events */ #define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | \ (ESR_ELx_WFx_ISS_TI & ~ESR_ELx_WFx_ISS_WFxT)) #define ESR_ELx_WFx_WFI_VAL ((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) | \ ESR_ELx_WFx_ISS_WFI) /* BRK instruction trap from AArch64 state */ #define ESR_ELx_BRK64_ISS_COMMENT_MASK 0xffff /* ISS field definitions for System instruction traps */ #define ESR_ELx_SYS64_ISS_RES0_SHIFT 22 #define ESR_ELx_SYS64_ISS_RES0_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_RES0_SHIFT) #define ESR_ELx_SYS64_ISS_DIR_MASK 0x1 #define ESR_ELx_SYS64_ISS_DIR_READ 0x1 #define ESR_ELx_SYS64_ISS_DIR_WRITE 0x0 #define ESR_ELx_SYS64_ISS_RT_SHIFT 5 #define ESR_ELx_SYS64_ISS_RT_MASK (UL(0x1f) << ESR_ELx_SYS64_ISS_RT_SHIFT) #define ESR_ELx_SYS64_ISS_CRM_SHIFT 1 #define ESR_ELx_SYS64_ISS_CRM_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRM_SHIFT) #define ESR_ELx_SYS64_ISS_CRN_SHIFT 10 #define ESR_ELx_SYS64_ISS_CRN_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRN_SHIFT) #define ESR_ELx_SYS64_ISS_OP1_SHIFT 14 #define ESR_ELx_SYS64_ISS_OP1_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP1_SHIFT) #define ESR_ELx_SYS64_ISS_OP2_SHIFT 17 #define ESR_ELx_SYS64_ISS_OP2_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP2_SHIFT) #define ESR_ELx_SYS64_ISS_OP0_SHIFT 20 #define ESR_ELx_SYS64_ISS_OP0_MASK (UL(0x3) << ESR_ELx_SYS64_ISS_OP0_SHIFT) #define ESR_ELx_SYS64_ISS_SYS_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \ ESR_ELx_SYS64_ISS_OP1_MASK | \ ESR_ELx_SYS64_ISS_OP2_MASK | \ ESR_ELx_SYS64_ISS_CRN_MASK | \ ESR_ELx_SYS64_ISS_CRM_MASK) #define ESR_ELx_SYS64_ISS_SYS_VAL(op0, op1, op2, crn, crm) \ (((op0) << ESR_ELx_SYS64_ISS_OP0_SHIFT) | \ ((op1) << ESR_ELx_SYS64_ISS_OP1_SHIFT) | \ ((op2) << ESR_ELx_SYS64_ISS_OP2_SHIFT) | \ ((crn) << ESR_ELx_SYS64_ISS_CRN_SHIFT) | \ ((crm) << ESR_ELx_SYS64_ISS_CRM_SHIFT)) #define ESR_ELx_SYS64_ISS_SYS_OP_MASK (ESR_ELx_SYS64_ISS_SYS_MASK | \ ESR_ELx_SYS64_ISS_DIR_MASK) #define ESR_ELx_SYS64_ISS_RT(esr) \ (((esr) & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT) /* * User space cache operations have the following sysreg encoding * in System instructions. * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 13, 14 }, WRITE (L=0) */ #define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC 14 #define ESR_ELx_SYS64_ISS_CRM_DC_CVADP 13 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAP 12 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAU 11 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAC 10 #define ESR_ELx_SYS64_ISS_CRM_IC_IVAU 5 #define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \ ESR_ELx_SYS64_ISS_OP1_MASK | \ ESR_ELx_SYS64_ISS_OP2_MASK | \ ESR_ELx_SYS64_ISS_CRN_MASK | \ ESR_ELx_SYS64_ISS_DIR_MASK) #define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \ (ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \ ESR_ELx_SYS64_ISS_DIR_WRITE) /* * User space MRS operations which are supported for emulation * have the following sysreg encoding in System instructions. * op0 = 3, op1= 0, crn = 0, {crm = 0, 4-7}, READ (L = 1) */ #define ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \ ESR_ELx_SYS64_ISS_OP1_MASK | \ ESR_ELx_SYS64_ISS_CRN_MASK | \ ESR_ELx_SYS64_ISS_DIR_MASK) #define ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL \ (ESR_ELx_SYS64_ISS_SYS_VAL(3, 0, 0, 0, 0) | \ ESR_ELx_SYS64_ISS_DIR_READ) #define ESR_ELx_SYS64_ISS_SYS_CTR ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0) #define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \ ESR_ELx_SYS64_ISS_DIR_READ) #define ESR_ELx_SYS64_ISS_SYS_CNTVCT (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 2, 14, 0) | \ ESR_ELx_SYS64_ISS_DIR_READ) #define ESR_ELx_SYS64_ISS_SYS_CNTVCTSS (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 6, 14, 0) | \ ESR_ELx_SYS64_ISS_DIR_READ) #define ESR_ELx_SYS64_ISS_SYS_CNTFRQ (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 0, 14, 0) | \ ESR_ELx_SYS64_ISS_DIR_READ) #define esr_sys64_to_sysreg(e) \ sys_reg((((e) & ESR_ELx_SYS64_ISS_OP0_MASK) >> \ ESR_ELx_SYS64_ISS_OP0_SHIFT), \ (((e) & ESR_ELx_SYS64_ISS_OP1_MASK) >> \ ESR_ELx_SYS64_ISS_OP1_SHIFT), \ (((e) & ESR_ELx_SYS64_ISS_CRN_MASK) >> \ ESR_ELx_SYS64_ISS_CRN_SHIFT), \ (((e) & ESR_ELx_SYS64_ISS_CRM_MASK) >> \ ESR_ELx_SYS64_ISS_CRM_SHIFT), \ (((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >> \ ESR_ELx_SYS64_ISS_OP2_SHIFT)) #define esr_cp15_to_sysreg(e) \ sys_reg(3, \ (((e) & ESR_ELx_SYS64_ISS_OP1_MASK) >> \ ESR_ELx_SYS64_ISS_OP1_SHIFT), \ (((e) & ESR_ELx_SYS64_ISS_CRN_MASK) >> \ ESR_ELx_SYS64_ISS_CRN_SHIFT), \ (((e) & ESR_ELx_SYS64_ISS_CRM_MASK) >> \ ESR_ELx_SYS64_ISS_CRM_SHIFT), \ (((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >> \ ESR_ELx_SYS64_ISS_OP2_SHIFT)) /* ISS field definitions for ERET/ERETAA/ERETAB trapping */ #define ESR_ELx_ERET_ISS_ERET 0x2 #define ESR_ELx_ERET_ISS_ERETA 0x1 /* * ISS field definitions for floating-point exception traps * (FP_EXC_32/FP_EXC_64). * * (The FPEXC_* constants are used instead for common bits.) */ #define ESR_ELx_FP_EXC_TFV (UL(1) << 23) /* * ISS field definitions for CP15 accesses */ #define ESR_ELx_CP15_32_ISS_DIR_MASK 0x1 #define ESR_ELx_CP15_32_ISS_DIR_READ 0x1 #define ESR_ELx_CP15_32_ISS_DIR_WRITE 0x0 #define ESR_ELx_CP15_32_ISS_RT_SHIFT 5 #define ESR_ELx_CP15_32_ISS_RT_MASK (UL(0x1f) << ESR_ELx_CP15_32_ISS_RT_SHIFT) #define ESR_ELx_CP15_32_ISS_CRM_SHIFT 1 #define ESR_ELx_CP15_32_ISS_CRM_MASK (UL(0xf) << ESR_ELx_CP15_32_ISS_CRM_SHIFT) #define ESR_ELx_CP15_32_ISS_CRN_SHIFT 10 #define ESR_ELx_CP15_32_ISS_CRN_MASK (UL(0xf) << ESR_ELx_CP15_32_ISS_CRN_SHIFT) #define ESR_ELx_CP15_32_ISS_OP1_SHIFT 14 #define ESR_ELx_CP15_32_ISS_OP1_MASK (UL(0x7) << ESR_ELx_CP15_32_ISS_OP1_SHIFT) #define ESR_ELx_CP15_32_ISS_OP2_SHIFT 17 #define ESR_ELx_CP15_32_ISS_OP2_MASK (UL(0x7) << ESR_ELx_CP15_32_ISS_OP2_SHIFT) #define ESR_ELx_CP15_32_ISS_SYS_MASK (ESR_ELx_CP15_32_ISS_OP1_MASK | \ ESR_ELx_CP15_32_ISS_OP2_MASK | \ ESR_ELx_CP15_32_ISS_CRN_MASK | \ ESR_ELx_CP15_32_ISS_CRM_MASK | \ ESR_ELx_CP15_32_ISS_DIR_MASK) #define ESR_ELx_CP15_32_ISS_SYS_VAL(op1, op2, crn, crm) \ (((op1) << ESR_ELx_CP15_32_ISS_OP1_SHIFT) | \ ((op2) << ESR_ELx_CP15_32_ISS_OP2_SHIFT) | \ ((crn) << ESR_ELx_CP15_32_ISS_CRN_SHIFT) | \ ((crm) << ESR_ELx_CP15_32_ISS_CRM_SHIFT)) #define ESR_ELx_CP15_64_ISS_DIR_MASK 0x1 #define ESR_ELx_CP15_64_ISS_DIR_READ 0x1 #define ESR_ELx_CP15_64_ISS_DIR_WRITE 0x0 #define ESR_ELx_CP15_64_ISS_RT_SHIFT 5 #define ESR_ELx_CP15_64_ISS_RT_MASK (UL(0x1f) << ESR_ELx_CP15_64_ISS_RT_SHIFT) #define ESR_ELx_CP15_64_ISS_RT2_SHIFT 10 #define ESR_ELx_CP15_64_ISS_RT2_MASK (UL(0x1f) << ESR_ELx_CP15_64_ISS_RT2_SHIFT) #define ESR_ELx_CP15_64_ISS_OP1_SHIFT 16 #define ESR_ELx_CP15_64_ISS_OP1_MASK (UL(0xf) << ESR_ELx_CP15_64_ISS_OP1_SHIFT) #define ESR_ELx_CP15_64_ISS_CRM_SHIFT 1 #define ESR_ELx_CP15_64_ISS_CRM_MASK (UL(0xf) << ESR_ELx_CP15_64_ISS_CRM_SHIFT) #define ESR_ELx_CP15_64_ISS_SYS_VAL(op1, crm) \ (((op1) << ESR_ELx_CP15_64_ISS_OP1_SHIFT) | \ ((crm) << ESR_ELx_CP15_64_ISS_CRM_SHIFT)) #define ESR_ELx_CP15_64_ISS_SYS_MASK (ESR_ELx_CP15_64_ISS_OP1_MASK | \ ESR_ELx_CP15_64_ISS_CRM_MASK | \ ESR_ELx_CP15_64_ISS_DIR_MASK) #define ESR_ELx_CP15_64_ISS_SYS_CNTVCT (ESR_ELx_CP15_64_ISS_SYS_VAL(1, 14) | \ ESR_ELx_CP15_64_ISS_DIR_READ) #define ESR_ELx_CP15_64_ISS_SYS_CNTVCTSS (ESR_ELx_CP15_64_ISS_SYS_VAL(9, 14) | \ ESR_ELx_CP15_64_ISS_DIR_READ) #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ (ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\ ESR_ELx_CP15_32_ISS_DIR_READ) /* * ISS values for SME traps */ #define ESR_ELx_SME_ISS_SMTC_MASK GENMASK(2, 0) #define ESR_ELx_SME_ISS_SMTC(esr) ((esr) & ESR_ELx_SME_ISS_SMTC_MASK) #define ESR_ELx_SME_ISS_SMTC_SME_DISABLED 0 #define ESR_ELx_SME_ISS_SMTC_ILL 1 #define ESR_ELx_SME_ISS_SMTC_SM_DISABLED 2 #define ESR_ELx_SME_ISS_SMTC_ZA_DISABLED 3 #define ESR_ELx_SME_ISS_SMTC_ZT_DISABLED 4 /* ISS field definitions for MOPS exceptions */ #define ESR_ELx_MOPS_ISS_MEM_INST (UL(1) << 24) #define ESR_ELx_MOPS_ISS_FROM_EPILOGUE (UL(1) << 18) #define ESR_ELx_MOPS_ISS_WRONG_OPTION (UL(1) << 17) #define ESR_ELx_MOPS_ISS_OPTION_A (UL(1) << 16) #define ESR_ELx_MOPS_ISS_DESTREG(esr) (((esr) & (UL(0x1f) << 10)) >> 10) #define ESR_ELx_MOPS_ISS_SRCREG(esr) (((esr) & (UL(0x1f) << 5)) >> 5) #define ESR_ELx_MOPS_ISS_SIZEREG(esr) (((esr) & (UL(0x1f) << 0)) >> 0) /* ISS field definitions for GCS */ #define ESR_ELx_ExType_SHIFT (20) #define ESR_ELx_ExType_MASK GENMASK(23, 20) #define ESR_ELx_Raddr_SHIFT (10) #define ESR_ELx_Raddr_MASK GENMASK(14, 10) #define ESR_ELx_Rn_SHIFT (5) #define ESR_ELx_Rn_MASK GENMASK(9, 5) #define ESR_ELx_Rvalue_SHIFT 5 #define ESR_ELx_Rvalue_MASK GENMASK(9, 5) #define ESR_ELx_IT_SHIFT (0) #define ESR_ELx_IT_MASK GENMASK(4, 0) #define ESR_ELx_ExType_DATA_CHECK 0 #define ESR_ELx_ExType_EXLOCK 1 #define ESR_ELx_ExType_STR 2 #define ESR_ELx_IT_RET 0 #define ESR_ELx_IT_GCSPOPM 1 #define ESR_ELx_IT_RET_KEYA 2 #define ESR_ELx_IT_RET_KEYB 3 #define ESR_ELx_IT_GCSSS1 4 #define ESR_ELx_IT_GCSSS2 5 #define ESR_ELx_IT_GCSPOPCX 6 #define ESR_ELx_IT_GCSPOPX 7 #ifndef __ASSEMBLY__ #include <asm/types.h> static inline unsigned long esr_brk_comment(unsigned long esr) { return esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; } static inline bool esr_is_data_abort(unsigned long esr) { const unsigned long ec = ESR_ELx_EC(esr); return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR; } static inline bool esr_is_cfi_brk(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 && (esr_brk_comment(esr) & ~CFI_BRK_IMM_MASK) == CFI_BRK_IMM_BASE; } static inline bool esr_is_ubsan_brk(unsigned long esr) { return (esr_brk_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM; } static inline bool esr_fsc_is_translation_fault(unsigned long esr) { esr = esr & ESR_ELx_FSC; return (esr == ESR_ELx_FSC_FAULT_L(3)) || (esr == ESR_ELx_FSC_FAULT_L(2)) || (esr == ESR_ELx_FSC_FAULT_L(1)) || (esr == ESR_ELx_FSC_FAULT_L(0)) || (esr == ESR_ELx_FSC_FAULT_L(-1)); } static inline bool esr_fsc_is_permission_fault(unsigned long esr) { esr = esr & ESR_ELx_FSC; return (esr == ESR_ELx_FSC_PERM_L(3)) || (esr == ESR_ELx_FSC_PERM_L(2)) || (esr == ESR_ELx_FSC_PERM_L(1)) || (esr == ESR_ELx_FSC_PERM_L(0)); } static inline bool esr_fsc_is_access_flag_fault(unsigned long esr) { esr = esr & ESR_ELx_FSC; return (esr == ESR_ELx_FSC_ACCESS_L(3)) || (esr == ESR_ELx_FSC_ACCESS_L(2)) || (esr == ESR_ELx_FSC_ACCESS_L(1)) || (esr == ESR_ELx_FSC_ACCESS_L(0)); } static inline bool esr_fsc_is_addr_sz_fault(unsigned long esr) { esr &= ESR_ELx_FSC; return (esr == ESR_ELx_FSC_ADDRSZ_L(3)) || (esr == ESR_ELx_FSC_ADDRSZ_L(2)) || (esr == ESR_ELx_FSC_ADDRSZ_L(1)) || (esr == ESR_ELx_FSC_ADDRSZ_L(0)) || (esr == ESR_ELx_FSC_ADDRSZ_L(-1)); } static inline bool esr_fsc_is_sea_ttw(unsigned long esr) { esr = esr & ESR_ELx_FSC; return (esr == ESR_ELx_FSC_SEA_TTW(3)) || (esr == ESR_ELx_FSC_SEA_TTW(2)) || (esr == ESR_ELx_FSC_SEA_TTW(1)) || (esr == ESR_ELx_FSC_SEA_TTW(0)) || (esr == ESR_ELx_FSC_SEA_TTW(-1)); } static inline bool esr_fsc_is_secc_ttw(unsigned long esr) { esr = esr & ESR_ELx_FSC; return (esr == ESR_ELx_FSC_SECC_TTW(3)) || (esr == ESR_ELx_FSC_SECC_TTW(2)) || (esr == ESR_ELx_FSC_SECC_TTW(1)) || (esr == ESR_ELx_FSC_SECC_TTW(0)) || (esr == ESR_ELx_FSC_SECC_TTW(-1)); } /* Indicate whether ESR.EC==0x1A is for an ERETAx instruction */ static inline bool esr_iss_is_eretax(unsigned long esr) { return esr & ESR_ELx_ERET_ISS_ERET; } /* Indicate which key is used for ERETAx (false: A-Key, true: B-Key) */ static inline bool esr_iss_is_eretab(unsigned long esr) { return esr & ESR_ELx_ERET_ISS_ERETA; } const char *esr_get_class_string(unsigned long esr); #endif /* __ASSEMBLY */ #endif /* __ASM_ESR_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 */ #ifndef _LINUX_TIMENS_H #define _LINUX_TIMENS_H #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> #include <linux/time64.h> struct user_namespace; extern struct user_namespace init_user_ns; struct seq_file; struct vm_area_struct; struct timens_offsets { struct timespec64 monotonic; struct timespec64 boottime; }; struct time_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; struct timens_offsets offsets; struct page *vvar_page; /* If set prevents changing offsets after any task joined namespace. */ bool frozen_offsets; } __randomize_layout; extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS extern int vdso_join_timens(struct task_struct *task, struct time_namespace *ns); extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { refcount_inc(&ns->ns.count); return ns; } struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) { if (refcount_dec_and_test(&ns->ns.count)) free_time_ns(ns); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m); struct proc_timens_offset { int clockid; struct timespec64 val; }; int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int n); static inline void timens_add_monotonic(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->monotonic); } static inline void timens_add_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->boottime); } static inline u64 timens_add_boottime_ns(u64 nsec) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; return nsec + timespec64_to_ns(&ns_offsets->boottime); } static inline void timens_sub_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_sub(*ts, ns_offsets->boottime); } ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *offsets); static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { struct time_namespace *ns = current->nsproxy->time_ns; if (likely(ns == &init_time_ns)) return tim; return do_timens_ktime_to_host(clockid, tim, &ns->offsets); } #else static inline int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { return 0; } static inline void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { } static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { return NULL; } static inline void put_time_ns(struct time_namespace *ns) { } static inline struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (flags & CLONE_NEWTIME) return ERR_PTR(-EINVAL); return old_ns; } static inline void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { return; } static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) { return NULL; } static inline void timens_add_monotonic(struct timespec64 *ts) { } static inline void timens_add_boottime(struct timespec64 *ts) { } static inline u64 timens_add_boottime_ns(u64 nsec) { return nsec; } static inline void timens_sub_boottime(struct timespec64 *ts) { } static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { return tim; } #endif #endif /* _LINUX_TIMENS_H */ |
| 255 255 255 255 254 255 255 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/atomic.h> #include <linux/bpf_verifier.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/sock_diag.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/if_arp.h> #include <linux/gfp.h> #include <net/inet_common.h> #include <net/ip.h> #include <net/protocol.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/skmsg.h> #include <net/sock.h> #include <net/flow_dissector.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <linux/unaligned.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> #include <linux/btf.h> #include <net/sch_generic.h> #include <net/cls_cgroup.h> #include <net/dst_metadata.h> #include <net/dst.h> #include <net/sock_reuseport.h> #include <net/busy_poll.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/udp.h> #include <linux/bpf_trace.h> #include <net/xdp_sock.h> #include <linux/inetdevice.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/flow.h> #include <net/arp.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include <linux/seg6_local.h> #include <net/seg6.h> #include <net/seg6_local.h> #include <net/lwtunnel.h> #include <net/ipv6_stubs.h> #include <net/bpf_sk_storage.h> #include <net/transp_v6.h> #include <linux/btf_ids.h> #include <net/tls.h> #include <net/xdp.h> #include <net/mptcp.h> #include <net/netfilter/nf_conntrack_bpf.h> #include <net/netkit.h> #include <linux/un.h> #include <net/xdp_sock_drv.h> #include <net/inet_dscp.h> #include "dev.h" /* Keep the struct bpf_fib_lookup small so that it fits into a cacheline */ static_assert(sizeof(struct bpf_fib_lookup) == 64, "struct bpf_fib_lookup size check"); static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { if (in_compat_syscall()) { struct compat_sock_fprog f32; if (len != sizeof(f32)) return -EINVAL; if (copy_from_sockptr(&f32, src, sizeof(f32))) return -EFAULT; memset(dst, 0, sizeof(*dst)); dst->len = f32.len; dst->filter = compat_ptr(f32.filter); } else { if (len != sizeof(*dst)) return -EINVAL; if (copy_from_sockptr(dst, src, sizeof(*dst))) return -EFAULT; } return 0; } EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); /** * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter * @cap: limit on how short the eBPF program may trim the packet * @reason: record drop reason on errors (negative return value) * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level * wrapper to bpf_prog_run. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap, enum skb_drop_reason *reason) { int err; struct sk_filter *filter; /* * 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)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); *reason = SKB_DROP_REASON_PFMEMALLOC; return -ENOMEM; } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); if (err) { *reason = SKB_DROP_REASON_SOCKET_FILTER; return err; } err = security_sock_rcv_skb(sk, skb); if (err) { *reason = SKB_DROP_REASON_SECURITY_HOOK; return err; } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { struct sock *save_sk = skb->sk; unsigned int pkt_len; skb->sk = sk; pkt_len = bpf_prog_run_save_cb(filter->prog, skb); skb->sk = save_sk; err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; if (err) *reason = SKB_DROP_REASON_SOCKET_FILTER; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(sk_filter_trim_cap); BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb) { return skb_get_poff(skb); } BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *) &skb->data[a]; if (!nla_ok(nla, skb->len - a)) return 0; nla = nla_find_nested(nla, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset) { if (likely(offset >= 0)) return offset; if (offset >= SKF_NET_OFF) return offset - SKF_NET_OFF + skb_network_offset(skb); if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb)) return offset - SKF_LL_OFF + skb_mac_offset(skb); return INT_MIN; } BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { u8 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return *(u8 *)(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return tmp; else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be16 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be16(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be16_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be32 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be32(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be32_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len, offset); } static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; switch (skb_field) { case SKF_AD_MARK: BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); break; case SKF_AD_PKTTYPE: *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); #endif break; case SKF_AD_QUEUE: BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_all) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, vlan_all)); *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, dst_reg, 1); break; } return insn - insn_buf; } static bool convert_bpf_extensions(struct sock_filter *fp, struct bpf_insn **insnp) { struct bpf_insn *insn = *insnp; u32 cnt; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, protocol)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PKTTYPE: cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, dev)); /* if (tmp != 0) goto pc + 1 */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); *insn++ = BPF_EXIT_INSN(); if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, ifindex)); else *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, type)); break; case SKF_AD_OFF + SKF_AD_MARK: cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_RXHASH: BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); break; case SKF_AD_OFF + SKF_AD_QUEUE: cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: cnt = convert_skb_access(SKF_AD_VLAN_TAG, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, vlan_proto)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PAY_OFFSET: case SKF_AD_OFF + SKF_AD_NLATTR: case SKF_AD_OFF + SKF_AD_NLATTR_NEST: case SKF_AD_OFF + SKF_AD_CPU: case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = CTX */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); /* arg2 = A */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); /* arg3 = X */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); /* Emit call(arg1=CTX, arg2=A, arg3=X) */ switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); bpf_user_rnd_init_once(); break; } break; case SKF_AD_OFF + SKF_AD_ALU_XOR_X: /* A ^= X */ *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); break; default: /* This is just a dummy call to avoid letting the compiler * evict __bpf_call_base() as an optimization. Placed here * where no-one bothers. */ BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); return false; } *insnp = insn; return true; } static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) { const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS); int size = bpf_size_to_bytes(BPF_SIZE(fp->code)); bool endian = BPF_SIZE(fp->code) == BPF_H || BPF_SIZE(fp->code) == BPF_W; bool indirect = BPF_MODE(fp->code) == BPF_IND; const int ip_align = NET_IP_ALIGN; struct bpf_insn *insn = *insnp; int offset = fp->k; if (!indirect && ((unaligned_ok && offset >= 0) || (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && offset + ip_align % size == 0))) { bool ldx_off_ok = offset <= S16_MAX; *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); if (offset) *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian + (!ldx_off_ok * 2)); if (ldx_off_ok) { *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_TMP, 0); } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); } *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D); *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X); if (fp->k) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset); } switch (BPF_SIZE(fp->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32); break; default: return false; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn = BPF_EXIT_INSN(); *insnp = insn; return true; } /** * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program * @seen_ld_abs: bool whether we've seen ld_abs/ind * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' * style extended BPF (eBPF). * Conversion workflow: * * 1) First pass for calculating the new program length: * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs) */ static int bpf_convert_filter(struct sock_filter *prog, int len, struct bpf_prog *new_prog, int *new_len, bool *seen_ld_abs) { int new_flen = 0, pass = 0, target, i, stack_off; struct bpf_insn *new_insn, *first_insn = NULL; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); if (len <= 0 || len > BPF_MAXINSNS) return -EINVAL; if (new_prog) { first_insn = new_prog->insnsi; addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL | __GFP_NOWARN); if (!addrs) return -ENOMEM; } do_pass: new_insn = first_insn; fp = prog; /* Classic BPF related prologue emission. */ if (new_prog) { /* Classic BPF expects A and X to be reset first. These need * to be guaranteed to be the first two instructions. */ *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_X, BPF_REG_X); /* All programs must keep CTX in callee saved BPF_REG_CTX. * In eBPF case it's done by the compiler, here we need to * do this ourself. Initial CTX is present in BPF_REG_ARG1. */ *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); if (*seen_ld_abs) { /* For packet access in classic BPF, cache skb->data * in callee-saved BPF R8 and skb->len - skb->data_len * (headlen) in BPF R9. Since classic BPF is read-only * on CTX, we only need to cache it once. */ *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), BPF_REG_D, BPF_REG_CTX, offsetof(struct sk_buff, data)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX, offsetof(struct sk_buff, len)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, data_len)); *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP); } } else { new_insn += 3; } for (i = 0; i < len; fp++, i++) { struct bpf_insn tmp_insns[32] = { }; struct bpf_insn *insn = tmp_insns; if (addrs) addrs[i] = new_insn - first_insn; switch (fp->code) { /* All arithmetic insns and skb loads map as-is. */ case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_ABS | BPF_W: case BPF_LD | BPF_ABS | BPF_H: case BPF_LD | BPF_ABS | BPF_B: case BPF_LD | BPF_IND | BPF_W: case BPF_LD | BPF_IND | BPF_H: case BPF_LD | BPF_IND | BPF_B: /* Check for overloaded BPF extension and * directly convert it if found, otherwise * just move on with mapping. */ if (BPF_CLASS(fp->code) == BPF_LD && BPF_MODE(fp->code) == BPF_ABS && convert_bpf_extensions(fp, &insn)) break; if (BPF_CLASS(fp->code) == BPF_LD && convert_bpf_ld_abs(fp, &insn)) { *seen_ld_abs = true; break; } if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || fp->code == (BPF_ALU | BPF_MOD | BPF_X)) { *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); /* Error with exception code on div/mod by 0. * For cBPF programs, this was always return 0. */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_X, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn++ = BPF_EXIT_INSN(); } *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; /* Jump transformation cannot use BPF block macros * everywhere as offset calculation and target updates * require a bit more work than the rest, i.e. jump * opcodes map as-is, but offsets need adjustment. */ #define BPF_EMIT_JMP \ do { \ const s32 off_min = S16_MIN, off_max = S16_MAX; \ s32 off; \ \ if (target >= len || target < 0) \ goto err; \ off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ /* Adjust pc relative offset for 2nd or 3rd insn. */ \ off -= insn - tmp_insns; \ /* Reject anything not fitting into insn->off. */ \ if (off < off_min || off > off_max) \ goto err; \ insn->off = off; \ } while (0) case BPF_JMP | BPF_JA: target = i + fp->k + 1; insn->code = fp->code; BPF_EMIT_JMP; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { /* BPF immediates are signed, zero extend * immediate into tmp register and use it * in compare insn. */ *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); insn->dst_reg = BPF_REG_A; insn->src_reg = BPF_REG_TMP; bpf_src = BPF_X; } else { insn->dst_reg = BPF_REG_A; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0; } /* Common case where 'jump_false' is next insn. */ if (fp->jf == 0) { insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; target = i + fp->jt + 1; BPF_EMIT_JMP; break; } /* Convert some jumps when 'jump_true' is next insn. */ if (fp->jt == 0) { switch (BPF_OP(fp->code)) { case BPF_JEQ: insn->code = BPF_JMP | BPF_JNE | bpf_src; break; case BPF_JGT: insn->code = BPF_JMP | BPF_JLE | bpf_src; break; case BPF_JGE: insn->code = BPF_JMP | BPF_JLT | bpf_src; break; default: goto jmp_rest; } target = i + fp->jf + 1; BPF_EMIT_JMP; break; } jmp_rest: /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; BPF_EMIT_JMP; insn++; insn->code = BPF_JMP | BPF_JA; target = i + fp->jf + 1; BPF_EMIT_JMP; break; /* ldxb 4 * ([14] & 0xf) is remapped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: { struct sock_filter tmp = { .code = BPF_LD | BPF_ABS | BPF_B, .k = fp->k, }; *seen_ld_abs = true; /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ convert_bpf_ld_abs(&tmp, &insn); insn++; /* A &= 0xf */ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); /* tmp = X */ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X); /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; } /* RET_K is remapped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: if (BPF_RVAL(fp->code) == BPF_K) *insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0, 0, fp->k); *insn = BPF_EXIT_INSN(); break; /* Store to stack. */ case BPF_ST: case BPF_STX: stack_off = fp->k * 4 + 4; *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == BPF_ST ? BPF_REG_A : BPF_REG_X, -stack_off); /* check_load_and_stores() verifies that classic BPF can * load from stack only after write, so tracking * stack_depth for ST|STX insns is enough */ if (new_prog && new_prog->aux->stack_depth < stack_off) new_prog->aux->stack_depth = stack_off; break; /* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: stack_off = fp->k * 4 + 4; *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_FP, -stack_off); break; /* A = K or X = K */ case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, fp->k); break; /* X = A */ case BPF_MISC | BPF_TAX: *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); break; /* A = X */ case BPF_MISC | BPF_TXA: *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); break; /* A = skb->len or X = skb->len */ case BPF_LD | BPF_W | BPF_LEN: case BPF_LDX | BPF_W | BPF_LEN: *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_CTX, offsetof(struct sk_buff, len)); break; /* Access seccomp_data fields. */ case BPF_LDX | BPF_ABS | BPF_W: /* A = *(u32 *) (ctx + K) */ *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; /* Unknown instruction. */ default: goto err; } insn++; if (new_prog) memcpy(new_insn, tmp_insns, sizeof(*insn) * (insn - tmp_insns)); new_insn += insn - tmp_insns; } if (!new_prog) { /* Only calculating new length. */ *new_len = new_insn - first_insn; if (*seen_ld_abs) *new_len += 4; /* Prologue bits. */ return 0; } pass++; if (new_flen != new_insn - first_insn) { new_flen = new_insn - first_insn; if (pass > 2) goto err; goto do_pass; } kfree(addrs); BUG_ON(*new_len != new_flen); return 0; err: kfree(addrs); return -EINVAL; } /* Security: * * As we dont want to clear mem[] array for each packet going through * __bpf_prog_run(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(const struct sock_filter *filter, int flen) { u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; BUILD_BUG_ON(BPF_MEMWORDS > 16); masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; memset(masks, 0xff, flen * sizeof(*masks)); for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc]; switch (filter[pc].code) { case BPF_ST: case BPF_STX: memvalid |= (1 << filter[pc].k); break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; case BPF_JMP | BPF_JA: /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; break; } } error: kfree(masks); return ret; } static bool chk_code_allowed(u16 code_to_probe) { static const bool codes[] = { /* 32 bit ALU operations */ [BPF_ALU | BPF_ADD | BPF_K] = true, [BPF_ALU | BPF_ADD | BPF_X] = true, [BPF_ALU | BPF_SUB | BPF_K] = true, [BPF_ALU | BPF_SUB | BPF_X] = true, [BPF_ALU | BPF_MUL | BPF_K] = true, [BPF_ALU | BPF_MUL | BPF_X] = true, [BPF_ALU | BPF_DIV | BPF_K] = true, [BPF_ALU | BPF_DIV | BPF_X] = true, [BPF_ALU | BPF_MOD | BPF_K] = true, [BPF_ALU | BPF_MOD | BPF_X] = true, [BPF_ALU | BPF_AND | BPF_K] = true, [BPF_ALU | BPF_AND | BPF_X] = true, [BPF_ALU | BPF_OR | BPF_K] = true, [BPF_ALU | BPF_OR | BPF_X] = true, [BPF_ALU | BPF_XOR | BPF_K] = true, [BPF_ALU | BPF_XOR | BPF_X] = true, [BPF_ALU | BPF_LSH | BPF_K] = true, [BPF_ALU | BPF_LSH | BPF_X] = true, [BPF_ALU | BPF_RSH | BPF_K] = true, [BPF_ALU | BPF_RSH | BPF_X] = true, [BPF_ALU | BPF_NEG] = true, /* Load instructions */ [BPF_LD | BPF_W | BPF_ABS] = true, [BPF_LD | BPF_H | BPF_ABS] = true, [BPF_LD | BPF_B | BPF_ABS] = true, [BPF_LD | BPF_W | BPF_LEN] = true, [BPF_LD | BPF_W | BPF_IND] = true, [BPF_LD | BPF_H | BPF_IND] = true, [BPF_LD | BPF_B | BPF_IND] = true, [BPF_LD | BPF_IMM] = true, [BPF_LD | BPF_MEM] = true, [BPF_LDX | BPF_W | BPF_LEN] = true, [BPF_LDX | BPF_B | BPF_MSH] = true, [BPF_LDX | BPF_IMM] = true, [BPF_LDX | BPF_MEM] = true, /* Store instructions */ [BPF_ST] = true, [BPF_STX] = true, /* Misc instructions */ [BPF_MISC | BPF_TAX] = true, [BPF_MISC | BPF_TXA] = true, /* Return instructions */ [BPF_RET | BPF_K] = true, [BPF_RET | BPF_A] = true, /* Jump instructions */ [BPF_JMP | BPF_JA] = true, [BPF_JMP | BPF_JEQ | BPF_K] = true, [BPF_JMP | BPF_JEQ | BPF_X] = true, [BPF_JMP | BPF_JGE | BPF_K] = true, [BPF_JMP | BPF_JGE | BPF_X] = true, [BPF_JMP | BPF_JGT | BPF_K] = true, [BPF_JMP | BPF_JGT | BPF_X] = true, [BPF_JMP | BPF_JSET | BPF_K] = true, [BPF_JMP | BPF_JSET | BPF_X] = true, }; if (code_to_probe >= ARRAY_SIZE(codes)) return false; return codes[code_to_probe]; } static bool bpf_check_basics_ok(const struct sock_filter *filter, unsigned int flen) { if (filter == NULL) return false; if (flen == 0 || flen > BPF_MAXINSNS) return false; return true; } /** * bpf_check_classic - verify socket filter code * @filter: filter to verify * @flen: length of filter * * Check the user's filter code. If we let some ugly * filter code slip through kaboom! The filter must contain * no references or jumps that are out of range, no illegal * instructions, and must end with a RET instruction. * * All jumps are forward as they are not signed. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) { bool anc_found; int pc; /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { const struct sock_filter *ftest = &filter[pc]; /* May we actually operate on this code? */ if (!chk_code_allowed(ftest->code)) return -EINVAL; /* Some instructions need special checks */ switch (ftest->code) { case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; break; case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: if (ftest->k >= 32) return -EINVAL; break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; case BPF_JMP | BPF_JA: /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: anc_found = false; if (bpf_anc_helper(ftest) & BPF_ANC) anc_found = true; /* Ancillary operation unknown or unsupported */ if (anc_found == false && ftest->k >= SKF_AD_OFF) return -EINVAL; } } /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { case BPF_RET | BPF_K: case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } return -EINVAL; } static int bpf_prog_store_orig_filter(struct bpf_prog *fp, const struct sock_fprog *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct sock_fprog_kern *fkprog; fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); if (!fp->orig_prog) return -ENOMEM; fkprog = fp->orig_prog; fkprog->len = fprog->len; fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL | __GFP_NOWARN); if (!fkprog->filter) { kfree(fp->orig_prog); return -ENOMEM; } return 0; } static void bpf_release_orig_filter(struct bpf_prog *fp) { struct sock_fprog_kern *fprog = fp->orig_prog; if (fprog) { kfree(fprog->filter); kfree(fprog); } } static void __bpf_prog_release(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); } else { bpf_release_orig_filter(prog); bpf_prog_free(prog); } } static void __sk_filter_release(struct sk_filter *fp) { __bpf_prog_release(fp->prog); kfree(fp); } /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); __sk_filter_release(fp); } /** * sk_filter_release - release a socket filter * @fp: filter to remove * * Remove a filter from a socket and release its resources. */ static void sk_filter_release(struct sk_filter *fp) { if (refcount_dec_and_test(&fp->refcnt)) call_rcu(&fp->rcu, sk_filter_release_rcu); } void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); atomic_sub(filter_size, &sk->sk_omem_alloc); sk_filter_release(fp); } /* try to charge the socket memory if there is space available * return true on success */ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); u32 filter_size = bpf_prog_size(fp->prog->len); /* same check as in sock_kmalloc() */ if (filter_size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } return false; } bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { if (!refcount_inc_not_zero(&fp->refcnt)) return false; if (!__sk_filter_charge(sk, fp)) { sk_filter_release(fp); return false; } return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; bool seen_ld_abs = false; /* We are free to overwrite insns et al right here as it won't be used at * this point in time anymore internally after the migration to the eBPF * instruction representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct bpf_insn)); /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. */ old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter), GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; } /* 1st pass: calculate the new program length. */ err = bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs); if (err) goto out_err_free; /* Expand fp for appending the new filter representation. */ old_fp = fp; fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. */ fp = old_fp; err = -ENOMEM; goto out_err_free; } fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ err = bpf_convert_filter(old_prog, old_len, fp, &new_len, &seen_ld_abs); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, * that at this time old_fp has already been released * by krealloc(). */ goto out_err_free; fp = bpf_prog_select_runtime(fp, &err); if (err) goto out_err_free; kfree(old_prog); return fp; out_err_free: kfree(old_prog); out_err: __bpf_prog_release(fp); return ERR_PTR(err); } static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, bpf_aux_classic_check_t trans) { int err; fp->bpf_func = NULL; fp->jited = 0; err = bpf_check_classic(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } /* There might be additional checks and transformations * needed on classic filters, f.e. in case of seccomp. */ if (trans) { err = trans(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } } /* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. */ bpf_jit_compile(fp); /* JIT compiler couldn't process this filter, so do the eBPF translation * for the optimized interpreter. */ if (!fp->jited) fp = bpf_migrate_filter(fp); return fp; } /** * bpf_prog_create - create an unattached filter * @pfp: the unattached filter that is created * @fprog: the filter program * * Create a filter independent of any socket. We first run some * sanity checks on it to make sure it does not explode on us later. * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. */ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); fp->len = fprog->len; /* Since unattached filters are not copied back to user * space through sk_get_filter(), we do not need to hold * a copy here, and can spare us the work. */ fp->orig_prog = NULL; /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, NULL); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create); /** * bpf_prog_create_from_user - create an unattached filter from user buffer * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; int err; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; if (copy_from_user(fp->insns, fprog->filter, fsize)) { __bpf_prog_free(fp); return -EFAULT; } fp->len = fprog->len; fp->orig_prog = NULL; if (save_orig) { err = bpf_prog_store_orig_filter(fp, fprog); if (err) { __bpf_prog_free(fp); return -ENOMEM; } } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, trans); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create_from_user); void bpf_prog_destroy(struct bpf_prog *fp) { __bpf_prog_release(fp); } EXPORT_SYMBOL_GPL(bpf_prog_destroy); static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) { struct sk_filter *fp, *old_fp; fp = kmalloc(sizeof(*fp), GFP_KERNEL); if (!fp) return -ENOMEM; fp->prog = prog; if (!__sk_filter_charge(sk, fp)) { kfree(fp); return -ENOMEM; } refcount_set(&fp->refcnt, 1); old_fp = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) sk_filter_uncharge(sk, old_fp); return 0; } static struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return ERR_PTR(-EINVAL); prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!prog) return ERR_PTR(-ENOMEM); if (copy_from_user(prog->insns, fprog->filter, fsize)) { __bpf_prog_free(prog); return ERR_PTR(-EFAULT); } prog->len = fprog->len; err = bpf_prog_store_orig_filter(prog, fprog); if (err) { __bpf_prog_free(prog); return ERR_PTR(-ENOMEM); } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ return bpf_prepare_filter(prog, NULL); } /** * sk_attach_filter - attach a socket filter * @fprog: the filter program * @sk: the socket to use * * Attach the user's filter code. We first run some sanity checks on * it to make sure it does not explode on us later. If an error * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { __bpf_prog_release(prog); return err; } return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err, optmem_max; if (IS_ERR(prog)) return PTR_ERR(prog); optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); if (err) __bpf_prog_release(prog); return err; } static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk) { if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); } int sk_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog = __get_bpf(ufd, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { bpf_prog_put(prog); return err; } return 0; } int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog; int err, optmem_max; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); if (PTR_ERR(prog) == -EINVAL) prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) { /* Like other non BPF_PROG_TYPE_SOCKET_FILTER * bpf prog (e.g. sockmap). It depends on the * limitation imposed by bpf_prog_load(). * Hence, sysctl_optmem_max is not checked. */ if ((sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_DGRAM) || (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_TCP) || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { err = -ENOTSUPP; goto err_prog_put; } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) { err = -ENOMEM; goto err_prog_put; } } err = reuseport_attach_prog(sk, prog); err_prog_put: if (err) bpf_prog_put(prog); return err; } void sk_reuseport_prog_free(struct bpf_prog *prog) { if (!prog) return; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) bpf_prog_put(prog); else bpf_prog_destroy(prog); } static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { #ifdef CONFIG_DEBUG_NET /* Avoid a splat in pskb_may_pull_reason() */ if (write_len > INT_MAX) return -EINVAL; #endif return skb_ensure_writable(skb, write_len); } static inline int bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { int err = __bpf_try_make_writable(skb, write_len); bpf_compute_data_pointers(skb); return err; } static int bpf_try_make_head_writable(struct sk_buff *skb) { return bpf_try_make_writable(skb, skb_headlen(skb)); } static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); } static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); } BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len, u64, flags) { void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return ____bpf_skb_store_bytes(skb, offset, from, len, flags); } BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return ____bpf_skb_load_bytes(skb, offset, to, len); } BPF_CALL_4(bpf_flow_dissector_load_bytes, const struct bpf_flow_dissector *, ctx, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > 0xffff)) goto err_clear; if (unlikely(!ctx->skb)) goto err_clear; ptr = skb_header_pointer(ctx->skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { .func = bpf_flow_dissector_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); u8 *start, *ptr; if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: if (unlikely(!skb_mac_header_was_set(skb))) goto err_clear; start = skb_mac_header(skb); break; case BPF_HDR_START_NET: start = skb_network_header(skb); break; default: goto err_clear; } ptr = start + offset; if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = { .func = bpf_skb_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto bpf_skb_pull_data_proto = { .func = bpf_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk) { return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL; } static const struct bpf_func_proto bpf_sk_fullsock_proto = { .func = bpf_sk_fullsock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return __bpf_try_make_writable(skb, write_len); } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto sk_skb_pull_data_proto = { .func = sk_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; csum_replace_by_diff(ptr, to); break; case 2: csum_replace2(ptr, from, to); break; case 4: csum_replace4(ptr, from, to); break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; bool do_mforce = flags & BPF_F_MARK_ENFORCE; bool is_ipv6 = flags & BPF_F_IPV6; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !do_mforce && !*ptr) return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6); break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); break; case 4: inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo); break; default: return -EINVAL; } if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; return 0; } static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, __be32 *, to, u32, to_size, __wsum, seed) { /* This is quite flexible, some examples: * * from_size == 0, to_size > 0, seed := csum --> pushing data * from_size > 0, to_size == 0, seed := csum --> pulling data * from_size > 0, to_size > 0, seed := 0 --> diffing data * * Even for diffing, from_size and to_size don't need to be equal. */ __wsum ret = seed; if (from_size && to_size) ret = csum_sub(csum_partial(to, to_size, ret), csum_partial(from, from_size, 0)); else if (to_size) ret = csum_partial(to, to_size, ret); else if (from_size) ret = ~csum_partial(from, from_size, ~ret); return csum_from32to16((__force unsigned int)ret); } static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) { /* The interface is to be used in combination with bpf_csum_diff() * for direct packet writes. csum rotation for alignment as well * as emulating csum_sub() can be done from the eBPF program. */ if (skb->ip_summed == CHECKSUM_COMPLETE) return (skb->csum = csum_add(skb->csum, csum)); return -ENOTSUPP; } static const struct bpf_func_proto bpf_csum_update_proto = { .func = bpf_csum_update, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level) { /* The interface is to be used in combination with bpf_skb_adjust_room() * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET * is passed as flags, for example. */ switch (level) { case BPF_CSUM_LEVEL_INC: __skb_incr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_DEC: __skb_decr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_RESET: __skb_reset_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_QUERY: return skb->ip_summed == CHECKSUM_UNNECESSARY ? skb->csum_level : -EACCES; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_csum_level_proto = { .func = bpf_csum_level, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb_nomtu(dev, skb); } static inline int __bpf_rx_skb_no_mac(struct net_device *dev, struct sk_buff *skb) { int ret = ____dev_forward_skb(dev, skb, false); if (likely(!ret)) { skb->dev = dev; ret = netif_rx(skb); } return ret; } static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); kfree_skb(skb); return -ENETDOWN; } skb->dev = dev; skb_set_redirected_noclear(skb, skb_at_tc_ingress(skb)); skb_clear_tstamp(skb); dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); dev_xmit_recursion_dec(); return ret; } static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { unsigned int mlen = skb_network_offset(skb); if (unlikely(skb->len <= mlen)) { kfree_skb(skb); return -ERANGE; } if (mlen) { __skb_pull(skb, mlen); /* At ingress, the mac header has already been pulled once. * At egress, skb_pospull_rcsum has to be done in case that * the skb is originated from ingress (i.e. a forwarded skb) * to ensure that rcsum starts at net header. */ if (!skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { /* Verify that a link layer header is carried */ if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) { kfree_skb(skb); return -ERANGE; } bpf_push_mac_rcsum(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, u32 flags) { if (dev_is_mac_header_xmit(dev)) return __bpf_redirect_common(skb, dev, flags); else return __bpf_redirect_no_mac(skb, dev, flags); } #if IS_ENABLED(CONFIG_IPV6) static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *nexthop; struct dst_entry *dst = NULL; struct neighbour *neigh; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } rcu_read_lock(); if (!nh) { dst = skb_dst(skb); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); } else { nexthop = &nh->ipv6_nh; } neigh = ip_neigh_gw6(dev, nexthop); if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, false); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); if (dst) IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_flags = FLOWI_FLAG_ANYSRC, .flowi6_mark = skb->mark, .flowlabel = ip6_flowinfo(ip6h), .flowi6_oif = dev->ifindex, .flowi6_proto = ip6h->nexthdr, .daddr = ip6h->daddr, .saddr = ip6h->saddr, }; dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) goto out_drop; skb_dst_set(skb, dst); } else if (nh->nh_family != AF_INET6) { goto out_drop; } err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_IPV6 */ #if IS_ENABLED(CONFIG_INET) static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } rcu_read_lock(); if (!nh) { struct rtable *rt = skb_rtable(skb); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { neigh = ip_neigh_gw4(dev, nh->ipv4_nh); } else { rcu_read_unlock(); goto out_drop; } if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, is_v6gw); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct iphdr *ip4h = ip_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct flowi4 fl4 = { .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)), .flowi4_oif = dev->ifindex, .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr, .saddr = ip4h->saddr, }; struct rtable *rt; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out_drop; if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); goto out_drop; } skb_dst_set(skb, &rt->dst); } err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_INET */ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { struct ethhdr *ethh = eth_hdr(skb); if (unlikely(skb->mac_header >= skb->network_header)) goto out; bpf_push_mac_rcsum(skb); if (is_multicast_ether_addr(ethh->h_dest)) goto out; skb_pull(skb, sizeof(*ethh)); skb_unset_mac_header(skb); skb_reset_network_header(skb); if (skb->protocol == htons(ETH_P_IP)) return __bpf_redirect_neigh_v4(skb, dev, nh); else if (skb->protocol == htons(ETH_P_IPV6)) return __bpf_redirect_neigh_v6(skb, dev, nh); out: kfree_skb(skb); return -ENOTSUPP; } /* Internal, non-exposed redirect flags. */ enum { BPF_F_NEIGH = (1ULL << 16), BPF_F_PEER = (1ULL << 17), BPF_F_NEXTHOP = (1ULL << 18), #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) }; BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; BUILD_BUG_ON(BPF_F_REDIRECT_INTERNAL & BPF_F_REDIRECT_FLAGS); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); if (unlikely(!dev)) return -EINVAL; clone = skb_clone(skb, GFP_ATOMIC); if (unlikely(!clone)) return -ENOMEM; /* For direct write, we need to keep the invariant that the skbs * we're dealing with need to be uncloned. Should uncloning fail * here, we need to free the just generated clone to unclone once * again. */ ret = bpf_try_make_head_writable(skb); if (unlikely(ret)) { kfree_skb(clone); return -ENOMEM; } return __bpf_redirect(clone, dev, flags); } static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static struct net_device *skb_get_peer_dev(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; if (likely(ops->ndo_get_peer_dev)) return INDIRECT_CALL_1(ops->ndo_get_peer_dev, netkit_peer_dev, dev); return NULL; } int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; dev = dev_get_by_index_rcu(net, ri->tgt_index); ri->tgt_index = 0; ri->flags = 0; if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { if (unlikely(!skb_at_tc_ingress(skb))) goto out_drop; dev = skb_get_peer_dev(dev); if (unlikely(!dev || !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); skb_scrub_packet(skb, false); return -EAGAIN; } return flags & BPF_F_NEIGH ? __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ? &ri->nh : NULL) : __bpf_redirect(skb, dev, flags); out_drop: kfree_skb(skb); return -EINVAL; } BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; ri->flags = flags; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return TC_ACT_SHOT; ri->flags = BPF_F_PEER; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_peer_proto = { .func = bpf_redirect_peer, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely((plen && plen < sizeof(*params)) || flags)) return TC_ACT_SHOT; ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0); ri->tgt_index = ifindex; BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params)); if (plen) memcpy(&ri->nh, params, sizeof(ri->nh)); return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_neigh_proto = { .func = bpf_redirect_neigh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; return 0; } static const struct bpf_func_proto bpf_msg_apply_bytes_proto = { .func = bpf_msg_apply_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) { msg->cork_bytes = bytes; return 0; } static void sk_msg_reset_curr(struct sk_msg *msg) { if (!msg->sg.size) { msg->sg.curr = msg->sg.start; msg->sg.copybreak = 0; } else { u32 i = msg->sg.end; sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } } static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, u32, end, u64, flags) { u32 len = 0, offset = 0, copy = 0, poffset = 0, bytes = end - start; u32 first_sge, last_sge, i, shift, bytes_sg_total; struct scatterlist *sge; u8 *raw, *to, *from; struct page *page; if (unlikely(flags || end <= start)) return -EINVAL; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += len; len = sk_msg_elem(msg, i)->length; if (start < offset + len) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (unlikely(start >= offset + len)) return -EINVAL; first_sge = i; /* The start may point into the sg element so we need to also * account for the headroom. */ bytes_sg_total = start - offset + bytes; if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to * copy into a linear buffer exclusively owned by BPF. Then * place the buffer in the scatterlist and fixup the original * entries by removing the entries now in the linear buffer * and shifting the remaining entries. For now we do not try * to copy partial entries to avoid complexity of running out * of sg_entry slots. The downside is reading a single byte * will copy the entire sg entry. */ do { copy += sk_msg_elem(msg, i)->length; sk_msg_iter_var_next(i); if (bytes_sg_total <= copy) break; } while (i != msg->sg.end); last_sge = i; if (unlikely(bytes_sg_total > copy)) return -EINVAL; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy)); if (unlikely(!page)) return -ENOMEM; raw = page_address(page); i = first_sge; do { sge = sk_msg_elem(msg, i); from = sg_virt(sge); len = sge->length; to = raw + poffset; memcpy(to, from, len); poffset += len; sge->length = 0; put_page(sg_page(sge)); sk_msg_iter_var_next(i); } while (i != last_sge); sg_set_page(&msg->sg.data[first_sge], page, copy, 0); /* To repair sg ring we need to shift entries. If we only * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; i = first_sge; sk_msg_iter_var_next(i); do { u32 move_from; if (i + shift >= NR_MSG_FRAG_IDS) move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) break; msg->sg.data[i] = msg->sg.data[move_from]; msg->sg.data[move_from].length = 0; msg->sg.data[move_from].page_link = 0; msg->sg.data[move_from].offset = 0; sk_msg_iter_var_next(i); } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; } static const struct bpf_func_proto bpf_msg_pull_data_proto = { .func = bpf_msg_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; u32 new, i = 0, l = 0, space, copy = 0, offset = 0; u8 *raw, *to, *from; struct page *page; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (start > offset + l) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); /* If no space available will fallback to copy, we need at * least one scatterlist elem available to push data into * when start aligns to the beginning of an element or two * when it falls inside an element. We handle the start equals * offset case because its the common case for inserting a * header. */ if (!space || (space == 1 && start != offset)) copy = msg->sg.data[i].length; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy + len)); if (unlikely(!page)) return -ENOMEM; if (copy) { int front, back; raw = page_address(page); if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); front = start - offset; back = psge->length - front; from = sg_virt(psge); if (front) memcpy(raw, from, front); if (back) { from += front; to = raw + front + len; memcpy(to, from, back); } put_page(sg_page(psge)); new = i; goto place_new; } if (start - offset) { if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); rsge = sk_msg_elem_cpy(msg, i); psge->length = start - offset; rsge.length -= psge->length; rsge.offset += start; sk_msg_iter_var_next(i); sg_unmark_end(psge); sg_unmark_end(&rsge); } /* Slot(s) to place newly allocated data */ sk_msg_iter_next(msg, end); new = i; sk_msg_iter_var_next(i); if (i == msg->sg.end) { if (!rsge.length) goto place_new; sk_msg_iter_next(msg, end); goto place_new; } /* Shift one or two slots as needed */ sge = sk_msg_elem_cpy(msg, new); sg_unmark_end(&sge); nsge = sk_msg_elem_cpy(msg, i); if (rsge.length) { sk_msg_iter_var_next(i); nnsge = sk_msg_elem_cpy(msg, i); sk_msg_iter_next(msg, end); } while (i != msg->sg.end) { msg->sg.data[i] = sge; sge = nsge; sk_msg_iter_var_next(i); if (rsge.length) { nsge = nnsge; nnsge = sk_msg_elem_cpy(msg, i); } else { nsge = sk_msg_elem_cpy(msg, i); } } place_new: /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; __clear_bit(new, msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); sk_msg_iter_var_next(new); msg->sg.data[new] = rsge; } sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_push_data_proto = { .func = bpf_msg_push_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static void sk_msg_shift_left(struct sk_msg *msg, int i) { struct scatterlist *sge = sk_msg_elem(msg, i); int prev; put_page(sg_page(sge)); do { prev = i; sk_msg_iter_var_next(i); msg->sg.data[prev] = msg->sg.data[i]; } while (i != msg->sg.end); sk_msg_iter_prev(msg, end); } static void sk_msg_shift_right(struct sk_msg *msg, int i) { struct scatterlist tmp, sge; sk_msg_iter_next(msg, end); sge = sk_msg_elem_cpy(msg, i); sk_msg_iter_var_next(i); tmp = sk_msg_elem_cpy(msg, i); while (i != msg->sg.end) { msg->sg.data[i] = sge; sk_msg_iter_var_next(i); sge = tmp; tmp = sk_msg_elem_cpy(msg, i); } } BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { u32 i = 0, l = 0, space, offset = 0; u64 last = start + len; int pop; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); /* Bounds checks: start and pop must be inside message */ if (start >= offset + l || last > msg->sg.size) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); pop = len; /* --------------| offset * -| start |-------- len -------| * * |----- a ----|-------- pop -------|----- b ----| * |______________________________________________| length * * * a: region at front of scatter element to save * b: region at back of scatter element to save when length > A + pop * pop: region to pop from element, same as input 'pop' here will be * decremented below per iteration. * * Two top-level cases to handle when start != offset, first B is non * zero and second B is zero corresponding to when a pop includes more * than one element. * * Then if B is non-zero AND there is no space allocate space and * compact A, B regions into page. If there is space shift ring to * the right free'ing the next element in ring to place B, leaving * A untouched except to reduce length. */ if (start != offset) { struct scatterlist *nsge, *sge = sk_msg_elem(msg, i); int a = start - offset; int b = sge->length - pop - a; sk_msg_iter_var_next(i); if (b > 0) { if (space) { sge->length = a; sk_msg_shift_right(msg, i); nsge = sk_msg_elem(msg, i); get_page(sg_page(sge)); sg_set_page(nsge, sg_page(sge), b, sge->offset + pop + a); } else { struct page *page, *orig; u8 *to, *from; page = alloc_pages(__GFP_NOWARN | __GFP_COMP | GFP_ATOMIC, get_order(a + b)); if (unlikely(!page)) return -ENOMEM; orig = sg_page(sge); from = sg_virt(sge); to = page_address(page); memcpy(to, from, a); memcpy(to + a, from + a + pop, b); sg_set_page(sge, page, a + b, 0); put_page(orig); } pop = 0; } else { pop -= (sge->length - a); sge->length = a; } } /* From above the current layout _must_ be as follows, * * -| offset * -| start * * |---- pop ---|---------------- b ------------| * |____________________________________________| length * * Offset and start of the current msg elem are equal because in the * previous case we handled offset != start and either consumed the * entire element and advanced to the next element OR pop == 0. * * Two cases to handle here are first pop is less than the length * leaving some remainder b above. Simply adjust the element's layout * in this case. Or pop >= length of the element so that b = 0. In this * case advance to next element decrementing pop. */ while (pop) { struct scatterlist *sge = sk_msg_elem(msg, i); if (pop < sge->length) { sge->length -= pop; sge->offset += pop; pop = 0; } else { pop -= sge->length; sk_msg_shift_left(msg, i); } } sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_pop_data_proto = { .func = bpf_msg_pop_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; #ifdef CONFIG_CGROUP_NET_CLASSID BPF_CALL_0(bpf_get_cgroup_classid_curr) { return __task_get_classid(current); } const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .func = bpf_get_cgroup_classid_curr, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) { struct sock *sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return 0; return sock_cgroup_classid(&sk->sk_cgrp_data); } static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { .func = bpf_skb_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); } static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .func = bpf_get_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb) { return dst_tclassid(skb); } static const struct bpf_func_proto bpf_get_route_realm_proto = { .func = bpf_get_route_realm, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb) { /* If skb_clear_hash() was called due to mangling, we can * trigger SW recalculation here. Later access to hash * can then use the inline skb->hash via context directly * instead of calling this helper again. */ return skb_get_hash(skb); } static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .func = bpf_get_hash_recalc, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb) { /* After all direct packet write, this can be used once for * triggering a lazy recalc on next skb_get_hash() invocation. */ skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_set_hash_invalid_proto = { .func = bpf_set_hash_invalid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_2(bpf_set_hash, struct sk_buff *, skb, u32, hash) { /* Set user specified hash as L4(+), so that it gets returned * on skb_get_hash() call unless BPF prog later on triggers a * skb_clear_hash(). */ __skb_set_sw_hash(skb, hash, true); return 0; } static const struct bpf_func_proto bpf_set_hash_proto = { .func = bpf_set_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, u16, vlan_tci) { int ret; if (unlikely(vlan_proto != htons(ETH_P_8021Q) && vlan_proto != htons(ETH_P_8021AD))) vlan_proto = htons(ETH_P_8021Q); bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); skb_reset_mac_len(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_push_proto = { .func = bpf_skb_vlan_push, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { int ret; bpf_push_mac_rcsum(skb); ret = skb_vlan_pop(skb); bpf_pull_mac_rcsum(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .func = bpf_skb_vlan_pop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto) { skb->protocol = htons(proto); if (skb_valid_dst(skb)) skb_dst_drop(skb); } static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { /* Caller already did skb_cow() with len as headroom, * so no need to do it here. */ skb_push(skb, len); memmove(skb->data, skb->data + len, off); memset(skb->data + off, 0, len); /* No skb_postpush_rcsum(skb, skb->data + off, len) * needed here as it does not change the skb->csum * result for checksum complete when summing over * zeroed blocks. */ return 0; } static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) { void *old_data; /* skb_ensure_writable() is not needed here, as we're * already working on an uncloned skb. */ if (unlikely(!pskb_may_pull(skb, off + len))) return -ENOMEM; old_data = skb->data; __skb_pull(skb, len); skb_postpull_rcsum(skb, old_data + off, len); memmove(skb->data, old_data, off); return 0; } static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* There's no need for __skb_push()/__skb_pull() pair to * get to the start of the mac header as we're guaranteed * to always start from here under eBPF. */ ret = bpf_skb_generic_push(skb, off, len); if (likely(!ret)) { skb->mac_header -= len; skb->network_header -= len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* Same here, __skb_push()/__skb_pull() pair not needed. */ ret = bpf_skb_generic_pop(skb, off, len); if (likely(!ret)) { skb->mac_header += len; skb->network_header += len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_proto_4_to_6(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } } bpf_skb_change_protocol(skb, ETH_P_IPV6); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_6_to_4(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } } bpf_skb_change_protocol(skb, ETH_P_IP); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) { __be16 from_proto = skb->protocol; if (from_proto == htons(ETH_P_IP) && to_proto == htons(ETH_P_IPV6)) return bpf_skb_proto_4_to_6(skb); if (from_proto == htons(ETH_P_IPV6) && to_proto == htons(ETH_P_IP)) return bpf_skb_proto_6_to_4(skb); return -ENOTSUPP; } BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, u64, flags) { int ret; if (unlikely(flags)) return -EINVAL; /* General idea is that this helper does the basic groundwork * needed for changing the protocol, and eBPF program fills the * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace() * and other helpers, rather than passing a raw buffer here. * * The rationale is to keep this minimal and without a need to * deal with raw packet data. F.e. even if we would pass buffers * here, the program still needs to call the bpf_lX_csum_replace() * helpers anyway. Plus, this way we keep also separation of * concerns, since f.e. bpf_skb_store_bytes() should only take * care of stores. * * Currently, additional options and extension header space are * not supported, but flags register is reserved so we can adapt * that. For offloads, we mark packet as dodgy, so that headers * need to be verified first. */ ret = bpf_skb_proto_xlat(skb, proto); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_proto_proto = { .func = bpf_skb_change_proto, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type) { /* We only allow a restricted subset to be changed for now. */ if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || !skb_pkt_type_ok(pkt_type))) return -EINVAL; skb->pkt_type = pkt_type; return 0; } static const struct bpf_func_proto bpf_skb_change_type_proto = { .func = bpf_skb_change_type, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static u32 bpf_skb_net_base_len(const struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): return sizeof(struct iphdr); case htons(ETH_P_IPV6): return sizeof(struct ipv6hdr); default: return ~0U; } } #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) #define BPF_F_ADJ_ROOM_DECAP_L3_MASK (BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_DECAP_L3_IPV6) #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \ BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \ BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \ BPF_F_ADJ_ROOM_ENCAP_L2( \ BPF_ADJ_ROOM_ENCAP_L2_MASK) | \ BPF_F_ADJ_ROOM_DECAP_L3_MASK) static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT; bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK; u16 mac_len = 0, inner_net = 0, inner_trans = 0; unsigned int gso_type = SKB_GSO_DODGY; int ret; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_cow_head(skb, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -ENOTSUPP; if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE && flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH && inner_mac_len < ETH_HLEN) return -EINVAL; if (skb->encapsulation) return -EALREADY; mac_len = skb->network_header - skb->mac_header; inner_net = skb->network_header; if (inner_mac_len > len_diff) return -EINVAL; inner_trans = skb->transport_header; } ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { skb->inner_mac_header = inner_net - inner_mac_len; skb->inner_network_header = inner_net; skb->inner_transport_header = inner_trans; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH) skb_set_inner_protocol(skb, htons(ETH_P_TEB)); else skb_set_inner_protocol(skb, skb->protocol); skb->encapsulation = 1; skb_set_network_header(skb, mac_len); if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) gso_type |= SKB_GSO_UDP_TUNNEL; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE) gso_type |= SKB_GSO_GRE; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) gso_type |= SKB_GSO_IPXIP6; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) gso_type |= SKB_GSO_IPXIP4; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE || flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) { int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr); skb_set_transport_header(skb, mac_len + nh_len); } /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) bpf_skb_change_protocol(skb, ETH_P_IP); } if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; /* Due to header growth, MSS needs to be downgraded. * There is a BUG_ON() when segmenting the frag_list with * head_frag true, so linearize the skb after downgrading * the MSS. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { skb_decrease_gso_size(shinfo, len_diff); if (shinfo->frag_list) return skb_linearize(skb); } } return 0; } static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_DECAP_L3_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6) bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4) bpf_skb_change_protocol(skb, ETH_P_IP); if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Due to header shrink, MSS can be upgraded. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } return 0; } #define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_diff_abs = abs(len_diff); bool shrink = len_diff < 0; int ret = 0; if (unlikely(flags || mode)) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (!shrink) { ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; __skb_push(skb, len_diff_abs); memset(skb->data, 0, len_diff_abs); } else { if (unlikely(!pskb_may_pull(skb, len_diff_abs))) return -ENOMEM; __skb_pull(skb, len_diff_abs); } if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); rxm->full_len += len_diff; } return ret; } static const struct bpf_func_proto sk_skb_adjust_room_proto = { .func = sk_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (unlikely(proto != htons(ETH_P_IP) && proto != htons(ETH_P_IPV6))) return -ENOTSUPP; off = skb_mac_header_len(skb); switch (mode) { case BPF_ADJ_ROOM_NET: off += bpf_skb_net_base_len(skb); break; case BPF_ADJ_ROOM_MAC: break; default: return -ENOTSUPP; } if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { if (!shrink) return -EINVAL; switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { case BPF_F_ADJ_ROOM_DECAP_L3_IPV4: len_min = sizeof(struct iphdr); break; case BPF_F_ADJ_ROOM_DECAP_L3_IPV6: len_min = sizeof(struct ipv6hdr); break; default: return -EINVAL; } } len_cur = skb->len - skb_network_offset(skb); if ((shrink && (len_diff_abs >= len_cur || len_cur - len_diff_abs < len_min)) || (!shrink && (skb->len + len_diff_abs > len_max && !skb_is_gso(skb)))) return -ENOTSUPP; ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) : bpf_skb_net_grow(skb, off, len_diff_abs, flags); if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET)) __skb_reset_checksum_unnecessary(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_adjust_room_proto = { .func = bpf_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static u32 __bpf_skb_min_len(const struct sk_buff *skb) { int offset = skb_network_offset(skb); u32 min_len = 0; if (offset > 0) min_len = offset; if (skb_transport_header_was_set(skb)) { offset = skb_transport_offset(skb); if (offset > 0) min_len = offset; } if (skb->ip_summed == CHECKSUM_PARTIAL) { offset = skb_checksum_start_offset(skb) + skb->csum_offset + sizeof(__sum16); if (offset > 0) min_len = offset; } return min_len; } static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) { unsigned int old_len = skb->len; int ret; ret = __skb_grow_rcsum(skb, new_len); if (!ret) memset(skb->data + old_len, 0, new_len - old_len); return ret; } static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) { return __skb_trim_rcsum(skb, new_len); } static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; if (unlikely(flags || new_len > max_len || new_len < min_len)) return -EINVAL; if (skb->encapsulation) return -ENOTSUPP; /* The basic idea of this helper is that it's performing the * needed work to either grow or trim an skb, and eBPF program * rewrites the rest via helpers like bpf_skb_store_bytes(), * bpf_lX_csum_replace() and others rather than passing a raw * buffer here. This one is a slow path helper and intended * for replies with control messages. * * Like in bpf_skb_change_proto(), we want to keep this rather * minimal and without protocol specifics so that we are able * to separate concerns as in bpf_skb_store_bytes() should only * be the one responsible for writing buffers. * * It's really expected to be a slow path operation here for * control message replies, so we're implicitly linearizing, * uncloning and drop offloads from the skb by this. */ ret = __bpf_try_make_writable(skb, skb->len); if (!ret) { if (new_len > skb->len) ret = bpf_skb_grow_rcsum(skb, new_len); else if (new_len < skb->len) ret = bpf_skb_trim_rcsum(skb, new_len); if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } return ret; } BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_tail_proto = { .func = bpf_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { return __bpf_skb_change_tail(skb, new_len, flags); } static const struct bpf_func_proto sk_skb_change_tail_proto = { .func = sk_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) || new_len < skb->len)) return -EINVAL; ret = skb_cow(skb, head_room); if (likely(!ret)) { /* Idea for this helper is that we currently only * allow to expand on mac header. This means that * skb->protocol network header, etc, stay as is. * Compared to bpf_skb_change_tail(), we're more * flexible due to not needing to linearize or * reset GSO. Intention for this helper is to be * used by an L3 skb that needs to push mac header * for redirection into L2 device. */ __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); skb_reset_mac_len(skb); } return ret; } BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { int ret = __bpf_skb_change_head(skb, head_room, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { .func = bpf_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { return __bpf_skb_change_head(skb, head_room, flags); } static const struct bpf_func_proto sk_skb_change_head_proto = { .func = sk_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) { return xdp_get_buff_len(xdp); } static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], }; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; } BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); unsigned long metalen = xdp_get_metalen(xdp); void *data_start = xdp_frame_end + metalen; void *data = xdp->data + offset; if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; if (metalen) memmove(xdp->data_meta + offset, xdp->data_meta, metalen); xdp->data_meta += offset; xdp->data = data; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .func = bpf_xdp_adjust_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { unsigned long ptr_len, ptr_off = 0; skb_frag_t *next_frag, *end_frag; struct skb_shared_info *sinfo; void *src, *dst; u8 *ptr_buf; if (likely(xdp->data_end - xdp->data >= off + len)) { src = flush ? buf : xdp->data + off; dst = flush ? xdp->data + off : buf; memcpy(dst, src, len); return; } sinfo = xdp_get_shared_info_from_buff(xdp); end_frag = &sinfo->frags[sinfo->nr_frags]; next_frag = &sinfo->frags[0]; ptr_len = xdp->data_end - xdp->data; ptr_buf = xdp->data; while (true) { if (off < ptr_off + ptr_len) { unsigned long copy_off = off - ptr_off; unsigned long copy_len = min(len, ptr_len - copy_off); src = flush ? buf : ptr_buf + copy_off; dst = flush ? ptr_buf + copy_off : buf; memcpy(dst, src, copy_len); off += copy_len; len -= copy_len; buf += copy_len; } if (!len || next_frag == end_frag) break; ptr_off += ptr_len; ptr_buf = skb_frag_address(next_frag); ptr_len = skb_frag_size(next_frag); next_frag++; } } void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { u32 size = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; void *addr = xdp->data; int i; if (unlikely(offset > 0xffff || len > 0xffff)) return ERR_PTR(-EFAULT); if (unlikely(offset + len > xdp_get_buff_len(xdp))) return ERR_PTR(-EINVAL); if (likely(offset < size)) /* linear area */ goto out; sinfo = xdp_get_shared_info_from_buff(xdp); offset -= size; for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ u32 frag_size = skb_frag_size(&sinfo->frags[i]); if (offset < frag_size) { addr = skb_frag_address(&sinfo->frags[i]); size = frag_size; break; } offset -= frag_size; } out: return offset + len <= size ? addr + offset : NULL; } BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, false); else memcpy(buf, ptr, len); return 0; } static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { .func = bpf_xdp_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_load_bytes(xdp, offset, buf, len); } BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, true); else memcpy(ptr, buf, len); return 0; } static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { .func = bpf_xdp_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_store_bytes(xdp, offset, buf, len); } static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; unsigned int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); if (unlikely(offset > tailroom)) return -EINVAL; memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); skb_frag_size_add(frag, offset); sinfo->xdp_frags_size += offset; if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) xsk_buff_get_tail(xdp)->data_end += offset; return 0; } static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, enum xdp_mem_type mem_type, bool release) { struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp); if (release) { xsk_buff_del_tail(zc_frag); __xdp_return(0, mem_type, false, zc_frag); } else { zc_frag->data_end -= shrink; } } static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag, int shrink) { enum xdp_mem_type mem_type = xdp->rxq->mem.type; bool release = skb_frag_size(frag) == shrink; if (mem_type == MEM_TYPE_XSK_BUFF_POOL) { bpf_xdp_shrink_data_zc(xdp, shrink, mem_type, release); goto out; } if (release) __xdp_return(skb_frag_netmem(frag), mem_type, false, NULL); out: return release; } static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i, n_frags_free = 0, len_free = 0; if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) return -EINVAL; for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { skb_frag_t *frag = &sinfo->frags[i]; int shrink = min_t(int, offset, skb_frag_size(frag)); len_free += shrink; offset -= shrink; if (bpf_xdp_shrink_data(xdp, frag, shrink)) { n_frags_free++; } else { skb_frag_size_sub(frag, shrink); break; } } sinfo->nr_frags -= n_frags_free; sinfo->xdp_frags_size -= len_free; if (unlikely(!sinfo->nr_frags)) { xdp_buff_clear_frags_flag(xdp); xdp->data_end -= offset; } return 0; } BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */ if (offset < 0) return bpf_xdp_frags_shrink_tail(xdp, -offset); return bpf_xdp_frags_increase_tail(xdp, offset); } /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; /* Clear memory area on grow, can contain uninit kernel memory */ if (offset > 0) memset(xdp->data_end, 0, offset); xdp->data_end = data_end; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = { .func = bpf_xdp_adjust_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *meta = xdp->data_meta + offset; unsigned long metalen = xdp->data - meta; if (xdp_data_meta_unsupported(xdp)) return -ENOTSUPP; if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; if (unlikely(xdp_metalen_invalid(metalen))) return -EACCES; xdp->data_meta = meta; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .func = bpf_xdp_adjust_meta, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; /** * DOC: xdp redirect * * XDP_REDIRECT works by a three-step process, implemented in the functions * below: * * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target * of the redirect and store it (along with some other metadata) in a per-CPU * struct bpf_redirect_info. * * 2. When the program returns the XDP_REDIRECT return code, the driver will * call xdp_do_redirect() which will use the information in struct * bpf_redirect_info to actually enqueue the frame into a map type-specific * bulk queue structure. * * 3. Before exiting its NAPI poll loop, the driver will call * xdp_do_flush(), which will flush all the different bulk queues, * thus completing the redirect. Note that xdp_do_flush() must be * called before napi_complete_done() in the driver, as the * XDP_REDIRECT logic relies on being inside a single NAPI instance * through to the xdp_do_flush() call for RCU protection of all * in-kernel data structures. */ /* * Pointers to the map entries will be kept around for this whole sequence of * steps, protected by RCU. However, there is no top-level rcu_read_lock() in * the core code; instead, the RCU protection relies on everything happening * inside a single NAPI poll sequence, which means it's between a pair of calls * to local_bh_disable()/local_bh_enable(). * * The map entries are marked as __rcu and the map code makes sure to * dereference those pointers with rcu_dereference_check() in a way that works * for both sections that to hold an rcu_read_lock() and sections that are * called from NAPI without a separate rcu_read_lock(). The code below does not * use RCU annotations, but relies on those in the map code. */ void xdp_do_flush(void) { struct list_head *lh_map, *lh_dev, *lh_xsk; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) __dev_flush(lh_dev); if (lh_map) __cpu_map_flush(lh_map); if (lh_xsk) __xsk_map_flush(lh_xsk); } EXPORT_SYMBOL_GPL(xdp_do_flush); #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) void xdp_do_check_flushed(struct napi_struct *napi) { struct list_head *lh_map, *lh_dev, *lh_xsk; bool missed = false; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) { __dev_flush(lh_dev); missed = true; } if (lh_map) { __cpu_map_flush(lh_map); missed = true; } if (lh_xsk) { __xsk_map_flush(lh_xsk); missed = true; } WARN_ONCE(missed, "Missing xdp_do_flush() invocation after NAPI by %ps\n", napi->poll); } #endif DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net_device *master, *slave; master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); if (slave && slave != xdp->rxq->dev) { /* The target device is different from the receiving device, so * redirect it to the new device. * Using XDP_REDIRECT gets the correct behaviour from XDP enabled * drivers to unmap the packet from their rx ring. */ ri->tgt_index = slave->ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } return XDP_TX; } EXPORT_SYMBOL_GPL(xdp_master_redirect); static inline int __xdp_do_redirect_xsk(struct bpf_redirect_info *ri, const struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; err = __xsk_map_redirect(fwd, xdp); if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, struct net_device *dev, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { err = -EOVERFLOW; goto err; } switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdpf, dev); break; case BPF_MAP_TYPE_UNSPEC: if (map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; break; } err = dev_xdp_enqueue(fwd, xdpf, dev); break; } fallthrough; default: err = -EBADRQC; } if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdpf, xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog, void *fwd, enum bpf_map_type map_type, u32 map_id, u32 flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } if (unlikely(err)) goto err; break; case BPF_MAP_TYPE_XSKMAP: err = xsk_generic_rcv(fwd, xdp); if (err) goto err; consume_skb(skb); break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_generic_redirect(fwd, skb); if (unlikely(err)) goto err; break; default: err = -EBADRQC; goto err; } _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } err = xdp_ok_fwd_dev(fwd, skb->len); if (unlikely(err)) goto err; skb->dev = fwd; _trace_xdp_redirect(dev, xdp_prog, ri->tgt_index); generic_xdp_tx(skb, xdp_prog); return 0; } return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; } BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return XDP_ABORTED; /* NB! Map type UNSPEC and map_id == INT_MAX (never generated * by map_idr) is used for ifindex based XDP redirect. */ ri->tgt_index = ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } static const struct bpf_func_proto bpf_xdp_redirect_proto = { .func = bpf_xdp_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key, u64, flags) { return map->ops->map_redirect(map, key, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { .func = bpf_xdp_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, unsigned long off, unsigned long len) { void *ptr = skb_header_pointer(skb, off, len, dst_buff); if (unlikely(!ptr)) return len; if (ptr != dst_buff) memcpy(dst_buff, ptr, len); return 0; } BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!skb || skb_size > skb->len)) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, bpf_skb_copy); } static const struct bpf_func_proto bpf_skb_event_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff) const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; } BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to, u32, size, u64, flags) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); u8 compat[sizeof(struct bpf_tunnel_key)]; void *to_orig = to; int err; if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_TUNINFO_FLAGS)))) { err = -EINVAL; goto err_clear; } if (ip_tunnel_info_af(info) != bpf_tunnel_key_af(flags)) { err = -EPROTO; goto err_clear; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) { err = -EINVAL; switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) goto err_clear; set_compat: to = (struct bpf_tunnel_key *)compat; break; default: goto err_clear; } } to->tunnel_id = be64_to_cpu(info->key.tun_id); to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; if (flags & BPF_F_TUNINFO_FLAGS) to->tunnel_flags = ip_tunnel_flags_to_be16(info->key.tun_flags); else to->tunnel_ext = 0; if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); memcpy(to->local_ipv6, &info->key.u.ipv6.dst, sizeof(to->local_ipv6)); to->tunnel_label = be32_to_cpu(info->key.label); } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst); memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3); to->tunnel_label = 0; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy(to_orig, to, size); return 0; err_clear: memset(to_orig, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); int err; if (unlikely(!info || !ip_tunnel_is_options_present(info->key.tun_flags))) { err = -ENOENT; goto err_clear; } if (unlikely(size < info->options_len)) { err = -ENOMEM; goto err_clear; } ip_tunnel_info_opts_get(to, info); if (size > info->options_len) memset(to + info->options_len, 0, size - info->options_len); return info->options_len; err_clear: memset(to, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { .func = bpf_skb_get_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; static struct metadata_dst __percpu *md_dst; BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, const struct bpf_tunnel_key *, from, u32, size, u64, flags) { struct metadata_dst *md = this_cpu_ptr(md_dst); u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER | BPF_F_NO_TUNNEL_KEY))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ memcpy(compat, from, size); memset(compat + size, 0, sizeof(compat) - size); from = (const struct bpf_tunnel_key *) compat; break; default: return -EINVAL; } } if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || from->tunnel_ext)) return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); skb_dst_set(skb, (struct dst_entry *) md); info = &md->u.tun_info; memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; __set_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); __assign_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags, flags & BPF_F_DONT_FRAGMENT); __assign_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags, !(flags & BPF_F_ZERO_CSUM_TX)); __assign_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags, flags & BPF_F_SEQ_NUMBER); __assign_bit(IP_TUNNEL_KEY_BIT, info->key.tun_flags, !(flags & BPF_F_NO_TUNNEL_KEY)); info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; if (flags & BPF_F_TUNINFO_IPV6) { info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); memcpy(&info->key.u.ipv6.src, from->local_ipv6, sizeof(from->local_ipv6)); info->key.label = cpu_to_be32(from->tunnel_label) & IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4); info->key.flow_flags = FLOWI_FLAG_ANYSRC; } return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, const u8 *, from, u32, size) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); IP_TUNNEL_DECLARE_FLAGS(present) = { }; if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; ip_tunnel_set_options_present(present); ip_tunnel_info_opts_set(info, from, size, present); return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { .func = bpf_skb_set_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { struct metadata_dst __percpu *tmp; tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, METADATA_IP_TUNNEL, GFP_KERNEL); if (!tmp) return NULL; if (cmpxchg(&md_dst, NULL, tmp)) metadata_dst_free_percpu(tmp); } switch (which) { case BPF_FUNC_skb_set_tunnel_key: return &bpf_skb_set_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_opt: return &bpf_skb_set_tunnel_opt_proto; default: return NULL; } } BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; struct sock *sk; sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return -ENOENT; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return sk_under_cgroup_hierarchy(sk, cgrp); } static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SOCK_CGROUP_DATA static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { .func = bpf_skb_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, int ancestor_level) { struct cgroup *ancestor; struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) return 0; return cgroup_id(ancestor); } BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { .func = bpf_skb_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk) { return __bpf_sk_cgroup_id(sk); } static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); } static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { struct xdp_buff *xdp = (struct xdp_buff *)ctx; bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp))) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } static const struct bpf_func_proto bpf_xdp_event_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { .func = bpf_get_socket_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { .func = bpf_get_socket_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { .func = bpf_get_socket_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_ptr_cookie, struct sock *, sk) { return sk ? sock_gen_cookie(sk) : 0; } const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = { .func = bpf_get_socket_ptr_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | PTR_MAYBE_NULL, }; BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { .func = bpf_get_socket_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static u64 __bpf_get_netns_cookie(struct sock *sk) { const struct net *net = sk ? sock_net(sk) : &init_net; return net->net_cookie; } BPF_CALL_1(bpf_get_netns_cookie, struct sk_buff *, skb) { return __bpf_get_netns_cookie(skb && skb->sk ? skb->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_proto = { .func = bpf_get_netns_cookie, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) { return __bpf_get_netns_cookie(ctx); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = { .func = bpf_get_netns_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = { .func = bpf_get_netns_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_ops_proto = { .func = bpf_get_netns_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sk_msg, struct sk_msg *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sk_msg_proto = { .func = bpf_get_netns_cookie_sk_msg, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); kuid_t kuid; if (!sk || !sk_fullsock(sk)) return overflowuid; kuid = sock_net_uid(sock_net(sk), sk); return from_kuid_munged(sock_net(sk)->user_ns, kuid); } static const struct bpf_func_proto bpf_get_socket_uid_proto = { .func = bpf_get_socket_uid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt) { u32 sk_bpf_cb_flags; if (getopt) { *(u32 *)optval = sk->sk_bpf_cb_flags; return 0; } sk_bpf_cb_flags = *(u32 *)optval; if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK) return -EINVAL; sk->sk_bpf_cb_flags = sk_bpf_cb_flags; return 0; } static int sol_socket_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { switch (optname) { case SO_REUSEADDR: case SO_SNDBUF: case SO_RCVBUF: case SO_KEEPALIVE: case SO_PRIORITY: case SO_REUSEPORT: case SO_RCVLOWAT: case SO_MARK: case SO_MAX_PACING_RATE: case SO_BINDTOIFINDEX: case SO_TXREHASH: case SK_BPF_CB_FLAGS: if (*optlen != sizeof(int)) return -EINVAL; break; case SO_BINDTODEVICE: break; default: return -EINVAL; } if (optname == SK_BPF_CB_FLAGS) return sk_bpf_set_get_cb_flags(sk, optval, getopt); if (getopt) { if (optname == SO_BINDTODEVICE) return -EINVAL; return sk_getsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return sk_setsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), *optlen); } static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname, char *optval, int optlen) { if (optlen != sizeof(int)) return -EINVAL; switch (optname) { case TCP_BPF_SOCK_OPS_CB_FLAGS: { int cb_flags = tcp_sk(sk)->bpf_sock_ops_cb_flags; memcpy(optval, &cb_flags, optlen); break; } case TCP_BPF_RTO_MIN: { int rto_min_us = jiffies_to_usecs(inet_csk(sk)->icsk_rto_min); memcpy(optval, &rto_min_us, optlen); break; } case TCP_BPF_DELACK_MAX: { int delack_max_us = jiffies_to_usecs(inet_csk(sk)->icsk_delack_max); memcpy(optval, &delack_max_us, optlen); break; } default: return -EINVAL; } return 0; } static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, char *optval, int optlen) { struct tcp_sock *tp = tcp_sk(sk); unsigned long timeout; int val; if (optlen != sizeof(int)) return -EINVAL; val = *(int *)optval; /* Only some options are supported */ switch (optname) { case TCP_BPF_IW: if (val <= 0 || tp->data_segs_out > tp->syn_data) return -EINVAL; tcp_snd_cwnd_set(tp, val); break; case TCP_BPF_SNDCWND_CLAMP: if (val <= 0) return -EINVAL; tp->snd_cwnd_clamp = val; tp->snd_ssthresh = val; break; case TCP_BPF_DELACK_MAX: timeout = usecs_to_jiffies(val); if (timeout > TCP_DELACK_MAX || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_delack_max = timeout; break; case TCP_BPF_RTO_MIN: timeout = usecs_to_jiffies(val); if (timeout > TCP_RTO_MIN || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_rto_min = timeout; break; case TCP_BPF_SOCK_OPS_CB_FLAGS: if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS)) return -EINVAL; tp->bpf_sock_ops_cb_flags = val; break; default: return -EINVAL; } return 0; } static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval, int *optlen, bool getopt) { struct tcp_sock *tp; int ret; if (*optlen < 2) return -EINVAL; if (getopt) { if (!inet_csk(sk)->icsk_ca_ops) return -EINVAL; /* BPF expects NULL-terminated tcp-cc string */ optval[--(*optlen)] = '\0'; return do_tcp_getsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } /* "cdg" is the only cc that alloc a ptr * in inet_csk_ca area. The bpf-tcp-cc may * overwrite this ptr after switching to cdg. */ if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen)) return -ENOTSUPP; /* It stops this looping * * .init => bpf_setsockopt(tcp_cc) => .init => * bpf_setsockopt(tcp_cc)" => .init => .... * * The second bpf_setsockopt(tcp_cc) is not allowed * in order to break the loop when both .init * are the same bpf prog. * * This applies even the second bpf_setsockopt(tcp_cc) * does not cause a loop. This limits only the first * '.init' can call bpf_setsockopt(TCP_CONGESTION) to * pick a fallback cc (eg. peer does not support ECN) * and the second '.init' cannot fallback to * another. */ tp = tcp_sk(sk); if (tp->bpf_chg_cc_inprogress) return -EBUSY; tp->bpf_chg_cc_inprogress = 1; ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), *optlen); tp->bpf_chg_cc_inprogress = 0; return ret; } static int sol_tcp_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_protocol != IPPROTO_TCP) return -EINVAL; switch (optname) { case TCP_NODELAY: case TCP_MAXSEG: case TCP_KEEPIDLE: case TCP_KEEPINTVL: case TCP_KEEPCNT: case TCP_SYNCNT: case TCP_WINDOW_CLAMP: case TCP_THIN_LINEAR_TIMEOUTS: case TCP_USER_TIMEOUT: case TCP_NOTSENT_LOWAT: case TCP_SAVE_SYN: case TCP_RTO_MAX_MS: if (*optlen != sizeof(int)) return -EINVAL; break; case TCP_CONGESTION: return sol_tcp_sockopt_congestion(sk, optval, optlen, getopt); case TCP_SAVED_SYN: if (*optlen < 1) return -EINVAL; break; default: if (getopt) return bpf_sol_tcp_getsockopt(sk, optname, optval, *optlen); return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); } if (getopt) { if (optname == TCP_SAVED_SYN) { struct tcp_sock *tp = tcp_sk(sk); if (!tp->saved_syn || *optlen > tcp_saved_syn_len(tp->saved_syn)) return -EINVAL; memcpy(optval, tp->saved_syn->data, *optlen); /* It cannot free tp->saved_syn here because it * does not know if the user space still needs it. */ return 0; } return do_tcp_getsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return do_tcp_setsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ip_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET) return -EINVAL; switch (optname) { case IP_TOS: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return do_ip_getsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return do_ip_setsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ipv6_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET6) return -EINVAL; switch (optname) { case IPV6_TCLASS: case IPV6_AUTOFLOWLABEL: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return ipv6_bpf_stub->ipv6_getsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return ipv6_bpf_stub->ipv6_setsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), *optlen); } static int __bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (!sk_fullsock(sk)) return -EINVAL; if (level == SOL_SOCKET) return sol_socket_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) return sol_ip_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) return sol_ipv6_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) return sol_tcp_sockopt(sk, optname, optval, &optlen, false); return -EINVAL; } static bool is_locked_tcp_sock_ops(struct bpf_sock_ops_kern *bpf_sock) { return bpf_sock->op <= BPF_SOCK_OPS_WRITE_HDR_OPT_CB; } static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_setsockopt(sk, level, optname, optval, optlen); } static int __bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { int err, saved_optlen = optlen; if (!sk_fullsock(sk)) { err = -EINVAL; goto done; } if (level == SOL_SOCKET) err = sol_socket_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) err = sol_tcp_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) err = sol_ip_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) err = sol_ipv6_sockopt(sk, optname, optval, &optlen, true); else err = -EINVAL; done: if (err) optlen = 0; if (optlen < saved_optlen) memset(optval + optlen, 0, saved_optlen - optlen); return err; } static int _bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_getsockopt(sk, level, optname, optval, optlen); } BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_setsockopt_proto = { .func = bpf_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_getsockopt_proto = { .func = bpf_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto = { .func = bpf_unlocked_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto = { .func = bpf_unlocked_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { .func = bpf_sock_addr_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { .func = bpf_sock_addr_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .func = bpf_sock_ops_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, int optname, const u8 **start) { struct sk_buff *syn_skb = bpf_sock->syn_skb; const u8 *hdr_start; int ret; if (syn_skb) { /* sk is a request_sock here */ if (optname == TCP_BPF_SYN) { hdr_start = syn_skb->data; ret = tcp_hdrlen(syn_skb); } else if (optname == TCP_BPF_SYN_IP) { hdr_start = skb_network_header(syn_skb); ret = skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } else { /* optname == TCP_BPF_SYN_MAC */ hdr_start = skb_mac_header(syn_skb); ret = skb_mac_header_len(syn_skb) + skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } } else { struct sock *sk = bpf_sock->sk; struct saved_syn *saved_syn; if (sk->sk_state == TCP_NEW_SYN_RECV) /* synack retransmit. bpf_sock->syn_skb will * not be available. It has to resort to * saved_syn (if it is saved). */ saved_syn = inet_reqsk(sk)->saved_syn; else saved_syn = tcp_sk(sk)->saved_syn; if (!saved_syn) return -ENOENT; if (optname == TCP_BPF_SYN) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen + saved_syn->network_hdrlen; ret = saved_syn->tcp_hdrlen; } else if (optname == TCP_BPF_SYN_IP) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen; ret = saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } else { /* optname == TCP_BPF_SYN_MAC */ /* TCP_SAVE_SYN may not have saved the mac hdr */ if (!saved_syn->mac_hdrlen) return -ENOENT; hdr_start = saved_syn->data; ret = saved_syn->mac_hdrlen + saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } } *start = hdr_start; return ret; } BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { int ret, copy_len = 0; const u8 *start; ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); if (ret > 0) { copy_len = ret; if (optlen < copy_len) { copy_len = optlen; ret = -ENOSPC; } memcpy(optval, start, copy_len); } /* Zero out unused buffer at the end */ memset(optval + copy_len, 0, optlen - copy_len); return ret; } return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = { .func = bpf_sock_ops_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock, int, argval) { struct sock *sk = bpf_sock->sk; int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk)) return -EINVAL; tcp_sk(sk)->bpf_sock_ops_cb_flags = val; return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS); } static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = { .func = bpf_sock_ops_cb_flags_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; EXPORT_SYMBOL_GPL(ipv6_bpf_stub); BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, int, addr_len) { #ifdef CONFIG_INET struct sock *sk = ctx->sk; u32 flags = BIND_FROM_BPF; int err; err = -EINVAL; if (addr_len < offsetofend(struct sockaddr, sa_family)) return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; if (((struct sockaddr_in *)addr)->sin_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; return __inet_bind(sk, addr, addr_len, flags); #if IS_ENABLED(CONFIG_IPV6) } else if (addr->sa_family == AF_INET6) { if (addr_len < SIN6_LEN_RFC2133) return err; if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; /* ipv6_bpf_stub cannot be NULL, since it's called from * bpf_cgroup_inet6_connect hook and ipv6 is already loaded */ return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags); #endif /* CONFIG_IPV6 */ } #endif /* CONFIG_INET */ return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_bind_proto = { .func = bpf_bind, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; #ifdef CONFIG_XFRM #if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) struct metadata_dst __percpu *xfrm_bpf_md_dst; EXPORT_SYMBOL_GPL(xfrm_bpf_md_dst); #endif BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, struct bpf_xfrm_state *, to, u32, size, u64, flags) { const struct sec_path *sp = skb_sec_path(skb); const struct xfrm_state *x; if (!sp || unlikely(index >= sp->len || flags)) goto err_clear; x = sp->xvec[index]; if (unlikely(size != sizeof(struct bpf_xfrm_state))) goto err_clear; to->reqid = x->props.reqid; to->spi = x->id.spi; to->family = x->props.family; to->ext = 0; if (to->family == AF_INET6) { memcpy(to->remote_ipv6, x->props.saddr.a6, sizeof(to->remote_ipv6)); } else { to->remote_ipv4 = x->props.saddr.a4; memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); } return 0; err_clear: memset(to, 0, size); return -EINVAL; } static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { .func = bpf_skb_get_xfrm_state, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) { params->h_vlan_TCI = 0; params->h_vlan_proto = 0; if (mtu) params->mtu_result = mtu; /* union with tot_len */ return 0; } #endif #if IS_ENABLED(CONFIG_INET) static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct fib_nh_common *nhc; struct in_device *in_dev; struct neighbour *neigh; struct net_device *dev; struct fib_result res; struct flowi4 fl4; u32 mtu = 0; int err; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; fl4.flowi4_oif = params->ifindex; } else { fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } fl4.flowi4_tos = params->tos & INET_DSCP_MASK; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.flowi4_proto = params->l4_protocol; fl4.daddr = params->ipv4_dst; fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl4.flowi4_mark = params->mark; else fl4.flowi4_mark = 0; fl4.flowi4_secid = 0; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } if (err) { /* map fib lookup errors to RTN_ type */ if (err == -EINVAL) return BPF_FIB_LKUP_RET_BLACKHOLE; if (err == -EHOSTUNREACH) return BPF_FIB_LKUP_RET_UNREACHABLE; if (err == -EACCES) return BPF_FIB_LKUP_RET_PROHIBIT; return BPF_FIB_LKUP_RET_NOT_FWDED; } if (res.type != RTN_UNICAST) return BPF_FIB_LKUP_RET_NOT_FWDED; if (fib_info_num_path(res.fi) > 1) fib_select_path(net, &res, &fl4, NULL); if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } nhc = res.nhc; /* do not handle lwt encaps right now */ if (nhc->nhc_lwtstate) return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) params->ipv4_src = fib_result_prefsrc(net, &res); /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ if (likely(nhc->nhc_gw_family != AF_INET6)) { if (nhc->nhc_gw_family) params->ipv4_dst = nhc->nhc_gw.ipv4; } else { struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst; params->family = AF_INET6; *dst = nhc->nhc_gw.ipv6; } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; if (likely(nhc->nhc_gw_family != AF_INET6)) neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); else neigh = __ipv6_neigh_lookup_noref_stub(dev, params->ipv6_dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #if IS_ENABLED(CONFIG_IPV6) static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct in6_addr *src = (struct in6_addr *) params->ipv6_src; struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst; struct fib6_result res = {}; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; struct flowi6 fl6; int strict = 0; int oif, err; u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !READ_ONCE(idev->cnf.forwarding))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; oif = fl6.flowi6_oif = params->ifindex; } else { oif = fl6.flowi6_iif = params->ifindex; fl6.flowi6_oif = 0; strict = RT6_LOOKUP_F_HAS_SADDR; } fl6.flowlabel = params->flowinfo; fl6.flowi6_scope = 0; fl6.flowi6_flags = 0; fl6.mp_hash = 0; fl6.flowi6_proto = params->l4_protocol; fl6.daddr = *dst; fl6.saddr = *src; fl6.fl6_sport = params->sport; fl6.fl6_dport = params->dport; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res, strict); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl6.flowi6_mark = params->mark; else fl6.flowi6_mark = 0; fl6.flowi6_secid = 0; fl6.flowi6_tun_key.tun_id = 0; fl6.flowi6_uid = sock_net_uid(net, NULL); err = ipv6_stub->fib6_lookup(net, oif, &fl6, &res, strict); } if (unlikely(err || IS_ERR_OR_NULL(res.f6i) || res.f6i == net->ipv6.fib6_null_entry)) return BPF_FIB_LKUP_RET_NOT_FWDED; switch (res.fib6_type) { /* only unicast is forwarded */ case RTN_UNICAST: break; case RTN_BLACKHOLE: return BPF_FIB_LKUP_RET_BLACKHOLE; case RTN_UNREACHABLE: return BPF_FIB_LKUP_RET_UNREACHABLE; case RTN_PROHIBIT: return BPF_FIB_LKUP_RET_PROHIBIT; default: return BPF_FIB_LKUP_RET_NOT_FWDED; } ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif, fl6.flowi6_oif != 0, NULL, strict); if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } if (res.nh->fib_nh_lws) return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (res.nh->fib_nh_gw_family) *dst = res.nh->fib_nh_gw6; dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) { if (res.f6i->fib6_prefsrc.plen) { *src = res.f6i->fib6_prefsrc.addr; } else { err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, &fl6.daddr, 0, src); if (err) return BPF_FIB_LKUP_RET_NO_SRC_ADDR; } } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) { if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif } return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = { .func = bpf_xdp_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); int rc = -EAFNOSUPPORT; bool check_mtu = false; if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; if (params->tot_len) check_mtu = true; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu); break; #endif } if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) { struct net_device *dev; /* When tot_len isn't provided by user, check skb * against MTU of FIB lookup resulting net_device */ dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .func = bpf_skb_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; static struct net_device *__dev_via_ifindex(struct net_device *dev_curr, u32 ifindex) { struct net *netns = dev_net(dev_curr); /* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */ if (ifindex == 0) return dev_curr; return dev_get_by_index_rcu(netns, ifindex); } BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; int mtu, dev_len, skb_len; if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) return -EINVAL; if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len; skb_len += len_diff; /* minus result pass check */ if (skb_len <= dev_len) { ret = BPF_MTU_CHK_RET_SUCCESS; goto out; } /* At this point, skb->len exceed MTU, but as it include length of all * segments, it can still be below MTU. The SKB can possibly get * re-segmented in transmit path (see validate_xmit_skb). Thus, user * must choose if segs are to be MTU checked. */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; if (flags & BPF_MTU_CHK_SEGS && !skb_gso_validate_network_len(skb, mtu)) ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; } out: *mtu_len = mtu; return ret; } BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; int mtu, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ if (unlikely(flags)) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ if (*mtu_len) xdp_len = *mtu_len + dev->hard_header_len; xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; *mtu_len = mtu; return ret; } static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .func = bpf_skb_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .func = bpf_xdp_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) { int err; struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)hdr; if (!seg6_validate_srh(srh, len, false)) return -EINVAL; switch (type) { case BPF_LWT_ENCAP_SEG6_INLINE: if (skb->protocol != htons(ETH_P_IPV6)) return -EBADMSG; err = seg6_do_srh_inline(skb, srh); break; case BPF_LWT_ENCAP_SEG6: skb_reset_inner_headers(skb); skb->encapsulation = 1; err = seg6_do_srh_encap(skb, srh, IPPROTO_IPV6); break; default: return -EINVAL; } bpf_compute_data_pointers(skb); if (err) return err; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); } #endif /* CONFIG_IPV6_SEG6_BPF */ #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress) { return bpf_lwt_push_ip_encap(skb, hdr, len, ingress); } #endif BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_LWT_ENCAP_SEG6: case BPF_LWT_ENCAP_SEG6_INLINE: return bpf_push_seg6_encap(skb, type, hdr, len); #endif #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, true /* ingress */); #endif default: return -EINVAL; } } BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, false /* egress */); #endif default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = { .func = bpf_lwt_in_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = { .func = bpf_lwt_xmit_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_tlvs, *srh_end, *ptr; int srhoff = 0; lockdep_assert_held(&srh_state->bh_lock); if (srh == NULL) return -EINVAL; srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4)); srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (ptr >= srh_tlvs && ptr + len <= srh_end) srh_state->valid = false; else if (ptr < (void *)&srh->flags || ptr + len > (void *)&srh->segments) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); memcpy(skb->data + offset, from, len); return 0; } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { .func = bpf_lwt_seg6_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static void bpf_update_srh_state(struct sk_buff *skb) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) { srh_state->srh = NULL; } else { srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen = srh_state->srh->hdrlen << 3; srh_state->valid = true; } } BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int hdroff = 0; int err; lockdep_assert_held(&srh_state->bh_lock); switch (action) { case SEG6_LOCAL_ACTION_END_X: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(struct in6_addr)) return -EINVAL; return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0); case SEG6_LOCAL_ACTION_END_T: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_DT6: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0) return -EBADMSG; if (!pskb_pull(skb, hdroff)) return -EBADMSG; skb_postpull_rcsum(skb, skb_network_header(skb), hdroff); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; bpf_compute_data_pointers(skb); bpf_update_srh_state(skb); return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_B6: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE, param, param_len); if (!err) bpf_update_srh_state(skb); return err; case SEG6_LOCAL_ACTION_END_B6_ENCAP: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6, param, param_len); if (!err) bpf_update_srh_state(skb); return err; default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { .func = bpf_lwt_seg6_action, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_end, *srh_tlvs, *ptr; struct ipv6hdr *hdr; int srhoff = 0; int ret; lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return -EINVAL; srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) + ((srh->first_segment + 1) << 4)); srh_end = (void *)((unsigned char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (unlikely(ptr < srh_tlvs || ptr > srh_end)) return -EFAULT; if (unlikely(len < 0 && (void *)((char *)ptr - len) > srh_end)) return -EFAULT; if (len > 0) { ret = skb_cow_head(skb, len); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, offset, len); } else { ret = bpf_skb_net_hdr_pop(skb, offset, -1 * len); } bpf_compute_data_pointers(skb); if (unlikely(ret < 0)) return ret; hdr = (struct ipv6hdr *)skb->data; hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen += len; srh_state->valid = false; return 0; } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .func = bpf_lwt_seg6_adjust_srh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_IPV6_SEG6_BPF */ #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) { struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; bool refcounted = false; struct sock *sk = NULL; if (family == AF_INET) { __be32 src4 = tuple->ipv4.saddr; __be32 dst4 = tuple->ipv4.daddr; if (proto == IPPROTO_TCP) sk = __inet_lookup(net, hinfo, NULL, 0, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &refcounted); else sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, net->ipv4.udp_table, NULL); #if IS_ENABLED(CONFIG_IPV6) } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; if (proto == IPPROTO_TCP) sk = __inet6_lookup(net, hinfo, NULL, 0, src6, tuple->ipv6.sport, dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_bpf_stub)) sk = ipv6_bpf_stub->udp6_lib_lookup(net, src6, tuple->ipv6.sport, dst6, tuple->ipv6.dport, dif, sdif, net->ipv4.udp_table, NULL); #endif } if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); sk = NULL; } return sk; } /* bpf_skc_lookup performs the core lookup for different types of sockets, * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. */ static struct sock * __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = NULL; struct net *net; u8 family; if (len == sizeof(tuple->ipv4)) family = AF_INET; else if (len == sizeof(tuple->ipv6)) family = AF_INET6; else return NULL; if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (sdif < 0) { if (family == AF_INET) sdif = inet_sdif(skb); else sdif = inet6_sdif(skb); } if ((s32)netns_id < 0) { net = caller_net; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); } else { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); put_net(net); } out: return sk; } static struct sock * __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, sdif); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } static struct sock * bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct net *caller_net; int ifindex; if (skb->dev) { caller_net = dev_net(skb->dev); ifindex = skb->dev->ifindex; } else { caller_net = sock_net(skb->sk); ifindex = 0; } return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, -1); } static struct sock * bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id, flags); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = { .func = bpf_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { .func = bpf_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { .func = bpf_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = { .func = bpf_tc_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = { .func = bpf_tc_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = { .func = bpf_tc_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_release, struct sock *, sk) { if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | OBJ_RELEASE, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { .func = bpf_xdp_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = { .func = bpf_xdp_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { .func = bpf_xdp_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = { .func = bpf_sock_addr_skc_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { .func = bpf_sock_addr_sk_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_UDP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .func = bpf_sock_addr_sk_lookup_udp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, icsk_retransmits)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_tcp_sock, bytes_received): case offsetof(struct bpf_tcp_sock, bytes_acked): return size == sizeof(__u64); default: return size == sizeof(__u32); } } u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ } while (0) #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ si->dst_reg, si->src_reg, \ offsetof( \ struct inet_connection_sock, \ FIELD)); \ } while (0) BTF_TYPE_EMIT(struct bpf_tcp_sock); switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct tcp_sock, rtt_min) + offsetof(struct minmax_sample, v)); break; case offsetof(struct bpf_tcp_sock, snd_cwnd): BPF_TCP_SOCK_GET_COMMON(snd_cwnd); break; case offsetof(struct bpf_tcp_sock, srtt_us): BPF_TCP_SOCK_GET_COMMON(srtt_us); break; case offsetof(struct bpf_tcp_sock, snd_ssthresh): BPF_TCP_SOCK_GET_COMMON(snd_ssthresh); break; case offsetof(struct bpf_tcp_sock, rcv_nxt): BPF_TCP_SOCK_GET_COMMON(rcv_nxt); break; case offsetof(struct bpf_tcp_sock, snd_nxt): BPF_TCP_SOCK_GET_COMMON(snd_nxt); break; case offsetof(struct bpf_tcp_sock, snd_una): BPF_TCP_SOCK_GET_COMMON(snd_una); break; case offsetof(struct bpf_tcp_sock, mss_cache): BPF_TCP_SOCK_GET_COMMON(mss_cache); break; case offsetof(struct bpf_tcp_sock, ecn_flags): BPF_TCP_SOCK_GET_COMMON(ecn_flags); break; case offsetof(struct bpf_tcp_sock, rate_delivered): BPF_TCP_SOCK_GET_COMMON(rate_delivered); break; case offsetof(struct bpf_tcp_sock, rate_interval_us): BPF_TCP_SOCK_GET_COMMON(rate_interval_us); break; case offsetof(struct bpf_tcp_sock, packets_out): BPF_TCP_SOCK_GET_COMMON(packets_out); break; case offsetof(struct bpf_tcp_sock, retrans_out): BPF_TCP_SOCK_GET_COMMON(retrans_out); break; case offsetof(struct bpf_tcp_sock, total_retrans): BPF_TCP_SOCK_GET_COMMON(total_retrans); break; case offsetof(struct bpf_tcp_sock, segs_in): BPF_TCP_SOCK_GET_COMMON(segs_in); break; case offsetof(struct bpf_tcp_sock, data_segs_in): BPF_TCP_SOCK_GET_COMMON(data_segs_in); break; case offsetof(struct bpf_tcp_sock, segs_out): BPF_TCP_SOCK_GET_COMMON(segs_out); break; case offsetof(struct bpf_tcp_sock, data_segs_out): BPF_TCP_SOCK_GET_COMMON(data_segs_out); break; case offsetof(struct bpf_tcp_sock, lost_out): BPF_TCP_SOCK_GET_COMMON(lost_out); break; case offsetof(struct bpf_tcp_sock, sacked_out): BPF_TCP_SOCK_GET_COMMON(sacked_out); break; case offsetof(struct bpf_tcp_sock, bytes_received): BPF_TCP_SOCK_GET_COMMON(bytes_received); break; case offsetof(struct bpf_tcp_sock, bytes_acked): BPF_TCP_SOCK_GET_COMMON(bytes_acked); break; case offsetof(struct bpf_tcp_sock, dsack_dups): BPF_TCP_SOCK_GET_COMMON(dsack_dups); break; case offsetof(struct bpf_tcp_sock, delivered): BPF_TCP_SOCK_GET_COMMON(delivered); break; case offsetof(struct bpf_tcp_sock, delivered_ce): BPF_TCP_SOCK_GET_COMMON(delivered_ce); break; case offsetof(struct bpf_tcp_sock, icsk_retransmits): BPF_INET_SOCK_GET_COMMON(icsk_retransmits); break; } return insn - insn_buf; } BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) { if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_tcp_sock_proto = { .func = bpf_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk) { sk = sk_to_full_sk(sk); if (sk && sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE)) return (unsigned long)sk; return (unsigned long)NULL; } static const struct bpf_func_proto bpf_get_listener_sock_proto = { .func = bpf_get_listener_sock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); break; case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); break; default: return 0; } if (skb_headlen(skb) < iphdr_len) return 0; if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len)) return 0; return INET_ECN_set_ce(skb); } bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id)) return false; if (off % size != 0) return false; switch (off) { default: return size == sizeof(__u32); } } u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_XDP_SOCK_GET(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ } while (0) switch (si->off) { case offsetof(struct bpf_xdp_sock, queue_id): BPF_XDP_SOCK_GET(queue_id); break; } return insn - insn_buf; } static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { .func = bpf_skb_ecn_set_ce, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES int ret; if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) return -ENOENT; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; ret = __cookie_v6_check((struct ipv6hdr *)iph, th); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (ret > 0) return 0; return -ENOENT; #else return -ENOTSUPP; #endif } static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .func = bpf_tcp_check_syncookie, .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES u32 cookie; u16 mss; if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) return -EINVAL; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; mss = tcp_v6_get_syncookie(sk, iph, th, &cookie); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (mss == 0) return -ENOENT; return cookie | ((u64)mss << 32); #else return -EOPNOTSUPP; #endif /* CONFIG_SYN_COOKIES */ } static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .func = bpf_tcp_gen_syncookie, .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) return -ENOENT; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_pfree; return 0; } static const struct bpf_func_proto bpf_sk_assign_proto = { .func = bpf_sk_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_ANYTHING, }; static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, u8 search_kind, const u8 *magic, u8 magic_len, bool *eol) { u8 kind, kind_len; *eol = false; while (op < opend) { kind = op[0]; if (kind == TCPOPT_EOL) { *eol = true; return ERR_PTR(-ENOMSG); } else if (kind == TCPOPT_NOP) { op++; continue; } if (opend - op < 2 || opend - op < op[1] || op[1] < 2) /* Something is wrong in the received header. * Follow the TCP stack's tcp_parse_options() * and just bail here. */ return ERR_PTR(-EFAULT); kind_len = op[1]; if (search_kind == kind) { if (!magic_len) return op; if (magic_len > kind_len - 2) return ERR_PTR(-ENOMSG); if (!memcmp(&op[2], magic, magic_len)) return op; } op += kind_len; } return ERR_PTR(-ENOMSG); } BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, void *, search_res, u32, len, u64, flags) { bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; const u8 *op, *opend, *magic, *search = search_res; u8 search_kind, search_len, copy_len, magic_len; int ret; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; /* 2 byte is the minimal option len except TCPOPT_NOP and * TCPOPT_EOL which are useless for the bpf prog to learn * and this helper disallow loading them also. */ if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) return -EINVAL; search_kind = search[0]; search_len = search[1]; if (search_len > len || search_kind == TCPOPT_NOP || search_kind == TCPOPT_EOL) return -EINVAL; if (search_kind == TCPOPT_EXP || search_kind == 253) { /* 16 or 32 bit magic. +2 for kind and kind length */ if (search_len != 4 && search_len != 6) return -EINVAL; magic = &search[2]; magic_len = search_len - 2; } else { if (search_len) return -EINVAL; magic = NULL; magic_len = 0; } if (load_syn) { ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); if (ret < 0) return ret; opend = op + ret; op += sizeof(struct tcphdr); } else { if (!bpf_sock->skb || bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) /* This bpf_sock->op cannot call this helper */ return -EPERM; opend = bpf_sock->skb_data_end; op = bpf_sock->skb->data + sizeof(struct tcphdr); } op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, &eol); if (IS_ERR(op)) return PTR_ERR(op); copy_len = op[1]; ret = copy_len; if (copy_len > len) { ret = -ENOSPC; copy_len = len; } memcpy(search_res, op, copy_len); return ret; } static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { .func = bpf_sock_ops_load_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, const void *, from, u32, len, u64, flags) { u8 new_kind, new_kind_len, magic_len = 0, *opend; const u8 *op, *new_op, *magic = NULL; struct sk_buff *skb; bool eol; if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) return -EPERM; if (len < 2 || flags) return -EINVAL; new_op = from; new_kind = new_op[0]; new_kind_len = new_op[1]; if (new_kind_len > len || new_kind == TCPOPT_NOP || new_kind == TCPOPT_EOL) return -EINVAL; if (new_kind_len > bpf_sock->remaining_opt_len) return -ENOSPC; /* 253 is another experimental kind */ if (new_kind == TCPOPT_EXP || new_kind == 253) { if (new_kind_len < 4) return -EINVAL; /* Match for the 2 byte magic also. * RFC 6994: the magic could be 2 or 4 bytes. * Hence, matching by 2 byte only is on the * conservative side but it is the right * thing to do for the 'search-for-duplication' * purpose. */ magic = &new_op[2]; magic_len = 2; } /* Check for duplication */ skb = bpf_sock->skb; op = skb->data + sizeof(struct tcphdr); opend = bpf_sock->skb_data_end; op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, &eol); if (!IS_ERR(op)) return -EEXIST; if (PTR_ERR(op) != -ENOMSG) return PTR_ERR(op); if (eol) /* The option has been ended. Treat it as no more * header option can be written. */ return -ENOSPC; /* No duplication found. Store the header option. */ memcpy(opend, from, new_kind_len); bpf_sock->remaining_opt_len -= new_kind_len; bpf_sock->skb_data_end += new_kind_len; return 0; } static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { .func = bpf_sock_ops_store_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, u32, len, u64, flags) { if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) return -EPERM; if (flags || len < 2) return -EINVAL; if (len > bpf_sock->remaining_opt_len) return -ENOSPC; bpf_sock->remaining_opt_len -= len; return 0; } static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .func = bpf_sock_ops_reserve_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, u64, tstamp, u32, tstamp_type) { /* skb_clear_delivery_time() is done for inet protocol */ if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -EOPNOTSUPP; switch (tstamp_type) { case BPF_SKB_CLOCK_REALTIME: skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_REALTIME; break; case BPF_SKB_CLOCK_MONOTONIC: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_MONOTONIC; break; case BPF_SKB_CLOCK_TAI: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_TAI; break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { .func = bpf_skb_set_tstamp, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SYN_COOKIES BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th, u32, th_len) { u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT; cookie = __cookie_v4_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th, u32, th_len) { #if IS_BUILTIN(CONFIG_IPV6) const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: mss_clamp; cookie = __cookie_v6_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th) { if (__cookie_v4_check(iph, th) > 0) return 0; return -EACCES; } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = { .func = bpf_tcp_raw_check_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg2_size = sizeof(struct tcphdr), }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th) { #if IS_BUILTIN(CONFIG_IPV6) if (__cookie_v6_check(iph, th) > 0) return 0; return -EACCES; #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { .func = bpf_tcp_raw_check_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg2_size = sizeof(struct tcphdr), }; #endif /* CONFIG_SYN_COOKIES */ #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_clone_redirect: case BPF_FUNC_l3_csum_replace: case BPF_FUNC_l4_csum_replace: case BPF_FUNC_lwt_push_encap: case BPF_FUNC_lwt_seg6_action: case BPF_FUNC_lwt_seg6_adjust_srh: case BPF_FUNC_lwt_seg6_store_bytes: case BPF_FUNC_msg_pop_data: case BPF_FUNC_msg_pull_data: case BPF_FUNC_msg_push_data: case BPF_FUNC_skb_adjust_room: case BPF_FUNC_skb_change_head: case BPF_FUNC_skb_change_proto: case BPF_FUNC_skb_change_tail: case BPF_FUNC_skb_pull_data: case BPF_FUNC_skb_store_bytes: case BPF_FUNC_skb_vlan_pop: case BPF_FUNC_skb_vlan_push: case BPF_FUNC_store_hdr_opt: case BPF_FUNC_xdp_adjust_head: case BPF_FUNC_xdp_adjust_meta: case BPF_FUNC_xdp_adjust_tail: /* tail-called program could call any of the above */ case BPF_FUNC_tail_call: return true; default: return false; } } const struct bpf_func_proto bpf_event_output_data_proto __weak; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak; static const struct bpf_func_proto * sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_bind: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_bind_proto; default: return NULL; } case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_addr_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_addr_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sock_addr_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sock_addr_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_sock_addr_skc_lookup_tcp_proto; #endif /* CONFIG_INET */ case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; } case BPF_FUNC_getsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; } default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_storage_get_proto __weak; const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; case BPF_FUNC_sk_cgroup_id: return &bpf_sk_cgroup_id_proto; case BPF_FUNC_sk_ancestor_cgroup_id: return &bpf_sk_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; #endif default: return sk_filter_func_proto(func_id, prog); } } static const struct bpf_func_proto * tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_skb_vlan_push: return &bpf_skb_vlan_push_proto; case BPF_FUNC_skb_vlan_pop: return &bpf_skb_vlan_pop_proto; case BPF_FUNC_skb_change_proto: return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; case BPF_FUNC_skb_adjust_room: return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_redirect_neigh: return &bpf_redirect_neigh_proto; case BPF_FUNC_redirect_peer: return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_set_hash: return &bpf_set_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_skb_check_mtu_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_skb_cgroup_classid: return &bpf_skb_cgroup_classid_proto; #endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_tc_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_tc_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_tc_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; case BPF_FUNC_skb_set_tstamp: return &bpf_skb_set_tstamp_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_xdp_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; case BPF_FUNC_xdp_adjust_meta: return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_xdp_get_buff_len: return &bpf_xdp_get_buff_len_proto; case BPF_FUNC_xdp_load_bytes: return &bpf_xdp_load_bytes_proto; case BPF_FUNC_xdp_store_bytes: return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_xdp_check_mtu_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_udp: return &bpf_xdp_sk_lookup_udp_proto; case BPF_FUNC_sk_lookup_tcp: return &bpf_xdp_sk_lookup_tcp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_xdp_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) /* The nf_conn___init type is used in the NF_CONNTRACK kfuncs. The * kfuncs are defined in two different modules, and we want to be able * to use them interchangeably with the same BTF type ID. Because modules * can't de-duplicate BTF IDs between each other, we need the type to be * referenced in the vmlinux BTF or the verifier will get confused about * the different types. So we add this dummy type reference which will * be included in vmlinux BTF, allowing both modules to refer to the * same type ID. */ BTF_TYPE_EMIT(struct nf_conn___init); #endif } const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto bpf_sock_hash_update_proto __weak; static const struct bpf_func_proto * sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sock_ops_setsockopt_proto; case BPF_FUNC_getsockopt: return &bpf_sock_ops_getsockopt_proto; case BPF_FUNC_sock_ops_cb_flags_set: return &bpf_sock_ops_cb_flags_set_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; case BPF_FUNC_sock_hash_update: return &bpf_sock_hash_update_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_ops_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_ops_proto; #ifdef CONFIG_INET case BPF_FUNC_load_hdr_opt: return &bpf_sock_ops_load_hdr_opt_proto; case BPF_FUNC_store_hdr_opt: return &bpf_sock_ops_store_hdr_opt_proto; case BPF_FUNC_reserve_hdr_opt: return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_msg_redirect_map_proto __weak; const struct bpf_func_proto bpf_msg_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_msg_redirect_map: return &bpf_msg_redirect_map_proto; case BPF_FUNC_msg_redirect_hash: return &bpf_msg_redirect_hash_proto; case BPF_FUNC_msg_apply_bytes: return &bpf_msg_apply_bytes_proto; case BPF_FUNC_msg_cork_bytes: return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; case BPF_FUNC_msg_push_data: return &bpf_msg_push_data_proto; case BPF_FUNC_msg_pop_data: return &bpf_msg_pop_data_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sk_msg_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_redirect_map_proto __weak; const struct bpf_func_proto bpf_sk_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &sk_skb_change_head_proto; case BPF_FUNC_skb_adjust_room: return &sk_skb_adjust_room_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_sk_redirect_map: return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_lwt_push_encap: return &bpf_lwt_in_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_lwt_push_encap: return &bpf_lwt_xmit_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; #endif default: return lwt_out_func_proto(func_id, prog); } } static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): if (size != size_default) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, hwtstamp): if (type == BPF_WRITE || size != sizeof(__u64)) return false; break; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, sk): if (type == BPF_WRITE || size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; case offsetof(struct __sk_buff, tstamp_type): return false; case offsetofend(struct __sk_buff, tstamp_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { if (size != size_default) return false; } else { bpf_ctx_record_field_size(info, size_default); if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } } return true; } static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool cg_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool lwt_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } /* Attach type specific accesses */ static bool __sock_filter_check_attach_type(int off, enum bpf_access_type access_type, enum bpf_attach_type attach_type) { switch (off) { case offsetof(struct bpf_sock, bound_dev_if): case offsetof(struct bpf_sock, mark): case offsetof(struct bpf_sock, priority): switch (attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: goto full_access; default: return false; } case bpf_ctx_range(struct bpf_sock, src_ip4): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): switch (attach_type) { case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range(struct bpf_sock, src_port): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } } read_only: return access_type == BPF_READ; full_access: return true; } bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range_till(struct bpf_sock, type, priority): return false; default: return bpf_sock_is_valid_access(off, size, type, info); } } bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_sock, state): case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): case bpf_ctx_range(struct bpf_sock, dst_ip4): case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock, dst_port): field_size = size == size_default ? size_default : sizeof_field(struct bpf_sock, dst_port); bpf_ctx_record_field_size(info, field_size); return bpf_ctx_narrow_access_ok(off, size, field_size); case offsetofend(struct bpf_sock, dst_port) ... offsetof(struct bpf_sock, dst_ip4) - 1: return false; } return size == size_default; } static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_sock_is_valid_access(off, size, type, info)) return false; return __sock_filter_check_attach_type(off, type, prog->expected_attach_type); } static int bpf_noop_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { /* Neither direct read nor direct write requires any preliminary * action. */ return 0; } static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog, int drop_verdict) { struct bpf_insn *insn = insn_buf; if (!direct_write) return 0; /* if (!skb->cloned) * goto start; * * (Fast-path, otherwise approximation that we might be * a clone, do the rest in helper.) */ *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); /* ret = bpf_skb_pull_data(skb, 0); */ *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_pull_data); /* if (!ret) * goto restore; * return TC_ACT_SHOT; */ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, drop_verdict); *insn++ = BPF_EXIT_INSN(); /* restore: */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); /* start: */ *insn++ = prog->insnsi[0]; return insn - insn_buf; } static int bpf_gen_ld_abs(const struct bpf_insn *orig, struct bpf_insn *insn_buf) { bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg); if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } /* We're guaranteed here that CTX is in R6. */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache); break; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); *insn++ = BPF_EXIT_INSN(); return insn - insn_buf; } static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, TC_ACT_SHOT); } static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, queue_mapping): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; case offsetof(struct __sk_buff, tstamp_type): /* The convert_ctx_access() on reading and writing * __sk_buff->tstamp depends on whether the bpf prog * has used __sk_buff->tstamp_type or not. * Thus, we need to set prog->tstamp_type_access * earlier during is_valid_access() here. */ ((struct bpf_prog *)prog)->tstamp_type_access = 1; return size == sizeof(__u8); } return bpf_skb_is_valid_access(off, size, type, prog, info); } DEFINE_MUTEX(nf_conn_btf_access_lock); EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); EXPORT_SYMBOL_GPL(nfct_btf_struct_access); static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) return false; if (off % size != 0) return false; if (size != sizeof(__u32)) return false; return true; } static bool xdp_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (prog->expected_attach_type != BPF_XDP_DEVMAP) { switch (off) { case offsetof(struct xdp_md, egress_ifindex): return false; } } if (type == BPF_WRITE) { if (bpf_prog_is_offloaded(prog->aux)) { switch (off) { case offsetof(struct xdp_md, rx_queue_index): return __is_valid_xdp_access(off, size); } } return false; } else { switch (off) { case offsetof(struct xdp_md, data_meta): case offsetof(struct xdp_md, data): case offsetof(struct xdp_md, data_end): if (info->is_ldsx) return false; } } switch (off) { case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; case offsetof(struct xdp_md, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return __is_valid_xdp_access(off, size); } void bpf_warn_invalid_xdp_action(const struct net_device *dev, const struct bpf_prog *prog, u32 act) { const u32 act_max = XDP_REDIRECT; pr_warn_once("%s XDP return value %u on prog %s (id %d) dev %s, expect packet loss!\n", act > act_max ? "Illegal" : "Driver unsupported", act, prog->aux->name, prog->aux->id, dev ? dev->name : "N/A"); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static int xdp_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool sock_addr_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_addr)) return false; if (off % size != 0) return false; /* Disallow access to fields not belonging to the attach type's address * family. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP6_RECVMSG: break; default: return false; } break; case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; } break; } switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, user_port): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } else { if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (size != size_default) return false; } break; case bpf_ctx_range_ptr(struct bpf_sock_addr, sk): if (type != BPF_READ) return false; if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; default: if (type == BPF_READ) { if (size != size_default) return false; } else { return false; } } return true; } static bool sock_ops_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_ops)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; if (type == BPF_WRITE) { switch (off) { case offsetof(struct bpf_sock_ops, reply): case offsetof(struct bpf_sock_ops, sk_txhash): if (size != size_default) return false; break; default: return false; } } else { switch (off) { case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received, bytes_acked): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock_ops, skb_hwtstamp): if (size != sizeof(__u64)) return false; break; default: if (size != size_default) return false; break; } } return true; } static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, SK_DROP); } static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, mark): return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool sk_msg_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) return false; if (off % size != 0) return false; switch (off) { case bpf_ctx_range_ptr(struct sk_msg_md, data): info->reg_type = PTR_TO_PACKET; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, data_end): info->reg_type = PTR_TO_PACKET_END; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct sk_msg_md, family): case bpf_ctx_range(struct sk_msg_md, remote_ip4): case bpf_ctx_range(struct sk_msg_md, local_ip4): case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct sk_msg_md, remote_port): case bpf_ctx_range(struct sk_msg_md, local_port): case bpf_ctx_range(struct sk_msg_md, size): if (size != sizeof(__u32)) return false; break; default: return false; } return true; } static bool flow_dissector_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; if (off % size != 0) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_FLOW_KEYS; return true; default: return false; } } static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data)); break; case offsetof(struct __sk_buff, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data_end)); break; case offsetof(struct __sk_buff, flow_keys): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, flow_keys)); break; } return insn - insn_buf; } static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI); BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME); BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC); BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI); *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT); #else BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1)); #endif return insn; } static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, skb_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), dst_reg, skb_reg, offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), dst_reg, skb_reg, offsetof(struct sk_buff, end)); #endif return insn; } static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, read skb->tstamp as is if tstamp_type_access is true. */ if (!prog->tstamp_type_access) { /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* check if ingress mask bits is set */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); *insn++ = BPF_JMP_A(4); *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1); *insn++ = BPF_JMP_A(2); /* skb->tc_at_ingress && skb->tstamp_type, * read 0 as the (rcv) timestamp. */ *insn++ = BPF_MOV64_IMM(value_reg, 0); *insn++ = BPF_JMP_A(1); } #endif *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg, offsetof(struct sk_buff, tstamp)); return insn; } static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->src_reg; __u8 skb_reg = si->dst_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the * skb->tstamp_type bit also. */ if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* Writing __sk_buff->tstamp as ingress, goto <clear> */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); /* goto <store> */ *insn++ = BPF_JMP_A(2); /* <clear>: skb->tstamp_type */ *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK); *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif /* <store>: skb->tstamp = tstamp */ *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_DW | BPF_MEM, skb_reg, value_reg, offsetof(struct sk_buff, tstamp), si->imm); return insn; } #define BPF_EMIT_STORE(size, si, off) \ BPF_RAW_INSN(BPF_CLASS((si)->code) | (size) | BPF_MEM, \ (si)->dst_reg, (si)->src_reg, (off), (si)->imm) static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, len): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, len, 4, target_size)); break; case offsetof(struct __sk_buff, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, protocol, 2, target_size)); break; case offsetof(struct __sk_buff, vlan_proto): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_proto, 2, target_size)); break; case offsetof(struct __sk_buff, priority): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, priority, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, priority, 4, target_size)); break; case offsetof(struct __sk_buff, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, skb_iif, 4, target_size)); break; case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; case offsetof(struct __sk_buff, hash): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, hash, 4, target_size)); break; case offsetof(struct __sk_buff, mark): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, mark, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, mark, 4, target_size)); break; case offsetof(struct __sk_buff, pkt_type): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 5); #endif break; case offsetof(struct __sk_buff, queue_mapping): if (type == BPF_WRITE) { u32 offset = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); if (BPF_CLASS(si->code) == BPF_ST && si->imm >= NO_QUEUE_MAPPING) { *insn++ = BPF_JMP_A(0); /* noop */ break; } if (BPF_CLASS(si->code) == BPF_STX) *insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_EMIT_STORE(BPF_H, si, offset); } else { *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, queue_mapping, 2, target_size)); } break; case offsetof(struct __sk_buff, vlan_present): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_all, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_tci, 2, target_size)); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_classid): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, tc_classid); *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, off); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->src_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct __sk_buff, data_meta): off = si->off; off -= offsetof(struct __sk_buff, data_meta); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_meta); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_end); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); #else *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, napi_id): #if defined(CONFIG_NET_RX_BUSY_POLL) *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, napi_id, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else *target_size = 4; *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_family, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_daddr, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, 4, target_size)); break; case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_dport, 2, target_size)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct __sk_buff, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_num, 2, target_size)); break; case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) insn = bpf_convert_tstamp_write(prog, si, insn); else insn = bpf_convert_tstamp_read(prog, si, insn); break; case offsetof(struct __sk_buff, tstamp_type): insn = bpf_convert_tstamp_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_segs, 2, target_size)); break; case offsetof(struct __sk_buff, gso_size): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_size, 2, target_size)); break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, pkt_len); *target_size = 4; *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; case offsetof(struct __sk_buff, hwtstamp): BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); break; } return insn - insn_buf; } u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_bound_dev_if)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); break; case offsetof(struct bpf_sock, mark): BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_mark)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_mark)); break; case offsetof(struct bpf_sock, priority): BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_priority)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_priority)); break; case offsetof(struct bpf_sock, family): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_family), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, sizeof_field(struct sock_common, skc_family), target_size)); break; case offsetof(struct bpf_sock, type): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_type), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_type, sizeof_field(struct sock, sk_type), target_size)); break; case offsetof(struct bpf_sock, protocol): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_protocol), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_protocol, sizeof_field(struct sock, sk_protocol), target_size)); break; case offsetof(struct bpf_sock, src_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; case offsetof(struct bpf_sock, dst_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, sizeof_field(struct sock_common, skc_daddr), target_size)); break; case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, src_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else (void)off; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, dst_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); *target_size = 4; #endif break; case offsetof(struct bpf_sock, src_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, sizeof_field(struct sock_common, skc_num), target_size)); break; case offsetof(struct bpf_sock, dst_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, sizeof_field(struct sock_common, skc_dport), target_size)); break; case offsetof(struct bpf_sock, state): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, sizeof_field(struct sock_common, skc_state), target_size)); break; case offsetof(struct bpf_sock, rx_queue_mapping): #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_rx_queue_mapping, sizeof_field(struct sock, sk_rx_queue_mapping), target_size)); *insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); #else *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); *target_size = 2; #endif break; } return insn - insn_buf; } static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 xdp_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct xdp_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_meta): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_meta)); break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_end)); break; case offsetof(struct xdp_md, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_rxq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; case offsetof(struct xdp_md, rx_queue_index): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, queue_index)); break; case offsetof(struct xdp_md, egress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, txq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_txq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; } return insn - insn_buf; } /* SOCK_ADDR_LOAD_NESTED_FIELD() loads Nested Field S.F.NF where S is type of * context Structure, F is Field in context structure that contains a pointer * to Nested Structure of type NS that has the field NF. * * SIZE encodes the load size (BPF_B, BPF_H, etc). It's up to caller to make * sure that SIZE is not greater than actual size of S.F.NF. * * If offset OFF is provided, the load happens from that offset relative to * offset of NF. */ #define SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF) \ do { \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), si->dst_reg, \ si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) #define SOCK_ADDR_LOAD_NESTED_FIELD(S, NS, F, NF) \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, \ BPF_FIELD_SIZEOF(NS, NF), 0) /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation. * * In addition it uses Temporary Field TF (member of struct S) as the 3rd * "register" since two registers available in convert_ctx_access are not * enough: we can't override neither SRC, since it contains value to store, nor * DST since it contains pointer to context that may be used by later * instructions. But we need a temporary place to save pointer to nested * structure whose field we want to store to. */ #define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF) \ do { \ int tmp_reg = BPF_REG_9; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, tmp_reg, \ offsetof(S, TF)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_RAW_INSN(SIZE | BPF_MEM | BPF_CLASS(si->code), \ tmp_reg, si->src_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF, \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ offsetof(S, TF)); \ } while (0) #define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF, \ TF) \ do { \ if (type == BPF_WRITE) { \ SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, \ OFF, TF); \ } else { \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( \ S, NS, F, NF, SIZE, OFF); \ } \ } while (0) static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port); struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sock_addr, user_family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr, uaddr, sa_family); break; case offsetof(struct bpf_sock_addr, user_ip4): SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in, uaddr, sin_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, user_ip6[0]); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_addr.s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, user_port): /* To get port we need to know sa_family first and then treat * sockaddr as either sockaddr_in or sockaddr_in6. * Though we can simplify since port field has same offset and * size in both structures. * Here we check this invariant and use just one of the * structures if it's true. */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != sizeof_field(struct sockaddr_in6, sin6_port)); /* Account for sin6_port being smaller than user_port. */ port_size = min(port_size, BPF_LDST_BYTES(si)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg); break; case offsetof(struct bpf_sock_addr, family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_family); break; case offsetof(struct bpf_sock_addr, type): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_type); break; case offsetof(struct bpf_sock_addr, protocol): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_protocol); break; case offsetof(struct bpf_sock_addr, msg_src_ip4): /* Treat t_ctx as struct in_addr for msg_src_ip4. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in_addr, t_ctx, s_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in6_addr, t_ctx, s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_addr_kern, sk)); break; } return insn - insn_buf; } static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \ OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_SK() \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock) /* Helper macro for adding write access to tcp_sock or sock fields. * The macro is called with two registers, dst_reg which contains a pointer * to ctx (context) and src_reg which contains the value that should be * stored. However, we need an additional register since we cannot overwrite * dst_reg because it may be used later in the program. * Instead we "borrow" one of the other register. We first save its value * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore * it at the end of the macro. */ #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_RAW_INSN(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD) | \ BPF_MEM | BPF_CLASS(si->code), \ reg, si->src_reg, \ offsetof(OBJ, OBJ_FIELD), \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } while (0) #define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ do { \ if (TYPE == BPF_WRITE) \ SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ else \ SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ } while (0) switch (si->off) { case offsetof(struct bpf_sock_ops, op): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, op), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, op)); break; case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, replylong[0]); off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, off); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct bpf_sock_ops, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct bpf_sock_ops, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct bpf_sock_ops, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct bpf_sock_ops, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct bpf_sock_ops, is_fullsock): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, is_fullsock), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, is_fullsock)); break; case offsetof(struct bpf_sock_ops, state): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_state)); break; case offsetof(struct bpf_sock_ops, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags, struct tcp_sock); break; case offsetof(struct bpf_sock_ops, sk_txhash): SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; case offsetof(struct bpf_sock_ops, snd_cwnd): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd); break; case offsetof(struct bpf_sock_ops, srtt_us): SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us); break; case offsetof(struct bpf_sock_ops, snd_ssthresh): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh); break; case offsetof(struct bpf_sock_ops, rcv_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt); break; case offsetof(struct bpf_sock_ops, snd_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt); break; case offsetof(struct bpf_sock_ops, snd_una): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una); break; case offsetof(struct bpf_sock_ops, mss_cache): SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache); break; case offsetof(struct bpf_sock_ops, ecn_flags): SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags); break; case offsetof(struct bpf_sock_ops, rate_delivered): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered); break; case offsetof(struct bpf_sock_ops, rate_interval_us): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us); break; case offsetof(struct bpf_sock_ops, packets_out): SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out); break; case offsetof(struct bpf_sock_ops, retrans_out): SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out); break; case offsetof(struct bpf_sock_ops, total_retrans): SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans); break; case offsetof(struct bpf_sock_ops, segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in); break; case offsetof(struct bpf_sock_ops, data_segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in); break; case offsetof(struct bpf_sock_ops, segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out); break; case offsetof(struct bpf_sock_ops, data_segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out); break; case offsetof(struct bpf_sock_ops, lost_out): SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out); break; case offsetof(struct bpf_sock_ops, sacked_out): SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out); break; case offsetof(struct bpf_sock_ops, bytes_received): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received); break; case offsetof(struct bpf_sock_ops, bytes_acked): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; case offsetof(struct bpf_sock_ops, skb_data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb_data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb_data_end)); break; case offsetof(struct bpf_sock_ops, skb_data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct bpf_sock_ops, skb_len): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, len)); break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): off = offsetof(struct sk_buff, cb); off += offsetof(struct tcp_skb_cb, tcp_flags); *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, tcp_flags), si->dst_reg, si->dst_reg, off); break; case offsetof(struct bpf_sock_ops, skb_hwtstamp): { struct bpf_insn *jmp_on_null_skb; *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); /* Reserve one insn to test skb == NULL */ jmp_on_null_skb = insn++; insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, insn - jmp_on_null_skb - 1); break; } } return insn - insn_buf; } /* data_end = skb->data + skb_headlen() */ static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, struct bpf_insn *insn) { int reg; int temp_reg_off = offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, temp_reg); if (si->src_reg == si->dst_reg) { /* We need an extra register, choose and save a register. */ reg = BPF_REG_9; if (si->src_reg == reg || si->dst_reg == reg) reg--; if (si->src_reg == reg || si->dst_reg == reg) reg--; *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, temp_reg_off); } else { reg = si->dst_reg; } /* reg = skb->data */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), reg, si->src_reg, offsetof(struct sk_buff, data)); /* AX = skb->len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, len)); /* reg = skb->data + skb->len */ *insn++ = BPF_ALU64_REG(BPF_ADD, reg, BPF_REG_AX); /* AX = skb->data_len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, data_len)); /* reg = skb->data + skb->len - skb->data_len */ *insn++ = BPF_ALU64_REG(BPF_SUB, reg, BPF_REG_AX); if (si->src_reg == si->dst_reg) { /* Restore the saved register */ *insn++ = BPF_MOV64_REG(BPF_REG_AX, si->src_reg); *insn++ = BPF_MOV64_REG(si->dst_reg, reg); *insn++ = BPF_LDX_MEM(BPF_DW, reg, BPF_REG_AX, temp_reg_off); } return insn; } static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): insn = bpf_convert_data_end_access(si, insn); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct sk_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #if IS_ENABLED(CONFIG_IPV6) int off; #endif /* convert ctx uses the fact sg element is first in struct */ BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0); switch (si->off) { case offsetof(struct sk_msg_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data)); break; case offsetof(struct sk_msg_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data_end), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct sk_msg_md, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct sk_msg_md, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct sk_msg_md, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct sk_msg_md, size): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size), si->dst_reg, si->src_reg, offsetof(struct sk_msg_sg, size)); break; case offsetof(struct sk_msg_md, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops sk_filter_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, .btf_struct_access = tc_cls_act_btf_struct_access, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, .gen_prologue = bpf_noop_prologue, .btf_struct_access = xdp_btf_struct_access, }; const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = cg_skb_func_proto, .is_valid_access = cg_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_in_verifier_ops = { .get_func_proto = lwt_in_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_in_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_out_verifier_ops = { .get_func_proto = lwt_out_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_out_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, }; const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_seg6local_verifier_ops = { .get_func_proto = lwt_seg6local_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_seg6local_prog_ops = { }; const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = bpf_sock_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_prog_ops = { }; const struct bpf_verifier_ops cg_sock_addr_verifier_ops = { .get_func_proto = sock_addr_func_proto, .is_valid_access = sock_addr_is_valid_access, .convert_ctx_access = sock_addr_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_addr_prog_ops = { }; const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; const struct bpf_prog_ops sock_ops_prog_ops = { }; const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = sk_skb_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; const struct bpf_prog_ops sk_skb_prog_ops = { }; const struct bpf_verifier_ops sk_msg_verifier_ops = { .get_func_proto = sk_msg_func_proto, .is_valid_access = sk_msg_is_valid_access, .convert_ctx_access = sk_msg_convert_ctx_access, .gen_prologue = bpf_noop_prologue, }; const struct bpf_prog_ops sk_msg_prog_ops = { }; const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { .test_run = bpf_prog_test_run_flow_dissector, }; int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; struct sk_filter *filter; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); ret = 0; } return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; int ret = 0; sockopt_lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (!filter) goto out; /* We're copying the filter that has been originally attached, * so no conversion/decode needed anymore. eBPF programs that * have no original program cannot be dumped through this. */ ret = -EACCES; fprog = filter->prog->orig_prog; if (!fprog) goto out; ret = fprog->len; if (!len) /* User space only enquires number of filter blocks. */ goto out; ret = -EINVAL; if (len < fprog->len) goto out; ret = -EFAULT; if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number * of filter blocks. */ ret = fprog->len; out: sockopt_release_sock(sk); return ret; } #ifdef CONFIG_INET static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; reuse_kern->bind_inany = reuse->bind_inany; } struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = bpf_prog_run(prog, &reuse_kern); if (action == SK_PASS) return reuse_kern.selected_sk; else return ERR_PTR(-ECONNREFUSED); } BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, struct bpf_map *, map, void *, key, u32, flags) { bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) return -ENOENT; reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. * * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ err = is_sockarray ? -ENOENT : -EINVAL; goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; if (sk->sk_protocol != selected_sk->sk_protocol) { err = -EPROTOTYPE; } else if (sk->sk_family != selected_sk->sk_family) { err = -EAFNOSUPPORT; } else { /* Catch all. Likely bound to a different sockaddr. */ err = -EBADFD; } goto error; } reuse_kern->selected_sk = selected_sk; return 0; error: /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ if (sk_is_refcounted(selected_sk)) sock_put(selected_sk); return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { .func = sk_select_reuseport, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(sk_reuseport_load_bytes, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len) { return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len); } static const struct bpf_func_proto sk_reuseport_load_bytes_proto = { .func = sk_reuseport_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(sk_reuseport_load_bytes_relative, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len, u32, start_header) { return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to, len, start_header); } static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = { .func = sk_reuseport_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_reuseport_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sk_select_reuseport: return &sk_select_reuseport_proto; case BPF_FUNC_skb_load_bytes: return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool sk_reuseport_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const u32 size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct sk_reuseport_md) || off % size || type != BPF_READ) return false; switch (off) { case offsetof(struct sk_reuseport_md, data): info->reg_type = PTR_TO_PACKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, data_end): info->reg_type = PTR_TO_PACKET_END; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, hash): return size == size_default; case offsetof(struct sk_reuseport_md, sk): info->reg_type = PTR_TO_SOCKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, migrating_sk): info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; return size == sizeof(__u64); /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) return false; fallthrough; case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): case bpf_ctx_range(struct sk_reuseport_md, bind_inany): case bpf_ctx_range(struct sk_reuseport_md, len): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); default: return false; } } #define SK_REUSEPORT_LOAD_FIELD(F) ({ \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) #define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sk_buff, \ skb, \ SKB_FIELD) #define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sock, \ sk, \ SK_FIELD) static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct sk_reuseport_md, data): SK_REUSEPORT_LOAD_SKB_FIELD(data); break; case offsetof(struct sk_reuseport_md, len): SK_REUSEPORT_LOAD_SKB_FIELD(len); break; case offsetof(struct sk_reuseport_md, eth_protocol): SK_REUSEPORT_LOAD_SKB_FIELD(protocol); break; case offsetof(struct sk_reuseport_md, ip_protocol): SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol); break; case offsetof(struct sk_reuseport_md, data_end): SK_REUSEPORT_LOAD_FIELD(data_end); break; case offsetof(struct sk_reuseport_md, hash): SK_REUSEPORT_LOAD_FIELD(hash); break; case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; case offsetof(struct sk_reuseport_md, sk): SK_REUSEPORT_LOAD_FIELD(sk); break; case offsetof(struct sk_reuseport_md, migrating_sk): SK_REUSEPORT_LOAD_FIELD(migrating_sk); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_reuseport_verifier_ops = { .get_func_proto = sk_reuseport_func_proto, .is_valid_access = sk_reuseport_is_valid_access, .convert_ctx_access = sk_reuseport_convert_ctx_access, }; const struct bpf_prog_ops sk_reuseport_prog_ops = { }; DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled); EXPORT_SYMBOL(bpf_sk_lookup_enabled); BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, struct sock *, sk, u64, flags) { if (unlikely(flags & ~(BPF_SK_LOOKUP_F_REPLACE | BPF_SK_LOOKUP_F_NO_REUSEPORT))) return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN)) return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */ if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE)) return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) return -EPROTOTYPE; if (sk && sk->sk_family != ctx->family && (sk->sk_family == AF_INET || ipv6_only_sock(sk))) return -EAFNOSUPPORT; if (ctx->selected_sk && !(flags & BPF_SK_LOOKUP_F_REPLACE)) return -EEXIST; /* Select socket as lookup result */ ctx->selected_sk = sk; ctx->no_reuseport = flags & BPF_SK_LOOKUP_F_NO_REUSEPORT; return 0; } static const struct bpf_func_proto bpf_sk_lookup_assign_proto = { .func = bpf_sk_lookup_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_SOCKET_OR_NULL, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_assign: return &bpf_sk_lookup_assign_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static bool sk_lookup_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_sk_lookup)) return false; if (off % size != 0) return false; if (type != BPF_READ) return false; switch (off) { case bpf_ctx_range_ptr(struct bpf_sk_lookup, sk): info->reg_type = PTR_TO_SOCKET_OR_NULL; return size == sizeof(__u64); case bpf_ctx_range(struct bpf_sk_lookup, family): case bpf_ctx_range(struct bpf_sk_lookup, protocol): case bpf_ctx_range(struct bpf_sk_lookup, remote_ip4): case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); case bpf_ctx_range(struct bpf_sk_lookup, remote_port): /* Allow 4-byte access to 2-byte field for backward compatibility */ if (size == sizeof(__u32)) return true; bpf_ctx_record_field_size(info, sizeof(__be16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__be16)); case offsetofend(struct bpf_sk_lookup, remote_port) ... offsetof(struct bpf_sk_lookup, local_ip4) - 1: /* Allow access to zero padding for backward compatibility */ bpf_ctx_record_field_size(info, sizeof(__u16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u16)); default: return false; } } static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sk_lookup, sk): *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, selected_sk)); break; case offsetof(struct bpf_sk_lookup, family): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, family, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, protocol, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, remote_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.saddr, 4, target_size)); break; case offsetof(struct bpf_sk_lookup, local_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.daddr, 4, target_size)); break; case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, remote_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.saddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, local_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.daddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case offsetof(struct bpf_sk_lookup, remote_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, sport, 2, target_size)); break; case offsetofend(struct bpf_sk_lookup, remote_port): *target_size = 2; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); break; case offsetof(struct bpf_sk_lookup, local_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, dport, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, ingress_ifindex, 4, target_size)); break; } return insn - insn_buf; } const struct bpf_prog_ops sk_lookup_prog_ops = { .test_run = bpf_prog_test_run_sk_lookup, }; const struct bpf_verifier_ops sk_lookup_verifier_ops = { .get_func_proto = sk_lookup_func_proto, .is_valid_access = sk_lookup_is_valid_access, .convert_ctx_access = sk_lookup_convert_ctx_access, }; #endif /* CONFIG_INET */ DEFINE_BPF_DISPATCHER(xdp) void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) { bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } BTF_ID_LIST_GLOBAL(btf_sock_ids, MAX_BTF_SOCK_TYPE) #define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type) BTF_SOCK_TYPE_xxx #undef BTF_SOCK_TYPE BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { /* tcp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct tcp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { .func = bpf_skc_to_tcp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { .func = bpf_skc_to_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { /* BTF types for tcp_timewait_sock and inet_timewait_sock are not * generated if CONFIG_INET=n. Trigger an explicit generation here. */ BTF_TYPE_EMIT(struct inet_timewait_sock); BTF_TYPE_EMIT(struct tcp_timewait_sock); #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { .func = bpf_skc_to_tcp_timewait_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) { #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { .func = bpf_skc_to_tcp_request_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) { /* udp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct udp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .func = bpf_skc_to_udp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) { /* unix_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct unix_sock); if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { .func = bpf_skc_to_unix_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], }; BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk) { BTF_TYPE_EMIT(struct mptcp_sock); return (unsigned long)bpf_mptcp_sock_from_subflow(sk); } const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = { .func = bpf_skc_to_mptcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_MPTCP], }; BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); } BTF_ID_LIST(bpf_sock_from_file_btf_ids) BTF_ID(struct, socket) BTF_ID(struct, file) const struct bpf_func_proto bpf_sock_from_file_proto = { .func = bpf_sock_from_file, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .ret_btf_id = &bpf_sock_from_file_btf_ids[0], .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_sock_from_file_btf_ids[1], }; static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; switch (func_id) { case BPF_FUNC_skc_to_tcp6_sock: func = &bpf_skc_to_tcp6_sock_proto; break; case BPF_FUNC_skc_to_tcp_sock: func = &bpf_skc_to_tcp_sock_proto; break; case BPF_FUNC_skc_to_tcp_timewait_sock: func = &bpf_skc_to_tcp_timewait_sock_proto; break; case BPF_FUNC_skc_to_tcp_request_sock: func = &bpf_skc_to_tcp_request_sock_proto; break; case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; case BPF_FUNC_skc_to_mptcp_sock: func = &bpf_skc_to_mptcp_sock_proto; break; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; } __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct sk_buff *skb = (struct sk_buff *)s; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len); return 0; } __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_md *x, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct xdp_buff *xdp = (struct xdp_buff *)x; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp)); return 0; } __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, const u8 *sun_path, u32 sun_path__sz) { struct sockaddr_un *un; if (sa_kern->sk->sk_family != AF_UNIX) return -EINVAL; /* We do not allow changing the address to unnamed or larger than the * maximum allowed address size for a unix sockaddr. */ if (sun_path__sz == 0 || sun_path__sz > UNIX_PATH_MAX) return -EINVAL; un = (struct sockaddr_un *)sa_kern->uaddr; memcpy(un->sun_path, sun_path, sun_path__sz); sa_kern->uaddrlen = offsetof(struct sockaddr_un, sun_path) + sun_path__sz; return 0; } __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, struct bpf_tcp_req_attrs *attrs, int attrs__sz) { #if IS_ENABLED(CONFIG_SYN_COOKIES) struct sk_buff *skb = (struct sk_buff *)s; const struct request_sock_ops *ops; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct request_sock *req; struct net *net; __u16 min_mss; u32 tsoff = 0; if (attrs__sz != sizeof(*attrs) || attrs->reserved[0] || attrs->reserved[1] || attrs->reserved[2]) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EINVAL; net = dev_net(skb->dev); if (net != sock_net(sk)) return -ENETUNREACH; switch (skb->protocol) { case htons(ETH_P_IP): ops = &tcp_request_sock_ops; min_mss = 536; break; #if IS_BUILTIN(CONFIG_IPV6) case htons(ETH_P_IPV6): ops = &tcp6_request_sock_ops; min_mss = IPV6_MIN_MTU - 60; break; #endif default: return -EINVAL; } if (sk->sk_type != SOCK_STREAM || sk->sk_state != TCP_LISTEN || sk_is_mptcp(sk)) return -EINVAL; if (attrs->mss < min_mss) return -EINVAL; if (attrs->wscale_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) return -EINVAL; if (attrs->snd_wscale > TCP_MAX_WSCALE || attrs->rcv_wscale > TCP_MAX_WSCALE) return -EINVAL; } if (attrs->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return -EINVAL; if (attrs->tstamp_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return -EINVAL; tsoff = attrs->rcv_tsecr - tcp_ns_to_ts(attrs->usec_ts_ok, tcp_clock_ns()); } req = inet_reqsk_alloc(ops, sk, false); if (!req) return -ENOMEM; ireq = inet_rsk(req); treq = tcp_rsk(req); req->rsk_listener = sk; req->syncookie = 1; req->mss = attrs->mss; req->ts_recent = attrs->rcv_tsval; ireq->snd_wscale = attrs->snd_wscale; ireq->rcv_wscale = attrs->rcv_wscale; ireq->tstamp_ok = !!attrs->tstamp_ok; ireq->sack_ok = !!attrs->sack_ok; ireq->wscale_ok = !!attrs->wscale_ok; ireq->ecn_ok = !!attrs->ecn_ok; treq->req_usec_ts = !!attrs->usec_ts_ok; treq->ts_off = tsoff; skb_orphan(skb); skb->sk = req_to_sk(req); skb->destructor = sock_pfree; return 0; #else return -EOPNOTSUPP; #endif } __bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, u64 flags) { struct sk_buff *skb; if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) return -EOPNOTSUPP; if (flags) return -EINVAL; skb = skops->skb; skb_shinfo(skb)->tx_flags |= SKBTX_BPF; TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF; skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; return 0; } __bpf_kfunc_end_defs(); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; int err; err = bpf_dynptr_from_skb(skb, flags, ptr__uninit); if (err) return err; bpf_dynptr_set_rdonly(ptr); return 0; } BTF_KFUNCS_START(bpf_kfunc_check_set_skb) BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_skb) BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) BTF_KFUNCS_END(bpf_kfunc_check_set_xdp) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr) BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_addr) BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops) BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops) static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb, }; static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_xdp, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_addr, }; static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_tcp_reqsk, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_ops, }; static int __init bpf_kfunc_init(void) { int ret; ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SK_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCKET_FILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_OUT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_IN, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, &bpf_kfunc_set_sock_addr); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops); } late_initcall(bpf_kfunc_init); __bpf_kfunc_start_defs(); /* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code. * * The function expects a non-NULL pointer to a socket, and invokes the * protocol specific socket destroy handlers. * * The helper can only be called from BPF contexts that have acquired the socket * locks. * * Parameters: * @sock: Pointer to socket to be destroyed * * Return: * On error, may return EPROTONOSUPPORT, EINVAL. * EPROTONOSUPPORT if protocol specific destroy handler is not supported. * 0 otherwise */ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock) { struct sock *sk = (struct sock *)sock; /* The locking semantics that allow for synchronous execution of the * destroy handlers are only supported for TCP and UDP. * Supporting protocols will need to acquire sock lock in the BPF context * prior to invoking this kfunc. */ if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_UDP)) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, ECONNABORTED); } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(bpf_sk_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_sk_iter_kfunc_ids) static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id) { if (btf_id_set8_contains(&bpf_sk_iter_kfunc_ids, kfunc_id) && prog->expected_attach_type != BPF_TRACE_ITER) return -EACCES; return 0; } static const struct btf_kfunc_id_set bpf_sk_iter_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_sk_iter_kfunc_ids, .filter = tracing_iter_filter, }; static int init_subsystem(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_sk_iter_kfunc_set); } late_initcall(init_subsystem); |
| 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 | /* SPDX-License-Identifier: GPL-1.0+ */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes * NCM: Network and Communications Management, Inc. * * BUT, I'm the one who modified it for ethernet, so: * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov * */ #ifndef _NET_BONDING_H #define _NET_BONDING_H #include <linux/timer.h> #include <linux/proc_fs.h> #include <linux/if_bonding.h> #include <linux/cpumask.h> #include <linux/in6.h> #include <linux/netpoll.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/reciprocal_div.h> #include <linux/if_link.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #include <net/bond_options.h> #include <net/ipv6.h> #include <net/addrconf.h> #define BOND_MAX_ARP_TARGETS 16 #define BOND_MAX_NS_TARGETS BOND_MAX_ARP_TARGETS #define BOND_DEFAULT_MIIMON 100 #ifndef __long_aligned #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif #define slave_info(bond_dev, slave_dev, fmt, ...) \ netdev_info(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_warn(bond_dev, slave_dev, fmt, ...) \ netdev_warn(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_dbg(bond_dev, slave_dev, fmt, ...) \ netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_err(bond_dev, slave_dev, fmt, ...) \ netdev_err(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define BOND_MODE(bond) ((bond)->params.mode) /* slave list primitives */ #define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) #define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) /* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ #define bond_first_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ NULL) #define bond_last_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ NULL) /* Caller must have rcu_read_lock */ #define bond_first_slave_rcu(bond) \ netdev_lower_get_first_private_rcu(bond->dev) #define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) #define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) /** * bond_for_each_slave - iterate over all slaves * @bond: the bond holding this list * @pos: current slave * @iter: list_head * iterator * * Caller must hold RTNL */ #define bond_for_each_slave(bond, pos, iter) \ netdev_for_each_lower_private((bond)->dev, pos, iter) /* Caller must have rcu_read_lock */ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; static inline void block_netpoll_tx(void) { atomic_inc(&netpoll_block_tx); } static inline void unblock_netpoll_tx(void) { atomic_dec(&netpoll_block_tx); } static inline int is_netpoll_tx_blocked(struct net_device *dev) { if (unlikely(netpoll_tx_running(dev))) return atomic_read(&netpoll_block_tx); return 0; } #else #define block_netpoll_tx() #define unblock_netpoll_tx() #define is_netpoll_tx_blocked(dev) (0) #endif DECLARE_STATIC_KEY_FALSE(bond_bcast_neigh_enabled); struct bond_params { int mode; int xmit_policy; int miimon; u8 num_peer_notif; u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; int use_carrier; int fail_over_mac; int updelay; int downdelay; int peer_notif_delay; int lacp_active; int lacp_fast; unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; int primary_reselect; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; int tx_queues; int all_slaves_active; int resend_igmp; int lp_interval; int packets_per_slave; int tlb_dynamic_lb; struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; #endif int coupled_control; int broadcast_neighbor; /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; }; struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ int delay; /* all 4 in jiffies */ unsigned long last_link_up; unsigned long last_tx; unsigned long last_rx; unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 link_new_state; /* one of BOND_LINK_XXXX */ u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ rx_disabled:1, /* indicates whether slave's Rx is disabled */ should_notify:1, /* indicates whether the state changed */ should_notify_link:1; /* indicates whether the link changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif struct delayed_work notify_work; struct kobject kobj; struct rtnl_link_stats64 slave_stats; }; static inline struct slave *to_slave(struct kobject *kobj) { return container_of(kobj, struct slave, kobj); } struct bond_up_slave { unsigned int count; struct rcu_head rcu; struct slave *arr[]; }; /* * Link pseudo-state only used internally by monitors */ #define BOND_LINK_NOCHANGE -1 struct bond_ipsec { struct list_head list; struct xfrm_state *xs; }; /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ struct slave __rcu *curr_active_slave; struct slave __rcu *current_arp_slave; struct slave __rcu *primary_slave; struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); /* mode_lock is used for mode-specific locking needs, currently used by: * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and * bond_3ad_state_machine_handler() concurrently and also * the access to the state machine shared variables. * TLB mode (5) - to sync the use and modifications of its hash table * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; spinlock_t stats_lock; u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; struct workqueue_struct *wq; struct delayed_work mii_work; struct delayed_work arp_work; struct delayed_work alb_work; struct delayed_work ad_work; struct delayed_work mcast_work; struct delayed_work slave_arr_work; #ifdef CONFIG_DEBUG_FS /* debugging support via debugfs */ struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ struct mutex ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) #define bond_slave_get_rtnl(dev) \ ((struct slave *) rtnl_dereference(dev->rx_handler_data)) void bond_queue_slave_event(struct slave *slave); void bond_lower_state_changed(struct slave *slave); struct bond_vlan_tag { __be16 vlan_proto; unsigned short vlan_id; }; /* * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read */ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) { return netdev_lower_dev_get_private(bond->dev, slave_dev); } static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) { return slave->bond; } static inline bool bond_should_override_tx_queue(struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; } static inline bool bond_is_lb(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB; } static inline bool bond_needs_speed_duplex(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_8023AD || bond_is_lb(bond); } static inline bool bond_is_nondyn_tlb(const struct bonding *bond) { return (bond_is_lb(bond) && bond->params.tlb_dynamic_lb == 0); } static inline bool bond_mode_can_use_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB); } static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || bond_is_nondyn_tlb(bond)); } static inline bool bond_mode_uses_arp(int mode) { return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && mode != BOND_MODE_ALB; } static inline bool bond_mode_uses_primary(int mode) { return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || mode == BOND_MODE_ALB; } static inline bool bond_uses_primary(struct bonding *bond) { return bond_mode_uses_primary(BOND_MODE(bond)); } static inline struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); return bond_uses_primary(bond) && slave ? slave->dev : NULL; } static inline bool bond_slave_is_up(struct slave *slave) { return netif_running(slave->dev) && netif_carrier_ok(slave->dev); } static inline void bond_set_active_slave(struct slave *slave) { if (slave->backup) { slave->backup = 0; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_backup_slave(struct slave *slave) { if (!slave->backup) { slave->backup = 1; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_slave_state(struct slave *slave, int slave_state, bool notify) { if (slave->backup == slave_state) return; slave->backup = slave_state; if (notify) { bond_lower_state_changed(slave); bond_queue_slave_event(slave); slave->should_notify = 0; } else { if (slave->should_notify) slave->should_notify = 0; else slave->should_notify = 1; } } static inline void bond_slave_state_change(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->link == BOND_LINK_UP) bond_set_active_slave(tmp); else if (tmp->link == BOND_LINK_DOWN) bond_set_backup_slave(tmp); } } static inline void bond_slave_state_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify) { bond_lower_state_changed(tmp); tmp->should_notify = 0; } } } static inline int bond_slave_state(struct slave *slave) { return slave->backup; } static inline bool bond_is_active_slave(struct slave *slave) { return !bond_slave_state(slave); } static inline bool bond_slave_can_tx(struct slave *slave) { return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && bond_is_active_slave(slave); } static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev) { struct slave *slave; bool active; rcu_read_lock(); slave = bond_slave_get_rcu(slave_dev); active = bond_is_active_slave(slave); rcu_read_unlock(); return active; } static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len) { if (len == ETH_ALEN) { ether_addr_copy(dst, src); return; } memcpy(dst, src, len); } #define BOND_PRI_RESELECT_ALWAYS 0 #define BOND_PRI_RESELECT_BETTER 1 #define BOND_PRI_RESELECT_FAILURE 2 #define BOND_FOM_NONE 0 #define BOND_FOM_ACTIVE 1 #define BOND_FOM_FOLLOW 2 #define BOND_ARP_TARGETS_ANY 0 #define BOND_ARP_TARGETS_ALL 1 #define BOND_ARP_VALIDATE_NONE 0 #define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) #define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) #define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_VALIDATE_BACKUP) #define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) #define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_FILTER) #define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ BOND_ARP_FILTER) #define BOND_SLAVE_NOTIFY_NOW true #define BOND_SLAVE_NOTIFY_LATER false static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) { return bond->params.arp_validate & (1 << bond_slave_state(slave)); } static inline int slave_do_arp_validate_only(struct bonding *bond) { return bond->params.arp_validate & BOND_ARP_FILTER; } static inline int bond_is_ip_target_ok(__be32 addr) { return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_is_ip6_target_ok(struct in6_addr *addr) { return !ipv6_addr_any(addr) && !ipv6_addr_loopback(addr) && !ipv6_addr_is_multicast(addr); } #endif /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, struct slave *slave) { int i = 1; unsigned long ret = slave->target_last_arp_rx[0]; for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) if (time_before(slave->target_last_arp_rx[i], ret)) ret = slave->target_last_arp_rx[i]; return ret; } static inline unsigned long slave_last_rx(struct bonding *bond, struct slave *slave) { if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) return slave_oldest_target_arp_rx(bond, slave); return slave->last_rx; } static inline void slave_update_last_tx(struct slave *slave) { WRITE_ONCE(slave->last_tx, jiffies); } static inline unsigned long slave_last_tx(struct slave *slave) { return READ_ONCE(slave->last_tx); } #ifdef CONFIG_NET_POLL_CONTROLLER static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { return netpoll_send_skb(slave->np, skb); } #else static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { BUG(); return NETDEV_TX_OK; } #endif static inline void bond_set_slave_inactive_flags(struct slave *slave, bool notify) { if (!bond_is_lb(slave->bond)) bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 1; } static inline void bond_set_slave_tx_disabled_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); } static inline void bond_set_slave_active_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 0; } static inline void bond_set_slave_rx_enabled_flags(struct slave *slave, bool notify) { slave->rx_disabled = 0; } static inline bool bond_is_slave_inactive(struct slave *slave) { return slave->inactive; } static inline bool bond_is_slave_rx_disabled(struct slave *slave) { return slave->rx_disabled; } static inline void bond_propose_link_state(struct slave *slave, int state) { slave->link_new_state = state; } static inline void bond_commit_link_state(struct slave *slave, bool notify) { if (slave->link_new_state == BOND_LINK_NOCHANGE) return; slave->link = slave->link_new_state; if (notify) { bond_queue_slave_event(slave); bond_lower_state_changed(slave); slave->should_notify_link = 0; } else { if (slave->should_notify_link) slave->should_notify_link = 0; else slave->should_notify_link = 1; } } static inline void bond_set_slave_link_state(struct slave *slave, int state, bool notify) { bond_propose_link_state(slave, state); bond_commit_link_state(slave, notify); } static inline void bond_slave_link_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify_link) { bond_queue_slave_event(tmp); bond_lower_state_changed(tmp); tmp->should_notify_link = 0; } } } static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) { struct in_device *in_dev; __be32 addr = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, RT_SCOPE_HOST); rcu_read_unlock(); return addr; } struct bond_net { struct net *net; /* Associated network namespace */ struct list_head dev_list; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_dir; #endif struct class_attribute class_attr_bonding_masters; }; int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); void bond_xdp_set_features(struct net_device *bond_dev); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); int bond_set_carrier(struct bonding *bond); void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); void bond_create_debugfs(void); void bond_destroy_debugfs(void); void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); void bond_netlink_fini(void); struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); const char *bond_slave_link_status(s8 link); struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level); int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); void bond_work_init_all(struct bonding *bond); #ifdef CONFIG_PROC_FS void bond_create_proc_entry(struct bonding *bond); void bond_remove_proc_entry(struct bonding *bond); void bond_create_proc_dir(struct bond_net *bn); void bond_destroy_proc_dir(struct bond_net *bn); #else static inline void bond_create_proc_entry(struct bonding *bond) { } static inline void bond_remove_proc_entry(struct bonding *bond) { } static inline void bond_create_proc_dir(struct bond_net *bn) { } static inline void bond_destroy_proc_dir(struct bond_net *bn) { } #endif static inline struct slave *bond_slave_has_mac(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; return NULL; } /* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; return false; } /* Check if the ip is present in arp ip list, or first free slot if ip == 0 * Returns -1 if not found, index if found */ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) { int i; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) if (targets[i] == ip) return i; else if (targets[i] == 0) break; return -1; } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { struct in6_addr mcaddr; int i; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { addrconf_addr_solict_mult(&targets[i], &mcaddr); if ((ipv6_addr_equal(&targets[i], ip)) || (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; } return -1; } #endif /* exported from bond_main.c */ extern unsigned int bond_net_id; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; /* exported from bond_sysfs_slave.c */ extern const struct sysfs_ops slave_sysfs_ops; /* exported from bond_3ad.c */ extern const u8 lacpdu_mcast_addr[]; static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); return NET_XMIT_DROP; } #endif /* _NET_BONDING_H */ |
| 207 204 8 204 203 204 205 204 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <linux/pidfs.h> #include <linux/seqlock.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; static int pid_max_min = RESERVED_PIDS + 1; static int pid_max_max = PID_MAX_LIMIT; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .ns.count = REFCOUNT_INIT(2), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .ns.inum = PROC_PID_INIT_INO, #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif .pid_max = PID_MAX_DEFAULT, #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); seqcount_spinlock_t pidmap_lock_seq = SEQCNT_SPINLOCK_ZERO(pidmap_lock_seq, &pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { pidfs_free_pid(pid); kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { int i; lockdep_assert_not_held(&tasklist_lock); spin_lock(&pidmap_lock); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; break; } idr_remove(&ns->idr, upid->nr); } pidfs_remove_pid(pid); spin_unlock(&pidmap_lock); call_rcu(&pid->rcu, delayed_put_pid); } void free_pids(struct pid **pids) { int tmp; /* * This can batch pidmap_lock. */ for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pids[tmp]) free_pid(pids[tmp]); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; /* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int tid = 0; int pid_max = READ_ONCE(tmp->pid_max); if (set_tid_size) { tid = set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; } idr_preload(GFP_KERNEL); spin_lock(&pidmap_lock); if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); } spin_unlock(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. */ retval = -ENOMEM; get_pid_ns(ns); refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; idr_preload(GFP_KERNEL); spin_lock(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; pidfs_add_pid(pid); for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock(&pidmap_lock); idr_preload_end(); return pid; out_unlock: spin_unlock(&pidmap_lock); idr_preload_end(); put_pid_ns(ns); out_free: spin_lock(&pidmap_lock); while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; lockdep_assert_held_write(&tasklist_lock); pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct pid **pids, struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr, *pid; int tmp; lockdep_assert_held_write(&tasklist_lock); pid_ptr = task_pid_ptr(task, type); pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; WARN_ON(pids[type]); pids[type] = pid; } void detach_pid(struct pid **pids, struct task_struct *task, enum pid_type type) { __change_pid(pids, task, type, NULL); } void change_pid(struct pid **pids, struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(pids, task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; lockdep_assert_held_write(&tasklist_lock); /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { WARN_ON_ONCE(type == PIDTYPE_PID); lockdep_assert_held_write(&tasklist_lock); hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } EXPORT_SYMBOL_GPL(find_ge_pid); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { CLASS(fd, f)(fd); struct pid *pid; if (fd_empty(f)) return ERR_PTR(-EBADF); pid = pidfd_pid(fd_file(f)); if (!IS_ERR(pid)) { get_pid(pid); *flags = fd_file(f)->f_flags; } return pid; } /** * pidfd_get_task() - Get the task associated with a pidfd * * @pidfd: pidfd for which to get the task * @flags: flags associated with this pidfd * * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) { unsigned int f_flags = 0; struct pid *pid; struct task_struct *task; enum pid_type type; switch (pidfd) { case PIDFD_SELF_THREAD: type = PIDTYPE_PID; pid = get_task_pid(current, type); break; case PIDFD_SELF_THREAD_GROUP: type = PIDTYPE_TGID; pid = get_task_pid(current, type); break; default: pid = pidfd_get_pid(pidfd, &f_flags); if (IS_ERR(pid)) return ERR_CAST(pid); type = PIDTYPE_TGID; break; } task = get_pid_task(pid, type); put_pid(pid); if (!task) return ERR_PTR(-ESRCH); *flags = f_flags; return task; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ static int pidfd_create(struct pid *pid, unsigned int flags) { int pidfd; struct file *pidfd_file; pidfd = pidfd_prepare(pid, flags, &pidfd_file); if (pidfd < 0) return pidfd; fd_install(pidfd, pidfd_file); return pidfd; } /** * sys_pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the task identified by @pid. Without PIDFD_THREAD flag the target task * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } #ifdef CONFIG_SYSCTL static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root) { return &task_active_pid_ns(current)->set; } static int set_is_seen(struct ctl_table_set *set) { return &task_active_pid_ns(current)->set == set; } static int pid_table_root_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct pid_namespace *pidns = container_of(head->set, struct pid_namespace, set); int mode = table->mode; if (ns_capable(pidns->user_ns, CAP_SYS_ADMIN) || uid_eq(current_euid(), make_kuid(pidns->user_ns, 0))) mode = (mode & S_IRWXU) >> 6; else if (in_egroup_p(make_kgid(pidns->user_ns, 0))) mode = (mode & S_IRWXG) >> 3; else mode = mode & S_IROTH; return (mode << 6) | (mode << 3) | mode; } static void pid_table_root_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct pid_namespace *pidns = container_of(head->set, struct pid_namespace, set); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(pidns->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(pidns->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root pid_table_root = { .lookup = pid_table_root_lookup, .permissions = pid_table_root_permissions, .set_ownership = pid_table_root_set_ownership, }; static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct pid *new_pid; pid_t tmp_pid; int r; struct ctl_table tmp_table = *table; tmp_pid = pid_vnr(cad_pid); tmp_table.data = &tmp_pid; r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); if (r || !write) return r; new_pid = find_get_pid(tmp_pid); if (!new_pid) return -ESRCH; put_pid(xchg(&cad_pid, new_pid)); return 0; } static const struct ctl_table pid_table[] = { { .procname = "pid_max", .data = &init_pid_ns.pid_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &pid_max_min, .extra2 = &pid_max_max, }, #ifdef CONFIG_PROC_SYSCTL { .procname = "cad_pid", .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_do_cad_pid, }, #endif }; #endif int register_pidns_sysctls(struct pid_namespace *pidns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen); tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL); if (!tbl) return -ENOMEM; tbl->data = &pidns->pid_max; pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl, ARRAY_SIZE(pid_table)); if (!pidns->sysctls) { kfree(tbl); retire_sysctl_set(&pidns->set); return -ENOMEM; } #endif return 0; } void unregister_pidns_sysctls(struct pid_namespace *pidns) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; tbl = pidns->sysctls->ctl_table_arg; unregister_sysctl_table(pidns->sysctls); retire_sysctl_set(&pidns->set); kfree(tbl); #endif } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = kmem_cache_create("pid", struct_size_t(struct pid, numbers, 1), __alignof__(struct pid), SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); } static __init int pid_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL /* "kernel" directory will have already been initialized. */ BUG_ON(register_pidns_sysctls(&init_pid_ns)); #endif return 0; } subsys_initcall(pid_namespace_sysctl_init); static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); if (!file) { /* * It is possible that the target thread is exiting; it can be * either: * 1. before exit_signals(), which gives a real fd * 2. before exit_files() takes the task_lock() gives a real fd * 3. after exit_files() releases task_lock(), ->files is NULL; * this has PF_EXITING, since it was set in exit_signals(), * __pidfd_fget() returns EBADF. * In case 3 we get EBADF, but that really means ESRCH, since * the task is currently exiting and has freed its files * struct, so we fix it up. */ if (task->flags & PF_EXITING) file = ERR_PTR(-ESRCH); else file = ERR_PTR(-EBADF); } return file; } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, NULL, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; CLASS(fd, f)(pidfd); if (fd_empty(f)) return -EBADF; pid = pidfd_pid(fd_file(f)); if (IS_ERR(pid)) return PTR_ERR(pid); return pidfd_getfd(pid, fd); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 5 4 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 | // SPDX-License-Identifier: GPL-2.0-only #include <net/netdev_lock.h> #include <net/netdev_queues.h> #include <net/sock.h> #include <linux/ethtool_netlink.h> #include <linux/phy_link_topology.h> #include <linux/pm_runtime.h> #include "netlink.h" #include "module_fw.h" static struct genl_family ethtool_genl_family; static bool ethnl_ok __read_mostly; static u32 ethnl_bcast_seq; #define ETHTOOL_FLAGS_BASIC (ETHTOOL_FLAG_COMPACT_BITSETS | \ ETHTOOL_FLAG_OMIT_REPLY) #define ETHTOOL_FLAGS_STATS (ETHTOOL_FLAGS_BASIC | ETHTOOL_FLAG_STATS) const struct nla_policy ethnl_header_policy[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_BASIC), }; const struct nla_policy ethnl_header_policy_stats[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_STATS), }; const struct nla_policy ethnl_header_policy_phy[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_BASIC), [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; const struct nla_policy ethnl_header_policy_phy_stats[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_STATS), [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid, enum ethnl_sock_type type) { struct ethnl_sock_priv *sk_priv; sk_priv = genl_sk_priv_get(ðtool_genl_family, NETLINK_CB(skb).sk); if (IS_ERR(sk_priv)) return PTR_ERR(sk_priv); sk_priv->dev = dev; sk_priv->portid = portid; sk_priv->type = type; return 0; } static void ethnl_sock_priv_destroy(void *priv) { struct ethnl_sock_priv *sk_priv = priv; switch (sk_priv->type) { case ETHTOOL_SOCK_TYPE_MODULE_FW_FLASH: ethnl_module_fw_flash_sock_destroy(sk_priv); break; default: break; } } u32 ethnl_bcast_seq_next(void) { ASSERT_RTNL(); return ++ethnl_bcast_seq; } int ethnl_ops_begin(struct net_device *dev) { int ret; if (!dev) return -ENODEV; if (dev->dev.parent) pm_runtime_get_sync(dev->dev.parent); netdev_ops_assert_locked(dev); if (!netif_device_present(dev) || dev->reg_state >= NETREG_UNREGISTERING) { ret = -ENODEV; goto err; } if (dev->ethtool_ops->begin) { ret = dev->ethtool_ops->begin(dev); if (ret) goto err; } return 0; err: if (dev->dev.parent) pm_runtime_put(dev->dev.parent); return ret; } void ethnl_ops_complete(struct net_device *dev) { if (dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); if (dev->dev.parent) pm_runtime_put(dev->dev.parent); } /** * ethnl_parse_header_dev_get() - parse request header * @req_info: structure to put results into * @header: nest attribute with request header * @net: request netns * @extack: netlink extack for error reporting * @require_dev: fail if no device identified in header * * Parse request header in nested attribute @nest and puts results into * the structure pointed to by @req_info. Extack from @info is used for error * reporting. If req_info->dev is not null on return, reference to it has * been taken. If error is returned, *req_info is null initialized and no * reference is held. * * Return: 0 on success or negative error code */ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)]; const struct nlattr *devname_attr; struct net_device *dev = NULL; u32 flags = 0; int ret; if (!header) { if (!require_dev) return 0; NL_SET_ERR_MSG(extack, "request header missing"); return -EINVAL; } /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header, NULL, extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_HEADER_FLAGS]) flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]); devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME]; if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) { u32 ifindex = nla_get_u32(tb[ETHTOOL_A_HEADER_DEV_INDEX]); dev = netdev_get_by_index(net, ifindex, &req_info->dev_tracker, GFP_KERNEL); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_HEADER_DEV_INDEX], "no device matches ifindex"); return -ENODEV; } /* if both ifindex and ifname are passed, they must match */ if (devname_attr && strncmp(dev->name, nla_data(devname_attr), IFNAMSIZ)) { netdev_put(dev, &req_info->dev_tracker); NL_SET_ERR_MSG_ATTR(extack, header, "ifindex and name do not match"); return -ENODEV; } } else if (devname_attr) { dev = netdev_get_by_name(net, nla_data(devname_attr), &req_info->dev_tracker, GFP_KERNEL); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, devname_attr, "no device matches name"); return -ENODEV; } } else if (require_dev) { NL_SET_ERR_MSG_ATTR(extack, header, "neither ifindex nor name specified"); return -EINVAL; } if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { if (dev) { req_info->phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]); } else { NL_SET_ERR_MSG_ATTR(extack, header, "phy_index set without a netdev"); return -EINVAL; } } req_info->dev = dev; req_info->flags = flags; return 0; } struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, struct nlattr **tb, unsigned int header, struct netlink_ext_ack *extack) { struct phy_device *phydev; ASSERT_RTNL(); if (!req_info->dev) return NULL; if (!req_info->phy_index) return req_info->dev->phydev; phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index); if (!phydev && tb) { NL_SET_ERR_MSG_ATTR(extack, tb[header], "no phy matching phyindex"); return ERR_PTR(-ENODEV); } return phydev; } /** * ethnl_fill_reply_header() - Put common header into a reply message * @skb: skb with the message * @dev: network device to describe in header * @attrtype: attribute type to use for the nest * * Create a nested attribute with attributes describing given network device. * * Return: 0 on success, error value (-EMSGSIZE only) on error */ int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, u16 attrtype) { struct nlattr *nest; if (!dev) return 0; nest = nla_nest_start(skb, attrtype); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_HEADER_DEV_INDEX, (u32)dev->ifindex) || nla_put_string(skb, ETHTOOL_A_HEADER_DEV_NAME, dev->name)) goto nla_put_failure; /* If more attributes are put into reply header, ethnl_header_size() * must be updated to account for them. */ nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } /** * ethnl_reply_init() - Create skb for a reply and fill device identification * @payload: payload length (without netlink and genetlink header) * @dev: device the reply is about (may be null) * @cmd: ETHTOOL_MSG_* message type for reply * @hdr_attrtype: attribute type for common header * @info: genetlink info of the received packet we respond to * @ehdrp: place to store payload pointer returned by genlmsg_new() * * Return: pointer to allocated skb on success, NULL on error */ struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, u16 hdr_attrtype, struct genl_info *info, void **ehdrp) { struct sk_buff *skb; skb = genlmsg_new(payload, GFP_KERNEL); if (!skb) goto err; *ehdrp = genlmsg_put_reply(skb, info, ðtool_genl_family, 0, cmd); if (!*ehdrp) goto err_free; if (dev) { int ret; ret = ethnl_fill_reply_header(skb, dev, hdr_attrtype); if (ret < 0) goto err_free; } return skb; err_free: nlmsg_free(skb); err: if (info) GENL_SET_ERR_MSG(info, "failed to setup reply message"); return NULL; } void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd) { return genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, ðtool_genl_family, 0, cmd); } void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd) { return genlmsg_put(skb, 0, ++ethnl_bcast_seq, ðtool_genl_family, 0, cmd); } void *ethnl_unicast_put(struct sk_buff *skb, u32 portid, u32 seq, u8 cmd) { return genlmsg_put(skb, portid, seq, ðtool_genl_family, 0, cmd); } int ethnl_multicast(struct sk_buff *skb, struct net_device *dev) { return genlmsg_multicast_netns(ðtool_genl_family, dev_net(dev), skb, 0, ETHNL_MCGRP_MONITOR, GFP_KERNEL); } /* GET request helpers */ /** * struct ethnl_dump_ctx - context structure for generic dumpit() callback * @ops: request ops of currently processed message type * @req_info: parsed request header of processed request * @reply_data: data needed to compose the reply * @pos_ifindex: saved iteration position - ifindex * * These parameters are kept in struct netlink_callback as context preserved * between iterations. They are initialized by ethnl_default_start() and used * in ethnl_default_dumpit() and ethnl_default_done(). */ struct ethnl_dump_ctx { const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct ethnl_reply_data *reply_data; unsigned long pos_ifindex; }; /** * struct ethnl_perphy_dump_ctx - context for dumpit() PHY-aware callbacks * @ethnl_ctx: generic ethnl context * @ifindex: For Filtered DUMP requests, the ifindex of the targeted netdev * @pos_phyindex: iterator position for multi-msg DUMP */ struct ethnl_perphy_dump_ctx { struct ethnl_dump_ctx ethnl_ctx; unsigned int ifindex; unsigned long pos_phyindex; }; static const struct ethnl_request_ops * ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_STRSET_GET] = ðnl_strset_request_ops, [ETHTOOL_MSG_LINKINFO_GET] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKINFO_SET] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKMODES_GET] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_LINKMODES_SET] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_LINKSTATE_GET] = ðnl_linkstate_request_ops, [ETHTOOL_MSG_DEBUG_GET] = ðnl_debug_request_ops, [ETHTOOL_MSG_DEBUG_SET] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_GET] = ðnl_wol_request_ops, [ETHTOOL_MSG_WOL_SET] = ðnl_wol_request_ops, [ETHTOOL_MSG_FEATURES_GET] = ðnl_features_request_ops, [ETHTOOL_MSG_PRIVFLAGS_GET] = ðnl_privflags_request_ops, [ETHTOOL_MSG_PRIVFLAGS_SET] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_GET] = ðnl_rings_request_ops, [ETHTOOL_MSG_RINGS_SET] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_GET] = ðnl_channels_request_ops, [ETHTOOL_MSG_CHANNELS_SET] = ðnl_channels_request_ops, [ETHTOOL_MSG_COALESCE_GET] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_COALESCE_SET] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_PAUSE_GET] = ðnl_pause_request_ops, [ETHTOOL_MSG_PAUSE_SET] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_GET] = ðnl_eee_request_ops, [ETHTOOL_MSG_EEE_SET] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_GET] = ðnl_fec_request_ops, [ETHTOOL_MSG_FEC_SET] = ðnl_fec_request_ops, [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, [ETHTOOL_MSG_MODULE_SET] = ðnl_module_request_ops, [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, [ETHTOOL_MSG_PSE_SET] = ðnl_pse_request_ops, [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, [ETHTOOL_MSG_RSS_SET] = ðnl_rss_request_ops, [ETHTOOL_MSG_PLCA_GET_CFG] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_PLCA_SET_CFG] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, [ETHTOOL_MSG_TSCONFIG_GET] = ðnl_tsconfig_request_ops, [ETHTOOL_MSG_TSCONFIG_SET] = ðnl_tsconfig_request_ops, [ETHTOOL_MSG_PHY_GET] = ðnl_phy_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) { return (struct ethnl_dump_ctx *)cb->ctx; } static struct ethnl_perphy_dump_ctx * ethnl_perphy_dump_context(struct netlink_callback *cb) { return (struct ethnl_perphy_dump_ctx *)cb->ctx; } /** * ethnl_default_parse() - Parse request message * @req_info: pointer to structure to put data into * @info: genl_info from the request * @request_ops: struct request_ops for request type * @require_dev: fail if no device identified in header * * Parse universal request header and call request specific ->parse_request() * callback (if defined) to parse the rest of the message. * * Return: 0 on success or negative error code */ static int ethnl_default_parse(struct ethnl_req_info *req_info, const struct genl_info *info, const struct ethnl_request_ops *request_ops, bool require_dev) { struct nlattr **tb = info->attrs; int ret; ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr], genl_info_net(info), info->extack, require_dev); if (ret < 0) return ret; if (request_ops->parse_request) { ret = request_ops->parse_request(req_info, tb, info->extack); if (ret < 0) goto err_dev; } return 0; err_dev: netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; return ret; } /** * ethnl_init_reply_data() - Initialize reply data for GET request * @reply_data: pointer to embedded struct ethnl_reply_data * @ops: instance of struct ethnl_request_ops describing the layout * @dev: network device to initialize the reply for * * Fills the reply data part with zeros and sets the dev member. Must be called * before calling the ->fill_reply() callback (for each iteration when handling * dump requests). */ static void ethnl_init_reply_data(struct ethnl_reply_data *reply_data, const struct ethnl_request_ops *ops, struct net_device *dev) { memset(reply_data, 0, ops->reply_data_size); reply_data->dev = dev; } /* default ->doit() handler for GET type requests */ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) { struct ethnl_reply_data *reply_data = NULL; struct ethnl_req_info *req_info = NULL; const u8 cmd = info->genlhdr->cmd; const struct ethnl_request_ops *ops; int hdr_len, reply_len; struct sk_buff *rskb; void *reply_payload; int ret; ops = ethnl_default_requests[cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", cmd)) return -EOPNOTSUPP; if (GENL_REQ_ATTR_CHECK(info, ops->hdr_attr)) return -EINVAL; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { kfree(req_info); return -ENOMEM; } ret = ethnl_default_parse(req_info, info, ops, !ops->allow_nodev_do); if (ret < 0) goto err_free; ethnl_init_reply_data(reply_data, ops, req_info->dev); rtnl_lock(); if (req_info->dev) netdev_lock_ops(req_info->dev); ret = ops->prepare_data(req_info, reply_data, info); if (req_info->dev) netdev_unlock_ops(req_info->dev); rtnl_unlock(); if (ret < 0) goto err_dev; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; reply_len = ret; ret = -ENOMEM; rskb = ethnl_reply_init(reply_len + ethnl_reply_header_size(), req_info->dev, ops->reply_cmd, ops->hdr_attr, info, &reply_payload); if (!rskb) goto err_cleanup; hdr_len = rskb->len; ret = ops->fill_reply(rskb, req_info, reply_data); if (ret < 0) goto err_msg; WARN_ONCE(rskb->len - hdr_len > reply_len, "ethnl cmd %d: calculated reply length %d, but consumed %d\n", cmd, reply_len, rskb->len - hdr_len); if (ops->cleanup_data) ops->cleanup_data(reply_data); genlmsg_end(rskb, reply_payload); netdev_put(req_info->dev, &req_info->dev_tracker); kfree(reply_data); kfree(req_info); return genlmsg_reply(rskb, info); err_msg: WARN_ONCE(ret == -EMSGSIZE, "calculated message payload length (%d) not sufficient\n", reply_len); nlmsg_free(rskb); err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); err_dev: netdev_put(req_info->dev, &req_info->dev_tracker); err_free: kfree(reply_data); kfree(req_info); return ret; } static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, const struct ethnl_dump_ctx *ctx, const struct genl_info *info) { void *ehdr; int ret; ehdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, ðtool_genl_family, NLM_F_MULTI, ctx->ops->reply_cmd); if (!ehdr) return -EMSGSIZE; ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev); rtnl_lock(); netdev_lock_ops(dev); ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, info); netdev_unlock_ops(dev); rtnl_unlock(); if (ret < 0) goto out_cancel; ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr); if (ret < 0) goto out; ret = ctx->ops->fill_reply(skb, ctx->req_info, ctx->reply_data); out: if (ctx->ops->cleanup_data) ctx->ops->cleanup_data(ctx->reply_data); out_cancel: ctx->reply_data->dev = NULL; if (ret < 0) genlmsg_cancel(skb, ehdr); else genlmsg_end(skb, ehdr); return ret; } /* Default ->dumpit() handler for GET requests. */ static int ethnl_default_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct net *net = sock_net(skb->sk); netdevice_tracker dev_tracker; struct net_device *dev; int ret = 0; rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->pos_ifindex) { netdev_hold(dev, &dev_tracker, GFP_ATOMIC); rcu_read_unlock(); ret = ethnl_default_dump_one(skb, dev, ctx, genl_info_dump(cb)); rcu_read_lock(); netdev_put(dev, &dev_tracker); if (ret < 0 && ret != -EOPNOTSUPP) { if (likely(skb->len)) ret = skb->len; break; } ret = 0; } rcu_read_unlock(); return ret; } /* generic ->start() handler for GET requests */ static int ethnl_default_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct genlmsghdr *ghdr; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); ghdr = nlmsg_data(cb->nlh); ops = ethnl_default_requests[ghdr->cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", ghdr->cmd)) return -EOPNOTSUPP; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { ret = -ENOMEM; goto free_req_info; } ret = ethnl_default_parse(req_info, &info->info, ops, false); if (ret < 0) goto free_reply_data; if (req_info->dev) { /* We ignore device specification in dump requests but as the * same parser as for non-dump (doit) requests is used, it * would take reference to the device if it finds one */ netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } ctx->ops = ops; ctx->req_info = req_info; ctx->reply_data = reply_data; ctx->pos_ifindex = 0; return 0; free_reply_data: kfree(reply_data); free_req_info: kfree(req_info); return ret; } /* per-PHY ->start() handler for GET requests */ static int ethnl_perphy_start(struct netlink_callback *cb) { struct ethnl_perphy_dump_ctx *phy_ctx = ethnl_perphy_dump_context(cb); const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ctx = &phy_ctx->ethnl_ctx; struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct genlmsghdr *ghdr; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); ghdr = nlmsg_data(cb->nlh); ops = ethnl_default_requests[ghdr->cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", ghdr->cmd)) return -EOPNOTSUPP; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { ret = -ENOMEM; goto free_req_info; } /* Unlike per-dev dump, don't ignore dev. The dump handler * will notice it and dump PHYs from given dev. We only keep track of * the dev's ifindex, .dumpit() will grab and release the netdev itself. */ ret = ethnl_default_parse(req_info, &info->info, ops, false); if (ret < 0) goto free_reply_data; if (req_info->dev) { phy_ctx->ifindex = req_info->dev->ifindex; netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } ctx->ops = ops; ctx->req_info = req_info; ctx->reply_data = reply_data; ctx->pos_ifindex = 0; return 0; free_reply_data: kfree(reply_data); free_req_info: kfree(req_info); return ret; } static int ethnl_perphy_dump_one_dev(struct sk_buff *skb, struct ethnl_perphy_dump_ctx *ctx, const struct genl_info *info) { struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; struct net_device *dev = ethnl_ctx->req_info->dev; struct phy_device_node *pdn; int ret; if (!dev->link_topo) return 0; xa_for_each_start(&dev->link_topo->phys, ctx->pos_phyindex, pdn, ctx->pos_phyindex) { ethnl_ctx->req_info->phy_index = ctx->pos_phyindex; /* We can re-use the original dump_one as ->prepare_data in * commands use ethnl_req_get_phydev(), which gets the PHY from * the req_info->phy_index */ ret = ethnl_default_dump_one(skb, dev, ethnl_ctx, info); if (ret) return ret; } ctx->pos_phyindex = 0; return 0; } static int ethnl_perphy_dump_all_dev(struct sk_buff *skb, struct ethnl_perphy_dump_ctx *ctx, const struct genl_info *info) { struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; struct net *net = sock_net(skb->sk); netdevice_tracker dev_tracker; struct net_device *dev; int ret = 0; rcu_read_lock(); for_each_netdev_dump(net, dev, ethnl_ctx->pos_ifindex) { netdev_hold(dev, &dev_tracker, GFP_ATOMIC); rcu_read_unlock(); /* per-PHY commands use ethnl_req_get_phydev(), which needs the * net_device in the req_info */ ethnl_ctx->req_info->dev = dev; ret = ethnl_perphy_dump_one_dev(skb, ctx, info); rcu_read_lock(); netdev_put(dev, &dev_tracker); ethnl_ctx->req_info->dev = NULL; if (ret < 0 && ret != -EOPNOTSUPP) { if (likely(skb->len)) ret = skb->len; break; } ret = 0; } rcu_read_unlock(); return ret; } /* per-PHY ->dumpit() handler for GET requests. */ static int ethnl_perphy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_perphy_dump_ctx *ctx = ethnl_perphy_dump_context(cb); const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; int ret = 0; if (ctx->ifindex) { netdevice_tracker dev_tracker; struct net_device *dev; dev = netdev_get_by_index(genl_info_net(&info->info), ctx->ifindex, &dev_tracker, GFP_KERNEL); if (!dev) return -ENODEV; ethnl_ctx->req_info->dev = dev; ret = ethnl_perphy_dump_one_dev(skb, ctx, genl_info_dump(cb)); if (ret < 0 && ret != -EOPNOTSUPP && likely(skb->len)) ret = skb->len; netdev_put(dev, &dev_tracker); } else { ret = ethnl_perphy_dump_all_dev(skb, ctx, genl_info_dump(cb)); } return ret; } /* per-PHY ->done() handler for GET requests */ static int ethnl_perphy_done(struct netlink_callback *cb) { struct ethnl_perphy_dump_ctx *ctx = ethnl_perphy_dump_context(cb); struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; kfree(ethnl_ctx->reply_data); kfree(ethnl_ctx->req_info); return 0; } /* default ->done() handler for GET requests */ static int ethnl_default_done(struct netlink_callback *cb) { struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); kfree(ctx->reply_data); kfree(ctx->req_info); return 0; } static int ethnl_default_set_doit(struct sk_buff *skb, struct genl_info *info) { const struct ethnl_request_ops *ops; const u8 cmd = info->genlhdr->cmd; struct ethnl_req_info *req_info; struct net_device *dev; int ret; ops = ethnl_default_requests[cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", cmd)) return -EOPNOTSUPP; if (GENL_REQ_ATTR_CHECK(info, ops->hdr_attr)) return -EINVAL; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; ret = ethnl_default_parse(req_info, info, ops, true); if (ret < 0) goto out_free_req; if (ops->set_validate) { ret = ops->set_validate(req_info, info); /* 0 means nothing to do */ if (ret <= 0) goto out_dev; } dev = req_info->dev; rtnl_lock(); netdev_lock_ops(dev); dev->cfg_pending = kmemdup(dev->cfg, sizeof(*dev->cfg), GFP_KERNEL_ACCOUNT); if (!dev->cfg_pending) { ret = -ENOMEM; goto out_tie_cfg; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out_free_cfg; ret = ops->set(req_info, info); if (ret < 0) goto out_ops; swap(dev->cfg, dev->cfg_pending); if (!ret) goto out_ops; ethnl_notify(dev, ops->set_ntf_cmd, req_info); ret = 0; out_ops: ethnl_ops_complete(dev); out_free_cfg: kfree(dev->cfg_pending); out_tie_cfg: dev->cfg_pending = dev->cfg; netdev_unlock_ops(dev); rtnl_unlock(); out_dev: ethnl_parse_header_dev_put(req_info); out_free_req: kfree(req_info); return ret; } static const struct ethnl_request_ops * ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_LINKINFO_NTF] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKMODES_NTF] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_DEBUG_NTF] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_NTF] = ðnl_wol_request_ops, [ETHTOOL_MSG_FEATURES_NTF] = ðnl_features_request_ops, [ETHTOOL_MSG_PRIVFLAGS_NTF] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_NTF] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_NTF] = ðnl_channels_request_ops, [ETHTOOL_MSG_COALESCE_NTF] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_PAUSE_NTF] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, [ETHTOOL_MSG_PLCA_NTF] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_MM_NTF] = ðnl_mm_request_ops, [ETHTOOL_MSG_RSS_NTF] = ðnl_rss_request_ops, [ETHTOOL_MSG_RSS_CREATE_NTF] = ðnl_rss_request_ops, }; /* default notification handler */ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, const struct ethnl_req_info *orig_req_info) { struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct genl_info info; struct sk_buff *skb; void *reply_payload; int reply_len; int ret; genl_info_init_ntf(&info, ðtool_genl_family, cmd); if (WARN_ONCE(cmd > ETHTOOL_MSG_KERNEL_MAX || !ethnl_default_notify_ops[cmd], "unexpected notification type %u\n", cmd)) return; ops = ethnl_default_notify_ops[cmd]; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { kfree(req_info); return; } req_info->dev = dev; req_info->flags |= ETHTOOL_FLAG_COMPACT_BITSETS; if (orig_req_info) { req_info->phy_index = orig_req_info->phy_index; memcpy(&req_info[1], &orig_req_info[1], ops->req_info_size - sizeof(*req_info)); } netdev_ops_assert_locked(dev); ethnl_init_reply_data(reply_data, ops, dev); ret = ops->prepare_data(req_info, reply_data, &info); if (ret < 0) goto err_rep; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; reply_len = ret + ethnl_reply_header_size(); skb = genlmsg_new(reply_len, GFP_KERNEL); if (!skb) goto err_cleanup; reply_payload = ethnl_bcastmsg_put(skb, cmd); if (!reply_payload) goto err_skb; ret = ethnl_fill_reply_header(skb, dev, ops->hdr_attr); if (ret < 0) goto err_msg; ret = ops->fill_reply(skb, req_info, reply_data); if (ret < 0) goto err_msg; if (ops->cleanup_data) ops->cleanup_data(reply_data); genlmsg_end(skb, reply_payload); kfree(reply_data); kfree(req_info); ethnl_multicast(skb, dev); return; err_msg: WARN_ONCE(ret == -EMSGSIZE, "calculated message payload length (%d) not sufficient\n", reply_len); err_skb: nlmsg_free(skb); err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); err_rep: kfree(reply_data); kfree(req_info); return; } /* notifications */ typedef void (*ethnl_notify_handler_t)(struct net_device *dev, unsigned int cmd, const struct ethnl_req_info *req_info); static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_LINKINFO_NTF] = ethnl_default_notify, [ETHTOOL_MSG_LINKMODES_NTF] = ethnl_default_notify, [ETHTOOL_MSG_DEBUG_NTF] = ethnl_default_notify, [ETHTOOL_MSG_WOL_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEATURES_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PRIVFLAGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RINGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_CHANNELS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_COALESCE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PAUSE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PLCA_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MM_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RSS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RSS_CREATE_NTF] = ethnl_default_notify, }; void ethnl_notify(struct net_device *dev, unsigned int cmd, const struct ethnl_req_info *req_info) { if (unlikely(!ethnl_ok)) return; ASSERT_RTNL(); if (likely(cmd < ARRAY_SIZE(ethnl_notify_handlers) && ethnl_notify_handlers[cmd])) ethnl_notify_handlers[cmd](dev, cmd, req_info); else WARN_ONCE(1, "notification %u not implemented (dev=%s)\n", cmd, netdev_name(dev)); } void ethtool_notify(struct net_device *dev, unsigned int cmd) { ethnl_notify(dev, cmd, NULL); } EXPORT_SYMBOL(ethtool_notify); static void ethnl_notify_features(struct netdev_notifier_info *info) { struct net_device *dev = netdev_notifier_info_to_dev(info); ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF); } static int ethnl_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *info = ptr; struct netlink_ext_ack *extack; struct net_device *dev; dev = netdev_notifier_info_to_dev(info); extack = netdev_notifier_info_to_extack(info); switch (event) { case NETDEV_FEAT_CHANGE: ethnl_notify_features(ptr); break; case NETDEV_PRE_UP: if (dev->ethtool->module_fw_flash_in_progress) { NL_SET_ERR_MSG(extack, "Can't set port up while flashing module firmware"); return NOTIFY_BAD; } } return NOTIFY_DONE; } static struct notifier_block ethnl_netdev_notifier = { .notifier_call = ethnl_netdev_event, }; /* genetlink setup */ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_STRSET_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_strset_get_policy, .maxattr = ARRAY_SIZE(ethnl_strset_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_linkinfo_set_policy, .maxattr = ARRAY_SIZE(ethnl_linkinfo_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkmodes_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkmodes_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_linkmodes_set_policy, .maxattr = ARRAY_SIZE(ethnl_linkmodes_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKSTATE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkstate_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkstate_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_debug_get_policy, .maxattr = ARRAY_SIZE(ethnl_debug_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_debug_set_policy, .maxattr = ARRAY_SIZE(ethnl_debug_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_GET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_wol_get_policy, .maxattr = ARRAY_SIZE(ethnl_wol_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_wol_set_policy, .maxattr = ARRAY_SIZE(ethnl_wol_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_features_get_policy, .maxattr = ARRAY_SIZE(ethnl_features_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_features, .policy = ethnl_features_set_policy, .maxattr = ARRAY_SIZE(ethnl_features_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_privflags_get_policy, .maxattr = ARRAY_SIZE(ethnl_privflags_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_privflags_set_policy, .maxattr = ARRAY_SIZE(ethnl_privflags_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_rings_get_policy, .maxattr = ARRAY_SIZE(ethnl_rings_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_rings_set_policy, .maxattr = ARRAY_SIZE(ethnl_rings_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_channels_get_policy, .maxattr = ARRAY_SIZE(ethnl_channels_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_channels_set_policy, .maxattr = ARRAY_SIZE(ethnl_channels_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_coalesce_get_policy, .maxattr = ARRAY_SIZE(ethnl_coalesce_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_coalesce_set_policy, .maxattr = ARRAY_SIZE(ethnl_coalesce_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_pause_get_policy, .maxattr = ARRAY_SIZE(ethnl_pause_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_pause_set_policy, .maxattr = ARRAY_SIZE(ethnl_pause_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_eee_get_policy, .maxattr = ARRAY_SIZE(ethnl_eee_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_eee_set_policy, .maxattr = ARRAY_SIZE(ethnl_eee_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSINFO_GET, .doit = ethnl_default_doit, .start = ethnl_tsinfo_start, .dumpit = ethnl_tsinfo_dumpit, .done = ethnl_tsinfo_done, .policy = ethnl_tsinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_tsinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test, .policy = ethnl_cable_test_act_policy, .maxattr = ARRAY_SIZE(ethnl_cable_test_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_TDR_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test_tdr, .policy = ethnl_cable_test_tdr_act_policy, .maxattr = ARRAY_SIZE(ethnl_cable_test_tdr_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_TUNNEL_INFO_GET, .doit = ethnl_tunnel_info_doit, .start = ethnl_tunnel_info_start, .dumpit = ethnl_tunnel_info_dumpit, .policy = ethnl_tunnel_info_get_policy, .maxattr = ARRAY_SIZE(ethnl_tunnel_info_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEC_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_fec_get_policy, .maxattr = ARRAY_SIZE(ethnl_fec_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEC_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_fec_set_policy, .maxattr = ARRAY_SIZE(ethnl_fec_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_EEPROM_GET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_module_eeprom_get_policy, .maxattr = ARRAY_SIZE(ethnl_module_eeprom_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_STATS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_stats_get_policy, .maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_phc_vclocks_get_policy, .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_module_get_policy, .maxattr = ARRAY_SIZE(ethnl_module_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_module_set_policy, .maxattr = ARRAY_SIZE(ethnl_module_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PSE_GET, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_pse_get_policy, .maxattr = ARRAY_SIZE(ethnl_pse_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PSE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_pse_set_policy, .maxattr = ARRAY_SIZE(ethnl_pse_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_GET, .doit = ethnl_default_doit, .start = ethnl_rss_dump_start, .dumpit = ethnl_rss_dumpit, .policy = ethnl_rss_get_policy, .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PLCA_GET_CFG, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_plca_get_cfg_policy, .maxattr = ARRAY_SIZE(ethnl_plca_get_cfg_policy) - 1, }, { .cmd = ETHTOOL_MSG_PLCA_SET_CFG, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_plca_set_cfg_policy, .maxattr = ARRAY_SIZE(ethnl_plca_set_cfg_policy) - 1, }, { .cmd = ETHTOOL_MSG_PLCA_GET_STATUS, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_plca_get_status_policy, .maxattr = ARRAY_SIZE(ethnl_plca_get_status_policy) - 1, }, { .cmd = ETHTOOL_MSG_MM_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_mm_get_policy, .maxattr = ARRAY_SIZE(ethnl_mm_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MM_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_mm_set_policy, .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_FW_FLASH_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_module_fw_flash, .policy = ethnl_module_fw_flash_act_policy, .maxattr = ARRAY_SIZE(ethnl_module_fw_flash_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_PHY_GET, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_phy_get_policy, .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSCONFIG_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_tsconfig_get_policy, .maxattr = ARRAY_SIZE(ethnl_tsconfig_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSCONFIG_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_tsconfig_set_policy, .maxattr = ARRAY_SIZE(ethnl_tsconfig_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_rss_set_policy, .maxattr = ARRAY_SIZE(ethnl_rss_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_CREATE_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_rss_create_doit, .policy = ethnl_rss_create_policy, .maxattr = ARRAY_SIZE(ethnl_rss_create_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_DELETE_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_rss_delete_doit, .policy = ethnl_rss_delete_policy, .maxattr = ARRAY_SIZE(ethnl_rss_delete_policy) - 1, }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { [ETHNL_MCGRP_MONITOR] = { .name = ETHTOOL_MCGRP_MONITOR_NAME }, }; static struct genl_family ethtool_genl_family __ro_after_init = { .name = ETHTOOL_GENL_NAME, .version = ETHTOOL_GENL_VERSION, .netnsok = true, .parallel_ops = true, .ops = ethtool_genl_ops, .n_ops = ARRAY_SIZE(ethtool_genl_ops), .resv_start_op = ETHTOOL_MSG_MODULE_GET + 1, .mcgrps = ethtool_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(ethtool_nl_mcgrps), .sock_priv_size = sizeof(struct ethnl_sock_priv), .sock_priv_destroy = ethnl_sock_priv_destroy, }; /* module setup */ static int __init ethnl_init(void) { int ret; ret = genl_register_family(ðtool_genl_family); if (WARN(ret < 0, "ethtool: genetlink family registration failed")) return ret; ethnl_ok = true; ret = register_netdevice_notifier(ðnl_netdev_notifier); WARN(ret < 0, "ethtool: net device notifier registration failed"); return ret; } subsys_initcall(ethnl_init); |
| 283 539 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ASM__VIRT_H #define __ASM__VIRT_H /* * The arm64 hcall implementation uses x0 to specify the hcall * number. A value less than HVC_STUB_HCALL_NR indicates a special * hcall, such as set vector. Any other value is handled in a * hypervisor specific way. * * The hypercall is allowed to clobber any of the caller-saved * registers (x0-x18), so it is advisable to use it through the * indirection of a function call (as implemented in hyp-stub.S). */ /* * HVC_SET_VECTORS - Set the value of the vbar_el2 register. * * @x1: Physical address of the new vector table. */ #define HVC_SET_VECTORS 0 /* * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine. */ #define HVC_SOFT_RESTART 1 /* * HVC_RESET_VECTORS - Restore the vectors to the original HYP stubs */ #define HVC_RESET_VECTORS 2 /* * HVC_FINALISE_EL2 - Upgrade the CPU from EL1 to EL2, if possible */ #define HVC_FINALISE_EL2 3 /* Max number of HYP stub hypercalls */ #define HVC_STUB_HCALL_NR 4 /* Error returned when an invalid stub number is passed into x0 */ #define HVC_STUB_ERR 0xbadca11 #define BOOT_CPU_MODE_EL1 (0xe11) #define BOOT_CPU_MODE_EL2 (0xe12) /* * Flags returned together with the boot mode, but not preserved in * __boot_cpu_mode. Used by the idreg override code to work out the * boot state. */ #define BOOT_CPU_FLAG_E2H BIT_ULL(32) #ifndef __ASSEMBLY__ #include <asm/ptrace.h> #include <asm/sections.h> #include <asm/sysreg.h> #include <asm/cpufeature.h> /* * __boot_cpu_mode records what mode CPUs were booted in. * A correctly-implemented bootloader must start all CPUs in the same mode: * In this case, both 32bit halves of __boot_cpu_mode will contain the * same value (either BOOT_CPU_MODE_EL1 if booted in EL1, BOOT_CPU_MODE_EL2 if * booted in EL2). * * Should the bootloader fail to do this, the two values will be different. * This allows the kernel to flag an error when the secondaries have come up. */ extern u32 __boot_cpu_mode[2]; #define ARM64_VECTOR_TABLE_LEN SZ_2K void __hyp_set_vectors(phys_addr_t phys_vector_base); void __hyp_reset_vectors(void); bool is_kvm_arm_initialised(void); DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); static inline bool is_pkvm_initialized(void) { return IS_ENABLED(CONFIG_KVM) && static_branch_likely(&kvm_protected_mode_initialized); } /* Reports the availability of HYP mode */ static inline bool is_hyp_mode_available(void) { /* * If KVM protected mode is initialized, all CPUs must have been booted * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. */ if (is_pkvm_initialized()) return true; return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 && __boot_cpu_mode[1] == BOOT_CPU_MODE_EL2); } /* Check if the bootloader has booted CPUs in different modes */ static inline bool is_hyp_mode_mismatched(void) { /* * If KVM protected mode is initialized, all CPUs must have been booted * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1. */ if (is_pkvm_initialized()) return false; return __boot_cpu_mode[0] != __boot_cpu_mode[1]; } static __always_inline bool is_kernel_in_hyp_mode(void) { BUILD_BUG_ON(__is_defined(__KVM_NVHE_HYPERVISOR__) || __is_defined(__KVM_VHE_HYPERVISOR__)); return read_sysreg(CurrentEL) == CurrentEL_EL2; } static __always_inline bool has_vhe(void) { /* * Code only run in VHE/NVHE hyp context can assume VHE is present or * absent. Otherwise fall back to caps. * This allows the compiler to discard VHE-specific code from the * nVHE object, reducing the number of external symbol references * needed to link. */ if (is_vhe_hyp_code()) return true; else if (is_nvhe_hyp_code()) return false; else return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN); } static __always_inline bool is_protected_kvm_enabled(void) { if (is_vhe_hyp_code()) return false; else return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE); } static __always_inline bool has_hvhe(void) { if (is_vhe_hyp_code()) return false; return cpus_have_final_cap(ARM64_KVM_HVHE); } static inline bool is_hyp_nvhe(void) { return is_hyp_mode_available() && !is_kernel_in_hyp_mode(); } #endif /* __ASSEMBLY__ */ #endif /* ! __ASM__VIRT_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This is <linux/capability.h> * * Andrew G. Morgan <morgan@kernel.org> * Alexander Kjeldaas <astor@guardian.no> * with help from Aleph1, Roland Buresund and Andrew Main. * * See here for the libcap library ("POSIX draft" compliance): * * ftp://www.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.6/ */ #ifndef _LINUX_CAPABILITY_H #define _LINUX_CAPABILITY_H #include <uapi/linux/capability.h> #include <linux/uidgid.h> #include <linux/bits.h> #define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3 extern int file_caps_enabled; typedef struct { u64 val; } kernel_cap_t; /* same as vfs_ns_cap_data but in cpu endian and always filled completely */ struct cpu_vfs_cap_data { __u32 magic_etc; kuid_t rootid; kernel_cap_t permitted; kernel_cap_t inheritable; }; #define _USER_CAP_HEADER_SIZE (sizeof(struct __user_cap_header_struct)) #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) struct file; struct inode; struct dentry; struct task_struct; struct user_namespace; struct mnt_idmap; /* * CAP_FS_MASK and CAP_NFSD_MASKS: * * The fs mask is all the privileges that fsuid==0 historically meant. * At one time in the past, that included CAP_MKNOD and CAP_LINUX_IMMUTABLE. * * It has never meant setting security.* and trusted.* xattrs. * * We could also define fsmask as follows: * 1. CAP_FS_MASK is the privilege to bypass all fs-related DAC permissions * 2. The security.* and trusted.* xattrs are fs-related MAC permissions */ # define CAP_FS_MASK (BIT_ULL(CAP_CHOWN) \ | BIT_ULL(CAP_MKNOD) \ | BIT_ULL(CAP_DAC_OVERRIDE) \ | BIT_ULL(CAP_DAC_READ_SEARCH) \ | BIT_ULL(CAP_FOWNER) \ | BIT_ULL(CAP_FSETID) \ | BIT_ULL(CAP_MAC_OVERRIDE)) #define CAP_VALID_MASK (BIT_ULL(CAP_LAST_CAP+1)-1) # define CAP_EMPTY_SET ((kernel_cap_t) { 0 }) # define CAP_FULL_SET ((kernel_cap_t) { CAP_VALID_MASK }) # define CAP_FS_SET ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_LINUX_IMMUTABLE) }) # define CAP_NFSD_SET ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_SYS_RESOURCE) }) # define cap_clear(c) do { (c).val = 0; } while (0) #define cap_raise(c, flag) ((c).val |= BIT_ULL(flag)) #define cap_lower(c, flag) ((c).val &= ~BIT_ULL(flag)) #define cap_raised(c, flag) (((c).val & BIT_ULL(flag)) != 0) static inline kernel_cap_t cap_combine(const kernel_cap_t a, const kernel_cap_t b) { return (kernel_cap_t) { a.val | b.val }; } static inline kernel_cap_t cap_intersect(const kernel_cap_t a, const kernel_cap_t b) { return (kernel_cap_t) { a.val & b.val }; } static inline kernel_cap_t cap_drop(const kernel_cap_t a, const kernel_cap_t drop) { return (kernel_cap_t) { a.val &~ drop.val }; } static inline bool cap_isclear(const kernel_cap_t a) { return !a.val; } static inline bool cap_isidentical(const kernel_cap_t a, const kernel_cap_t b) { return a.val == b.val; } /* * Check if "a" is a subset of "set". * return true if ALL of the capabilities in "a" are also in "set" * cap_issubset(0101, 1111) will return true * return false if ANY of the capabilities in "a" are not in "set" * cap_issubset(1111, 0101) will return false */ static inline bool cap_issubset(const kernel_cap_t a, const kernel_cap_t set) { return !(a.val & ~set.val); } /* Used to decide between falling back on the old suser() or fsuser(). */ static inline kernel_cap_t cap_drop_fs_set(const kernel_cap_t a) { return cap_drop(a, CAP_FS_SET); } static inline kernel_cap_t cap_raise_fs_set(const kernel_cap_t a, const kernel_cap_t permitted) { return cap_combine(a, cap_intersect(permitted, CAP_FS_SET)); } static inline kernel_cap_t cap_drop_nfsd_set(const kernel_cap_t a) { return cap_drop(a, CAP_NFSD_SET); } static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a, const kernel_cap_t permitted) { return cap_combine(a, cap_intersect(permitted, CAP_NFSD_SET)); } #ifdef CONFIG_MULTIUSER extern bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap); extern bool has_capability_noaudit(struct task_struct *t, int cap); extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); extern bool ns_capable_setid(struct user_namespace *ns, int cap); #else static inline bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { return true; } static inline bool has_capability_noaudit(struct task_struct *t, int cap) { return true; } static inline bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { return true; } static inline bool capable(int cap) { return true; } static inline bool ns_capable(struct user_namespace *ns, int cap) { return true; } static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return true; } static inline bool ns_capable_setid(struct user_namespace *ns, int cap) { return true; } #endif /* CONFIG_MULTIUSER */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, struct mnt_idmap *idmap, const struct inode *inode); bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); static inline bool perfmon_capable(void) { return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN); } static inline bool bpf_capable(void) { return capable(CAP_BPF) || capable(CAP_SYS_ADMIN); } static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) { return ns_capable(ns, CAP_CHECKPOINT_RESTORE) || ns_capable(ns, CAP_SYS_ADMIN); } /* audit system wants to get cap info from files as well */ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size); #endif /* !_LINUX_CAPABILITY_H */ |
| 60 591 265 | 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> |
| 4 4 2 2 3 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/dax.h> #include <linux/overflow.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> /* * Performs necessary checks before doing a clone. * * Can adjust amount of bytes to clone via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the clone should be allowed. */ static int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; uint64_t count = *req_count; uint64_t bcount; loff_t size_in, size_out; loff_t bs = inode_out->i_sb->s_blocksize; int ret; /* The start of both ranges must be aligned to an fs block. */ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) return -EINVAL; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EINVAL; size_in = i_size_read(inode_in); size_out = i_size_read(inode_out); /* Dedupe requires both ranges to be within EOF. */ if ((remap_flags & REMAP_FILE_DEDUP) && (pos_in >= size_in || pos_in + count > size_in || pos_out >= size_out || pos_out + count > size_out)) return -EINVAL; /* Ensure the infile range is within the infile. */ if (pos_in >= size_in) return -EINVAL; count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* * If the user wanted us to link to the infile's EOF, round up to the * next block boundary for this check. * * Otherwise, make sure the count is also block-aligned, having * already confirmed the starting offsets' block alignment. */ if (pos_in + count == size_in && (!(remap_flags & REMAP_FILE_DEDUP) || pos_out + count == size_out)) { bcount = ALIGN(size_in, bs) - pos_in; } else { if (!IS_ALIGNED(count, bs)) count = ALIGN_DOWN(count, bs); bcount = count; } /* Don't allow overlapped cloning within the same file. */ if (inode_in == inode_out && pos_out + bcount > pos_in && pos_out < pos_in + bcount) return -EINVAL; /* * We shortened the request but the caller can't deal with that, so * bounce the request back to userspace. */ if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) return -EINVAL; *req_count = count; return 0; } int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write) { int mask = write ? MAY_WRITE : MAY_READ; loff_t tmp; int ret; if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely(check_add_overflow(pos, len, &tmp))) return -EINVAL; ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, &pos, len); } EXPORT_SYMBOL_GPL(remap_verify_area); /* * Ensure that we don't remap a partial EOF block in the middle of something * else. Assume that the offsets have already been checked for block * alignment. * * For clone we only link a partial EOF block above or at the destination file's * EOF. For deduplication we accept a partial EOF block only if it ends at the * destination file's EOF (can not link it into the middle of a file). * * Shorten the request if possible. */ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; loff_t new_len = *len; if ((*len & blkmask) == 0) return 0; if (pos_out + *len < i_size_read(inode_out)) new_len &= ~blkmask; if (new_len == *len) return 0; if (remap_flags & REMAP_FILE_CAN_SHORTEN) { *len = new_len; return 0; } return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } /* Read a page's worth of file data into the page cache. */ static struct folio *vfs_dedupe_get_folio(struct file *file, loff_t pos) { return read_mapping_folio(file->f_mapping, pos >> PAGE_SHIFT, file); } /* * Lock two folios, ensuring that we lock in offset order if the folios * are from the same file. */ static void vfs_lock_two_folios(struct folio *folio1, struct folio *folio2) { /* Always lock in order of increasing index. */ if (folio1->index > folio2->index) swap(folio1, folio2); folio_lock(folio1); if (folio1 != folio2) folio_lock(folio2); } /* Unlock two folios, being careful not to unlock the same folio twice. */ static void vfs_unlock_two_folios(struct folio *folio1, struct folio *folio2) { folio_unlock(folio1); if (folio1 != folio2) folio_unlock(folio2); } /* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races. */ static int vfs_dedupe_file_range_compare(struct file *src, loff_t srcoff, struct file *dest, loff_t dstoff, loff_t len, bool *is_same) { bool same = true; int error = -EINVAL; while (len) { struct folio *src_folio, *dst_folio; void *src_addr, *dst_addr; loff_t cmp_len = min(PAGE_SIZE - offset_in_page(srcoff), PAGE_SIZE - offset_in_page(dstoff)); cmp_len = min(cmp_len, len); if (cmp_len <= 0) goto out_error; src_folio = vfs_dedupe_get_folio(src, srcoff); if (IS_ERR(src_folio)) { error = PTR_ERR(src_folio); goto out_error; } dst_folio = vfs_dedupe_get_folio(dest, dstoff); if (IS_ERR(dst_folio)) { error = PTR_ERR(dst_folio); folio_put(src_folio); goto out_error; } vfs_lock_two_folios(src_folio, dst_folio); /* * Now that we've locked both folios, make sure they're still * mapped to the file data we're interested in. If not, * someone is invalidating pages on us and we lose. */ if (!folio_test_uptodate(src_folio) || !folio_test_uptodate(dst_folio) || src_folio->mapping != src->f_mapping || dst_folio->mapping != dest->f_mapping) { same = false; goto unlock; } src_addr = kmap_local_folio(src_folio, offset_in_folio(src_folio, srcoff)); dst_addr = kmap_local_folio(dst_folio, offset_in_folio(dst_folio, dstoff)); flush_dcache_folio(src_folio); flush_dcache_folio(dst_folio); if (memcmp(src_addr, dst_addr, cmp_len)) same = false; kunmap_local(dst_addr); kunmap_local(src_addr); unlock: vfs_unlock_two_folios(src_folio, dst_folio); folio_put(dst_folio); folio_put(src_folio); if (!same) break; srcoff += cmp_len; dstoff += cmp_len; len -= cmp_len; } *is_same = same; return 0; out_error: return error; } /* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the * inodes have been locked against any other modifications. * * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Don't reflink dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { loff_t isize = i_size_read(inode_in); if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize) return 0; if (pos_in > isize) return -EINVAL; *len = isize - pos_in; if (*len == 0) return 0; } /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); if (!same_inode) inode_dio_wait(inode_out); ret = filemap_write_and_wait_range(inode_in->i_mapping, pos_in, pos_in + *len - 1); if (ret) return ret; ret = filemap_write_and_wait_range(inode_out->i_mapping, pos_out, pos_out + *len - 1); if (ret) return ret; /* * Check that the extents are the same. */ if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; if (!IS_DAX(inode_in)) ret = vfs_dedupe_file_range_compare(file_in, pos_in, file_out, pos_out, *len, &is_same); else if (dax_read_ops) ret = dax_dedupe_file_range_compare(inode_in, pos_in, inode_out, pos_out, *len, &is_same, dax_read_ops); else return -EINVAL; if (ret) return ret; if (!is_same) return -EBADE; } ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, remap_flags); if (ret || *len == 0) return ret; /* If can't alter the file contents, we're done. */ if (!(remap_flags & REMAP_FILE_DEDUP)) ret = file_modified(file_out); return ret; } int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags) { return __generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, len, remap_flags, NULL); } EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; ret = generic_file_rw_checks(file_in, file_out); if (ret < 0) return ret; if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file_in, pos_in, len, false); if (ret) return ret; ret = remap_verify_area(file_out, pos_out, len, true); if (ret) return ret; file_start_write(file_out); ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, remap_flags); file_end_write(file_out); if (ret < 0) return ret; fsnotify_access(file_in); fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(vfs_clone_file_range); /* Check whether we are allowed to dedupe the destination file */ static bool may_dedupe_file(struct file *file) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); if (capable(CAP_SYS_ADMIN)) return true; if (file->f_mode & FMODE_WRITE) return true; if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) return true; if (!inode_permission(idmap, inode, MAY_WRITE)) return true; return false; } loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags) { loff_t ret; WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_CAN_SHORTEN)); /* * This is redundant if called from vfs_dedupe_file_range(), but other * callers need it and it's not performance sesitive... */ ret = remap_verify_area(src_file, src_pos, len, false); if (ret) return ret; ret = remap_verify_area(dst_file, dst_pos, len, true); if (ret) return ret; /* * This needs to be called after remap_verify_area() because of * sb_start_write() and before may_dedupe_file() because the mount's * MAY_WRITE need to be checked with mnt_get_write_access_file() held. */ ret = mnt_want_write_file(dst_file); if (ret) return ret; ret = -EPERM; if (!may_dedupe_file(dst_file)) goto out_drop_write; ret = -EXDEV; if (file_inode(src_file)->i_sb != file_inode(dst_file)->i_sb) goto out_drop_write; ret = -EISDIR; if (S_ISDIR(file_inode(dst_file)->i_mode)) goto out_drop_write; ret = -EINVAL; if (!dst_file->f_op->remap_file_range) goto out_drop_write; if (len == 0) { ret = 0; goto out_drop_write; } ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, dst_pos, len, remap_flags | REMAP_FILE_DEDUP); out_drop_write: mnt_drop_write_file(dst_file); return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range_one); int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) { struct file_dedupe_range_info *info; struct inode *src = file_inode(file); u64 off; u64 len; int i; int ret; u16 count = same->dest_count; loff_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; if (same->reserved1 || same->reserved2) return -EINVAL; off = same->src_offset; len = same->src_length; if (S_ISDIR(src->i_mode)) return -EISDIR; if (!S_ISREG(src->i_mode)) return -EINVAL; if (!file->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file, off, len, false); if (ret < 0) return ret; ret = 0; if (off + len > i_size_read(src)) return -EINVAL; /* Arbitrary 1G limit on a single dedupe request, can be raised. */ len = min_t(u64, len, 1 << 30); /* pre-format output fields to sane values */ for (i = 0; i < count; i++) { same->info[i].bytes_deduped = 0ULL; same->info[i].status = FILE_DEDUPE_RANGE_SAME; } for (i = 0, info = same->info; i < count; i++, info++) { CLASS(fd, dst_fd)(info->dest_fd); if (fd_empty(dst_fd)) { info->status = -EBADF; goto next_loop; } if (info->reserved) { info->status = -EINVAL; goto next_loop; } deduped = vfs_dedupe_file_range_one(file, off, fd_file(dst_fd), info->dest_offset, len, REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) info->status = deduped; else info->bytes_deduped = len; next_loop: if (fatal_signal_pending(current)) break; } return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range); |
| 249 24 248 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_MM_H #define _LINUX_SCHED_MM_H #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> #include <linux/sched/coredump.h> /* * Routines for handling mm_structs */ extern struct mm_struct *mm_alloc(void); /** * mmgrab() - Pin a &struct mm_struct. * @mm: The &struct mm_struct to pin. * * Make sure that @mm will not get freed even after the owning task * exits. This doesn't guarantee that the associated address space * will still exist later on and mmget_not_zero() has to be used before * accessing it. * * This is a preferred way to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) { atomic_inc(&mm->mm_count); } static inline void smp_mb__after_mmgrab(void) { smp_mb__after_atomic(); } extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) { /* * The implicit full barrier implied by atomic_dec_and_test() is * required by the membarrier system call before returning to * user-space, after storing to rq->curr. */ if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } #ifdef CONFIG_PREEMPT_RT /* * RCU callback for delayed mm drop. Not strictly RCU, but call_rcu() is * by far the least expensive way to do that. */ static inline void __mmdrop_delayed(struct rcu_head *rhp) { struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); __mmdrop(mm); } /* * Invoked from finish_task_switch(). Delegates the heavy lifting on RT * kernels via RCU. */ static inline void mmdrop_sched(struct mm_struct *mm) { /* Provides a full memory barrier. See mmdrop() */ if (atomic_dec_and_test(&mm->mm_count)) call_rcu(&mm->delayed_drop, __mmdrop_delayed); } #else static inline void mmdrop_sched(struct mm_struct *mm) { mmdrop(mm); } #endif /* Helpers for lazy TLB mm refcounting */ static inline void mmgrab_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmgrab(mm); } static inline void mmdrop_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { mmdrop(mm); } else { /* * mmdrop_lazy_tlb must provide a full memory barrier, see the * membarrier comment finish_task_switch which relies on this. */ smp_mb(); } } static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmdrop_sched(mm); else smp_mb(); /* see mmdrop_lazy_tlb() above */ } /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. * * Make sure that the address space of the given &struct mm_struct doesn't * go away. This does not protect against parts of the address space being * modified or freed, however. * * Never use this function to pin this address space for an * unbounded/indefinite amount of time. * * Use mmput() to release the reference acquired by mmget(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) { atomic_inc(&mm->mm_users); } static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); } /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); #if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH) /* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ void mmput_async(struct mm_struct *); #endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* * Grab a reference to a task's mm, if it is not already going away * and ptrace_may_access with the mode parameter passed to it * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct on exit() */ extern void exit_mm_release(struct task_struct *, struct mm_struct *); /* Remove the current tasks stale references to the old mm_struct on exec() */ extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); #else static inline void mm_update_next_owner(struct mm_struct *mm) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) #endif #ifndef arch_get_mmap_base #define arch_get_mmap_base(addr, base) (base) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t); unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) { bool ret; /* * need RCU to access ->real_parent if CLONE_VM was used along with * CLONE_PARENT. * * We check real_parent->mm == tsk->mm because CLONE_VFORK does not * imply CLONE_VM * * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus * ->real_parent is not necessarily the task doing vfork(), so in * theory we can't rely on task_lock() if we want to dereference it. * * And in this case we can't trust the real_parent->mm == tsk->mm * check, it can be false negative. But we do not care, if init or * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); ret = tsk->vfork_done && rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; } /* * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; } return flags; } #ifdef CONFIG_LOCKDEP extern void __fs_reclaim_acquire(unsigned long ip); extern void __fs_reclaim_release(unsigned long ip); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else static inline void __fs_reclaim_acquire(unsigned long ip) { } static inline void __fs_reclaim_release(unsigned long ip) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif /* Any memory-allocation retry loop should use * memalloc_retry_wait(), and pass the flags for the most * constrained allocation attempt that might have failed. * This provides useful documentation of where loops are, * and a central place to fine tune the waiting as the MM * implementation changes. */ static inline void memalloc_retry_wait(gfp_t gfp_flags) { /* We use io_schedule_timeout because waiting for memory * typically included waiting for dirty pages to be * written out, which requires IO. */ __set_current_state(TASK_UNINTERRUPTIBLE); gfp_flags = current_gfp_context(gfp_flags); if (gfpflags_allow_blocking(gfp_flags) && !(gfp_flags & __GFP_NORETRY)) /* Probably waited already, no need for much more */ io_schedule_timeout(1); else /* Probably didn't wait, and has now released a lock, * so now is a good time to wait */ io_schedule_timeout(HZ/50); } /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate * * Similar to might_sleep() and other annotations, this can be used in functions * that might allocate, but often don't. Compiles to nothing without * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking. */ static inline void might_alloc(gfp_t gfp_mask) { fs_reclaim_acquire(gfp_mask); fs_reclaim_release(gfp_mask); might_sleep_if(gfpflags_allow_blocking(gfp_mask)); } /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). */ static inline unsigned memalloc_flags_save(unsigned flags) { unsigned oldflags = ~current->flags & flags; current->flags |= flags; return oldflags; } static inline void memalloc_flags_restore(unsigned flags) { current->flags &= ~flags; } /** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. * All further allocations will implicitly drop __GFP_IO flag and so * they are safe for the IO critical section from the allocation recursion * point of view. Use memalloc_noio_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_noio_restore. */ static inline unsigned int memalloc_noio_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOIO); } /** * memalloc_noio_restore - Ends the implicit GFP_NOIO scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope. * * This functions marks the beginning of the GFP_NOFS allocation scope. * All further allocations will implicitly drop __GFP_FS flag and so * they are safe for the FS critical section from the allocation recursion * point of view. Use memalloc_nofs_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_nofs_restore. */ static inline unsigned int memalloc_nofs_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOFS); } /** * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_noreclaim_save - Marks implicit __GFP_MEMALLOC scope. * * This function marks the beginning of the __GFP_MEMALLOC allocation scope. * All further allocations will implicitly add the __GFP_MEMALLOC flag, which * prevents entering reclaim and allows access to all memory reserves. This * should only be used when the caller guarantees the allocation will allow more * memory to be freed very shortly, i.e. it needs to allocate some memory in * the process of freeing memory, and cannot reclaim due to potential recursion. * * Users of this scope have to be extremely careful to not deplete the reserves * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. Usage of a * pre-allocated pool (e.g. mempool) should be always considered before using * this scope. * * Individual allocations under the scope can opt out using __GFP_NOMEMALLOC * * Context: This function should not be used in an interrupt context as that one * does not give PF_MEMALLOC access to reserves. * See __gfp_pfmemalloc_flags(). * Return: The saved flags to be passed to memalloc_noreclaim_restore. */ static inline unsigned int memalloc_noreclaim_save(void) { return memalloc_flags_save(PF_MEMALLOC); } /** * memalloc_noreclaim_restore - Ends the implicit __GFP_MEMALLOC scope. * @flags: Flags to restore. * * Ends the implicit __GFP_MEMALLOC scope started by memalloc_noreclaim_save * function. Always make sure that the given flags is the return value from the * pairing memalloc_noreclaim_save call. */ static inline void memalloc_noreclaim_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_pin_save - Marks implicit ~__GFP_MOVABLE scope. * * This function marks the beginning of the ~__GFP_MOVABLE allocation scope. * All further allocations will implicitly remove the __GFP_MOVABLE flag, which * will constraint the allocations to zones that allow long term pinning, i.e. * not ZONE_MOVABLE zones. * * Return: The saved flags to be passed to memalloc_pin_restore. */ static inline unsigned int memalloc_pin_save(void) { return memalloc_flags_save(PF_MEMALLOC_PIN); } /** * memalloc_pin_restore - Ends the implicit ~__GFP_MOVABLE scope. * @flags: Flags to restore. * * Ends the implicit ~__GFP_MOVABLE scope started by memalloc_pin_save function. * Always make sure that the given flags is the return value from the pairing * memalloc_pin_save call. */ static inline void memalloc_pin_restore(unsigned int flags) { memalloc_flags_restore(flags); } #ifdef CONFIG_MEMCG DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); /** * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * * Please, make sure that caller has a reference to the passed memcg structure, * so its lifetime is guaranteed to exceed the scope between two * set_active_memcg() calls. * * NOTE: This function can nest. Users must save the return value and * reset the previous value after their own charging scope is over. */ static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { struct mem_cgroup *old; if (!in_task()) { old = this_cpu_read(int_active_memcg); this_cpu_write(int_active_memcg, memcg); } else { old = current->active_memcg; current->active_memcg = memcg; } return old; } #else static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { return NULL; } #endif #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS #include <asm/membarrier.h> #endif static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { /* * The atomic_read() below prevents CSE. The following should * help the compiler generate more efficient code on architectures * where sync_core_before_usermode() is a no-op. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE)) return; if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) return; sync_core_before_usermode(); } extern void membarrier_exec_mmap(struct mm_struct *mm); extern void membarrier_update_current_mm(struct mm_struct *next_mm); #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { } #endif static inline void membarrier_exec_mmap(struct mm_struct *mm) { } static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } static inline void membarrier_update_current_mm(struct mm_struct *next_mm) { } #endif #endif /* _LINUX_SCHED_MM_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DAX_H #define _LINUX_DAX_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; struct iomap_iter; struct iomap; enum dax_access_mode { DAX_ACCESS, DAX_RECOVERY_WRITE, }; struct dax_operations { /* * direct_access: translate a device-relative * logical-page-offset into an absolute physical pfn. Return the * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, enum dax_access_mode, void **, unsigned long *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); /* * recovery_write: recover a poisoned range by DAX device driver * capable of clearing poison. */ size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *iter); }; struct dax_holder_operations { /* * notify_failure - notify memory failure into inner holder device * @dax_dev: the dax device which contains the holder * @offset: offset on this dax device where memory failure occurs * @len: length of this memory failure event * @flags: action flags for memory failure handler */ int (*notify_failure)(struct dax_device *dax_dev, u64 offset, u64 len, int mf_flags); }; #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); void *dax_holder(struct dax_device *dax_dev); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); void set_dax_nocache(struct dax_device *dax_dev); void set_dax_nomc(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ static inline bool daxdev_mapping_supported(vm_flags_t vm_flags, const struct inode *inode, struct dax_device *dax_dev) { if (!(vm_flags & VM_SYNC)) return true; if (!IS_DAX(inode)) return false; return dax_synchronous(dax_dev); } #else static inline void *dax_holder(struct dax_device *dax_dev) { return NULL; } static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { return ERR_PTR(-EOPNOTSUPP); } static inline void put_dax(struct dax_device *dax_dev) { } static inline void kill_dax(struct dax_device *dax_dev) { } static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) { } static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } static inline void set_dax_nocache(struct dax_device *dax_dev) { } static inline void set_dax_nomc(struct dax_device *dax_dev) { } static inline void set_dax_synchronous(struct dax_device *dax_dev) { } static inline bool daxdev_mapping_supported(vm_flags_t vm_flags, const struct inode *inode, struct dax_device *dax_dev) { return !(vm_flags & VM_SYNC); } static inline size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { return 0; } #endif struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops); void fs_put_dax(struct dax_device *dax_dev, void *holder); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { return 0; } static inline void dax_remove_host(struct gendisk *disk) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops) { return NULL; } static inline void fs_put_dax(struct dax_device *dax_dev, void *holder) { } #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ #if IS_ENABLED(CONFIG_FS_DAX) int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_folio(struct folio *folio); void dax_unlock_folio(struct folio *folio, dax_entry_t cookie); dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page); void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie); #else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; } static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) { return NULL; } static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } static inline dax_entry_t dax_lock_folio(struct folio *folio) { if (IS_DAX(folio->mapping->host)) return ~0UL; return 0; } static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie) { } static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page) { return 0; } static inline void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie) { } #endif int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); static inline bool dax_page_is_idle(struct page *page) { return page && page_ref_count(page) == 0; } #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); #else static inline int dax_read_lock(void) { return 0; } static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ #if !IS_ENABLED(CONFIG_FS_DAX) static inline int __must_check dax_break_layout(struct inode *inode, loff_t start, loff_t end, void (cb)(struct inode *)) { return 0; } static inline void dax_break_layout_final(struct inode *inode) { } #endif bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, unsigned long *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, int mf_flags); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order, unsigned long *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order, unsigned long pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); void dax_delete_mapping_range(struct address_space *mapping, loff_t start, loff_t end); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); int __must_check dax_break_layout(struct inode *inode, loff_t start, loff_t end, void (cb)(struct inode *)); static inline int __must_check dax_break_layout_inode(struct inode *inode, void (cb)(struct inode *)) { return dax_break_layout(inode, 0, LLONG_MAX, cb); } void dax_break_layout_final(struct inode *inode); int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same, const struct iomap_ops *ops); int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *ops); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } /* * Due to dax's memory and block duo personalities, hwpoison reporting * takes into consideration which personality is presently visible. * When dax acts like a block device, such as in block IO, an encounter of * dax hwpoison is reported as -EIO. * When dax acts like memory, such as in page fault, a detection of hwpoison * is reported as -EHWPOISON which leads to VM_FAULT_HWPOISON. */ static inline int dax_mem2blk_err(int err) { return (err == -EHWPOISON) ? -EIO : err; } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES void hmem_register_resource(int target_nid, struct resource *r); #else static inline void hmem_register_resource(int target_nid, struct resource *r) { } #endif typedef int (*walk_hmem_fn)(struct device *dev, int target_nid, const struct resource *res); int walk_hmem_resources(struct device *dev, walk_hmem_fn fn); #endif |
| 200 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Landlock - Credential hooks * * Copyright © 2019-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2019-2020 ANSSI * Copyright © 2021-2025 Microsoft Corporation */ #ifndef _SECURITY_LANDLOCK_CRED_H #define _SECURITY_LANDLOCK_CRED_H #include <linux/container_of.h> #include <linux/cred.h> #include <linux/init.h> #include <linux/rcupdate.h> #include "access.h" #include "limits.h" #include "ruleset.h" #include "setup.h" /** * struct landlock_cred_security - Credential security blob * * This structure is packed to minimize the size of struct * landlock_file_security. However, it is always aligned in the LSM cred blob, * see lsm_set_blob_size(). */ struct landlock_cred_security { /** * @domain: Immutable ruleset enforced on a task. */ struct landlock_ruleset *domain; #ifdef CONFIG_AUDIT /** * @domain_exec: Bitmask identifying the domain layers that were enforced by * the current task's executed file (i.e. no new execve(2) since * landlock_restrict_self(2)). */ u16 domain_exec; /** * @log_subdomains_off: Set if the domain descendants's log_status should be * set to %LANDLOCK_LOG_DISABLED. This is not a landlock_hierarchy * configuration because it applies to future descendant domains and it does * not require a current domain. */ u8 log_subdomains_off : 1; #endif /* CONFIG_AUDIT */ } __packed; #ifdef CONFIG_AUDIT /* Makes sure all layer executions can be stored. */ static_assert(BITS_PER_TYPE(typeof_member(struct landlock_cred_security, domain_exec)) >= LANDLOCK_MAX_NUM_LAYERS); #endif /* CONFIG_AUDIT */ static inline struct landlock_cred_security * landlock_cred(const struct cred *cred) { return cred->security + landlock_blob_sizes.lbs_cred; } static inline struct landlock_ruleset *landlock_get_current_domain(void) { return landlock_cred(current_cred())->domain; } /* * The call needs to come from an RCU read-side critical section. */ static inline const struct landlock_ruleset * landlock_get_task_domain(const struct task_struct *const task) { return landlock_cred(__task_cred(task))->domain; } static inline bool landlocked(const struct task_struct *const task) { bool has_dom; if (task == current) return !!landlock_get_current_domain(); rcu_read_lock(); has_dom = !!landlock_get_task_domain(task); rcu_read_unlock(); return has_dom; } /** * landlock_get_applicable_subject - Return the subject's Landlock credential * if its enforced domain applies to (i.e. * handles) at least one of the access rights * specified in @masks * * @cred: credential * @masks: access masks * @handle_layer: returned youngest layer handling a subset of @masks. Not set * if the function returns NULL. * * Returns: landlock_cred(@cred) if any access rights specified in @masks is * handled, or NULL otherwise. */ static inline const struct landlock_cred_security * landlock_get_applicable_subject(const struct cred *const cred, const struct access_masks masks, size_t *const handle_layer) { const union access_masks_all masks_all = { .masks = masks, }; const struct landlock_ruleset *domain; ssize_t layer_level; if (!cred) return NULL; domain = landlock_cred(cred)->domain; if (!domain) return NULL; for (layer_level = domain->num_layers - 1; layer_level >= 0; layer_level--) { union access_masks_all layer = { .masks = domain->access_masks[layer_level], }; if (layer.all & masks_all.all) { if (handle_layer) *handle_layer = layer_level; return landlock_cred(cred); } } return NULL; } __init void landlock_add_cred_hooks(void); #endif /* _SECURITY_LANDLOCK_CRED_H */ |
| 2 1 1 1 1 1 1 1 1 3 2 6 1 5 3 1 2 1 1 1 3 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VFIO-KVM bridge pseudo device * * Copyright (C) 2013 Red Hat, Inc. All rights reserved. * Author: Alex Williamson <alex.williamson@redhat.com> */ #include <linux/errno.h> #include <linux/file.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/vfio.h> #include "vfio.h" #ifdef CONFIG_SPAPR_TCE_IOMMU #include <asm/kvm_ppc.h> #endif struct kvm_vfio_file { struct list_head node; struct file *file; #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *iommu_group; #endif }; struct kvm_vfio { struct list_head file_list; struct mutex lock; bool noncoherent; }; static void kvm_vfio_file_set_kvm(struct file *file, struct kvm *kvm) { void (*fn)(struct file *file, struct kvm *kvm); fn = symbol_get(vfio_file_set_kvm); if (!fn) return; fn(file, kvm); symbol_put(vfio_file_set_kvm); } static bool kvm_vfio_file_enforced_coherent(struct file *file) { bool (*fn)(struct file *file); bool ret; fn = symbol_get(vfio_file_enforced_coherent); if (!fn) return false; ret = fn(file); symbol_put(vfio_file_enforced_coherent); return ret; } static bool kvm_vfio_file_is_valid(struct file *file) { bool (*fn)(struct file *file); bool ret; fn = symbol_get(vfio_file_is_valid); if (!fn) return false; ret = fn(file); symbol_put(vfio_file_is_valid); return ret; } #ifdef CONFIG_SPAPR_TCE_IOMMU static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file) { struct iommu_group *(*fn)(struct file *file); struct iommu_group *ret; fn = symbol_get(vfio_file_iommu_group); if (!fn) return NULL; ret = fn(file); symbol_put(vfio_file_iommu_group); return ret; } static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm, struct kvm_vfio_file *kvf) { if (WARN_ON_ONCE(!kvf->iommu_group)) return; kvm_spapr_tce_release_iommu_group(kvm, kvf->iommu_group); iommu_group_put(kvf->iommu_group); kvf->iommu_group = NULL; } #endif /* * Groups/devices can use the same or different IOMMU domains. If the same * then adding a new group/device may change the coherency of groups/devices * we've previously been told about. We don't want to care about any of * that so we retest each group/device and bail as soon as we find one that's * noncoherent. This means we only ever [un]register_noncoherent_dma once * for the whole device. */ static void kvm_vfio_update_coherency(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; bool noncoherent = false; struct kvm_vfio_file *kvf; list_for_each_entry(kvf, &kv->file_list, node) { if (!kvm_vfio_file_enforced_coherent(kvf->file)) { noncoherent = true; break; } } if (noncoherent != kv->noncoherent) { kv->noncoherent = noncoherent; if (kv->noncoherent) kvm_arch_register_noncoherent_dma(dev->kvm); else kvm_arch_unregister_noncoherent_dma(dev->kvm); } } static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; struct file *filp; int ret = 0; filp = fget(fd); if (!filp) return -EBADF; /* Ensure the FD is a vfio FD. */ if (!kvm_vfio_file_is_valid(filp)) { ret = -EINVAL; goto out_fput; } mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file == filp) { ret = -EEXIST; goto out_unlock; } } kvf = kzalloc(sizeof(*kvf), GFP_KERNEL_ACCOUNT); if (!kvf) { ret = -ENOMEM; goto out_unlock; } kvf->file = get_file(filp); list_add_tail(&kvf->node, &kv->file_list); kvm_vfio_file_set_kvm(kvf->file, dev->kvm); kvm_vfio_update_coherency(dev); out_unlock: mutex_unlock(&kv->lock); out_fput: fput(filp); return ret; } static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; CLASS(fd, f)(fd); int ret; if (fd_empty(f)) return -EBADF; ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file != fd_file(f)) continue; list_del(&kvf->node); #ifdef CONFIG_SPAPR_TCE_IOMMU kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif kvm_vfio_file_set_kvm(kvf->file, NULL); fput(kvf->file); kfree(kvf); ret = 0; break; } kvm_vfio_update_coherency(dev); mutex_unlock(&kv->lock); return ret; } #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev, void __user *arg) { struct kvm_vfio_spapr_tce param; struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; int ret; if (copy_from_user(¶m, arg, sizeof(struct kvm_vfio_spapr_tce))) return -EFAULT; CLASS(fd, f)(param.groupfd); if (fd_empty(f)) return -EBADF; ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file != fd_file(f)) continue; if (!kvf->iommu_group) { kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file); if (WARN_ON_ONCE(!kvf->iommu_group)) { ret = -EIO; goto err_fdput; } } ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd, kvf->iommu_group); break; } err_fdput: mutex_unlock(&kv->lock); return ret; } #endif static int kvm_vfio_set_file(struct kvm_device *dev, long attr, void __user *arg) { int32_t __user *argp = arg; int32_t fd; switch (attr) { case KVM_DEV_VFIO_FILE_ADD: if (get_user(fd, argp)) return -EFAULT; return kvm_vfio_file_add(dev, fd); case KVM_DEV_VFIO_FILE_DEL: if (get_user(fd, argp)) return -EFAULT; return kvm_vfio_file_del(dev, fd); #ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: return kvm_vfio_file_set_spapr_tce(dev, arg); #endif } return -ENXIO; } static int kvm_vfio_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_VFIO_FILE: return kvm_vfio_set_file(dev, attr->attr, u64_to_user_ptr(attr->addr)); } return -ENXIO; } static int kvm_vfio_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_VFIO_FILE: switch (attr->attr) { case KVM_DEV_VFIO_FILE_ADD: case KVM_DEV_VFIO_FILE_DEL: #ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: #endif return 0; } break; } return -ENXIO; } static void kvm_vfio_release(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf, *tmp; list_for_each_entry_safe(kvf, tmp, &kv->file_list, node) { #ifdef CONFIG_SPAPR_TCE_IOMMU kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif kvm_vfio_file_set_kvm(kvf->file, NULL); fput(kvf->file); list_del(&kvf->node); kfree(kvf); } kvm_vfio_update_coherency(dev); kfree(kv); kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */ } static int kvm_vfio_create(struct kvm_device *dev, u32 type); static const struct kvm_device_ops kvm_vfio_ops = { .name = "kvm-vfio", .create = kvm_vfio_create, .release = kvm_vfio_release, .set_attr = kvm_vfio_set_attr, .has_attr = kvm_vfio_has_attr, }; static int kvm_vfio_create(struct kvm_device *dev, u32 type) { struct kvm_device *tmp; struct kvm_vfio *kv; lockdep_assert_held(&dev->kvm->lock); /* Only one VFIO "device" per VM */ list_for_each_entry(tmp, &dev->kvm->devices, vm_node) if (tmp->ops == &kvm_vfio_ops) return -EBUSY; kv = kzalloc(sizeof(*kv), GFP_KERNEL_ACCOUNT); if (!kv) return -ENOMEM; INIT_LIST_HEAD(&kv->file_list); mutex_init(&kv->lock); dev->private = kv; return 0; } int kvm_vfio_ops_init(void) { return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO); } void kvm_vfio_ops_exit(void) { kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_ #define _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_ /** * __ffs - find first bit in word. * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ static __always_inline unsigned int __ffs(unsigned long word) { return __builtin_ctzl(word); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/signalfd.h * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H #include <uapi/linux/signalfd.h> #include <linux/sched/signal.h> #ifdef CONFIG_SIGNALFD /* * Deliver the signal to listening signalfd. */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { if (unlikely(waitqueue_active(&tsk->sighand->signalfd_wqh))) wake_up(&tsk->sighand->signalfd_wqh); } extern void signalfd_cleanup(struct sighand_struct *sighand); #else /* CONFIG_SIGNALFD */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { } static inline void signalfd_cleanup(struct sighand_struct *sighand) { } #endif /* CONFIG_SIGNALFD */ #endif /* _LINUX_SIGNALFD_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BLK_CGROUP_PRIVATE_H #define _BLK_CGROUP_PRIVATE_H /* * block cgroup private header * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> */ #include <linux/blk-cgroup.h> #include <linux/cgroup.h> #include <linux/kthread.h> #include <linux/blk-mq.h> #include <linux/llist.h> #include "blk.h" struct blkcg_gq; struct blkg_policy_data; /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) #ifdef CONFIG_BLK_CGROUP enum blkg_iostat_type { BLKG_IOSTAT_READ, BLKG_IOSTAT_WRITE, BLKG_IOSTAT_DISCARD, BLKG_IOSTAT_NR, }; struct blkg_iostat { u64 bytes[BLKG_IOSTAT_NR]; u64 ios[BLKG_IOSTAT_NR]; }; struct blkg_iostat_set { struct u64_stats_sync sync; struct blkcg_gq *blkg; struct llist_node lnode; int lqueued; /* queued in llist */ struct blkg_iostat cur; struct blkg_iostat last; }; /* association between a blk cgroup and a request queue */ struct blkcg_gq { /* Pointer to the associated request_queue */ struct request_queue *q; struct list_head q_node; struct hlist_node blkcg_node; struct blkcg *blkcg; /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; /* reference count */ struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; struct blkg_iostat_set __percpu *iostat_cpu; struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spinlock_t async_bio_lock; struct bio_list async_bios; #endif union { struct work_struct async_bio_work; struct work_struct free_work; }; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; struct rcu_head rcu_head; }; struct blkcg { struct cgroup_subsys_state css; spinlock_t lock; refcount_t online_pin; /* If there is block congestion on this cgroup. */ atomic_t congestion_count; struct radix_tree_root blkg_tree; struct blkcg_gq __rcu *blkg_hint; struct hlist_head blkg_list; struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node; /* * List of updated percpu blkg_iostat_set's since the last flush. */ struct llist_head __percpu *lhead; #ifdef CONFIG_BLK_CGROUP_FC_APPID char fc_app_id[FC_APPID_LEN]; #endif #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; #endif }; static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } /* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q). This is used by blkcg policies which need to track * information per blkcg - q pair. * * There can be multiple active blkcg policies and each blkg:policy pair is * represented by a blkg_policy_data which is allocated and freed by each * policy's pd_alloc/free_fn() methods. A policy can allocate private data * area by allocating larger data structure which embeds blkg_policy_data * at the beginning. */ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; bool online; }; /* * Policies that need to keep per-blkcg data which is independent from any * request_queue associated to it should implement cpd_alloc/free_fn() * methods. A policy can allocate private data area by allocating larger * data structure which embeds blkcg_policy_data at the beginning. * cpd_init() is invoked to let each policy handle per-blkcg data. */ struct blkcg_policy_data { /* the blkcg and policy id this per-policy data belongs to */ struct blkcg *blkcg; int plid; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp); typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, struct seq_file *s); struct blkcg_policy { int plid; /* cgroup files for the policy */ struct cftype *dfl_cftypes; struct cftype *legacy_cftypes; /* operations */ blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; blkcg_pol_free_cpd_fn *cpd_free_fn; blkcg_pol_alloc_pd_fn *pd_alloc_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; blkcg_pol_stat_pd_fn *pd_stat_fn; }; extern struct blkcg blkcg_root; extern bool blkcg_debug_stats; void blkg_init_queue(struct request_queue *q); int blkcg_init_disk(struct gendisk *disk); void blkcg_exit_disk(struct gendisk *disk); /* Blkio controller policy registration */ int blkcg_policy_register(struct blkcg_policy *pol); void blkcg_policy_unregister(struct blkcg_policy *pol); int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol); void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol); const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); struct blkg_conf_ctx { char *input; char *body; struct block_device *bdev; struct blkcg_gq *blkg; }; void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input); int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx); unsigned long blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx); int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx); void blkg_conf_exit(struct blkg_conf_ctx *ctx); void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags); /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @bio: the target &bio * * Return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning * blkg. The idea is we do bio_blkcg_css() to look up the actual context for * the bio and attach the appropriate blkg to the bio. Then we call this helper * and if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */ static inline bool bio_issue_as_root_blkg(struct bio *bio) { return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; } /** * blkg_lookup - lookup blkg for the specified blkcg - q pair * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. * * Must be called in a RCU critical section. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q) { struct blkcg_gq *blkg; if (blkcg == &blkcg_root) return q->root_blkg; blkg = rcu_dereference_check(blkcg->blkg_hint, lockdep_is_held(&q->queue_lock)); if (blkg && blkg->q == q) return blkg; blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id); if (blkg && blkg->q != q) blkg = NULL; return blkg; } /** * blkg_to_pd - get policy private data * @blkg: blkg of interest * @pol: policy of interest * * Return pointer to private data associated with the @blkg-@pol pair. */ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return blkg ? blkg->pd[pol->plid] : NULL; } static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, struct blkcg_policy *pol) { return blkcg ? blkcg->cpd[pol->plid] : NULL; } /** * pd_to_blkg - get blkg associated with policy private data * @pd: policy private data of interest * * @pd is policy private data. Determine the blkg it's associated with. */ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return pd ? pd->blkg : NULL; } static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) { return cpd ? cpd->blkcg : NULL; } /** * blkg_get - get a blkg reference * @blkg: blkg to get * * The caller should be holding an existing reference. */ static inline void blkg_get(struct blkcg_gq *blkg) { percpu_ref_get(&blkg->refcnt); } /** * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ static inline bool blkg_tryget(struct blkcg_gq *blkg) { return blkg && percpu_ref_tryget(&blkg->refcnt); } /** * blkg_put - put a blkg reference * @blkg: blkg to put */ static inline void blkg_put(struct blkcg_gq *blkg) { percpu_ref_put(&blkg->refcnt); } /** * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU * read locked. If called under either blkcg or queue lock, the iteration * is guaranteed to include all and only online blkgs. The caller may * update @pos_css by calling css_rightmost_descendant() to skip subtree. * @p_blkg is included in the iteration and the first node to be visited. */ #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q))) /** * blkg_for_each_descendant_post - post-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Similar to blkg_for_each_descendant_pre() but performs post-order * traversal instead. Synchronization rules are the same. @p_blkg is * included in the iteration and the last node to be visited. */ #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q))) static inline void blkcg_bio_issue_init(struct bio *bio) { bio_issue_init(&bio->bi_issue, bio_sectors(bio)); } static inline void blkcg_use_delay(struct blkcg_gq *blkg) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; if (atomic_add_return(1, &blkg->use_delay) == 1) atomic_inc(&blkg->blkcg->congestion_count); } static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); if (WARN_ON_ONCE(old < 0)) return 0; if (old == 0) return 0; /* * We do this song and dance because we can race with somebody else * adding or removing delay. If we just did an atomic_dec we'd end up * negative and we'd already be in trouble. We need to subtract 1 and * then check to see if we were the last delay so we can drop the * congestion count on the cgroup. */ while (old && !atomic_try_cmpxchg(&blkg->use_delay, &old, old - 1)) ; if (old == 0) return 0; if (old == 1) atomic_dec(&blkg->blkcg->congestion_count); return 1; } /** * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount * @blkg: target blkg * @delay: delay duration in nsecs * * When enabled with this function, the delay is not decayed and must be * explicitly cleared with blkcg_clear_delay(). Must not be mixed with * blkcg_[un]use_delay() and blkcg_add_delay() usages. */ static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) { int old = atomic_read(&blkg->use_delay); /* We only want 1 person setting the congestion count for this blkg. */ if (!old && atomic_try_cmpxchg(&blkg->use_delay, &old, -1)) atomic_inc(&blkg->blkcg->congestion_count); atomic64_set(&blkg->delay_nsec, delay); } /** * blkcg_clear_delay - Disable allocator delay mechanism * @blkg: target blkg * * Disable use_delay mechanism. See blkcg_set_delay(). */ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); /* We only want 1 person clearing the congestion count for this blkg. */ if (old && atomic_try_cmpxchg(&blkg->use_delay, &old, 0)) atomic_dec(&blkg->blkcg->congestion_count); } /** * blk_cgroup_mergeable - Determine whether to allow or disallow merges * @rq: request to merge into * @bio: bio to merge * * @bio and @rq should belong to the same cgroup and their issue_as_root should * match. The latter is necessary as we don't want to throttle e.g. a metadata * update because it happens to be next to a regular IO. */ static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return rq->bio->bi_blkg == bio->bi_blkg && bio_issue_as_root_blkg(rq->bio) == bio_issue_as_root_blkg(bio); } void blk_cgroup_bio_start(struct bio *bio); void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); #else /* CONFIG_BLK_CGROUP */ struct blkg_policy_data { }; struct blkcg_policy_data { }; struct blkcg_policy { }; struct blkcg { }; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline void blkg_init_queue(struct request_queue *q) { } static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } static inline int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { return 0; } static inline void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return NULL; } static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline void blk_cgroup_bio_start(struct bio *bio) { } static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return true; } #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) #endif /* CONFIG_BLK_CGROUP */ #endif /* _BLK_CGROUP_PRIVATE_H */ |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_IODEV_H__ #define __KVM_IODEV_H__ #include <linux/kvm_types.h> #include <linux/errno.h> struct kvm_io_device; struct kvm_vcpu; /** * kvm_io_device_ops are called under kvm slots_lock. * read and write handlers return 0 if the transaction has been handled, * or non-zero to have it passed to the next device. **/ struct kvm_io_device_ops { int (*read)(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, void *val); int (*write)(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val); void (*destructor)(struct kvm_io_device *this); }; struct kvm_io_device { const struct kvm_io_device_ops *ops; }; static inline void kvm_iodevice_init(struct kvm_io_device *dev, const struct kvm_io_device_ops *ops) { dev->ops = ops; } static inline int kvm_iodevice_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int l, void *v) { return dev->ops->read ? dev->ops->read(vcpu, dev, addr, l, v) : -EOPNOTSUPP; } static inline int kvm_iodevice_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int l, const void *v) { return dev->ops->write ? dev->ops->write(vcpu, dev, addr, l, v) : -EOPNOTSUPP; } #endif /* __KVM_IODEV_H__ */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Lock-less NULL terminated single linked list * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/llist.h> /** * llist_del_first - delete the first entry of lock-less list * @head: the head for your lock-less list * * If list is empty, return NULL, otherwise, return the first entry * deleted, this is the newest added one. * * Only one llist_del_first user can be used simultaneously with * multiple llist_add users without lock. Because otherwise * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, * llist_add) sequence in another user may change @head->first->next, * but keep @head->first. If multiple consumers are needed, please * use llist_del_all or use lock between consumers. */ struct llist_node *llist_del_first(struct llist_head *head) { struct llist_node *entry, *next; entry = smp_load_acquire(&head->first); do { if (entry == NULL) return NULL; next = READ_ONCE(entry->next); } while (!try_cmpxchg(&head->first, &entry, next)); return entry; } EXPORT_SYMBOL_GPL(llist_del_first); /** * llist_del_first_this - delete given entry of lock-less list if it is first * @head: the head for your lock-less list * @this: a list entry. * * If head of the list is given entry, delete and return %true else * return %false. * * Multiple callers can safely call this concurrently with multiple * llist_add() callers, providing all the callers offer a different @this. */ bool llist_del_first_this(struct llist_head *head, struct llist_node *this) { struct llist_node *entry, *next; /* acquire ensures orderig wrt try_cmpxchg() is llist_del_first() */ entry = smp_load_acquire(&head->first); do { if (entry != this) return false; next = READ_ONCE(entry->next); } while (!try_cmpxchg(&head->first, &entry, next)); return true; } EXPORT_SYMBOL_GPL(llist_del_first_this); /** * llist_reverse_order - reverse order of a llist chain * @head: first item of the list to be reversed * * Reverse the order of a chain of llist entries and return the * new first entry. */ struct llist_node *llist_reverse_order(struct llist_node *head) { struct llist_node *new_head = NULL; while (head) { struct llist_node *tmp = head; head = head->next; tmp->next = new_head; new_head = tmp; } return new_head; } EXPORT_SYMBOL_GPL(llist_reverse_order); |
| 207 209 206 209 208 207 209 208 209 209 211 212 212 211 212 210 211 212 211 212 212 185 185 185 185 185 185 184 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/sysreg-sr.h> #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_nested.h> static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu) { /* These registers are common with EL1 */ __vcpu_assign_sys_reg(vcpu, PAR_EL1, read_sysreg(par_el1)); __vcpu_assign_sys_reg(vcpu, TPIDR_EL1, read_sysreg(tpidr_el1)); __vcpu_assign_sys_reg(vcpu, ESR_EL2, read_sysreg_el1(SYS_ESR)); __vcpu_assign_sys_reg(vcpu, AFSR0_EL2, read_sysreg_el1(SYS_AFSR0)); __vcpu_assign_sys_reg(vcpu, AFSR1_EL2, read_sysreg_el1(SYS_AFSR1)); __vcpu_assign_sys_reg(vcpu, FAR_EL2, read_sysreg_el1(SYS_FAR)); __vcpu_assign_sys_reg(vcpu, MAIR_EL2, read_sysreg_el1(SYS_MAIR)); __vcpu_assign_sys_reg(vcpu, VBAR_EL2, read_sysreg_el1(SYS_VBAR)); __vcpu_assign_sys_reg(vcpu, CONTEXTIDR_EL2, read_sysreg_el1(SYS_CONTEXTIDR)); __vcpu_assign_sys_reg(vcpu, AMAIR_EL2, read_sysreg_el1(SYS_AMAIR)); /* * In VHE mode those registers are compatible between EL1 and EL2, * and the guest uses the _EL1 versions on the CPU naturally. * So we save them into their _EL2 versions here. * For nVHE mode we trap accesses to those registers, so our * _EL2 copy in sys_regs[] is always up-to-date and we don't need * to save anything here. */ if (vcpu_el2_e2h_is_set(vcpu)) { u64 val; /* * We don't save CPTR_EL2, as accesses to CPACR_EL1 * are always trapped, ensuring that the in-memory * copy is always up-to-date. A small blessing... */ __vcpu_assign_sys_reg(vcpu, SCTLR_EL2, read_sysreg_el1(SYS_SCTLR)); __vcpu_assign_sys_reg(vcpu, TTBR0_EL2, read_sysreg_el1(SYS_TTBR0)); __vcpu_assign_sys_reg(vcpu, TTBR1_EL2, read_sysreg_el1(SYS_TTBR1)); __vcpu_assign_sys_reg(vcpu, TCR_EL2, read_sysreg_el1(SYS_TCR)); if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { __vcpu_assign_sys_reg(vcpu, TCR2_EL2, read_sysreg_el1(SYS_TCR2)); if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { __vcpu_assign_sys_reg(vcpu, PIRE0_EL2, read_sysreg_el1(SYS_PIRE0)); __vcpu_assign_sys_reg(vcpu, PIR_EL2, read_sysreg_el1(SYS_PIR)); } if (ctxt_has_s1poe(&vcpu->arch.ctxt)) __vcpu_assign_sys_reg(vcpu, POR_EL2, read_sysreg_el1(SYS_POR)); } /* * The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where * the interesting CNTHCTL_EL2 bits live. So preserve these * bits when reading back the guest-visible value. */ val = read_sysreg_el1(SYS_CNTKCTL); val &= CNTKCTL_VALID_BITS; __vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, &=, ~CNTKCTL_VALID_BITS); __vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, |=, val); } __vcpu_assign_sys_reg(vcpu, SP_EL2, read_sysreg(sp_el1)); __vcpu_assign_sys_reg(vcpu, ELR_EL2, read_sysreg_el1(SYS_ELR)); __vcpu_assign_sys_reg(vcpu, SPSR_EL2, read_sysreg_el1(SYS_SPSR)); if (ctxt_has_sctlr2(&vcpu->arch.ctxt)) __vcpu_assign_sys_reg(vcpu, SCTLR2_EL2, read_sysreg_el1(SYS_SCTLR2)); } static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu) { u64 val; /* These registers are common with EL1 */ write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1), par_el1); write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1), tpidr_el1); write_sysreg(ctxt_midr_el1(&vcpu->arch.ctxt), vpidr_el2); write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2); write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR); write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR); write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR); if (vcpu_el2_e2h_is_set(vcpu)) { /* * In VHE mode those registers are compatible between * EL1 and EL2. */ write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2), SYS_SCTLR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2), SYS_CPACR); write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2), SYS_TTBR0); write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2), SYS_TTBR1); write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2), SYS_TCR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CNTHCTL_EL2), SYS_CNTKCTL); } else { /* * CNTHCTL_EL2 only affects EL1 when running nVHE, so * no need to restore it. */ val = translate_sctlr_el2_to_sctlr_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2)); write_sysreg_el1(val, SYS_SCTLR); val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2)); write_sysreg_el1(val, SYS_CPACR); val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2)); write_sysreg_el1(val, SYS_TTBR0); val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2)); write_sysreg_el1(val, SYS_TCR); } if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR2_EL2), SYS_TCR2); if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { write_sysreg_el1(__vcpu_sys_reg(vcpu, PIR_EL2), SYS_PIR); write_sysreg_el1(__vcpu_sys_reg(vcpu, PIRE0_EL2), SYS_PIRE0); } if (ctxt_has_s1poe(&vcpu->arch.ctxt)) write_sysreg_el1(__vcpu_sys_reg(vcpu, POR_EL2), SYS_POR); } write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2), SYS_ESR); write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2), SYS_AFSR0); write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2), SYS_AFSR1); write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2), SYS_FAR); write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2), sp_el1); write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2), SYS_ELR); write_sysreg_el1(__vcpu_sys_reg(vcpu, SPSR_EL2), SYS_SPSR); if (ctxt_has_sctlr2(&vcpu->arch.ctxt)) write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR2_EL2), SYS_SCTLR2); } /* * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and * pstate, which are handled as part of the el2 return state) on every * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. */ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); /** * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU * * @vcpu: The VCPU pointer * * Load system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_load() function * and loading system register state early avoids having to load them on * every entry to the VM. */ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; u64 midr, mpidr; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_user_state(host_ctxt); /* * When running a normal EL1 guest, we only load a new vcpu * after a context switch, which imvolves a DSB, so all * speculative EL1&0 walks will have already completed. * If running NV, the vcpu may transition between vEL1 and * vEL2 without a context switch, so make sure we complete * those walks before loading a new context. */ if (vcpu_has_nv(vcpu)) dsb(nsh); /* * Load guest EL1 and user state * * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_user_state(guest_ctxt); if (unlikely(is_hyp_ctxt(vcpu))) { __sysreg_restore_vel2_state(vcpu); } else { if (vcpu_has_nv(vcpu)) { /* * As we're restoring a nested guest, set the value * provided by the guest hypervisor. */ midr = ctxt_sys_reg(guest_ctxt, VPIDR_EL2); mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2); } else { midr = ctxt_midr_el1(guest_ctxt); mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1); } __sysreg_restore_el1_state(guest_ctxt, midr, mpidr); } vcpu_set_flag(vcpu, SYSREGS_ON_CPU); } /** * __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU * * @vcpu: The VCPU pointer * * Save guest system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_put() function * and deferring saving system register state until we're no longer running the * VCPU avoids having to save them on every exit from the VM. */ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = host_data_ptr(host_ctxt); if (unlikely(is_hyp_ctxt(vcpu))) __sysreg_save_vel2_state(vcpu); else __sysreg_save_el1_state(guest_ctxt); __sysreg_save_user_state(guest_ctxt); __sysreg32_save_state(vcpu); /* Restore host user state */ __sysreg_restore_user_state(host_ctxt); vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); } |
| 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/printk.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Modified to make sys_syslog() more flexible: added commands to * return the last 4k of kernel messages, regardless of whether * they've been read or not. Added option to suppress kernel printk's * to the console. Added hook for sending the console messages * elsewhere, in preparation for a serial line console (someday). * Ted Ts'o, 2/11/93. * Modified for sysctl support, 1/8/97, Chris Horn. * Fixed SMP synchronization, 08/08/99, Manfred Spraul * manfred@colorfullife.com * Rewrote bits to get rid of console_lock * 01Mar01 Andrew Morton */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> #include <linux/memblock.h> #include <linux/syscalls.h> #include <linux/syscore_ops.h> #include <linux/vmcore_info.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> #include <linux/cpu.h> #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> #include <linux/ctype.h> #include <linux/uio.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> #include <asm/sections.h> #include <trace/events/initcall.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> #include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" #include "internal.h" int console_printk[4] = { CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); EXPORT_TRACEPOINT_SYMBOL_GPL(console); /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. */ int oops_in_progress; EXPORT_SYMBOL(oops_in_progress); /* * console_mutex protects console_list updates and console->flags updates. * The flags are synchronized only for consoles that are registered, i.e. * accessible via the console list. */ static DEFINE_MUTEX(console_mutex); /* * console_sem protects updates to console->seq * and also provides serialization for console printing. */ static DEFINE_SEMAPHORE(console_sem, 1); HLIST_HEAD(console_list); EXPORT_SYMBOL_GPL(console_list); DEFINE_STATIC_SRCU(console_srcu); /* * System may need to suppress printk message under certain * circumstances, like after kernel panic happens. */ int __read_mostly suppress_printk; #ifdef CONFIG_LOCKDEP static struct lockdep_map console_lock_dep_map = { .name = "console_lock" }; void lockdep_assert_console_list_lock_held(void) { lockdep_assert_held(&console_mutex); } EXPORT_SYMBOL(lockdep_assert_console_list_lock_held); #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC bool console_srcu_read_lock_is_held(void) { return srcu_read_lock_held(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock_is_held); #endif enum devkmsg_log_bits { __DEVKMSG_LOG_BIT_ON = 0, __DEVKMSG_LOG_BIT_OFF, __DEVKMSG_LOG_BIT_LOCK, }; enum devkmsg_log_masks { DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), }; /* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ #define DEVKMSG_LOG_MASK_DEFAULT 0 static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; static int __control_devkmsg(char *str) { size_t len; if (!str) return -EINVAL; len = str_has_prefix(str, "on"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_ON; return len; } len = str_has_prefix(str, "off"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_OFF; return len; } len = str_has_prefix(str, "ratelimit"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; return len; } return -EINVAL; } static int __init control_devkmsg(char *str) { if (__control_devkmsg(str) < 0) { pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; } /* * Set sysctl string accordingly: */ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) strscpy(devkmsg_log_str, "on"); else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) strscpy(devkmsg_log_str, "off"); /* else "ratelimit" which is set by default. */ /* * Sysctl cannot change it anymore. The kernel command line setting of * this parameter is to force the setting to be permanent throughout the * runtime of the system. This is a precation measure against userspace * trying to be a smarta** and attempting to change it up on us. */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; return 1; } __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char old_str[DEVKMSG_STR_MAX_SIZE]; unsigned int old; int err; if (write) { if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) return -EINVAL; old = devkmsg_log; strscpy(old_str, devkmsg_log_str); } err = proc_dostring(table, write, buffer, lenp, ppos); if (err) return err; if (write) { err = __control_devkmsg(devkmsg_log_str); /* * Do not accept an unknown string OR a known string with * trailing crap... */ if (err < 0 || (err + 1 != *lenp)) { /* ... and restore old setting. */ devkmsg_log = old; strscpy(devkmsg_log_str, old_str); return -EINVAL; } } return 0; } #endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ /** * console_list_lock - Lock the console list * * For console list or console->flags updates */ void console_list_lock(void) { /* * In unregister_console() and console_force_preferred_locked(), * synchronize_srcu() is called with the console_list_lock held. * Therefore it is not allowed that the console_list_lock is taken * with the srcu_lock held. * * Detecting if this context is really in the read-side critical * section is only possible if the appropriate debug options are * enabled. */ WARN_ON_ONCE(debug_lockdep_rcu_enabled() && srcu_read_lock_held(&console_srcu)); mutex_lock(&console_mutex); } EXPORT_SYMBOL(console_list_lock); /** * console_list_unlock - Unlock the console list * * Counterpart to console_list_lock() */ void console_list_unlock(void) { mutex_unlock(&console_mutex); } EXPORT_SYMBOL(console_list_unlock); /** * console_srcu_read_lock - Register a new reader for the * SRCU-protected console list * * Use for_each_console_srcu() to iterate the console list * * Context: Any context. * Return: A cookie to pass to console_srcu_read_unlock(). */ int console_srcu_read_lock(void) __acquires(&console_srcu) { return srcu_read_lock_nmisafe(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock); /** * console_srcu_read_unlock - Unregister an old reader from * the SRCU-protected console list * @cookie: cookie returned from console_srcu_read_lock() * * Counterpart to console_srcu_read_lock() */ void console_srcu_read_unlock(int cookie) __releases(&console_srcu) { srcu_read_unlock_nmisafe(&console_srcu, cookie); } EXPORT_SYMBOL(console_srcu_read_unlock); /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ #define down_console_sem() do { \ down(&console_sem);\ mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ } while (0) static int __down_trylock_console_sem(unsigned long ip) { int lock_failed; unsigned long flags; /* * Here and in __up_console_sem() we need to be in safe mode, * because spindump/WARN/etc from under console ->lock will * deadlock in printk()->down_trylock_console_sem() otherwise. */ printk_safe_enter_irqsave(flags); lock_failed = down_trylock(&console_sem); printk_safe_exit_irqrestore(flags); if (lock_failed) return 1; mutex_acquire(&console_lock_dep_map, 0, 1, ip); return 0; } #define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) static void __up_console_sem(unsigned long ip) { unsigned long flags; mutex_release(&console_lock_dep_map, ip); printk_safe_enter_irqsave(flags); up(&console_sem); printk_safe_exit_irqrestore(flags); } #define up_console_sem() __up_console_sem(_RET_IP_) static bool panic_in_progress(void) { return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } /* Return true if a panic is in progress on the current CPU. */ bool this_cpu_in_panic(void) { /* * We can use raw_smp_processor_id() here because it is impossible for * the task to be migrated to the panic_cpu, or away from it. If * panic_cpu has already been set, and we're not currently executing on * that CPU, then we never will be. */ return unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id()); } /* * Return true if a panic is in progress on a remote CPU. * * On true, the local CPU should immediately release any printing resources * that may be needed by the panic CPU. */ bool other_cpu_in_panic(void) { return (panic_in_progress() && !this_cpu_in_panic()); } /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's * definitely not the perfect debug tool (we don't know if _WE_ * hold it and are racing, but it helps tracking those weird code * paths in the console code where we end up in places I want * locked without the console semaphore held). */ static int console_locked; /* * Array of consoles built from command line options (console=) */ #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int preferred_console = -1; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; enum con_msg_format_flags { MSG_FORMAT_DEFAULT = 0, MSG_FORMAT_SYSLOG = (1 << 0), }; static int console_msg_format = MSG_FORMAT_DEFAULT; /* * The printk log buffer consists of a sequenced collection of records, each * containing variable length message text. Every record also contains its * own meta-data (@info). * * Every record meta-data carries the timestamp in microseconds, as well as * the standard userspace syslog level and syslog facility. The usual kernel * messages use LOG_KERN; userspace-injected messages always carry a matching * syslog facility, by default LOG_USER. The origin of every message can be * reliably determined that way. * * The human readable log message of a record is available in @text, the * length of the message text in @text_len. The stored message is not * terminated. * * Optionally, a record can carry a dictionary of properties (key/value * pairs), to provide userspace with a machine-readable message context. * * Examples for well-defined, commonly used property names are: * DEVICE=b12:8 device identifier * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname * SUBSYSTEM=pci driver-core subsystem name * * Valid characters in property names are [a-zA-Z0-9.-_]. Property names * and values are terminated by a '\0' character. * * Example of record values: * record.text_buf = "it's a line" (unterminated) * record.info.seq = 56 * record.info.ts_nsec = 36863 * record.info.text_len = 11 * record.info.facility = 0 (LOG_KERN) * record.info.flags = 0 * record.info.level = 3 (LOG_ERR) * record.info.caller_id = 299 (task 299) * record.info.dev_info.subsystem = "pci" (terminated) * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) * * The 'struct printk_info' buffer must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n" * * Users of the export format should ignore possible additional values * separated by ',', and find the message after the ';' character. * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible * non-prinatable characters are escaped in the "\xff" notation. */ /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); /* * Specifies if a legacy console is registered. If legacy consoles are * present, it is necessary to perform the console lock/unlock dance * whenever console flushing should occur. */ bool have_legacy_console; /* * Specifies if an nbcon console is registered. If nbcon consoles are present, * synchronous printing of legacy consoles will not occur during panic until * the backtrace has been stored to the ringbuffer. */ bool have_nbcon_console; /* * Specifies if a boot console is registered. If boot consoles are present, * nbcon consoles cannot print simultaneously and must be synchronized by * the console lock. This is because boot consoles and nbcon consoles may * have mapped the same hardware. */ bool have_boot_console; /* See printk_legacy_allow_panic_sync() for details. */ bool legacy_allow_panic_sync; #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); static DECLARE_WAIT_QUEUE_HEAD(legacy_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; /* True when _all_ printer threads are available for printing. */ bool printk_kthreads_running; struct latched_seq { seqcount_latch_t latch; u64 val[2]; }; /* * The next printk record to read after the last 'clear' command. There are * two copies (updated with seqcount_latch) so that reads can locklessly * access a valid value. Writers are synchronized by @syslog_lock. */ static struct latched_seq clear_seq = { .latch = SEQCNT_LATCH_ZERO(clear_seq.latch), .val[0] = 0, .val[1] = 0, }; #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) #define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; /* * Define the average message size. This only affects the number of * descriptors that will be available. Underestimating is better than * overestimating (too many available descriptors is better than not enough). */ #define PRB_AVGBITS 5 /* 32 character average length */ #if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS #error CONFIG_LOG_BUF_SHIFT value too small. #endif _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, PRB_AVGBITS, &__log_buf[0]); static struct printk_ringbuffer printk_rb_dynamic; struct printk_ringbuffer *prb = &printk_rb_static; /* * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before * per_cpu_areas are initialised. This variable is set to true when * it's safe to access per-CPU data. */ static bool __printk_percpu_data_ready __ro_after_init; bool printk_percpu_data_ready(void) { return __printk_percpu_data_ready; } /* Must be called under syslog_lock. */ static void latched_seq_write(struct latched_seq *ls, u64 val) { write_seqcount_latch_begin(&ls->latch); ls->val[0] = val; write_seqcount_latch(&ls->latch); ls->val[1] = val; write_seqcount_latch_end(&ls->latch); } /* Can be called from any context. */ static u64 latched_seq_read_nolock(struct latched_seq *ls) { unsigned int seq; unsigned int idx; u64 val; do { seq = read_seqcount_latch(&ls->latch); idx = seq & 0x1; val = ls->val[idx]; } while (read_seqcount_latch_retry(&ls->latch, seq)); return val; } /* Return log buffer address */ char *log_buf_addr_get(void) { return log_buf; } /* Return log buffer size */ u32 log_buf_len_get(void) { return log_buf_len; } /* * Define how much of the log buffer we could take at maximum. The value * must be greater than two. Note that only half of the buffer is available * when the index points to the middle. */ #define MAX_LOG_TAKE_PART 4 static const char trunc_msg[] = "<truncated>"; static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) { /* * The message should not take the whole buffer. Otherwise, it might * get removed too soon. */ u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; if (*text_len > max_text_len) *text_len = max_text_len; /* enable the warning message (if there is room) */ *trunc_msg_len = strlen(trunc_msg); if (*text_len >= *trunc_msg_len) *text_len -= *trunc_msg_len; else *trunc_msg_len = 0; } int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); static int syslog_action_restricted(int type) { if (dmesg_restrict) return 1; /* * Unless restricted, we allow "read all" and "get buffer size" * for everybody. */ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; } static int check_syslog_permissions(int type, int source) { /* * If this is from /proc/kmsg and we've already opened it, then we've * already done the capabilities checks at open time. */ if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) goto ok; return -EPERM; } ok: return security_syslog(type); } static void append_char(char **pp, char *e, char c) { if (*pp < e) *(*pp)++ = c; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { u64 ts_usec = info->ts_nsec; char caller[20]; #ifdef CONFIG_PRINTK_CALLER u32 id = info->caller_id; snprintf(caller, sizeof(caller), ",caller=%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); #else caller[0] = '\0'; #endif do_div(ts_usec, 1000); return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", (info->facility << 3) | info->level, info->seq, ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); } static ssize_t msg_add_ext_text(char *buf, size_t size, const char *text, size_t text_len, unsigned char endc) { char *p = buf, *e = buf + size; size_t i; /* escape non-printable characters */ for (i = 0; i < text_len; i++) { unsigned char c = text[i]; if (c < ' ' || c >= 127 || c == '\\') p += scnprintf(p, e - p, "\\x%02x", c); else append_char(&p, e, c); } append_char(&p, e, endc); return p - buf; } static ssize_t msg_add_dict_text(char *buf, size_t size, const char *key, const char *val) { size_t val_len = strlen(val); ssize_t len; if (!val_len) return 0; len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); return len; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { ssize_t len; len = msg_add_ext_text(buf, size, text, text_len, '\n'); if (!dev_info) goto out; len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", dev_info->subsystem); len += msg_add_dict_text(buf + len, size - len, "DEVICE", dev_info->device); out: return len; } /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { atomic64_t seq; struct ratelimit_state rs; struct mutex lock; struct printk_buffers pbufs; }; static __printf(3, 4) __cold int devkmsg_emit(int facility, int level, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_emit(facility, level, NULL, fmt, args); va_end(args); return r; } static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) { char *buf, *line; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ struct file *file = iocb->ki_filp; struct devkmsg_user *user = file->private_data; size_t len = iov_iter_count(from); ssize_t ret = len; if (len > PRINTKRB_RECORD_MAX) return -EINVAL; /* Ignore when user logging is disabled. */ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return len; /* Ratelimit when not explicitly enabled. */ if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { if (!___ratelimit(&user->rs, current->comm)) return ret; } buf = kmalloc(len+1, GFP_KERNEL); if (buf == NULL) return -ENOMEM; buf[len] = '\0'; if (!copy_from_iter_full(buf, len, from)) { kfree(buf); return -EFAULT; } /* * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace * the decimal value represents 32bit, the lower 3 bit are the log * level, the rest are the log facility. * * If no prefix or no userspace facility is specified, we * enforce LOG_USER, to be able to reliably distinguish * kernel-generated messages from userspace-injected ones. */ line = buf; if (line[0] == '<') { char *endp = NULL; unsigned int u; u = simple_strtoul(line + 1, &endp, 10); if (endp && endp[0] == '>') { level = LOG_LEVEL(u); if (LOG_FACILITY(u) != 0) facility = LOG_FACILITY(u); endp++; line = endp; } } devkmsg_emit(facility, level, "%s", line); kfree(buf); return ret; } static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; char *outbuf = &user->pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &user->pbufs, }; ssize_t ret; ret = mutex_lock_interruptible(&user->lock); if (ret) return ret; if (!printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; goto out; } /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ ret = wait_event_interruptible(log_wait, printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)); /* LMM(devkmsg_read:A) */ if (ret) goto out; } if (pmsg.dropped) { /* our last seen message is gone, return error and reset */ atomic64_set(&user->seq, pmsg.seq); ret = -EPIPE; goto out; } atomic64_set(&user->seq, pmsg.seq + 1); if (pmsg.outbuf_len > count) { ret = -EINVAL; goto out; } if (copy_to_user(buf, outbuf, pmsg.outbuf_len)) { ret = -EFAULT; goto out; } ret = pmsg.outbuf_len; out: mutex_unlock(&user->lock); return ret; } /* * Be careful when modifying this function!!! * * Only few operations are supported because the device works only with the * entire variable length messages (records). Non-standard values are * returned in the other cases and has been this way for quite some time. * User space applications might depend on this behavior. */ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) { struct devkmsg_user *user = file->private_data; loff_t ret = 0; if (offset) return -ESPIPE; switch (whence) { case SEEK_SET: /* the first record */ atomic64_set(&user->seq, prb_first_valid_seq(prb)); break; case SEEK_DATA: /* * The first record after the last SYSLOG_ACTION_CLEAR, * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq)); break; case SEEK_END: /* after the last record */ atomic64_set(&user->seq, prb_next_seq(prb)); break; default: ret = -EINVAL; } return ret; } static __poll_t devkmsg_poll(struct file *file, poll_table *wait) { struct devkmsg_user *user = file->private_data; struct printk_info info; __poll_t ret = 0; poll_wait(file, &log_wait, wait); if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != atomic64_read(&user->seq)) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; } return ret; } static int devkmsg_open(struct inode *inode, struct file *file) { struct devkmsg_user *user; int err; if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return -EPERM; /* write-only does not need any file context */ if ((file->f_flags & O_ACCMODE) != O_WRONLY) { err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, SYSLOG_FROM_READER); if (err) return err; } user = kvmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); if (!user) return -ENOMEM; ratelimit_default_init(&user->rs); ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); mutex_init(&user->lock); atomic64_set(&user->seq, prb_first_valid_seq(prb)); file->private_data = user; return 0; } static int devkmsg_release(struct inode *inode, struct file *file) { struct devkmsg_user *user = file->private_data; ratelimit_state_exit(&user->rs); mutex_destroy(&user->lock); kvfree(user); return 0; } const struct file_operations kmsg_fops = { .open = devkmsg_open, .read = devkmsg_read, .write_iter = devkmsg_write, .llseek = devkmsg_llseek, .poll = devkmsg_poll, .release = devkmsg_release, }; #ifdef CONFIG_VMCORE_INFO /* * This appends the listed symbols to /proc/vmcore * * /proc/vmcore is used by various utilities, like crash and makedumpfile to * obtain access to symbols that are otherwise very difficult to locate. These * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. */ void log_buf_vmcoreinfo_setup(void) { struct dev_printk_info *dev_info = NULL; VMCOREINFO_SYMBOL(prb); VMCOREINFO_SYMBOL(printk_rb_static); VMCOREINFO_SYMBOL(clear_seq); /* * Export struct size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); VMCOREINFO_OFFSET(printk_ringbuffer, fail); VMCOREINFO_STRUCT_SIZE(prb_desc_ring); VMCOREINFO_OFFSET(prb_desc_ring, count_bits); VMCOREINFO_OFFSET(prb_desc_ring, descs); VMCOREINFO_OFFSET(prb_desc_ring, infos); VMCOREINFO_OFFSET(prb_desc_ring, head_id); VMCOREINFO_OFFSET(prb_desc_ring, tail_id); VMCOREINFO_STRUCT_SIZE(prb_desc); VMCOREINFO_OFFSET(prb_desc, state_var); VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); VMCOREINFO_OFFSET(prb_data_blk_lpos, next); VMCOREINFO_STRUCT_SIZE(printk_info); VMCOREINFO_OFFSET(printk_info, seq); VMCOREINFO_OFFSET(printk_info, ts_nsec); VMCOREINFO_OFFSET(printk_info, text_len); VMCOREINFO_OFFSET(printk_info, caller_id); VMCOREINFO_OFFSET(printk_info, dev_info); VMCOREINFO_STRUCT_SIZE(dev_printk_info); VMCOREINFO_OFFSET(dev_printk_info, subsystem); VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); VMCOREINFO_OFFSET(dev_printk_info, device); VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); VMCOREINFO_STRUCT_SIZE(prb_data_ring); VMCOREINFO_OFFSET(prb_data_ring, size_bits); VMCOREINFO_OFFSET(prb_data_ring, data); VMCOREINFO_OFFSET(prb_data_ring, head_lpos); VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); VMCOREINFO_SIZE(atomic_long_t); VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); VMCOREINFO_STRUCT_SIZE(latched_seq); VMCOREINFO_OFFSET(latched_seq, val); } #endif /* requested log_buf_len from kernel cmdline */ static unsigned long __initdata new_log_buf_len; /* we practice scaling the ring buffer by powers of 2 */ static void __init log_buf_len_update(u64 size) { if (size > (u64)LOG_BUF_LEN_MAX) { size = (u64)LOG_BUF_LEN_MAX; pr_err("log_buf over 2G is not supported.\n"); } if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) new_log_buf_len = (unsigned long)size; } /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { u64 size; if (!str) return -EINVAL; size = memparse(str, &str); log_buf_len_update(size); return 0; } early_param("log_buf_len", log_buf_len_setup); #ifdef CONFIG_SMP #define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) static void __init log_buf_add_cpu(void) { unsigned int cpu_extra; /* * archs should set up cpu_possible_bits properly with * set_cpu_possible() after setup_arch() but just in * case lets ensure this is valid. */ if (num_possible_cpus() == 1) return; cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; /* by default this will only continue through for large > 64 CPUs */ if (cpu_extra <= __LOG_BUF_LEN / 2) return; pr_info("log_buf_len individual max cpu contribution: %d bytes\n", __LOG_CPU_MAX_BUF_LEN); pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", cpu_extra); pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); log_buf_len_update(cpu_extra + __LOG_BUF_LEN); } #else /* !CONFIG_SMP */ static inline void log_buf_add_cpu(void) {} #endif /* CONFIG_SMP */ static void __init set_percpu_data_ready(void) { __printk_percpu_data_ready = true; } static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_reserved_entry e; struct printk_record dest_r; prb_rec_init_wr(&dest_r, r->info->text_len); if (!prb_reserve(&e, rb, &dest_r)) return 0; memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); dest_r.info->text_len = r->info->text_len; dest_r.info->facility = r->info->facility; dest_r.info->level = r->info->level; dest_r.info->flags = r->info->flags; dest_r.info->ts_nsec = r->info->ts_nsec; dest_r.info->caller_id = r->info->caller_id; memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); prb_final_commit(&e); return prb_record_text_space(&e); } static char setup_text_buf[PRINTKRB_RECORD_MAX] __initdata; static void print_log_buf_usage_stats(void) { unsigned int descs_count = log_buf_len >> PRB_AVGBITS; size_t meta_data_size; meta_data_size = descs_count * (sizeof(struct prb_desc) + sizeof(struct printk_info)); pr_info("log buffer data + meta data: %u + %zu = %zu bytes\n", log_buf_len, meta_data_size, log_buf_len + meta_data_size); } void __init setup_log_buf(int early) { struct printk_info *new_infos; unsigned int new_descs_count; struct prb_desc *new_descs; struct printk_info info; struct printk_record r; unsigned int text_size; size_t new_descs_size; size_t new_infos_size; unsigned long flags; char *new_log_buf; unsigned int free; u64 seq; /* * Some archs call setup_log_buf() multiple times - first is very * early, e.g. from setup_arch(), and second - when percpu_areas * are initialised. */ if (!early) set_percpu_data_ready(); if (log_buf != __log_buf) return; if (!early && !new_log_buf_len) log_buf_add_cpu(); if (!new_log_buf_len) { /* Show the memory stats only once. */ if (!early) goto out; return; } new_descs_count = new_log_buf_len >> PRB_AVGBITS; if (new_descs_count == 0) { pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); goto out; } new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); if (unlikely(!new_log_buf)) { pr_err("log_buf_len: %lu text bytes not available\n", new_log_buf_len); goto out; } new_descs_size = new_descs_count * sizeof(struct prb_desc); new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); if (unlikely(!new_descs)) { pr_err("log_buf_len: %zu desc bytes not available\n", new_descs_size); goto err_free_log_buf; } new_infos_size = new_descs_count * sizeof(struct printk_info); new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); if (unlikely(!new_infos)) { pr_err("log_buf_len: %zu info bytes not available\n", new_infos_size); goto err_free_descs; } prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); prb_init(&printk_rb_dynamic, new_log_buf, ilog2(new_log_buf_len), new_descs, ilog2(new_descs_count), new_infos); local_irq_save(flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; free = __LOG_BUF_LEN; prb_for_each_record(0, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } prb = &printk_rb_dynamic; local_irq_restore(flags); /* * Copy any remaining messages that might have appeared from * NMI context after copying but before switching to the * dynamic buffer. */ prb_for_each_record(seq, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", prb_next_seq(&printk_rb_static) - seq); } print_log_buf_usage_stats(); pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); return; err_free_descs: memblock_free(new_descs, new_descs_size); err_free_log_buf: memblock_free(new_log_buf, new_log_buf_len); out: print_log_buf_usage_stats(); } static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { ignore_loglevel = true; pr_info("debug: ignoring loglevel setting.\n"); return 0; } early_param("ignore_loglevel", ignore_loglevel_setup); module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting (prints all kernel messages to the console)"); static bool suppress_message_printing(int level) { return (level >= console_loglevel && !ignore_loglevel); } #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) { unsigned long lpj; lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ loops_per_msec = (unsigned long long)lpj / 1000 * HZ; get_option(&str, &boot_delay); if (boot_delay > 10 * 1000) boot_delay = 0; pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " "HZ: %d, loops_per_msec: %llu\n", boot_delay, preset_lpj, lpj, HZ, loops_per_msec); return 0; } early_param("boot_delay", boot_delay_setup); static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; bool suppress = !is_printk_force_console() && suppress_message_printing(level); if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress) return; k = (unsigned long long)loops_per_msec * boot_delay; timeout = jiffies + msecs_to_jiffies(boot_delay); while (k) { k--; cpu_relax(); /* * use (volatile) jiffies to prevent * compiler reduction; loop termination via jiffies * is secondary and may or may not happen. */ if (time_after(jiffies, timeout)) break; touch_nmi_watchdog(); } } #else static inline void boot_delay_msec(int level) { } #endif static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); static size_t print_syslog(unsigned int level, char *buf) { return sprintf(buf, "<%u>", level); } static size_t print_time(u64 ts, char *buf) { unsigned long rem_nsec = do_div(ts, 1000000000); return sprintf(buf, "[%5lu.%06lu]", (unsigned long)ts, rem_nsec / 1000); } #ifdef CONFIG_PRINTK_CALLER static size_t print_caller(u32 id, char *buf) { char caller[12]; snprintf(caller, sizeof(caller), "%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); return sprintf(buf, "[%6s]", caller); } #else #define print_caller(id, buf) 0 #endif static size_t info_print_prefix(const struct printk_info *info, bool syslog, bool time, char *buf) { size_t len = 0; if (syslog) len = print_syslog((info->facility << 3) | info->level, buf); if (time) len += print_time(info->ts_nsec, buf + len); len += print_caller(info->caller_id, buf + len); if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { buf[len++] = ' '; buf[len] = '\0'; } return len; } /* * Prepare the record for printing. The text is shifted within the given * buffer to avoid a need for another one. The following operations are * done: * * - Add prefix for each line. * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). * - Add a string terminator. * * Since the produced string is always terminated, the maximum possible * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added * prefixes and the newline. The terminator is not counted. The dropped * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) { size_t text_len = r->info->text_len; size_t buf_size = r->text_buf_size; char *text = r->text_buf; char prefix[PRINTK_PREFIX_MAX]; bool truncated = false; size_t prefix_len; size_t line_len; size_t len = 0; char *next; /* * If the message was truncated because the buffer was not large * enough, treat the available text as if it were the full text. */ if (text_len > buf_size) text_len = buf_size; prefix_len = info_print_prefix(r->info, syslog, time, prefix); /* * @text_len: bytes of unprocessed text * @line_len: bytes of current line _without_ newline * @text: pointer to beginning of current line * @len: number of bytes prepared in r->text_buf */ for (;;) { next = memchr(text, '\n', text_len); if (next) { line_len = next - text; } else { /* Drop truncated line(s). */ if (truncated) break; line_len = text_len; } /* * Truncate the text if there is not enough space to add the * prefix and a trailing newline and a terminator. */ if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ if (len + prefix_len + line_len + 1 + 1 > buf_size) break; text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); /* * Increment the prepared length to include the text and * prefix that were just moved+copied. Also increment for the * newline at the end of this line. If this is the last line, * there is no newline, but it will be added immediately below. */ len += prefix_len + line_len + 1; if (text_len == line_len) { /* * This is the last line. Add the trailing newline * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; } /* * Advance beyond the added prefix and the related line with * its newline. */ text += prefix_len + line_len + 1; /* * The remaining text has only decreased by the line with its * newline. * * Note that @text_len can become zero. It happens when @text * ended with a newline (either due to truncation or the * original string ending with "\n\n"). The loop is correctly * repeated and (if not truncated) an empty line with a prefix * will be prepared. */ text_len -= line_len + 1; } /* * If a buffer was provided, it will be terminated. Space for the * string terminator is guaranteed to be available. The terminator is * not counted in the return value. */ if (buf_size > 0) r->text_buf[len] = 0; return len; } static size_t get_record_print_text_size(struct printk_info *info, unsigned int line_count, bool syslog, bool time) { char prefix[PRINTK_PREFIX_MAX]; size_t prefix_len; prefix_len = info_print_prefix(info, syslog, time, prefix); /* * Each line will be preceded with a prefix. The intermediate * newlines are already within the text, but a final trailing * newline will be added. */ return ((prefix_len * line_count) + info->text_len + 1); } /* * Beginning with @start_seq, find the first record where it and all following * records up to (but not including) @max_seq fit into @size. * * @max_seq is simply an upper bound and does not need to exist. If the caller * does not require an upper bound, -1 can be used for @max_seq. */ static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size, bool syslog, bool time) { struct printk_info info; unsigned int line_count; size_t len = 0; u64 seq; /* Determine the size of the records up to @max_seq. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (info.seq >= max_seq) break; len += get_record_print_text_size(&info, line_count, syslog, time); } /* * Adjust the upper bound for the next loop to avoid subtracting * lengths that were never added. */ if (seq < max_seq) max_seq = seq; /* * Move first record forward until length fits into the buffer. Ignore * newest messages that were not counted in the above cycle. Messages * might appear and get lost in the meantime. This is a best effort * that prevents an infinite loop that could occur with a retry. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (len <= size || info.seq >= max_seq) break; len -= get_record_print_text_size(&info, line_count, syslog, time); } return seq; } /* The caller is responsible for making sure @size is greater than 0. */ static int syslog_print(char __user *buf, int size) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); mutex_lock(&syslog_lock); /* * Wait for the @syslog_seq record to be available. @syslog_seq may * change while waiting. */ do { seq = syslog_seq; mutex_unlock(&syslog_lock); /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */ mutex_lock(&syslog_lock); if (len) goto out; } while (syslog_seq != seq); /* * Copy records that fit into the buffer. The above cycle makes sure * that the first record is always available. */ do { size_t n; size_t skip; int err; if (!prb_read_valid(prb, syslog_seq, &r)) break; if (r.info->seq != syslog_seq) { /* message is gone, move to next valid one */ syslog_seq = r.info->seq; syslog_partial = 0; } /* * To keep reading/counting partial line consistent, * use printk_time value as of the beginning of a line. */ if (!syslog_partial) syslog_time = printk_time; skip = syslog_partial; n = record_print_text(&r, true, syslog_time); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_seq = r.info->seq + 1; n -= syslog_partial; syslog_partial = 0; } else if (!len){ /* partial read(), remember position */ n = size; syslog_partial += n; } else n = 0; if (!n) break; mutex_unlock(&syslog_lock); err = copy_to_user(buf, text + skip, n); mutex_lock(&syslog_lock); if (err) { if (!len) len = -EFAULT; break; } len += n; size -= n; buf += n; } while (size); out: mutex_unlock(&syslog_lock); kfree(text); return len; } static int syslog_print_all(char __user *buf, int size, bool clear) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; bool time; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; time = printk_time; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, size, true, time); prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); prb_for_each_record(seq, prb, seq, &r) { int textlen; textlen = record_print_text(&r, true, time); if (len + textlen > size) { seq--; break; } if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; if (len < 0) break; } if (clear) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, seq); mutex_unlock(&syslog_lock); } kfree(text); return len; } static void syslog_clear(void) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, prb_next_seq(prb)); mutex_unlock(&syslog_lock); } int do_syslog(int type, char __user *buf, int len, int source) { struct printk_info info; bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; error = check_syslog_permissions(type, source); if (error) return error; switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; case SYSLOG_ACTION_OPEN: /* Open log */ break; case SYSLOG_ACTION_READ: /* Read from log */ if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print(buf, len); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; fallthrough; /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_clear(); break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == LOGLEVEL_DEFAULT) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; /* Enable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != LOGLEVEL_DEFAULT) { console_loglevel = saved_console_loglevel; saved_console_loglevel = LOGLEVEL_DEFAULT; } break; /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: if (len < 1 || len > 8) return -EINVAL; if (len < minimum_console_loglevel) len = minimum_console_loglevel; console_loglevel = len; /* Implicitly re-enable logging to console */ saved_console_loglevel = LOGLEVEL_DEFAULT; break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: mutex_lock(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ mutex_unlock(&syslog_lock); return 0; } if (info.seq != syslog_seq) { /* messages are gone, move to first one */ syslog_seq = info.seq; syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of * records, not the length. */ error = prb_next_seq(prb) - syslog_seq; } else { bool time = syslog_partial ? syslog_time : printk_time; unsigned int line_count; u64 seq; prb_for_each_info(syslog_seq, prb, seq, &info, &line_count) { error += get_record_print_text_size(&info, line_count, true, time); time = printk_time; } error -= syslog_partial; } mutex_unlock(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map console_owner_dep_map = { .name = "console_owner" }; #endif static DEFINE_RAW_SPINLOCK(console_owner_lock); static struct task_struct *console_owner; static bool console_waiter; /** * console_lock_spinning_enable - mark beginning of code where another * thread might safely busy wait * * This basically converts console_lock into a spinlock. This marks * the section where the console_lock owner can not sleep, because * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ void console_lock_spinning_enable(void) { /* * Do not use spinning in panic(). The panic CPU wants to keep the lock. * Non-panic CPUs abandon the flush anyway. * * Just keep the lockdep annotation. The panic-CPU should avoid * taking console_owner_lock because it might cause a deadlock. * This looks like the easiest way how to prevent false lockdep * reports without handling races a lockless way. */ if (panic_in_progress()) goto lockdep; raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); lockdep: /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter * @cookie: cookie returned from console_srcu_read_lock() * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer * safe to start busy waiting for the lock. Second, it checks if * there is a busy waiter and passes the lock rights to her. * * Important: Callers lose both the console_lock and the SRCU read lock if * there was a busy waiter. They must not touch items synchronized by * console_lock or SRCU read lock in this case. * * Return: 1 if the lock rights were passed, 0 otherwise. */ int console_lock_spinning_disable_and_check(int cookie) { int waiter; /* * Ignore spinning waiters during panic() because they might get stopped * or blocked at any time, * * It is safe because nobody is allowed to start spinning during panic * in the first place. If there has been a waiter then non panic CPUs * might stay spinning. They would get stopped anyway. The panic context * will never start spinning and an interrupted spin on panic CPU will * never continue. */ if (panic_in_progress()) { /* Keep lockdep happy. */ spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; raw_spin_unlock(&console_owner_lock); if (!waiter) { spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); spin_release(&console_owner_dep_map, _THIS_IP_); /* * Preserve lockdep lock ordering. Release the SRCU read lock before * releasing the console_lock. */ console_srcu_read_unlock(cookie); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ mutex_release(&console_lock_dep_map, _THIS_IP_); return 1; } /** * console_trylock_spinning - try to get console_lock by busy waiting * * This allows to busy wait for the console_lock when the current * owner is running in specially marked sections. It means that * the current owner is running and cannot reschedule until it * is ready to lose the lock. * * Return: 1 if we got the lock, 0 othrewise */ static int console_trylock_spinning(void) { struct task_struct *owner = NULL; bool waiter; bool spin = false; unsigned long flags; if (console_trylock()) return 1; /* * It's unsafe to spin once a panic has begun. If we are the * panic CPU, we may have already halted the owner of the * console_sem. If we are not the panic CPU, then we should * avoid taking console_sem, so the panic CPU has a better * chance of cleanly acquiring it later. */ if (panic_in_progress()) return 0; printk_safe_enter_irqsave(flags); raw_spin_lock(&console_owner_lock); owner = READ_ONCE(console_owner); waiter = READ_ONCE(console_waiter); if (!waiter && owner && owner != current) { WRITE_ONCE(console_waiter, true); spin = true; } raw_spin_unlock(&console_owner_lock); /* * If there is an active printk() writing to the * consoles, instead of having it write our data too, * see if we can offload that load from the active * printer, and do some printing ourselves. * Go into a spin only if there isn't already a waiter * spinning, and there is an active printer, and * that active printer isn't us (recursive printk?). */ if (!spin) { printk_safe_exit_irqrestore(flags); return 0; } /* We spin waiting for the owner to release us */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); spin_release(&console_owner_dep_map, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* * The owner passed the console lock to us. * Since we did not spin on console lock, annotate * this as a trylock. Otherwise lockdep will * complain. */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); /* * Update @console_may_schedule for trylock because the previous * owner may have been schedulable. */ console_may_schedule = 0; return 1; } /* * Recursion is tracked separately on each CPU. If NMIs are supported, an * additional NMI context per CPU is also separately tracked. Until per-CPU * is available, a separate "early tracking" is performed. */ static DEFINE_PER_CPU(u8, printk_count); static u8 printk_count_early; #ifdef CONFIG_HAVE_NMI static DEFINE_PER_CPU(u8, printk_count_nmi); static u8 printk_count_nmi_early; #endif /* * Recursion is limited to keep the output sane. printk() should not require * more than 1 level of recursion (allowing, for example, printk() to trigger * a WARN), but a higher value is used in case some printk-internal errors * exist, such as the ringbuffer validation checks failing. */ #define PRINTK_MAX_RECURSION 3 /* * Return a pointer to the dedicated counter for the CPU+context of the * caller. */ static u8 *__printk_recursion_counter(void) { #ifdef CONFIG_HAVE_NMI if (in_nmi()) { if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count_nmi); return &printk_count_nmi_early; } #endif if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count); return &printk_count_early; } /* * Enter recursion tracking. Interrupts are disabled to simplify tracking. * The caller must check the boolean return value to see if the recursion is * allowed. On failure, interrupts are not disabled. * * @recursion_ptr must be a variable of type (u8 *) and is the same variable * that is passed to printk_exit_irqrestore(). */ #define printk_enter_irqsave(recursion_ptr, flags) \ ({ \ bool success = true; \ \ typecheck(u8 *, recursion_ptr); \ local_irq_save(flags); \ (recursion_ptr) = __printk_recursion_counter(); \ if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \ local_irq_restore(flags); \ success = false; \ } else { \ (*(recursion_ptr))++; \ } \ success; \ }) /* Exit recursion tracking, restoring interrupts. */ #define printk_exit_irqrestore(recursion_ptr, flags) \ do { \ typecheck(u8 *, recursion_ptr); \ (*(recursion_ptr))--; \ local_irq_restore(flags); \ } while (0) int printk_delay_msec __read_mostly; static inline void printk_delay(int level) { boot_delay_msec(level); if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; while (m--) { mdelay(1); touch_nmi_watchdog(); } } } static inline u32 printk_caller_id(void) { return in_task() ? task_pid_nr(current) : 0x80000000 + smp_processor_id(); } /** * printk_parse_prefix - Parse level and control flags. * * @text: The terminated text message. * @level: A pointer to the current level value, will be updated. * @flags: A pointer to the current printk_info flags, will be updated. * * @level may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @level must be set to * LOGLEVEL_DEFAULT in order to be updated with the parsed value. * * @flags may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @flags will be OR'd with the parsed * value. * * Return: The length of the parsed level and control flags. */ u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags) { u16 prefix_len = 0; int kern_level; while (*text) { kern_level = printk_get_level(text); if (!kern_level) break; switch (kern_level) { case '0' ... '7': if (level && *level == LOGLEVEL_DEFAULT) *level = kern_level - '0'; break; case 'c': /* KERN_CONT */ if (flags) *flags |= LOG_CONT; } prefix_len += 2; text += 2; } return prefix_len; } __printf(5, 0) static u16 printk_sprint(char *text, u16 size, int facility, enum printk_info_flags *flags, const char *fmt, va_list args) { u16 text_len; text_len = vscnprintf(text, size, fmt, args); /* Mark and strip a trailing newline. */ if (text_len && text[text_len - 1] == '\n') { text_len--; *flags |= LOG_NEWLINE; } /* Strip log level and control flags. */ if (facility == 0) { u16 prefix_len; prefix_len = printk_parse_prefix(text, NULL, NULL); if (prefix_len) { text_len -= prefix_len; memmove(text, text + prefix_len, text_len); } } trace_console(text, text_len); return text_len; } __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct prb_reserved_entry e; enum printk_info_flags flags = 0; struct printk_record r; unsigned long irqflags; u16 trunc_msg_len = 0; char prefix_buf[8]; u8 *recursion_ptr; u16 reserve_size; va_list args2; u32 caller_id; u16 text_len; int ret = 0; u64 ts_nsec; if (!printk_enter_irqsave(recursion_ptr, irqflags)) return 0; /* * Since the duration of printk() can vary depending on the message * and state of the ringbuffer, grab the timestamp now so that it is * close to the call of printk(). This provides a more deterministic * timestamp with respect to the caller. */ ts_nsec = local_clock(); caller_id = printk_caller_id(); /* * The sprintf needs to come first since the syslog prefix might be * passed in as a parameter. An extra byte must be reserved so that * later the vscnprintf() into the reserved buffer has room for the * terminating '\0', which is not counted by vsnprintf(). */ va_copy(args2, args); reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1; va_end(args2); if (reserve_size > PRINTKRB_RECORD_MAX) reserve_size = PRINTKRB_RECORD_MAX; /* Extract log level or control flags. */ if (facility == 0) printk_parse_prefix(&prefix_buf[0], &level, &flags); if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dev_info) flags |= LOG_NEWLINE; if (is_printk_force_console()) flags |= LOG_FORCE_CON; if (flags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); if (prb_reserve_in_last(&e, prb, &r, caller_id, PRINTKRB_RECORD_MAX)) { text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, facility, &flags, fmt, args); r.info->text_len += text_len; if (flags & LOG_FORCE_CON) r.info->flags |= LOG_FORCE_CON; if (flags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); } else { prb_commit(&e); } ret = text_len; goto out; } } /* * Explicitly initialize the record before every prb_reserve() call. * prb_reserve_in_last() and prb_reserve() purposely invalidate the * structure when they fail. */ prb_rec_init_wr(&r, reserve_size); if (!prb_reserve(&e, prb, &r)) { /* truncate the message if it is too long for empty buffer */ truncate_msg(&reserve_size, &trunc_msg_len); prb_rec_init_wr(&r, reserve_size + trunc_msg_len); if (!prb_reserve(&e, prb, &r)) goto out; } /* fill message */ text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args); if (trunc_msg_len) memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); r.info->text_len = text_len + trunc_msg_len; r.info->facility = facility; r.info->level = level & 7; r.info->flags = flags & 0x1f; r.info->ts_nsec = ts_nsec; r.info->caller_id = caller_id; if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); /* A message without a trailing newline can be continued. */ if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); ret = text_len + trunc_msg_len; out: printk_exit_irqrestore(recursion_ptr, irqflags); return ret; } /* * This acts as a one-way switch to allow legacy consoles to print from * the printk() caller context on a panic CPU. It also attempts to flush * the legacy consoles in this context. */ void printk_legacy_allow_panic_sync(void) { struct console_flush_type ft; legacy_allow_panic_sync = true; printk_get_console_flush_type(&ft); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } bool __read_mostly debug_non_panic_cpus; #ifdef CONFIG_PRINTK_CALLER static int __init debug_non_panic_cpus_setup(char *str) { debug_non_panic_cpus = true; pr_info("allow messages from non-panic CPUs in panic()\n"); return 0; } early_param("debug_non_panic_cpus", debug_non_panic_cpus_setup); module_param(debug_non_panic_cpus, bool, 0644); MODULE_PARM_DESC(debug_non_panic_cpus, "allow messages from non-panic CPUs in panic()"); #endif asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct console_flush_type ft; int printed_len; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) return 0; /* * The messages on the panic CPU are the most important. If * non-panic CPUs are generating any messages, they will be * silently dropped. */ if (other_cpu_in_panic() && !debug_non_panic_cpus && !panic_triggering_all_cpu_backtrace) return 0; printk_get_console_flush_type(&ft); /* If called from the scheduler, we can not call up(). */ if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; ft.legacy_offload |= ft.legacy_direct; ft.legacy_direct = false; } printk_delay(level); printed_len = vprintk_store(facility, level, dev_info, fmt, args); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_direct) { /* * The caller may be holding system-critical or * timing-sensitive locks. Disable preemption during * printing of all remaining records to all consoles so that * this context can return as soon as possible. Hopefully * another printk() caller will take over the printing. */ preempt_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers. With the * spinning variant, this context tries to take over the * printing from another printing context. */ if (console_trylock_spinning()) console_unlock(); preempt_enable(); } if (ft.legacy_offload) defer_console_output(); else wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); int vprintk_default(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } EXPORT_SYMBOL_GPL(vprintk_default); asmlinkage __visible int _printk(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk(fmt, args); va_end(args); return r; } EXPORT_SYMBOL(_printk); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); #else /* CONFIG_PRINTK */ #define printk_time false #define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 #define prb_next_seq(rb) 0 static u64 syslog_seq; static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } #endif /* CONFIG_PRINTK */ #ifdef CONFIG_EARLY_PRINTK struct console *early_console; asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; char buf[512]; int n; if (!early_console) return; va_start(ap, fmt); n = vscnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); early_console->write(early_console, buf, n); } #endif static void set_user_specified(struct console_cmdline *c, bool user_specified) { if (!user_specified) return; /* * @c console was defined by the user on the command line. * Do not clear when added twice also by SPCR or the device tree. */ c->user_specified = true; /* At least one console defined by the user on the command line. */ console_set_on_cmdline = 1; } static int __add_preferred_console(const char *name, const short idx, const char *devname, char *options, char *brl_options, bool user_specified) { struct console_cmdline *c; int i; if (!name && !devname) return -EINVAL; /* * We use a signed short index for struct console for device drivers to * indicate a not yet assigned index or port. However, a negative index * value is not valid when the console name and index are defined on * the command line. */ if (name && idx < 0) return -EINVAL; /* * See if this tty is not yet registered, and * if we have a slot free. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if ((name && strcmp(c->name, name) == 0 && c->index == idx) || (devname && strcmp(c->devname, devname) == 0)) { if (!brl_options) preferred_console = i; set_user_specified(c, user_specified); return 0; } } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) preferred_console = i; if (name) strscpy(c->name, name); if (devname) strscpy(c->devname, devname); c->options = options; set_user_specified(c, user_specified); braille_set_options(c, brl_options); c->index = idx; return 0; } static int __init console_msg_format_setup(char *str) { if (!strcmp(str, "syslog")) console_msg_format = MSG_FORMAT_SYSLOG; if (!strcmp(str, "default")) console_msg_format = MSG_FORMAT_DEFAULT; return 1; } __setup("console_msg_format=", console_msg_format_setup); /* * Set up a console. Called via do_early_param() in init/main.c * for each "console=" parameter in the boot command line. */ static int __init console_setup(char *str) { static_assert(sizeof(console_cmdline[0].devname) >= sizeof(console_cmdline[0].name) + 4); char buf[sizeof(console_cmdline[0].devname)]; char *brl_options = NULL; char *ttyname = NULL; char *devname = NULL; char *options; char *s; int idx; /* * console="" or console=null have been suggested as a way to * disable console output. Use ttynull that has been created * for exactly this purpose. */ if (str[0] == 0 || strcmp(str, "null") == 0) { __add_preferred_console("ttynull", 0, NULL, NULL, NULL, true); return 1; } if (_braille_console_setup(&str, &brl_options)) return 1; /* For a DEVNAME:0.0 style console the character device is unknown early */ if (strchr(str, ':')) devname = buf; else ttyname = buf; /* * Decode str into name, index, options. */ if (ttyname && isdigit(str[0])) scnprintf(buf, sizeof(buf), "ttyS%s", str); else strscpy(buf, str); options = strchr(str, ','); if (options) *(options++) = 0; #ifdef __sparc__ if (!strcmp(str, "ttya")) strscpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) strscpy(buf, "ttyS1"); #endif for (s = buf; *s; s++) if ((ttyname && isdigit(*s)) || *s == ',') break; /* @idx will get defined when devname matches. */ if (devname) idx = -1; else idx = simple_strtoul(s, NULL, 10); *s = 0; __add_preferred_console(ttyname, idx, devname, options, brl_options, true); return 1; } __setup("console=", console_setup); /** * add_preferred_console - add a device to the list of preferred consoles. * @name: device name * @idx: device index * @options: options for this console * * The last preferred console added will be used for kernel messages * and stdin/out/err for init. Normally this is used by console_setup * above to handle user-supplied console arguments; however it can also * be used by arch-specific code either to override the user or more * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ int add_preferred_console(const char *name, const short idx, char *options) { return __add_preferred_console(name, idx, NULL, options, NULL, false); } /** * match_devname_and_update_preferred_console - Update a preferred console * when matching devname is found. * @devname: DEVNAME:0.0 style device name * @name: Name of the corresponding console driver, e.g. "ttyS" * @idx: Console index, e.g. port number. * * The function checks whether a device with the given @devname is * preferred via the console=DEVNAME:0.0 command line option. * It fills the missing console driver name and console index * so that a later register_console() call could find (match) * and enable this device. * * It might be used when a driver subsystem initializes particular * devices with already known DEVNAME:0.0 style names. And it * could predict which console driver name and index this device * would later get associated with. * * Return: 0 on success, negative error code on failure. */ int match_devname_and_update_preferred_console(const char *devname, const char *name, const short idx) { struct console_cmdline *c = console_cmdline; int i; if (!devname || !strlen(devname) || !name || !strlen(name) || idx < 0) return -EINVAL; for (i = 0; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if (!strcmp(devname, c->devname)) { pr_info("associate the preferred console \"%s\" with \"%s%d\"\n", devname, name, idx); strscpy(c->name, name); c->index = idx; return 0; } } return -ENOENT; } EXPORT_SYMBOL_GPL(match_devname_and_update_preferred_console); bool console_suspend_enabled = true; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) { console_suspend_enabled = false; return 1; } __setup("no_console_suspend", console_suspend_disable); module_param_named(console_suspend, console_suspend_enabled, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); static bool printk_console_no_auto_verbose; void console_verbose(void) { if (console_loglevel && !printk_console_no_auto_verbose) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } EXPORT_SYMBOL_GPL(console_verbose); module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644); MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); /** * console_suspend_all - suspend the console subsystem * * This disables printk() while we go into suspend states */ void console_suspend_all(void) { struct console *con; if (!console_suspend_enabled) return; pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); pr_flush(1000, true); console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags | CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see that they are suspended so that it * is guaranteed that all printing has stopped when this function * completes. */ synchronize_srcu(&console_srcu); } void console_resume_all(void) { struct console_flush_type ft; struct console *con; if (!console_suspend_enabled) return; console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see they are no longer suspended so * that they are guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); printk_get_console_flush_type(&ft); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); pr_flush(1000, true); } /** * console_cpu_notify - print deferred console messages after CPU hotplug * @cpu: unused * * If printk() is called from a CPU that is not online yet, the messages * will be printed on the console only if there are CON_ANYTIME consoles. * This function is called when a new CPU comes online (or fails to come * up) or goes offline. */ static int console_cpu_notify(unsigned int cpu) { struct console_flush_type ft; if (!cpuhp_tasks_frozen) { printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } return 0; } /** * console_lock - block the console subsystem from printing * * Acquires a lock which guarantees that no consoles will * be in or enter their write() callback. * * Can sleep, returns nothing. */ void console_lock(void) { might_sleep(); /* On panic, the console_lock must be left to the panic cpu. */ while (other_cpu_in_panic()) msleep(1000); down_console_sem(); console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); /** * console_trylock - try to block the console subsystem from printing * * Try to acquire a lock which guarantees that no consoles will * be in or enter their write() callback. * * returns 1 on success, and 0 on failure to acquire the lock. */ int console_trylock(void) { /* On panic, the console_lock must be left to the panic cpu. */ if (other_cpu_in_panic()) return 0; if (down_trylock_console_sem()) return 0; console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { return console_locked; } EXPORT_SYMBOL(is_console_locked); static void __console_unlock(void) { console_locked = 0; up_console_sem(); } #ifdef CONFIG_PRINTK /* * Prepend the message in @pmsg->pbufs->outbuf. This is achieved by shifting * the existing message over and inserting the scratchbuf message. * * @pmsg is the original printk message. * @fmt is the printf format of the message which will prepend the existing one. * * If there is not enough space in @pmsg->pbufs->outbuf, the existing * message text will be sufficiently truncated. * * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated. */ __printf(2, 3) static void console_prepend_message(struct printk_message *pmsg, const char *fmt, ...) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; va_list args; size_t len; va_start(args, fmt); len = vscnprintf(scratchbuf, scratchbuf_sz, fmt, args); va_end(args); /* * Make sure outbuf is sufficiently large before prepending. * Keep at least the prefix when the message must be truncated. * It is a rather theoretical problem when someone tries to * use a minimalist buffer. */ if (WARN_ON_ONCE(len + PRINTK_PREFIX_MAX >= outbuf_sz)) return; if (pmsg->outbuf_len + len >= outbuf_sz) { /* Truncate the message, but keep it terminated. */ pmsg->outbuf_len = outbuf_sz - (len + 1); outbuf[pmsg->outbuf_len] = 0; } memmove(outbuf + len, outbuf, pmsg->outbuf_len + 1); memcpy(outbuf, scratchbuf, len); pmsg->outbuf_len += len; } /* * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. * * @dropped is the dropped count to report in the dropped message. */ void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) { console_prepend_message(pmsg, "** %lu printk messages dropped **\n", dropped); } /* * Prepend the message in @pmsg->pbufs->outbuf with a "replay message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. */ void console_prepend_replay(struct printk_message *pmsg) { console_prepend_message(pmsg, "** replaying previous printk message **\n"); } /* * Read and format the specified record (or a later record if the specified * record is not available). * * @pmsg will contain the formatted result. @pmsg->pbufs must point to a * struct printk_buffers. * * @seq is the record to read and format. If it is not available, the next * valid record is read. * * @is_extended specifies if the message should be formatted for extended * console output. * * @may_supress specifies if records may be skipped based on loglevel. * * Returns false if no record is available. Otherwise true and all fields * of @pmsg are valid. (See the documentation of struct printk_message * for information about the @pmsg fields.) */ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_suppress) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; struct printk_info info; struct printk_record r; size_t len = 0; bool force_con; /* * Formatting extended messages requires a separate buffer, so use the * scratch buffer to read in the ringbuffer text. * * Formatting normal messages is done in-place, so read the ringbuffer * text directly into the output buffer. */ if (is_extended) prb_rec_init_rd(&r, &info, scratchbuf, scratchbuf_sz); else prb_rec_init_rd(&r, &info, outbuf, outbuf_sz); if (!prb_read_valid(prb, seq, &r)) return false; pmsg->seq = r.info->seq; pmsg->dropped = r.info->seq - seq; force_con = r.info->flags & LOG_FORCE_CON; /* * Skip records that are not forced to be printed on consoles and that * has level above the console loglevel. */ if (!force_con && may_suppress && suppress_message_printing(r.info->level)) goto out; if (is_extended) { len = info_print_ext_header(outbuf, outbuf_sz, r.info); len += msg_print_ext_body(outbuf + len, outbuf_sz - len, &r.text_buf[0], r.info->text_len, &r.info->dev_info); } else { len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); } out: pmsg->outbuf_len = len; return true; } /* * Legacy console printing from printk() caller context does not respect * raw_spinlock/spinlock nesting. For !PREEMPT_RT the lockdep warning is a * false positive. For PREEMPT_RT the false positive condition does not * occur. * * This map is used to temporarily establish LD_WAIT_SLEEP context for the * console write() callback when legacy printing to avoid false positive * lockdep complaints, thus allowing lockdep to continue to function for * real issues. */ #ifdef CONFIG_PREEMPT_RT static inline void printk_legacy_allow_spinlock_enter(void) { } static inline void printk_legacy_allow_spinlock_exit(void) { } #else static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_SLEEP); static inline void printk_legacy_allow_spinlock_enter(void) { lock_map_acquire_try(&printk_legacy_map); } static inline void printk_legacy_allow_spinlock_exit(void) { lock_map_release(&printk_legacy_map); } #endif /* CONFIG_PREEMPT_RT */ /* * Used as the printk buffers for non-panic, serialized console printing. * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles. * Its usage requires the console_lock held. */ struct printk_buffers printk_shared_pbufs; /* * Print one record for the given console. The record printed is whatever * record is the next available record for the given console. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding both the * console_lock and the SRCU read lock. Otherwise it is set to false. * * @cookie is the cookie from the SRCU read lock. * * Returns false if the given console has no next record to print, otherwise * true. * * Requires the console_lock and the SRCU read lock. */ static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; char *outbuf = &printk_shared_pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &printk_shared_pbufs, }; unsigned long flags; *handover = false; if (!printk_get_next_message(&pmsg, con->seq, is_extended, true)) return false; con->dropped += pmsg.dropped; /* Skip messages of formatted length 0. */ if (pmsg.outbuf_len == 0) { con->seq = pmsg.seq + 1; goto skip; } if (con->dropped && !is_extended) { console_prepend_dropped(&pmsg, con->dropped); con->dropped = 0; } /* Write everything out to the hardware. */ if (force_legacy_kthread() && !panic_in_progress()) { /* * With forced threading this function is in a task context * (either legacy kthread or get_init_console_seq()). There * is no need for concern about printk reentrance, handovers, * or lockdep complaints. */ con->write(con, outbuf, pmsg.outbuf_len); con->seq = pmsg.seq + 1; } else { /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. * * Interrupts are disabled because the hand over to a waiter * must not be interrupted until the hand over is completed * (@console_waiter is cleared). */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); /* Do not trace print latency. */ stop_critical_timings(); printk_legacy_allow_spinlock_enter(); con->write(con, outbuf, pmsg.outbuf_len); printk_legacy_allow_spinlock_exit(); start_critical_timings(); con->seq = pmsg.seq + 1; *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } skip: return true; } #else static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { *handover = false; return false; } static inline void printk_kthreads_check_locked(void) { } #endif /* CONFIG_PRINTK */ /* * Print out all remaining records to all consoles. * * @do_cond_resched is set by the caller. It can be true only in schedulable * context. * * @next_seq is set to the sequence number after the last available record. * The value is valid only when this function returns true. It means that all * usable consoles are completely flushed. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the * console_lock. Otherwise it is set to false. * * Returns true when there was at least one usable console and all messages * were flushed to all usable consoles. A returned false informs the caller * that everything was not flushed (either there were no usable consoles or * another context has taken over printing or it is a panic situation and this * is not the panic CPU). Regardless the reason, the caller should assume it * is not useful to immediately try again. * * Requires the console_lock. */ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) { struct console_flush_type ft; bool any_usable = false; struct console *con; bool any_progress; int cookie; *next_seq = 0; *handover = false; do { any_progress = false; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; bool progress; /* * console_flush_all() is only responsible for nbcon * consoles when the nbcon consoles cannot print via * their atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, !do_cond_resched)) continue; any_usable = true; if (flags & CON_NBCON) { progress = nbcon_legacy_emit_next_record(con, handover, cookie, !do_cond_resched); printk_seq = nbcon_seq_read(con); } else { progress = console_emit_next_record(con, handover, cookie); printk_seq = con->seq; } /* * If a handover has occurred, the SRCU read lock * is already released. */ if (*handover) return false; /* Track the next of the highest seq flushed. */ if (printk_seq > *next_seq) *next_seq = printk_seq; if (!progress) continue; any_progress = true; /* Allow panic_cpu to take over the consoles safely. */ if (other_cpu_in_panic()) goto abandon; if (do_cond_resched) cond_resched(); } console_srcu_read_unlock(cookie); } while (any_progress); return any_usable; abandon: console_srcu_read_unlock(cookie); return false; } static void __console_flush_and_unlock(void) { bool do_cond_resched; bool handover; bool flushed; u64 next_seq; /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may * end up dumping a lot of lines, for example, if called from * console registration path, and should invoke cond_resched() * between lines if allowable. Not doing so can cause a very long * scheduling stall on a slow console leading to RCU stall and * softlockup warnings which exacerbate the issue with more * messages practically incapacitating the system. Therefore, create * a local to use for the printing loop. */ do_cond_resched = console_may_schedule; do { console_may_schedule = 0; flushed = console_flush_all(do_cond_resched, &next_seq, &handover); if (!handover) __console_unlock(); /* * Abort if there was a failure to flush all messages to all * usable consoles. Either it is not possible to flush (in * which case it would be an infinite loop of retrying) or * another context has taken over printing. */ if (!flushed) break; /* * Some context may have added new records after * console_flush_all() but before unlocking the console. * Re-check if there is a new record to flush. If the trylock * fails, another context is already handling the printing. */ } while (prb_read_valid(prb, next_seq, NULL) && console_trylock()); } /** * console_unlock - unblock the legacy console subsystem from printing * * Releases the console_lock which the caller holds to block printing of * the legacy console subsystem. * * While the console_lock was held, console output may have been buffered * by printk(). If this is the case, console_unlock() emits the output on * legacy consoles prior to releasing the lock. * * console_unlock(); may be called from any context. */ void console_unlock(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (ft.legacy_direct) __console_flush_and_unlock(); else __console_unlock(); } EXPORT_SYMBOL(console_unlock); /** * console_conditional_schedule - yield the CPU if required * * If the console code is currently allowed to sleep, and * if this CPU should yield the CPU to another task, do * so here. * * Must be called within console_lock();. */ void __sched console_conditional_schedule(void) { if (console_may_schedule) cond_resched(); } EXPORT_SYMBOL(console_conditional_schedule); void console_unblank(void) { bool found_unblank = false; struct console *c; int cookie; /* * First check if there are any consoles implementing the unblank() * callback. If not, there is no reason to continue and take the * console lock, which in particular can be dangerous if * @oops_in_progress is set. */ cookie = console_srcu_read_lock(); for_each_console_srcu(c) { short flags = console_srcu_read_flags(c); if (flags & CON_SUSPENDED) continue; if ((flags & CON_ENABLED) && c->unblank) { found_unblank = true; break; } } console_srcu_read_unlock(cookie); if (!found_unblank) return; /* * Stop console printing because the unblank() callback may * assume the console is not within its write() callback. * * If @oops_in_progress is set, this may be an atomic context. * In that case, attempt a trylock as best-effort. */ if (oops_in_progress) { /* Semaphores are not NMI-safe. */ if (in_nmi()) return; /* * Attempting to trylock the console lock can deadlock * if another CPU was stopped while modifying the * semaphore. "Hope and pray" that this is not the * current situation. */ if (down_trylock_console_sem() != 0) return; } else console_lock(); console_locked = 1; console_may_schedule = 0; cookie = console_srcu_read_lock(); for_each_console_srcu(c) { short flags = console_srcu_read_flags(c); if (flags & CON_SUSPENDED) continue; if ((flags & CON_ENABLED) && c->unblank) c->unblank(); } console_srcu_read_unlock(cookie); console_unlock(); if (!oops_in_progress) pr_flush(1000, true); } /* * Rewind all consoles to the oldest available record. * * IMPORTANT: The function is safe only when called under * console_lock(). It is not enforced because * it is used as a best effort in panic(). */ static void __console_rewind_all(void) { struct console *c; short flags; int cookie; u64 seq; seq = prb_first_valid_seq(prb); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { flags = console_srcu_read_flags(c); if (flags & CON_NBCON) { nbcon_seq_force(c, seq); } else { /* * This assignment is safe only when called under * console_lock(). On panic, legacy consoles are * only best effort. */ c->seq = seq; } } console_srcu_read_unlock(cookie); } /** * console_flush_on_panic - flush console content on panic * @mode: flush all messages in buffer or just the pending ones * * Immediately output all pending messages no matter what. */ void console_flush_on_panic(enum con_flush_mode mode) { struct console_flush_type ft; bool handover; u64 next_seq; /* * Ignore the console lock and flush out the messages. Attempting a * trylock would not be useful because: * * - if it is contended, it must be ignored anyway * - console_lock() and console_trylock() block and fail * respectively in panic for non-panic CPUs * - semaphores are not NMI-safe */ /* * If another context is holding the console lock, * @console_may_schedule might be set. Clear it so that * this context does not call cond_resched() while flushing. */ console_may_schedule = 0; if (mode == CONSOLE_REPLAY_ALL) __console_rewind_all(); printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); /* Flush legacy consoles once allowed, even when dangerous. */ if (legacy_allow_panic_sync) console_flush_all(false, &next_seq, &handover); } /* * Return the console tty driver structure and its associated index */ struct tty_driver *console_device(int *index) { struct console *c; struct tty_driver *driver = NULL; int cookie; /* * Take console_lock to serialize device() callback with * other console operations. For example, fg_console is * modified under console_lock when switching vt. */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (!c->device) continue; driver = c->device(c, index); if (driver) break; } console_srcu_read_unlock(cookie); console_unlock(); return driver; } /* * Prevent further output on the passed console device so that (for example) * serial drivers can suspend console output before suspending a port, and can * re-enable output afterwards. */ void console_suspend(struct console *console) { __pr_flush(console, 1000, true); console_list_lock(); console_srcu_write_flags(console, console->flags & ~CON_ENABLED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All contexts must * be able to see that this console is disabled so that (for example) * the caller can suspend the port without risk of another context * using the port. */ synchronize_srcu(&console_srcu); } EXPORT_SYMBOL(console_suspend); void console_resume(struct console *console) { struct console_flush_type ft; bool is_nbcon; console_list_lock(); console_srcu_write_flags(console, console->flags | CON_ENABLED); is_nbcon = console->flags & CON_NBCON; console_list_unlock(); /* * Ensure that all SRCU list walks have completed. The related * printing context must be able to see it is enabled so that * it is guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); printk_get_console_flush_type(&ft); if (is_nbcon && ft.nbcon_offload) nbcon_kthread_wake(console); else if (ft.legacy_offload) defer_console_output(); __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_resume); #ifdef CONFIG_PRINTK static int unregister_console_locked(struct console *console); /* True when system boot is far enough to create printer threads. */ bool printk_kthreads_ready __ro_after_init; static struct task_struct *printk_legacy_kthread; static bool legacy_kthread_should_wakeup(void) { struct console_flush_type ft; struct console *con; bool ret = false; int cookie; if (kthread_should_stop()) return true; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; /* * The legacy printer thread is only responsible for nbcon * consoles when the nbcon consoles cannot print via their * atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, false)) continue; if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(con); } else { /* * It is safe to read @seq because only this * thread context updates @seq. */ printk_seq = con->seq; } if (prb_read_valid(prb, printk_seq, NULL)) { ret = true; break; } } console_srcu_read_unlock(cookie); return ret; } static int legacy_kthread_func(void *unused) { for (;;) { wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup()); if (kthread_should_stop()) break; console_lock(); __console_flush_and_unlock(); } return 0; } static bool legacy_kthread_create(void) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy"); if (WARN_ON(IS_ERR(kt))) { pr_err("failed to start legacy printing thread\n"); return false; } printk_legacy_kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(printk_legacy_kthread, -20); return true; } /** * printk_kthreads_shutdown - shutdown all threaded printers * * On system shutdown all threaded printers are stopped. This allows printk * to transition back to atomic printing, thus providing a robust mechanism * for the final shutdown/reboot messages to be output. */ static void printk_kthreads_shutdown(void) { struct console *con; console_list_lock(); if (printk_kthreads_running) { printk_kthreads_running = false; for_each_console(con) { if (con->flags & CON_NBCON) nbcon_kthread_stop(con); } /* * The threads may have been stopped while printing a * backlog. Flush any records left over. */ nbcon_atomic_flush_pending(); } console_list_unlock(); } static struct syscore_ops printk_syscore_ops = { .shutdown = printk_kthreads_shutdown, }; /* * If appropriate, start nbcon kthreads and set @printk_kthreads_running. * If any kthreads fail to start, those consoles are unregistered. * * Must be called under console_list_lock(). */ static void printk_kthreads_check_locked(void) { struct hlist_node *tmp; struct console *con; lockdep_assert_console_list_lock_held(); if (!printk_kthreads_ready) return; /* Start or stop the legacy kthread when needed. */ if (have_legacy_console || have_boot_console) { if (!printk_legacy_kthread && force_legacy_kthread() && !legacy_kthread_create()) { /* * All legacy consoles must be unregistered. If there * are any nbcon consoles, they will set up their own * kthread. */ hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_NBCON) continue; unregister_console_locked(con); } } } else if (printk_legacy_kthread) { kthread_stop(printk_legacy_kthread); printk_legacy_kthread = NULL; } /* * Printer threads cannot be started as long as any boot console is * registered because there is no way to synchronize the hardware * registers between boot console code and regular console code. * It can only be known that there will be no new boot consoles when * an nbcon console is registered. */ if (have_boot_console || !have_nbcon_console) { /* Clear flag in case all nbcon consoles unregistered. */ printk_kthreads_running = false; return; } if (printk_kthreads_running) return; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_NBCON)) continue; if (!nbcon_kthread_create(con)) unregister_console_locked(con); } printk_kthreads_running = true; } static int __init printk_set_kthreads_ready(void) { register_syscore_ops(&printk_syscore_ops); console_list_lock(); printk_kthreads_ready = true; printk_kthreads_check_locked(); console_list_unlock(); return 0; } early_initcall(printk_set_kthreads_ready); #endif /* CONFIG_PRINTK */ static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; pr_info("debug: skip boot console de-registration.\n"); return 0; } early_param("keep_bootcon", keep_bootcon_setup); static int console_call_setup(struct console *newcon, char *options) { int err; if (!newcon->setup) return 0; /* Synchronize with possible boot console. */ console_lock(); err = newcon->setup(newcon, options); console_unlock(); return err; } /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected * by either the command line or add_preferred_console() and * setup/enable it. * * Care need to be taken with consoles that are statically * enabled such as netconsole */ static int try_enable_preferred_console(struct console *newcon, bool user_specified) { struct console_cmdline *c; int i, err; for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { /* Console not yet initialized? */ if (!c->name[0]) continue; if (c->user_specified != user_specified) continue; if (!newcon->match || newcon->match(newcon, c->name, c->index, c->options) != 0) { /* default matching */ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && newcon->index != c->index) continue; if (newcon->index < 0) newcon->index = c->index; if (_braille_register_console(newcon, c)) return 0; err = console_call_setup(newcon, c->options); if (err) return err; } newcon->flags |= CON_ENABLED; if (i == preferred_console) newcon->flags |= CON_CONSDEV; return 0; } /* * Some consoles, such as pstore and netconsole, can be enabled even * without matching. Accept the pre-enabled consoles only when match() * and setup() had a chance to be called. */ if (newcon->flags & CON_ENABLED && c->user_specified == user_specified) return 0; return -ENOENT; } /* Try to enable the console unconditionally */ static void try_enable_default_console(struct console *newcon) { if (newcon->index < 0) newcon->index = 0; if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; if (newcon->device) newcon->flags |= CON_CONSDEV; } /* Return the starting sequence number for a newly registered console. */ static u64 get_init_console_seq(struct console *newcon, bool bootcon_registered) { struct console *con; bool handover; u64 init_seq; if (newcon->flags & (CON_PRINTBUFFER | CON_BOOT)) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); init_seq = syslog_seq; mutex_unlock(&syslog_lock); } else { /* Begin with next message added to ringbuffer. */ init_seq = prb_next_seq(prb); /* * If any enabled boot consoles are due to be unregistered * shortly, some may not be caught up and may be the same * device as @newcon. Since it is not known which boot console * is the same device, flush all consoles and, if necessary, * start with the message of the enabled boot console that is * the furthest behind. */ if (bootcon_registered && !keep_bootcon) { /* * Hold the console_lock to stop console printing and * guarantee safe access to console->seq. */ console_lock(); /* * Flush all consoles and set the console to start at * the next unprinted sequence number. */ if (!console_flush_all(true, &init_seq, &handover)) { /* * Flushing failed. Just choose the lowest * sequence of the enabled boot consoles. */ /* * If there was a handover, this context no * longer holds the console_lock. */ if (handover) console_lock(); init_seq = prb_next_seq(prb); for_each_console(con) { u64 seq; if (!(con->flags & CON_BOOT) || !(con->flags & CON_ENABLED)) { continue; } if (con->flags & CON_NBCON) seq = nbcon_seq_read(con); else seq = con->seq; if (seq < init_seq) init_seq = seq; } } console_unlock(); } } return init_seq; } #define console_first() \ hlist_entry(console_list.first, struct console, node) static int unregister_console_locked(struct console *console); /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to * print any messages that were printed by the kernel before the * console driver was initialized. * * This can happen pretty early during the boot process (because of * early_printk) - sometimes before setup_arch() completes - be careful * of what kernel features are used - they may not be initialised yet. * * There are two types of consoles - bootconsoles (early_printk) and * "real" consoles (everything which is not a bootconsole) which are * handled differently. * - Any number of bootconsoles can be registered at any time. * - As soon as a "real" console is registered, all bootconsoles * will be unregistered automatically. * - Once a "real" console is registered, any attempt to register a * bootconsoles will be rejected */ void register_console(struct console *newcon) { bool use_device_lock = (newcon->flags & CON_NBCON) && newcon->write_atomic; bool bootcon_registered = false; bool realcon_registered = false; struct console *con; unsigned long flags; u64 init_seq; int err; console_list_lock(); for_each_console(con) { if (WARN(con == newcon, "console '%s%d' already registered\n", con->name, con->index)) { goto unlock; } if (con->flags & CON_BOOT) bootcon_registered = true; else realcon_registered = true; } /* Do not register boot consoles when there already is a real one. */ if ((newcon->flags & CON_BOOT) && realcon_registered) { pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); goto unlock; } if (newcon->flags & CON_NBCON) { /* * Ensure the nbcon console buffers can be allocated * before modifying any global data. */ if (!nbcon_alloc(newcon)) goto unlock; } /* * See if we want to enable this console driver by default. * * Nope when a console is preferred by the command line, device * tree, or SPCR. * * The first real console with tty binding (driver) wins. More * consoles might get enabled before the right one is found. * * Note that a console with tty binding will have CON_CONSDEV * flag set and will be first in the list. */ if (preferred_console < 0) { if (hlist_empty(&console_list) || !console_first()->device || console_first()->flags & CON_BOOT) { try_enable_default_console(newcon); } } /* See if this console matches one we selected on the command line */ err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) { if (newcon->flags & CON_NBCON) nbcon_free(newcon); goto unlock; } /* * If we have a bootconsole, and are switching to a real console, * don't print everything out again, since when the boot console, and * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) { newcon->flags &= ~CON_PRINTBUFFER; } newcon->dropped = 0; init_seq = get_init_console_seq(newcon, bootcon_registered); if (newcon->flags & CON_NBCON) { have_nbcon_console = true; nbcon_seq_force(newcon, init_seq); } else { have_legacy_console = true; newcon->seq = init_seq; } if (newcon->flags & CON_BOOT) have_boot_console = true; /* * If another context is actively using the hardware of this new * console, it will not be aware of the nbcon synchronization. This * is a risk that two contexts could access the hardware * simultaneously if this new console is used for atomic printing * and the other context is still using the hardware. * * Use the driver synchronization to ensure that the hardware is not * in use while this new console transitions to being registered. */ if (use_device_lock) newcon->device_lock(newcon, &flags); /* * Put this console in the list - keep the * preferred driver at the head of the list. */ if (hlist_empty(&console_list)) { /* Ensure CON_CONSDEV is always set for the head. */ newcon->flags |= CON_CONSDEV; hlist_add_head_rcu(&newcon->node, &console_list); } else if (newcon->flags & CON_CONSDEV) { /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(console_first(), console_first()->flags & ~CON_CONSDEV); hlist_add_head_rcu(&newcon->node, &console_list); } else { hlist_add_behind_rcu(&newcon->node, console_list.first); } /* * No need to synchronize SRCU here! The caller does not rely * on all contexts being able to see the new console before * register_console() completes. */ /* This new console is now registered. */ if (use_device_lock) newcon->device_unlock(newcon, flags); console_sysfs_notify(); /* * By unregistering the bootconsoles after we enable the real console * we get the "console xxx enabled" message on all the consoles - * boot consoles, real consoles, etc - this is to ensure that end * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ con_printk(KERN_INFO, newcon, "enabled\n"); if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { struct hlist_node *tmp; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_BOOT) unregister_console_locked(con); } } /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); unlock: console_list_unlock(); } EXPORT_SYMBOL(register_console); /* Must be called under console_list_lock(). */ static int unregister_console_locked(struct console *console) { bool use_device_lock = (console->flags & CON_NBCON) && console->write_atomic; bool found_legacy_con = false; bool found_nbcon_con = false; bool found_boot_con = false; unsigned long flags; struct console *c; int res; lockdep_assert_console_list_lock_held(); con_printk(KERN_INFO, console, "disabled\n"); res = _braille_unregister_console(console); if (res < 0) return res; if (res > 0) return 0; if (!console_is_registered_locked(console)) res = -ENODEV; else if (console_is_usable(console, console->flags, true)) __pr_flush(console, 1000, true); /* Disable it unconditionally */ console_srcu_write_flags(console, console->flags & ~CON_ENABLED); if (res < 0) return res; /* * Use the driver synchronization to ensure that the hardware is not * in use while this console transitions to being unregistered. */ if (use_device_lock) console->device_lock(console, &flags); hlist_del_init_rcu(&console->node); if (use_device_lock) console->device_unlock(console, flags); /* * <HISTORICAL> * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. * </HISTORICAL> * * The above makes no sense as there is no guarantee that the next * console has any device attached. Oh well.... */ if (!hlist_empty(&console_list) && console->flags & CON_CONSDEV) console_srcu_write_flags(console_first(), console_first()->flags | CON_CONSDEV); /* * Ensure that all SRCU list walks have completed. All contexts * must not be able to see this console in the list so that any * exit/cleanup routines can be performed safely. */ synchronize_srcu(&console_srcu); /* * With this console gone, the global flags tracking registered * console types may have changed. Update them. */ for_each_console(c) { if (c->flags & CON_BOOT) found_boot_con = true; if (c->flags & CON_NBCON) found_nbcon_con = true; else found_legacy_con = true; } if (!found_boot_con) have_boot_console = found_boot_con; if (!found_legacy_con) have_legacy_console = found_legacy_con; if (!found_nbcon_con) have_nbcon_console = found_nbcon_con; /* @have_nbcon_console must be updated before calling nbcon_free(). */ if (console->flags & CON_NBCON) nbcon_free(console); console_sysfs_notify(); if (console->exit) res = console->exit(console); /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); return res; } int unregister_console(struct console *console) { int res; console_list_lock(); res = unregister_console_locked(console); console_list_unlock(); return res; } EXPORT_SYMBOL(unregister_console); /** * console_force_preferred_locked - force a registered console preferred * @con: The registered console to force preferred. * * Must be called under console_list_lock(). */ void console_force_preferred_locked(struct console *con) { struct console *cur_pref_con; if (!console_is_registered_locked(con)) return; cur_pref_con = console_first(); /* Already preferred? */ if (cur_pref_con == con) return; /* * Delete, but do not re-initialize the entry. This allows the console * to continue to appear registered (via any hlist_unhashed_lockless() * checks), even though it was briefly removed from the console list. */ hlist_del_rcu(&con->node); /* * Ensure that all SRCU list walks have completed so that the console * can be added to the beginning of the console list and its forward * list pointer can be re-initialized. */ synchronize_srcu(&console_srcu); con->flags |= CON_CONSDEV; WARN_ON(!con->device); /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(cur_pref_con, cur_pref_con->flags & ~CON_CONSDEV); hlist_add_head_rcu(&con->node, &console_list); } EXPORT_SYMBOL(console_force_preferred_locked); /* * Initialize the console device. This is called *early*, so * we can't necessarily depend on lots of kernel help here. * Just do some early initializations, and do the complex setup * later. */ void __init console_init(void) { int ret; initcall_t call; initcall_entry_t *ce; #ifdef CONFIG_NULL_TTY_DEFAULT_CONSOLE if (!console_set_on_cmdline) add_preferred_console("ttynull", 0, NULL); #endif /* Setup the default TTY line discipline. */ n_tty_init(); /* * set up the console device so that later boot sequences can * inform about problems etc.. */ ce = __con_initcall_start; trace_initcall_level("console"); while (ce < __con_initcall_end) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); trace_initcall_finish(call, ret); ce++; } } /* * Some boot consoles access data that is in the init section and which will * be discarded after the initcalls have been run. To make sure that no code * will access this data, unregister the boot consoles in a late initcall. * * If for some reason, such as deferred probe or the driver being a loadable * module, the real console hasn't registered yet at this point, there will * be a brief interval in which no messages are logged to the console, which * makes it difficult to diagnose problems that occur during this time. * * To mitigate this problem somewhat, only unregister consoles whose memory * intersects with the init section. Note that all other boot consoles will * get unregistered when the real preferred console is registered. */ static int __init printk_late_init(void) { struct hlist_node *tmp; struct console *con; int ret; console_list_lock(); hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_BOOT)) continue; /* Check addresses that might be used for enabled consoles. */ if (init_section_intersects(con, sizeof(*con)) || init_section_contains(con->write, 0) || init_section_contains(con->read, 0) || init_section_contains(con->device, 0) || init_section_contains(con->unblank, 0) || init_section_contains(con->data, 0)) { /* * Please, consider moving the reported consoles out * of the init section. */ pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", con->name, con->index); unregister_console_locked(con); } } console_list_unlock(); ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); printk_sysctl_init(); return 0; } late_initcall(printk_late_init); #if defined CONFIG_PRINTK /* If @con is specified, only wait for that console. Otherwise wait for all. */ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms); unsigned long remaining_jiffies = timeout_jiffies; struct console_flush_type ft; struct console *c; u64 last_diff = 0; u64 printk_seq; short flags; int cookie; u64 diff; u64 seq; /* Sorry, pr_flush() will not work this early. */ if (system_state < SYSTEM_SCHEDULING) return false; might_sleep(); seq = prb_next_reserve_seq(prb); /* Flush the consoles so that records up to @seq are printed. */ printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { console_lock(); console_unlock(); } for (;;) { unsigned long begin_jiffies; unsigned long slept_jiffies; diff = 0; /* * Hold the console_lock to guarantee safe access to * console->seq. Releasing console_lock flushes more * records in case @seq is still not printed on all * usable consoles. * * Holding the console_lock is not necessary if there * are no legacy or boot consoles. However, such a * console could register at any time. Always hold the * console_lock as a precaution rather than * synchronizing against register_console(). */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (con && con != c) continue; flags = console_srcu_read_flags(c); /* * If consoles are not usable, it cannot be expected * that they make forward progress, so only increment * @diff for usable consoles. */ if (!console_is_usable(c, flags, true) && !console_is_usable(c, flags, false)) { continue; } if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(c); } else { printk_seq = c->seq; } if (printk_seq < seq) diff += seq - printk_seq; } console_srcu_read_unlock(cookie); if (diff != last_diff && reset_on_progress) remaining_jiffies = timeout_jiffies; console_unlock(); /* Note: @diff is 0 if there are no usable consoles. */ if (diff == 0 || remaining_jiffies == 0) break; /* msleep(1) might sleep much longer. Check time by jiffies. */ begin_jiffies = jiffies; msleep(1); slept_jiffies = jiffies - begin_jiffies; remaining_jiffies -= min(slept_jiffies, remaining_jiffies); last_diff = diff; } return (diff == 0); } /** * pr_flush() - Wait for printing threads to catch up. * * @timeout_ms: The maximum time (in ms) to wait. * @reset_on_progress: Reset the timeout if forward progress is seen. * * A value of 0 for @timeout_ms means no waiting will occur. A value of -1 * represents infinite waiting. * * If @reset_on_progress is true, the timeout will be reset whenever any * printer has been seen to make some forward progress. * * Context: Process context. May sleep while acquiring console lock. * Return: true if all usable printers are caught up. */ bool pr_flush(int timeout_ms, bool reset_on_progress) { return __pr_flush(NULL, timeout_ms, reset_on_progress); } /* * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 #define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { if (force_legacy_kthread()) { if (printk_legacy_kthread) wake_up_interruptible(&legacy_wait); } else { if (console_trylock()) console_unlock(); } } if (pending & PRINTK_PENDING_WAKEUP) wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func); static void __wake_up_klogd(int val) { if (!printk_percpu_data_ready()) return; preempt_disable(); /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the wait queue is empty. * * The full memory barrier within wq_has_sleeper() pairs with the full * memory barrier within set_current_state() of * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } /** * wake_up_klogd - Wake kernel logging daemon * * Use this function when new records have been added to the ringbuffer * and the console printing of those records has already occurred or is * known to be handled by some other context. This function will only * wake the logging daemon. * * Context: Any context. */ void wake_up_klogd(void) { __wake_up_klogd(PRINTK_PENDING_WAKEUP); } /** * defer_console_output - Wake kernel logging daemon and trigger * console printing in a deferred context * * Use this function when new records have been added to the ringbuffer, * this context is responsible for console printing those records, but * the current context is not allowed to perform the console printing. * Trigger an irq_work context to perform the console printing. This * function also wakes the logging daemon. * * Context: Any context. */ void defer_console_output(void) { /* * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } void printk_trigger_flush(void) { defer_console_output(); } int vprintk_deferred(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); } int _printk_deferred(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_deferred(fmt, args); va_end(args); return r; } /* * printk rate limiting, lifted from the networking subsystem. * * This enforces a rate limit: not more than 10 kernel messages * every 5s to make a denial-of-service attack impossible. */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); int __printk_ratelimit(const char *func) { return ___ratelimit(&printk_ratelimit_state, func); } EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting * @caller_jiffies: pointer to caller's state * @interval_msecs: minimum interval between prints * * printk_timed_ratelimit() returns true if more than @interval_msecs * milliseconds have elapsed since the last time printk_timed_ratelimit() * returned true. */ bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { unsigned long elapsed = jiffies - *caller_jiffies; if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) return false; *caller_jiffies = jiffies; return true; } EXPORT_SYMBOL(printk_timed_ratelimit); static DEFINE_SPINLOCK(dump_list_lock); static LIST_HEAD(dump_list); /** * kmsg_dump_register - register a kernel log dumper. * @dumper: pointer to the kmsg_dumper structure * * Adds a kernel log dumper to the system. The dump callback in the * structure will be called when the kernel oopses or panics and must be * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. */ int kmsg_dump_register(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EBUSY; /* The dump callback needs to be set */ if (!dumper->dump) return -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_register); /** * kmsg_dump_unregister - unregister a kmsg dumper. * @dumper: pointer to the kmsg_dumper structure * * Removes a dump device from the system. Returns zero on success and * %-EINVAL otherwise. */ int kmsg_dump_unregister(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) { switch (reason) { case KMSG_DUMP_PANIC: return "Panic"; case KMSG_DUMP_OOPS: return "Oops"; case KMSG_DUMP_EMERG: return "Emergency"; case KMSG_DUMP_SHUTDOWN: return "Shutdown"; default: return "Unknown"; } } EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); /** * kmsg_dump_desc - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * @desc: a short string to describe what caused the panic or oops. Can be NULL * if no additional description is available. * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc) { struct kmsg_dumper *dumper; struct kmsg_dump_detail detail = { .reason = reason, .description = desc}; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { enum kmsg_dump_reason max_reason = dumper->max_reason; /* * If client has not provided a specific max_reason, default * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. */ if (max_reason == KMSG_DUMP_UNDEF) { max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : KMSG_DUMP_OOPS; } if (reason > max_reason) continue; /* invoke dumper which will iterate over records */ dumper->dump(dumper, &detail); } rcu_read_unlock(); } /** * kmsg_dump_get_line - retrieve one kmsg log line * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; unsigned int line_count; struct printk_record r; size_t l = 0; bool ret = false; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ if (line) { if (!prb_read_valid(prb, iter->cur_seq, &r)) goto out; l = record_print_text(&r, syslog, printk_time); } else { if (!prb_read_valid_info(prb, iter->cur_seq, &info, &line_count)) { goto out; } l = get_record_print_text_size(&info, line_count, syslog, printk_time); } iter->cur_seq = r.info->seq + 1; ret = true; out: if (len) *len = l; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len_out: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * * Consecutive calls will fill the buffer with the next block of * available older records, not including the earlier retrieved ones. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, char *buf, size_t size, size_t *len_out) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; struct printk_record r; u64 seq; u64 next_seq; size_t len = 0; bool ret = false; bool time = printk_time; if (!buf || !size) goto out; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { if (info.seq != iter->cur_seq) { /* messages are gone, move to first available one */ iter->cur_seq = info.seq; } } /* last entry */ if (iter->cur_seq >= iter->next_seq) goto out; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. Pass in size-1 * because this function (by way of record_print_text()) will * not write more than size-1 bytes of text into @buf. */ seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq, size - 1, syslog, time); /* * Next kmsg_dump_get_buffer() invocation will dump block of * older records stored right before this one. */ next_seq = seq; prb_rec_init_rd(&r, &info, buf, size); prb_for_each_record(seq, prb, seq, &r) { if (r.info->seq >= iter->next_seq) break; len += record_print_text(&r, syslog, time); /* Adjust record to store to remaining buffer space. */ prb_rec_init_rd(&r, &info, buf + len, size - len); } iter->next_seq = next_seq; ret = true; out: if (len_out) *len_out = len; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** * kmsg_dump_rewind - reset the iterator * @iter: kmsg dump iterator * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { iter->cur_seq = latched_seq_read_nolock(&clear_seq); iter->next_seq = prb_next_seq(prb); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); /** * console_try_replay_all - try to replay kernel log on consoles * * Try to obtain lock on console subsystem and replay all * available records in printk buffer on the consoles. * Does nothing if lock is not obtained. * * Context: Any, except for NMI. */ void console_try_replay_all(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (console_trylock()) { __console_rewind_all(); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); /* Consoles are flushed as part of console_unlock(). */ console_unlock(); } } #endif #ifdef CONFIG_SMP static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1); static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0); bool is_printk_cpu_sync_owner(void) { return (atomic_read(&printk_cpu_sync_owner) == raw_smp_processor_id()); } /** * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant * spinning lock is not owned by any CPU. * * Context: Any context. */ void __printk_cpu_sync_wait(void) { do { cpu_relax(); } while (atomic_read(&printk_cpu_sync_owner) != -1); } EXPORT_SYMBOL(__printk_cpu_sync_wait); /** * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant * spinning lock. * * If no processor has the lock, the calling processor takes the lock and * becomes the owner. If the calling processor is already the owner of the * lock, this function succeeds immediately. * * Context: Any context. Expects interrupts to be disabled. * Return: 1 on success, otherwise 0. */ int __printk_cpu_sync_try_get(void) { int cpu; int old; cpu = smp_processor_id(); /* * Guarantee loads and stores from this CPU when it is the lock owner * are _not_ visible to the previous lock owner. This pairs with * __printk_cpu_sync_put:B. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_put:A can never read from * __printk_cpu_sync_try_get:B. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of the previous CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of this CPU */ old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1, cpu); /* LMM(__printk_cpu_sync_try_get:A) */ if (old == -1) { /* * This CPU is now the owner and begins loading/storing * data: LMM(__printk_cpu_sync_try_get:B) */ return 1; } else if (old == cpu) { /* This CPU is already the owner. */ atomic_inc(&printk_cpu_sync_nested); return 1; } return 0; } EXPORT_SYMBOL(__printk_cpu_sync_try_get); /** * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock. * * The calling processor must be the owner of the lock. * * Context: Any context. Expects interrupts to be disabled. */ void __printk_cpu_sync_put(void) { if (atomic_read(&printk_cpu_sync_nested)) { atomic_dec(&printk_cpu_sync_nested); return; } /* * This CPU is finished loading/storing data: * LMM(__printk_cpu_sync_put:A) */ /* * Guarantee loads and stores from this CPU when it was the * lock owner are visible to the next lock owner. This pairs * with __printk_cpu_sync_try_get:A. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of this CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of the next CPU */ atomic_set_release(&printk_cpu_sync_owner, -1); /* LMM(__printk_cpu_sync_put:B) */ } EXPORT_SYMBOL(__printk_cpu_sync_put); #endif /* CONFIG_SMP */ |
| 37 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/nodemask_types.h> #include <linux/random.h> extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mismatch error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_copy(dst, src) __nodes_copy(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_copy(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_copy(dstp->bits, srcp->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); if (ret == MAX_NUMNODES) ret = __first_node(srcp); return ret; } static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static __always_inline int node_state(int node, enum node_states state) { return node == 0; } static __always_inline void node_set_state(int node, enum node_states state) { } static __always_inline void node_clear_state(int node, enum node_states state) { } static __always_inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int node = find_random_bit(maskp->bits, MAX_NUMNODES); return node < MAX_NUMNODES ? node : NUMA_NO_NODE; #else return 0; #endif } #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) #define for_each_node_with_cpus(node) for_each_node_state(node, N_CPU) /* * For nodemask scratch area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* Example structure for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */ |
| 69 5 69 8 21 3 16 8 5 249 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 | /* 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))) /* * Return the ->prev pointer of a list_head in an rcu safe way. Don't * access it directly. * * Any list traversed with list_bidir_prev_rcu() must never use * list_del_rcu(). Doing so will poison the ->prev pointer that * list_bidir_prev_rcu() relies on, which will result in segfaults. * To prevent these segfaults, use list_bidir_del_rcu() instead * of list_del_rcu(). */ #define list_bidir_prev_rcu(list) (*((struct list_head __rcu **)(&(list)->prev))) /** * 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; } /** * list_bidir_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * In contrast to list_del_rcu() doesn't poison the prev pointer thus * allowing backwards traversal via list_bidir_prev_rcu(). * * Note: list_empty() on entry does not return true after this because * the entry is in a special undefined state that permits RCU-based * lockfree reverse traversal. In particular this means that we can not * poison the forward and backwards 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_bidir_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 list_del_rcu() and list_bidir_del_rcu() must not be used on * the same list. * * 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_bidir_del_rcu(struct list_head *entry) { __list_del_entry(entry); } /** * 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 |
| 77 95 95 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/backing-dev.h * * low-level device information and state which is propagated up through * to high-level code. */ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/writeback.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); return bdi; } struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wait_for_completion(struct wb_completion *done); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { return test_bit(WB_has_dirty_io, &wb->state); } static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { /* * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are * any dirty wbs. See wb_update_write_bandwidth(). */ return atomic_long_read(&bdi->tot_write_bandwidth); } static inline void wb_stat_mod(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_read_positive(&wb->stat[item]); } static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ static inline unsigned long wb_stat_error(void) { #ifdef CONFIG_SMP return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif } /* BDI ratio is expressed as part per 1000000 for finer granularity. */ #define BDI_RATIO_SCALE 10000 u64 bdi_get_min_bytes(struct backing_dev_info *bdi); u64 bdi_get_max_bytes(struct backing_dev_info *bdi); int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes); int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes); int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit); /* * Flags in backing_dev_info::capability * * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages * should contribute to accounting * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ #define BDI_CAP_WRITEBACK (1 << 0) #define BDI_CAP_WRITEBACK_ACCT (1 << 1) #define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; int bdi_init(struct backing_dev_info *bdi); /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest * * Determine whether there is writeback waiting to be handled against a * bdi_writeback. */ static inline bool writeback_in_progress(struct bdi_writeback *wb) { return test_bit(WB_writeback_running, &wb->state); } struct backing_dev_info *inode_to_bdi(struct inode *inode); static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * * Cgroup writeback requires support from the filesystem. Also, both memcg and * iocg have to be on the default hierarchy. Test whether all conditions are * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } /** * wb_find_current - find wb for %current on a bdi * @bdi: bdi of interest * * Find the wb of @bdi which matches both the memcg and blkcg of %current. * Must be called under rcu_read_lock() which protects the returend wb. * NULL if not found. */ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; memcg_css = task_css(current, memory_cgrp_id); if (!memcg_css->parent) return &bdi->wb; wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); /* * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } /** * wb_get_create_current - get or create wb for %current on a bdi * @bdi: bdi of interest * @gfp: allocation mask * * Equivalent to wb_get_create() on %current's memcg. This function is * called from a relatively hot path and optimizes the common cases using * wb_find_current(). */ static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { struct bdi_writeback *wb; rcu_read_lock(); wb = wb_find_current(bdi); if (wb && unlikely(!wb_tryget(wb))) wb = NULL; rcu_read_unlock(); if (unlikely(!wb)) { struct cgroup_subsys_state *memcg_css; memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, gfp); css_put(memcg_css); } return wb; } /** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (inode->i_sb->s_iflags & SB_I_CGROUPWB) && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { /* * If wbc does not have inode attached, it means cgroup writeback was * disabled when wbc started. Just use the default wb in that case. */ return wbc->wb ? wbc->wb : &inode_to_bdi(inode)->wb; } /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and * can't sleep during the transaction. IRQs may or may not be disabled on * return. */ static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); /* * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode * @cookie: @cookie from unlocked_inode_to_wb_begin() */ static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { if (unlikely(cookie->locked)) xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) { return false; } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; } static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { return &bdi->wb; } static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { return inode_to_wb(inode); } static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { } static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } #endif /* CONFIG_CGROUP_WRITEBACK */ const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ |
| 1459 291 85 | 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 */ |
| 105 42 42 105 105 105 1 1 1 1 205 105 105 197 198 242 243 18 18 202 202 11 11 11 11 11 11 197 208 208 202 202 202 200 42 42 42 42 321 323 30 30 1 1 1 1 33 215 18 18 18 18 249 249 243 243 243 18 17 18 105 105 105 105 202 202 201 201 1 1 201 205 204 2 175 205 205 1 203 205 9 3 201 4 4 203 200 201 5 202 201 2 201 200 2 3 201 202 202 1 200 202 201 175 197 208 209 207 1 209 209 2 208 196 207 3 169 205 198 207 27 27 116 6 105 1 105 105 120 120 4 110 19 110 110 110 9 119 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/acpi.h> #include <linux/mman.h> #include <linux/kvm_host.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/sched/signal.h> #include <trace/events/kvm.h> #include <asm/acpi.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> #include <asm/kvm_pkvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/virt.h> #include "trace.h" static struct kvm_pgtable *hyp_pgtable; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); static unsigned long __ro_after_init hyp_idmap_start; static unsigned long __ro_after_init hyp_idmap_end; static phys_addr_t __ro_after_init hyp_idmap_vector; u32 __ro_after_init __hyp_va_bits; static unsigned long __ro_after_init io_map_base; #define KVM_PGT_FN(fn) (!is_protected_kvm_enabled() ? fn : p ## fn) static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end, phys_addr_t size) { phys_addr_t boundary = ALIGN_DOWN(addr + size, size); return (boundary - 1 < end - 1) ? boundary : end; } static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) { phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL); return __stage2_range_addr_end(addr, end, size); } /* * Release kvm_mmu_lock periodically if the memory region is large. Otherwise, * we may see kernel panics with CONFIG_DETECT_HUNG_TASK, * CONFIG_LOCKUP_DETECTOR, CONFIG_LOCKDEP. Additionally, holding the lock too * long will also starve other vCPUs. We have to also make sure that the page * tables are not freed while we released the lock. */ static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end, int (*fn)(struct kvm_pgtable *, u64, u64), bool resched) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); int ret; u64 next; do { struct kvm_pgtable *pgt = mmu->pgt; if (!pgt) return -EINVAL; next = stage2_range_addr_end(addr, end); ret = fn(pgt, addr, next - addr); if (ret) break; if (resched && next != end) cond_resched_rwlock_write(&kvm->mmu_lock); } while (addr = next, addr != end); return ret; } #define stage2_apply_range_resched(mmu, addr, end, fn) \ stage2_apply_range(mmu, addr, end, fn, true) /* * Get the maximum number of page-tables pages needed to split a range * of blocks into PAGE_SIZE PTEs. It assumes the range is already * mapped at level 2, or at level 1 if allowed. */ static int kvm_mmu_split_nr_page_tables(u64 range) { int n = 0; if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2) n += DIV_ROUND_UP(range, PUD_SIZE); n += DIV_ROUND_UP(range, PMD_SIZE); return n; } static bool need_split_memcache_topup_or_resched(struct kvm *kvm) { struct kvm_mmu_memory_cache *cache; u64 chunk_size, min; if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) return true; chunk_size = kvm->arch.mmu.split_page_chunk_size; min = kvm_mmu_split_nr_page_tables(chunk_size); cache = &kvm->arch.mmu.split_page_cache; return kvm_mmu_memory_cache_nr_free_objects(cache) < min; } static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) { struct kvm_mmu_memory_cache *cache; struct kvm_pgtable *pgt; int ret, cache_capacity; u64 next, chunk_size; lockdep_assert_held_write(&kvm->mmu_lock); chunk_size = kvm->arch.mmu.split_page_chunk_size; cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size); if (chunk_size == 0) return 0; cache = &kvm->arch.mmu.split_page_cache; do { if (need_split_memcache_topup_or_resched(kvm)) { write_unlock(&kvm->mmu_lock); cond_resched(); /* Eager page splitting is best-effort. */ ret = __kvm_mmu_topup_memory_cache(cache, cache_capacity, cache_capacity); write_lock(&kvm->mmu_lock); if (ret) break; } pgt = kvm->arch.mmu.pgt; if (!pgt) return -EINVAL; next = __stage2_range_addr_end(addr, end, chunk_size); ret = KVM_PGT_FN(kvm_pgtable_stage2_split)(pgt, addr, next - addr, cache); if (ret) break; } while (addr = next, addr != end); return ret; } static bool memslot_is_logging(struct kvm_memory_slot *memslot) { return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); } /** * kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8 * @kvm: pointer to kvm structure. * * Interface to HYP function to flush all VM TLB entries */ int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { if (is_protected_kvm_enabled()) kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); else kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); return 0; } int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { u64 size = nr_pages << PAGE_SHIFT; u64 addr = gfn << PAGE_SHIFT; if (is_protected_kvm_enabled()) kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle); else kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size); return 0; } static void *stage2_memcache_zalloc_page(void *arg) { struct kvm_mmu_memory_cache *mc = arg; void *virt; /* Allocated with __GFP_ZERO, so no need to zero */ virt = kvm_mmu_memory_cache_alloc(mc); if (virt) kvm_account_pgtable_pages(virt, 1); return virt; } static void *kvm_host_zalloc_pages_exact(size_t size) { return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } static void *kvm_s2_zalloc_pages_exact(size_t size) { void *virt = kvm_host_zalloc_pages_exact(size); if (virt) kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT)); return virt; } static void kvm_s2_free_pages_exact(void *virt, size_t size) { kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT)); free_pages_exact(virt, size); } static struct kvm_pgtable_mm_ops kvm_s2_mm_ops; static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head) { struct page *page = container_of(head, struct page, rcu_head); void *pgtable = page_to_virt(page); s8 level = page_private(page); KVM_PGT_FN(kvm_pgtable_stage2_free_unlinked)(&kvm_s2_mm_ops, pgtable, level); } static void stage2_free_unlinked_table(void *addr, s8 level) { struct page *page = virt_to_page(addr); set_page_private(page, (unsigned long)level); call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb); } static void kvm_host_get_page(void *addr) { get_page(virt_to_page(addr)); } static void kvm_host_put_page(void *addr) { put_page(virt_to_page(addr)); } static void kvm_s2_put_page(void *addr) { struct page *p = virt_to_page(addr); /* Dropping last refcount, the page will be freed */ if (page_count(p) == 1) kvm_account_pgtable_pages(addr, -1); put_page(p); } static int kvm_host_page_count(void *addr) { return page_count(virt_to_page(addr)); } static phys_addr_t kvm_host_pa(void *addr) { return __pa(addr); } static void *kvm_host_va(phys_addr_t phys) { return __va(phys); } static void clean_dcache_guest_page(void *va, size_t size) { __clean_dcache_guest_page(va, size); } static void invalidate_icache_guest_page(void *va, size_t size) { __invalidate_icache_guest_page(va, size); } /* * Unmapping vs dcache management: * * If a guest maps certain memory pages as uncached, all writes will * bypass the data cache and go directly to RAM. However, the CPUs * can still speculate reads (not writes) and fill cache lines with * data. * * Those cache lines will be *clean* cache lines though, so a * clean+invalidate operation is equivalent to an invalidate * operation, because no cache lines are marked dirty. * * Those clean cache lines could be filled prior to an uncached write * by the guest, and the cache coherent IO subsystem would therefore * end up writing old data to disk. * * This is why right after unmapping a page/section and invalidating * the corresponding TLBs, we flush to make sure the IO subsystem will * never hit in the cache. * * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as * we then fully enforce cacheability of RAM, no matter what the guest * does. */ /** * __unmap_stage2_range -- Clear stage2 page table entries to unmap a range * @mmu: The KVM stage-2 MMU pointer * @start: The intermediate physical base address of the range to unmap * @size: The size of the area to unmap * @may_block: Whether or not we are permitted to block * * Clear a range of stage-2 mappings, lowering the various ref-counts. Must * be called while holding mmu_lock (unless for freeing the stage2 pgd before * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, bool may_block) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); phys_addr_t end = start + size; lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); WARN_ON(stage2_apply_range(mmu, start, end, KVM_PGT_FN(kvm_pgtable_stage2_unmap), may_block)); } void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, bool may_block) { __unmap_stage2_range(mmu, start, size, may_block); } void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_flush)); } static void stage2_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = addr + PAGE_SIZE * memslot->npages; kvm_stage2_flush_range(&kvm->arch.mmu, addr, end); } /** * stage2_flush_vm - Invalidate cache for pages mapped in stage 2 * @kvm: The struct kvm pointer * * Go through the stage 2 page tables and invalidate any cache lines * backing memory already mapped to the VM. */ static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int idx, bkt; idx = srcu_read_lock(&kvm->srcu); write_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); kvm_nested_s2_flush(kvm); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } /** * free_hyp_pgds - free Hyp-mode page tables */ void __init free_hyp_pgds(void) { mutex_lock(&kvm_hyp_pgd_mutex); if (hyp_pgtable) { kvm_pgtable_hyp_destroy(hyp_pgtable); kfree(hyp_pgtable); hyp_pgtable = NULL; } mutex_unlock(&kvm_hyp_pgd_mutex); } static bool kvm_host_owns_hyp_mappings(void) { if (is_kernel_in_hyp_mode()) return false; if (static_branch_likely(&kvm_protected_mode_initialized)) return false; /* * This can happen at boot time when __create_hyp_mappings() is called * after the hyp protection has been enabled, but the static key has * not been flipped yet. */ if (!hyp_pgtable && is_protected_kvm_enabled()) return false; WARN_ON(!hyp_pgtable); return true; } int __create_hyp_mappings(unsigned long start, unsigned long size, unsigned long phys, enum kvm_pgtable_prot prot) { int err; if (WARN_ON(!kvm_host_owns_hyp_mappings())) return -EINVAL; mutex_lock(&kvm_hyp_pgd_mutex); err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot); mutex_unlock(&kvm_hyp_pgd_mutex); return err; } static phys_addr_t kvm_kaddr_to_phys(void *kaddr) { if (!is_vmalloc_addr(kaddr)) { BUG_ON(!virt_addr_valid(kaddr)); return __pa(kaddr); } else { return page_to_phys(vmalloc_to_page(kaddr)) + offset_in_page(kaddr); } } struct hyp_shared_pfn { u64 pfn; int count; struct rb_node node; }; static DEFINE_MUTEX(hyp_shared_pfns_lock); static struct rb_root hyp_shared_pfns = RB_ROOT; static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node, struct rb_node **parent) { struct hyp_shared_pfn *this; *node = &hyp_shared_pfns.rb_node; *parent = NULL; while (**node) { this = container_of(**node, struct hyp_shared_pfn, node); *parent = **node; if (this->pfn < pfn) *node = &((**node)->rb_left); else if (this->pfn > pfn) *node = &((**node)->rb_right); else return this; } return NULL; } static int share_pfn_hyp(u64 pfn) { struct rb_node **node, *parent; struct hyp_shared_pfn *this; int ret = 0; mutex_lock(&hyp_shared_pfns_lock); this = find_shared_pfn(pfn, &node, &parent); if (this) { this->count++; goto unlock; } this = kzalloc(sizeof(*this), GFP_KERNEL); if (!this) { ret = -ENOMEM; goto unlock; } this->pfn = pfn; this->count = 1; rb_link_node(&this->node, parent, node); rb_insert_color(&this->node, &hyp_shared_pfns); ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1); unlock: mutex_unlock(&hyp_shared_pfns_lock); return ret; } static int unshare_pfn_hyp(u64 pfn) { struct rb_node **node, *parent; struct hyp_shared_pfn *this; int ret = 0; mutex_lock(&hyp_shared_pfns_lock); this = find_shared_pfn(pfn, &node, &parent); if (WARN_ON(!this)) { ret = -ENOENT; goto unlock; } this->count--; if (this->count) goto unlock; rb_erase(&this->node, &hyp_shared_pfns); kfree(this); ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1); unlock: mutex_unlock(&hyp_shared_pfns_lock); return ret; } int kvm_share_hyp(void *from, void *to) { phys_addr_t start, end, cur; u64 pfn; int ret; if (is_kernel_in_hyp_mode()) return 0; /* * The share hcall maps things in the 'fixed-offset' region of the hyp * VA space, so we can only share physically contiguous data-structures * for now. */ if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to)) return -EINVAL; if (kvm_host_owns_hyp_mappings()) return create_hyp_mappings(from, to, PAGE_HYP); start = ALIGN_DOWN(__pa(from), PAGE_SIZE); end = PAGE_ALIGN(__pa(to)); for (cur = start; cur < end; cur += PAGE_SIZE) { pfn = __phys_to_pfn(cur); ret = share_pfn_hyp(pfn); if (ret) return ret; } return 0; } void kvm_unshare_hyp(void *from, void *to) { phys_addr_t start, end, cur; u64 pfn; if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from) return; start = ALIGN_DOWN(__pa(from), PAGE_SIZE); end = PAGE_ALIGN(__pa(to)); for (cur = start; cur < end; cur += PAGE_SIZE) { pfn = __phys_to_pfn(cur); WARN_ON(unshare_pfn_hyp(pfn)); } } /** * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode * @from: The virtual kernel start address of the range * @to: The virtual kernel end address of the range (exclusive) * @prot: The protection to be applied to this range * * The same virtual address as the kernel virtual address is also used * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying * physical pages. */ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot) { phys_addr_t phys_addr; unsigned long virt_addr; unsigned long start = kern_hyp_va((unsigned long)from); unsigned long end = kern_hyp_va((unsigned long)to); if (is_kernel_in_hyp_mode()) return 0; if (!kvm_host_owns_hyp_mappings()) return -EPERM; start = start & PAGE_MASK; end = PAGE_ALIGN(end); for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { int err; phys_addr = kvm_kaddr_to_phys(from + virt_addr - start); err = __create_hyp_mappings(virt_addr, PAGE_SIZE, phys_addr, prot); if (err) return err; } return 0; } static int __hyp_alloc_private_va_range(unsigned long base) { lockdep_assert_held(&kvm_hyp_pgd_mutex); if (!PAGE_ALIGNED(base)) return -EINVAL; /* * Verify that BIT(VA_BITS - 1) hasn't been flipped by * allocating the new area, as it would indicate we've * overflowed the idmap/IO address range. */ if ((base ^ io_map_base) & BIT(VA_BITS - 1)) return -ENOMEM; io_map_base = base; return 0; } /** * hyp_alloc_private_va_range - Allocates a private VA range. * @size: The size of the VA range to reserve. * @haddr: The hypervisor virtual start address of the allocation. * * The private virtual address (VA) range is allocated below io_map_base * and aligned based on the order of @size. * * Return: 0 on success or negative error code on failure. */ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) { unsigned long base; int ret = 0; mutex_lock(&kvm_hyp_pgd_mutex); /* * This assumes that we have enough space below the idmap * page to allocate our VAs. If not, the check in * __hyp_alloc_private_va_range() will kick. A potential * alternative would be to detect that overflow and switch * to an allocation above the idmap. * * The allocated size is always a multiple of PAGE_SIZE. */ size = PAGE_ALIGN(size); base = io_map_base - size; ret = __hyp_alloc_private_va_range(base); mutex_unlock(&kvm_hyp_pgd_mutex); if (!ret) *haddr = base; return ret; } static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, unsigned long *haddr, enum kvm_pgtable_prot prot) { unsigned long addr; int ret = 0; if (!kvm_host_owns_hyp_mappings()) { addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping, phys_addr, size, prot); if (IS_ERR_VALUE(addr)) return addr; *haddr = addr; return 0; } size = PAGE_ALIGN(size + offset_in_page(phys_addr)); ret = hyp_alloc_private_va_range(size, &addr); if (ret) return ret; ret = __create_hyp_mappings(addr, size, phys_addr, prot); if (ret) return ret; *haddr = addr + offset_in_page(phys_addr); return ret; } int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr) { unsigned long base; size_t size; int ret; mutex_lock(&kvm_hyp_pgd_mutex); /* * Efficient stack verification using the NVHE_STACK_SHIFT bit implies * an alignment of our allocation on the order of the size. */ size = NVHE_STACK_SIZE * 2; base = ALIGN_DOWN(io_map_base - size, size); ret = __hyp_alloc_private_va_range(base); mutex_unlock(&kvm_hyp_pgd_mutex); if (ret) { kvm_err("Cannot allocate hyp stack guard page\n"); return ret; } /* * Since the stack grows downwards, map the stack to the page * at the higher address and leave the lower guard page * unbacked. * * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1 * and addresses corresponding to the guard page have the * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection. */ ret = __create_hyp_mappings(base + NVHE_STACK_SIZE, NVHE_STACK_SIZE, phys_addr, PAGE_HYP); if (ret) kvm_err("Cannot map hyp stack\n"); *haddr = base + size; return ret; } /** * create_hyp_io_mappings - Map IO into both kernel and HYP * @phys_addr: The physical start address which gets mapped * @size: Size of the region being mapped * @kaddr: Kernel VA for this mapping * @haddr: HYP VA for this mapping */ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, void __iomem **haddr) { unsigned long addr; int ret; if (is_protected_kvm_enabled()) return -EPERM; *kaddr = ioremap(phys_addr, size); if (!*kaddr) return -ENOMEM; if (is_kernel_in_hyp_mode()) { *haddr = *kaddr; return 0; } ret = __create_hyp_private_mapping(phys_addr, size, &addr, PAGE_HYP_DEVICE); if (ret) { iounmap(*kaddr); *kaddr = NULL; *haddr = NULL; return ret; } *haddr = (void __iomem *)addr; return 0; } /** * create_hyp_exec_mappings - Map an executable range into HYP * @phys_addr: The physical start address which gets mapped * @size: Size of the region being mapped * @haddr: HYP VA for this mapping */ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void **haddr) { unsigned long addr; int ret; BUG_ON(is_kernel_in_hyp_mode()); ret = __create_hyp_private_mapping(phys_addr, size, &addr, PAGE_HYP_EXEC); if (ret) { *haddr = NULL; return ret; } *haddr = (void *)addr; return 0; } static struct kvm_pgtable_mm_ops kvm_user_mm_ops = { /* We shouldn't need any other callback to walk the PT */ .phys_to_virt = kvm_host_va, }; static int get_user_mapping_size(struct kvm *kvm, u64 addr) { struct kvm_pgtable pgt = { .pgd = (kvm_pteref_t)kvm->mm->pgd, .ia_bits = vabits_actual, .start_level = (KVM_PGTABLE_LAST_LEVEL - ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1), .mm_ops = &kvm_user_mm_ops, }; unsigned long flags; kvm_pte_t pte = 0; /* Keep GCC quiet... */ s8 level = S8_MAX; int ret; /* * Disable IRQs so that we hazard against a concurrent * teardown of the userspace page tables (which relies on * IPI-ing threads). */ local_irq_save(flags); ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); local_irq_restore(flags); if (ret) return ret; /* * Not seeing an error, but not updating level? Something went * deeply wrong... */ if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL)) return -EFAULT; if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL)) return -EFAULT; /* Oops, the userspace PTs are gone... Replay the fault */ if (!kvm_pte_valid(pte)) return -EAGAIN; return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); } static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, .zalloc_pages_exact = kvm_s2_zalloc_pages_exact, .free_pages_exact = kvm_s2_free_pages_exact, .free_unlinked_table = stage2_free_unlinked_table, .get_page = kvm_host_get_page, .put_page = kvm_s2_put_page, .page_count = kvm_host_page_count, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, .dcache_clean_inval_poc = clean_dcache_guest_page, .icache_inval_pou = invalidate_icache_guest_page, }; static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type) { u32 kvm_ipa_limit = get_kvm_ipa_limit(); u64 mmfr0, mmfr1; u32 phys_shift; if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK) return -EINVAL; phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type); if (is_protected_kvm_enabled()) { phys_shift = kvm_ipa_limit; } else if (phys_shift) { if (phys_shift > kvm_ipa_limit || phys_shift < ARM64_MIN_PARANGE_BITS) return -EINVAL; } else { phys_shift = KVM_PHYS_SHIFT; if (phys_shift > kvm_ipa_limit) { pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n", current->comm); return -EINVAL; } } mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); return 0; } /* * Assume that @pgt is valid and unlinked from the KVM MMU to free the * page-table without taking the kvm_mmu_lock and without performing any * TLB invalidations. * * Also, the range of addresses can be large enough to cause need_resched * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke * cond_resched() periodically to prevent hogging the CPU for a long time * and schedule something else, if required. */ static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr, phys_addr_t end) { u64 next; do { next = stage2_range_addr_end(addr, end); KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr, next - addr); if (next != end) cond_resched(); } while (addr = next, addr != end); } static void kvm_stage2_destroy(struct kvm_pgtable *pgt) { unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr); stage2_destroy_range(pgt, 0, BIT(ia_bits)); KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt); } /** * kvm_init_stage2_mmu - Initialise a S2 MMU structure * @kvm: The pointer to the KVM structure * @mmu: The pointer to the s2 MMU structure * @type: The machine type of the virtual machine * * Allocates only the stage-2 HW PGD level table(s). * Note we don't need locking here as this is only called in two cases: * * - when the VM is created, which can't race against anything * * - when secondary kvm_s2_mmu structures are initialised for NV * guests, and the caller must hold kvm->lock as this is called on a * per-vcpu basis. */ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type) { int cpu, err; struct kvm_pgtable *pgt; /* * If we already have our page tables in place, and that the * MMU context is the canonical one, we have a bug somewhere, * as this is only supposed to ever happen once per VM. * * Otherwise, we're building nested page tables, and that's * probably because userspace called KVM_ARM_VCPU_INIT more * than once on the same vcpu. Since that's actually legal, * don't kick a fuss and leave gracefully. */ if (mmu->pgt != NULL) { if (kvm_is_nested_s2_mmu(kvm, mmu)) return 0; kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } err = kvm_init_ipa_range(mmu, type); if (err) return err; pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT); if (!pgt) return -ENOMEM; mmu->arch = &kvm->arch; err = KVM_PGT_FN(kvm_pgtable_stage2_init)(pgt, mmu, &kvm_s2_mm_ops); if (err) goto out_free_pgtable; mmu->pgt = pgt; if (is_protected_kvm_enabled()) return 0; mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran)); if (!mmu->last_vcpu_ran) { err = -ENOMEM; goto out_destroy_pgtable; } for_each_possible_cpu(cpu) *per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1; /* The eager page splitting is disabled by default */ mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT; mmu->split_page_cache.gfp_zero = __GFP_ZERO; mmu->pgd_phys = __pa(pgt->pgd); if (kvm_is_nested_s2_mmu(kvm, mmu)) kvm_init_nested_s2_mmu(mmu); return 0; out_destroy_pgtable: kvm_stage2_destroy(pgt); out_free_pgtable: kfree(pgt); return err; } void kvm_uninit_stage2_mmu(struct kvm *kvm) { kvm_free_stage2_pgd(&kvm->arch.mmu); kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); } static void stage2_unmap_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { hva_t hva = memslot->userspace_addr; phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t size = PAGE_SIZE * memslot->npages; hva_t reg_end = hva + size; /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them to find out if we should * unmap any of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ * | : VMA 1 | VMA 2 | | VMA 3 : | * +---------------+----------------+ +----------------+ * | memory region | * +--------------------------------------------+ */ do { struct vm_area_struct *vma; hva_t vm_start, vm_end; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) break; /* * Take the intersection of this VMA with the memory region */ vm_start = max(hva, vma->vm_start); vm_end = min(reg_end, vma->vm_end); if (!(vma->vm_flags & VM_PFNMAP)) { gpa_t gpa = addr + (vm_start - memslot->userspace_addr); kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true); } hva = vm_end; } while (hva < reg_end); } /** * stage2_unmap_vm - Unmap Stage-2 RAM mappings * @kvm: The struct kvm pointer * * Go through the memregions and unmap any regular RAM * backing memory already mapped to the VM. */ void stage2_unmap_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int idx, bkt; idx = srcu_read_lock(&kvm->srcu); mmap_read_lock(current->mm); write_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); kvm_nested_s2_unmap(kvm, true); write_unlock(&kvm->mmu_lock); mmap_read_unlock(current->mm); srcu_read_unlock(&kvm->srcu, idx); } void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); struct kvm_pgtable *pgt = NULL; write_lock(&kvm->mmu_lock); pgt = mmu->pgt; if (pgt) { mmu->pgd_phys = 0; mmu->pgt = NULL; free_percpu(mmu->last_vcpu_ran); } write_unlock(&kvm->mmu_lock); if (pgt) { kvm_stage2_destroy(pgt); kfree(pgt); } } static void hyp_mc_free_fn(void *addr, void *mc) { struct kvm_hyp_memcache *memcache = mc; if (memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2) kvm_account_pgtable_pages(addr, -1); free_page((unsigned long)addr); } static void *hyp_mc_alloc_fn(void *mc) { struct kvm_hyp_memcache *memcache = mc; void *addr; addr = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); if (addr && memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2) kvm_account_pgtable_pages(addr, 1); return addr; } void free_hyp_memcache(struct kvm_hyp_memcache *mc) { if (!is_protected_kvm_enabled()) return; kfree(mc->mapping); __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, mc); } int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) { if (!is_protected_kvm_enabled()) return 0; if (!mc->mapping) { mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT); if (!mc->mapping) return -ENOMEM; } return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn, kvm_host_pa, mc); } /** * kvm_phys_addr_ioremap - map a device range to guest IPA * * @kvm: The KVM pointer * @guest_ipa: The IPA at which to insert the mapping * @pa: The physical address of the device * @size: The size of the mapping * @writable: Whether or not to create a writable mapping */ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t pa, unsigned long size, bool writable) { phys_addr_t addr; int ret = 0; struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO }; struct kvm_s2_mmu *mmu = &kvm->arch.mmu; struct kvm_pgtable *pgt = mmu->pgt; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_R | (writable ? KVM_PGTABLE_PROT_W : 0); if (is_protected_kvm_enabled()) return -EPERM; size += offset_in_page(guest_ipa); guest_ipa &= PAGE_MASK; for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) { ret = kvm_mmu_topup_memory_cache(&cache, kvm_mmu_cache_min_pages(mmu)); if (ret) break; write_lock(&kvm->mmu_lock); ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, addr, PAGE_SIZE, pa, prot, &cache, 0); write_unlock(&kvm->mmu_lock); if (ret) break; pa += PAGE_SIZE; } kvm_mmu_free_memory_cache(&cache); return ret; } /** * kvm_stage2_wp_range() - write protect stage2 memory region range * @mmu: The KVM stage-2 MMU pointer * @addr: Start address of range * @end: End address of range */ void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_wrprotect)); } /** * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot * @kvm: The KVM pointer * @slot: The memory slot to write protect * * Called to start logging dirty pages after memory region * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns * all present PUD, PMD and PTEs are write protected in the memory region. * Afterwards read of dirty page log can be called. * * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired, * serializing operations for VM memory regions. */ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); phys_addr_t start, end; if (WARN_ON_ONCE(!memslot)) return; start = memslot->base_gfn << PAGE_SHIFT; end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_stage2_wp_range(&kvm->arch.mmu, start, end); kvm_nested_s2_wp(kvm); write_unlock(&kvm->mmu_lock); kvm_flush_remote_tlbs_memslot(kvm, memslot); } /** * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE * pages for memory slot * @kvm: The KVM pointer * @slot: The memory slot to split * * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired, * serializing operations for VM memory regions. */ static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; phys_addr_t start, end; lockdep_assert_held(&kvm->slots_lock); slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, slot); start = memslot->base_gfn << PAGE_SHIFT; end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_mmu_split_huge_pages(kvm, start, end); write_unlock(&kvm->mmu_lock); } /* * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages. * @kvm: The KVM pointer * @slot: The memory slot associated with mask * @gfn_offset: The gfn offset in memory slot * @mask: The mask of pages at offset 'gfn_offset' in this memory * slot to enable dirty logging on * * Writes protect selected pages to enable dirty logging, and then * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock. */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { phys_addr_t base_gfn = slot->base_gfn + gfn_offset; phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; lockdep_assert_held_write(&kvm->mmu_lock); kvm_stage2_wp_range(&kvm->arch.mmu, start, end); /* * Eager-splitting is done when manual-protect is set. We * also check for initially-all-set because we can avoid * eager-splitting if initially-all-set is false. * Initially-all-set equal false implies that huge-pages were * already split when enabling dirty logging: no need to do it * again. */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) kvm_mmu_split_huge_pages(kvm, start, end); kvm_nested_s2_wp(kvm); } static void kvm_send_hwpoison_signal(unsigned long address, short lsb) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current); } static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, unsigned long hva, unsigned long map_size) { gpa_t gpa_start; hva_t uaddr_start, uaddr_end; size_t size; /* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */ if (map_size == PAGE_SIZE) return true; /* pKVM only supports PMD_SIZE huge-mappings */ if (is_protected_kvm_enabled() && map_size != PMD_SIZE) return false; size = memslot->npages * PAGE_SIZE; gpa_start = memslot->base_gfn << PAGE_SHIFT; uaddr_start = memslot->userspace_addr; uaddr_end = uaddr_start + size; /* * Pages belonging to memslots that don't have the same alignment * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2 * PMD/PUD entries, because we'll end up mapping the wrong pages. * * Consider a layout like the following: * * memslot->userspace_addr: * +-----+--------------------+--------------------+---+ * |abcde|fgh Stage-1 block | Stage-1 block tv|xyz| * +-----+--------------------+--------------------+---+ * * memslot->base_gfn << PAGE_SHIFT: * +---+--------------------+--------------------+-----+ * |abc|def Stage-2 block | Stage-2 block |tvxyz| * +---+--------------------+--------------------+-----+ * * If we create those stage-2 blocks, we'll end up with this incorrect * mapping: * d -> f * e -> g * f -> h */ if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1))) return false; /* * Next, let's make sure we're not trying to map anything not covered * by the memslot. This means we have to prohibit block size mappings * for the beginning and end of a non-block aligned and non-block sized * memory slot (illustrated by the head and tail parts of the * userspace view above containing pages 'abcde' and 'xyz', * respectively). * * Note that it doesn't matter if we do the check using the * userspace_addr or the base_gfn, as both are equally aligned (per * the check above) and equally sized. */ return (hva & ~(map_size - 1)) >= uaddr_start && (hva & ~(map_size - 1)) + map_size <= uaddr_end; } /* * Check if the given hva is backed by a transparent huge page (THP) and * whether it can be mapped using block mapping in stage2. If so, adjust * the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently * supported. This will need to be updated to support other THP sizes. * * Returns the size of the mapping. */ static long transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) { kvm_pfn_t pfn = *pfnp; /* * Make sure the adjustment is done only for THP pages. Also make * sure that the HVA and IPA are sufficiently aligned and that the * block map is contained within the memslot. */ if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { int sz = get_user_mapping_size(kvm, hva); if (sz < 0) return sz; if (sz < PMD_SIZE) return PAGE_SIZE; *ipap &= PMD_MASK; pfn &= ~(PTRS_PER_PMD - 1); *pfnp = pfn; return PMD_SIZE; } /* Use page mapping if we cannot use block mapping. */ return PAGE_SIZE; } static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva) { unsigned long pa; if (is_vm_hugetlb_page(vma) && !(vma->vm_flags & VM_PFNMAP)) return huge_page_shift(hstate_vma(vma)); if (!(vma->vm_flags & VM_PFNMAP)) return PAGE_SHIFT; VM_BUG_ON(is_vm_hugetlb_page(vma)); pa = (vma->vm_pgoff << PAGE_SHIFT) + (hva - vma->vm_start); #ifndef __PAGETABLE_PMD_FOLDED if ((hva & (PUD_SIZE - 1)) == (pa & (PUD_SIZE - 1)) && ALIGN_DOWN(hva, PUD_SIZE) >= vma->vm_start && ALIGN(hva, PUD_SIZE) <= vma->vm_end) return PUD_SHIFT; #endif if ((hva & (PMD_SIZE - 1)) == (pa & (PMD_SIZE - 1)) && ALIGN_DOWN(hva, PMD_SIZE) >= vma->vm_start && ALIGN(hva, PMD_SIZE) <= vma->vm_end) return PMD_SHIFT; return PAGE_SHIFT; } /* * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be * able to see the page's tags and therefore they must be initialised first. If * PG_mte_tagged is set, tags have already been initialised. * * Must be called with kvm->mmu_lock held to ensure the memory remains mapped * while the tags are zeroed. */ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, unsigned long size) { unsigned long i, nr_pages = size >> PAGE_SHIFT; struct page *page = pfn_to_page(pfn); struct folio *folio = page_folio(page); if (!kvm_has_mte(kvm)) return; if (folio_test_hugetlb(folio)) { /* Hugetlb has MTE flags set on head page only */ if (folio_try_hugetlb_mte_tagging(folio)) { for (i = 0; i < nr_pages; i++, page++) mte_clear_page_tags(page_address(page)); folio_set_hugetlb_mte_tagged(folio); } return; } for (i = 0; i < nr_pages; i++, page++) { if (try_page_mte_tagging(page)) { mte_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } } } static bool kvm_vma_mte_allowed(struct vm_area_struct *vma) { return vma->vm_flags & VM_MTE_ALLOWED; } static bool kvm_vma_is_cacheable(struct vm_area_struct *vma) { switch (FIELD_GET(PTE_ATTRINDX_MASK, pgprot_val(vma->vm_page_prot))) { case MT_NORMAL_NC: case MT_DEVICE_nGnRnE: case MT_DEVICE_nGnRE: return false; default: return true; } } static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_s2_trans *nested, struct kvm_memory_slot *memslot, unsigned long hva, bool fault_is_perm) { int ret = 0; bool write_fault, writable, force_pte = false; bool exec_fault, mte_allowed, is_vma_cacheable; bool s2_force_noncacheable = false, vfio_allow_any_uc = false; unsigned long mmu_seq; phys_addr_t ipa = fault_ipa; struct kvm *kvm = vcpu->kvm; struct vm_area_struct *vma; short vma_shift; void *memcache; gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt; struct page *page; vm_flags_t vm_flags; enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; if (fault_is_perm) fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu); write_fault = kvm_is_write_fault(vcpu); exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); if (fault_is_perm && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; } if (!is_protected_kvm_enabled()) memcache = &vcpu->arch.mmu_page_cache; else memcache = &vcpu->arch.pkvm_memcache; /* * Permission faults just need to update the existing leaf entry, * and so normally don't require allocations from the memcache. The * only exception to this is when dirty logging is enabled at runtime * and a write fault needs to collapse a block entry into a table. */ if (!fault_is_perm || (logging_active && write_fault)) { int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu); if (!is_protected_kvm_enabled()) ret = kvm_mmu_topup_memory_cache(memcache, min_pages); else ret = topup_hyp_memcache(memcache, min_pages); if (ret) return ret; } /* * Let's check if we will get back a huge page backed by hugetlbfs, or * get block mapping for device MMIO region. */ mmap_read_lock(current->mm); vma = vma_lookup(current->mm, hva); if (unlikely(!vma)) { kvm_err("Failed to find VMA for hva 0x%lx\n", hva); mmap_read_unlock(current->mm); return -EFAULT; } /* * logging_active is guaranteed to never be true for VM_PFNMAP * memslots. */ if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; } else { vma_shift = get_vma_page_shift(vma, hva); } switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) break; fallthrough; #endif case CONT_PMD_SHIFT: vma_shift = PMD_SHIFT; fallthrough; case PMD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) break; fallthrough; case CONT_PTE_SHIFT: vma_shift = PAGE_SHIFT; force_pte = true; fallthrough; case PAGE_SHIFT: break; default: WARN_ONCE(1, "Unknown vma_shift %d", vma_shift); } vma_pagesize = 1UL << vma_shift; if (nested) { unsigned long max_map_size; max_map_size = force_pte ? PAGE_SIZE : PUD_SIZE; ipa = kvm_s2_trans_output(nested); /* * If we're about to create a shadow stage 2 entry, then we * can only create a block mapping if the guest stage 2 page * table uses at least as big a mapping. */ max_map_size = min(kvm_s2_trans_size(nested), max_map_size); /* * Be careful that if the mapping size falls between * two host sizes, take the smallest of the two. */ if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE) max_map_size = PMD_SIZE; else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE) max_map_size = PAGE_SIZE; force_pte = (max_map_size == PAGE_SIZE); vma_pagesize = min(vma_pagesize, (long)max_map_size); } /* * Both the canonical IPA and fault IPA must be hugepage-aligned to * ensure we find the right PFN and lay down the mapping in the right * place. */ if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) { fault_ipa &= ~(vma_pagesize - 1); ipa &= ~(vma_pagesize - 1); } gfn = ipa >> PAGE_SHIFT; mte_allowed = kvm_vma_mte_allowed(vma); vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED; vm_flags = vma->vm_flags; is_vma_cacheable = kvm_vma_is_cacheable(vma); /* Don't use the VMA after the unlock -- it may have vanished */ vma = NULL; /* * Read mmu_invalidate_seq so that KVM can detect if the results of * vma_lookup() or __kvm_faultin_pfn() become stale prior to * acquiring kvm->mmu_lock. * * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs * with the smp_wmb() in kvm_mmu_invalidate_end(). */ mmu_seq = vcpu->kvm->mmu_invalidate_seq; mmap_read_unlock(current->mm); pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0, &writable, &page); if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(hva, vma_shift); return 0; } if (is_error_noslot_pfn(pfn)) return -EFAULT; /* * Check if this is non-struct page memory PFN, and cannot support * CMOs. It could potentially be unsafe to access as cachable. */ if (vm_flags & (VM_PFNMAP | VM_MIXEDMAP) && !pfn_is_map_memory(pfn)) { if (is_vma_cacheable) { /* * Whilst the VMA owner expects cacheable mapping to this * PFN, hardware also has to support the FWB and CACHE DIC * features. * * ARM64 KVM relies on kernel VA mapping to the PFN to * perform cache maintenance as the CMO instructions work on * virtual addresses. VM_PFNMAP region are not necessarily * mapped to a KVA and hence the presence of hardware features * S2FWB and CACHE DIC are mandatory to avoid the need for * cache maintenance. */ if (!kvm_supports_cacheable_pfnmap()) ret = -EFAULT; } else { /* * If the page was identified as device early by looking at * the VMA flags, vma_pagesize is already representing the * largest quantity we can map. If instead it was mapped * via __kvm_faultin_pfn(), vma_pagesize is set to PAGE_SIZE * and must not be upgraded. * * In both cases, we don't let transparent_hugepage_adjust() * change things at the last minute. */ s2_force_noncacheable = true; } } else if (logging_active && !write_fault) { /* * Only actually map the page as writable if this was a write * fault. */ writable = false; } if (exec_fault && s2_force_noncacheable) ret = -ENOEXEC; if (ret) { kvm_release_page_unused(page); return ret; } /* * Potentially reduce shadow S2 permissions to match the guest's own * S2. For exec faults, we'd only reach this point if the guest * actually allowed it (see kvm_s2_handle_perm_fault). * * Also encode the level of the original translation in the SW bits * of the leaf entry as a proxy for the span of that translation. * This will be retrieved on TLB invalidation from the guest and * used to limit the invalidation scope if a TTL hint or a range * isn't provided. */ if (nested) { writable &= kvm_s2_trans_writable(nested); if (!kvm_s2_trans_readable(nested)) prot &= ~KVM_PGTABLE_PROT_R; prot |= kvm_encode_nested_level(nested); } kvm_fault_lock(kvm); pgt = vcpu->arch.hw_mmu->pgt; if (mmu_invalidate_retry(kvm, mmu_seq)) { ret = -EAGAIN; goto out_unlock; } /* * If we are not forced to use page mapping, check if we are * backed by a THP and thus use block mapping if possible. */ if (vma_pagesize == PAGE_SIZE && !(force_pte || s2_force_noncacheable)) { if (fault_is_perm && fault_granule > PAGE_SIZE) vma_pagesize = fault_granule; else vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &pfn, &fault_ipa); if (vma_pagesize < 0) { ret = vma_pagesize; goto out_unlock; } } if (!fault_is_perm && !s2_force_noncacheable && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new disallowed VMA */ if (mte_allowed) { sanitise_mte_tags(kvm, pfn, vma_pagesize); } else { ret = -EFAULT; goto out_unlock; } } if (writable) prot |= KVM_PGTABLE_PROT_W; if (exec_fault) prot |= KVM_PGTABLE_PROT_X; if (s2_force_noncacheable) { if (vfio_allow_any_uc) prot |= KVM_PGTABLE_PROT_NORMAL_NC; else prot |= KVM_PGTABLE_PROT_DEVICE; } else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC) && (!nested || kvm_s2_trans_executable(nested))) { prot |= KVM_PGTABLE_PROT_X; } /* * Under the premise of getting a FSC_PERM fault, we just need to relax * permissions only if vma_pagesize equals fault_granule. Otherwise, * kvm_pgtable_stage2_map() should be called to change block size. */ if (fault_is_perm && vma_pagesize == fault_granule) { /* * Drop the SW bits in favour of those stored in the * PTE, which will be preserved. */ prot &= ~KVM_NV_GUEST_MAP_SZ; ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, fault_ipa, prot, flags); } else { ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, memcache, flags); } out_unlock: kvm_release_faultin_page(kvm, page, !!ret, writable); kvm_fault_unlock(kvm); /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) mark_page_dirty_in_slot(kvm, memslot, gfn); return ret != -EAGAIN ? ret : 0; } /* Resolve the access fault by making the page young again. */ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED; struct kvm_s2_mmu *mmu; trace_kvm_access_fault(fault_ipa); read_lock(&vcpu->kvm->mmu_lock); mmu = vcpu->arch.hw_mmu; KVM_PGT_FN(kvm_pgtable_stage2_mkyoung)(mmu->pgt, fault_ipa, flags); read_unlock(&vcpu->kvm->mmu_lock); } int kvm_handle_guest_sea(struct kvm_vcpu *vcpu) { /* * Give APEI the opportunity to claim the abort before handling it * within KVM. apei_claim_sea() expects to be called with IRQs enabled. */ lockdep_assert_irqs_enabled(); if (apei_claim_sea(NULL) == 0) return 1; return kvm_inject_serror(vcpu); } /** * kvm_handle_guest_abort - handles all 2nd stage aborts * @vcpu: the VCPU pointer * * Any abort that gets to the host is almost guaranteed to be caused by a * missing second stage translation table entry, which can mean that either the * guest simply needs more memory and we must allocate an appropriate page or it * can mean that the guest tried to access I/O memory, which is emulated by user * space. The distinction is based on the IPA causing the fault and whether this * memory region has been registered as standard RAM by user space. */ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) { struct kvm_s2_trans nested_trans, *nested = NULL; unsigned long esr; phys_addr_t fault_ipa; /* The address we faulted on */ phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */ struct kvm_memory_slot *memslot; unsigned long hva; bool is_iabt, write_fault, writable; gfn_t gfn; int ret, idx; if (kvm_vcpu_abt_issea(vcpu)) return kvm_handle_guest_sea(vcpu); esr = kvm_vcpu_get_esr(vcpu); /* * The fault IPA should be reliable at this point as we're not dealing * with an SEA. */ ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm)) return -EFAULT; is_iabt = kvm_vcpu_trap_is_iabt(vcpu); if (esr_fsc_is_translation_fault(esr)) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); return 1; } /* Falls between the IPA range and the PARange? */ if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) { fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); return kvm_inject_sea(vcpu, is_iabt, fault_ipa); } } trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu), kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ if (!esr_fsc_is_translation_fault(esr) && !esr_fsc_is_permission_fault(esr) && !esr_fsc_is_access_flag_fault(esr)) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), (unsigned long)kvm_vcpu_get_esr(vcpu)); return -EFAULT; } idx = srcu_read_lock(&vcpu->kvm->srcu); /* * We may have faulted on a shadow stage 2 page table if we are * running a nested guest. In this case, we have to resolve the L2 * IPA to the L1 IPA first, before knowing what kind of memory should * back the L1 IPA. * * If the shadow stage 2 page table walk faults, then we simply inject * this to the guest and carry on. * * If there are no shadow S2 PTs because S2 is disabled, there is * nothing to walk and we treat it as a 1:1 before going through the * canonical translation. */ if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) && vcpu->arch.hw_mmu->nested_stage2_enabled) { u32 esr; ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans); if (ret) { esr = kvm_s2_trans_esr(&nested_trans); kvm_inject_s2_fault(vcpu, esr); goto out_unlock; } ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans); if (ret) { esr = kvm_s2_trans_esr(&nested_trans); kvm_inject_s2_fault(vcpu, esr); goto out_unlock; } ipa = kvm_s2_trans_output(&nested_trans); nested = &nested_trans; } gfn = ipa >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); write_fault = kvm_is_write_fault(vcpu); if (kvm_is_error_hva(hva) || (write_fault && !writable)) { /* * The guest has put either its instructions or its page-tables * somewhere it shouldn't have. Userspace won't be able to do * anything about this (there's no syndrome for a start), so * re-inject the abort back into the guest. */ if (is_iabt) { ret = -ENOEXEC; goto out; } if (kvm_vcpu_abt_iss1tw(vcpu)) { ret = kvm_inject_sea_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); goto out_unlock; } /* * Check for a cache maintenance operation. Since we * ended-up here, we know it is outside of any memory * slot. But we can't find out if that is for a device, * or if the guest is just being stupid. The only thing * we know for sure is that this range cannot be cached. * * So let's assume that the guest is just being * cautious, and skip the instruction. */ if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) { kvm_incr_pc(vcpu); ret = 1; goto out_unlock; } /* * The IPA is reported as [MAX:12], so we need to * complement it with the bottom 12 bits from the * faulting VA. This is always 12 bits, irrespective * of the page size. */ ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); ret = io_mem_abort(vcpu, ipa); goto out_unlock; } /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu)); if (esr_fsc_is_access_flag_fault(esr)) { handle_access_fault(vcpu, fault_ipa); ret = 1; goto out_unlock; } ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva, esr_fsc_is_permission_fault(esr)); if (ret == 0) ret = 1; out: if (ret == -ENOEXEC) ret = kvm_inject_sea_iabt(vcpu, kvm_vcpu_get_hfar(vcpu)); out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); kvm_nested_s2_unmap(kvm, range->may_block); return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { u64 size = (range->end - range->start) << PAGE_SHIFT; if (!kvm->arch.mmu.pgt) return false; return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, true); /* * TODO: Handle nested_mmu structures here using the reverse mapping in * a later version of patch series. */ } bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { u64 size = (range->end - range->start) << PAGE_SHIFT; if (!kvm->arch.mmu.pgt) return false; return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, size, false); } phys_addr_t kvm_mmu_get_httbr(void) { return __pa(hyp_pgtable->pgd); } phys_addr_t kvm_get_idmap_vector(void) { return hyp_idmap_vector; } static int kvm_map_idmap_text(void) { unsigned long size = hyp_idmap_end - hyp_idmap_start; int err = __create_hyp_mappings(hyp_idmap_start, size, hyp_idmap_start, PAGE_HYP_EXEC); if (err) kvm_err("Failed to idmap %lx-%lx\n", hyp_idmap_start, hyp_idmap_end); return err; } static void *kvm_hyp_zalloc_page(void *arg) { return (void *)get_zeroed_page(GFP_KERNEL); } static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = { .zalloc_page = kvm_hyp_zalloc_page, .get_page = kvm_host_get_page, .put_page = kvm_host_put_page, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, }; int __init kvm_mmu_init(u32 *hyp_va_bits) { int err; u32 idmap_bits; u32 kernel_bits; hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start); hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE); hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end); hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE); hyp_idmap_vector = __pa_symbol(__kvm_hyp_init); /* * We rely on the linker script to ensure at build time that the HYP * init code does not cross a page boundary. */ BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); /* * The ID map is always configured for 48 bits of translation, which * may be fewer than the number of VA bits used by the regular kernel * stage 1, when VA_BITS=52. * * At EL2, there is only one TTBR register, and we can't switch between * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom * line: we need to use the extended range with *both* our translation * tables. * * So use the maximum of the idmap VA bits and the regular kernel stage * 1 VA bits to assure that the hypervisor can both ID map its code page * and map any kernel memory. */ idmap_bits = IDMAP_VA_BITS; kernel_bits = vabits_actual; *hyp_va_bits = max(idmap_bits, kernel_bits); kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits); kvm_debug("IDMAP page: %lx\n", hyp_idmap_start); kvm_debug("HYP VA range: %lx:%lx\n", kern_hyp_va(PAGE_OFFSET), kern_hyp_va((unsigned long)high_memory - 1)); if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) && hyp_idmap_start < kern_hyp_va((unsigned long)high_memory - 1) && hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) { /* * The idmap page is intersecting with the VA space, * it is not safe to continue further. */ kvm_err("IDMAP intersecting with HYP VA, unable to continue\n"); err = -EINVAL; goto out; } hyp_pgtable = kzalloc(sizeof(*hyp_pgtable), GFP_KERNEL); if (!hyp_pgtable) { kvm_err("Hyp mode page-table not allocated\n"); err = -ENOMEM; goto out; } err = kvm_pgtable_hyp_init(hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops); if (err) goto out_free_pgtable; err = kvm_map_idmap_text(); if (err) goto out_destroy_pgtable; io_map_base = hyp_idmap_start; __hyp_va_bits = *hyp_va_bits; return 0; out_destroy_pgtable: kvm_pgtable_hyp_destroy(hyp_pgtable); out_free_pgtable: kfree(hyp_pgtable); hyp_pgtable = NULL; out: return err; } void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES; /* * At this point memslot has been committed and there is an * allocated dirty_bitmap[], dirty pages will be tracked while the * memory slot is write protected. */ if (log_dirty_pages) { if (change == KVM_MR_DELETE) return; /* * Huge and normal pages are write-protected and split * on either of these two cases: * * 1. with initial-all-set: gradually with CLEAR ioctls, */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) return; /* * or * 2. without initial-all-set: all in one shot when * enabling dirty logging. */ kvm_mmu_wp_memory_region(kvm, new->id); kvm_mmu_split_memory_region(kvm, new->id); } else { /* * Free any leftovers from the eager page splitting cache. Do * this when deleting, moving, disabling dirty logging, or * creating the memslot (a nop). Doing it for deletes makes * sure we don't leak memory, and there's no need to keep the * cache around for any of the other cases. */ kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache); } } int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { hva_t hva, reg_end; int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && change != KVM_MR_FLAGS_ONLY) return 0; /* * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT)) return -EFAULT; hva = new->userspace_addr; reg_end = hva + (new->npages << PAGE_SHIFT); mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and any holes * between them, so iterate over all of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ * | : VMA 1 | VMA 2 | | VMA 3 : | * +---------------+----------------+ +----------------+ * | memory region | * +--------------------------------------------+ */ do { struct vm_area_struct *vma; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) break; if (kvm_has_mte(kvm) && !kvm_vma_mte_allowed(vma)) { ret = -EINVAL; break; } if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; break; } /* * Cacheable PFNMAP is allowed only if the hardware * supports it. */ if (kvm_vma_is_cacheable(vma) && !kvm_supports_cacheable_pfnmap()) { ret = -EINVAL; break; } } hva = min(reg_end, vma->vm_end); } while (hva < reg_end); mmap_read_unlock(current->mm); return ret; } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { } void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { gpa_t gpa = slot->base_gfn << PAGE_SHIFT; phys_addr_t size = slot->npages << PAGE_SHIFT; write_lock(&kvm->mmu_lock); kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true); kvm_nested_s2_unmap(kvm, true); write_unlock(&kvm->mmu_lock); } /* * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). * * Main problems: * - S/W ops are local to a CPU (not broadcast) * - We have line migration behind our back (speculation) * - System caches don't support S/W at all (damn!) * * In the face of the above, the best we can do is to try and convert * S/W ops to VA ops. Because the guest is not allowed to infer the * S/W to PA mapping, it can only use S/W to nuke the whole cache, * which is a rather good thing for us. * * Also, it is only used when turning caches on/off ("The expected * usage of the cache maintenance instructions that operate by set/way * is associated with the cache maintenance instructions associated * with the powerdown and powerup of caches, if this is required by * the implementation."). * * We use the following policy: * * - If we trap a S/W operation, we enable VM trapping to detect * caches being turned on/off, and do a full clean. * * - We flush the caches on both caches being turned on and off. * * - Once the caches are enabled, we stop trapping VM ops. */ void kvm_set_way_flush(struct kvm_vcpu *vcpu) { unsigned long hcr = *vcpu_hcr(vcpu); /* * If this is the first time we do a S/W operation * (i.e. HCR_TVM not set) flush the whole memory, and set the * VM trapping. * * Otherwise, rely on the VM trapping to wait for the MMU + * Caches to be turned off. At that point, we'll be able to * clean the caches again. */ if (!(hcr & HCR_TVM)) { trace_kvm_set_way_flush(*vcpu_pc(vcpu), vcpu_has_cache_enabled(vcpu)); stage2_flush_vm(vcpu->kvm); *vcpu_hcr(vcpu) = hcr | HCR_TVM; } } void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled) { bool now_enabled = vcpu_has_cache_enabled(vcpu); /* * If switching the MMU+caches on, need to invalidate the caches. * If switching it off, need to clean the caches. * Clean + invalidate does the trick always. */ if (now_enabled != was_enabled) stage2_flush_vm(vcpu->kvm); /* Caches are now on, stop trapping VM ops (until a S/W op) */ if (now_enabled) *vcpu_hcr(vcpu) &= ~HCR_TVM; trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); } |
| 232 233 233 232 233 232 233 232 233 230 232 231 232 233 232 232 233 231 233 233 371 372 233 215 218 93 94 93 93 94 371 231 216 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) static void retrigger_next_event(void *arg); /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, { .index = HRTIMER_BASE_MONOTONIC_SOFT, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME_SOFT, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME_SOFT, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, }, .csd = CSD_INIT(retrigger_next_event, NULL) }; static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) { if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; else return likely(base->online); } /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; for (;;) { base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * Check if the elected target is suitable considering its next * event and the hotplug state of the current CPU. * * If the elected target is remote and its next event is after the timer * to queue, then a remote reprogram is necessary. However there is no * guarantee the IPI handling the operation would arrive in time to meet * the high resolution deadline. In this case the local CPU becomes a * preferred target, unless it is offline. * * High and low resolution modes are handled the same way for simplicity. * * Called with cpu_base->lock of target cpu held. */ static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base, struct hrtimer_cpu_base *new_cpu_base, struct hrtimer_cpu_base *this_cpu_base) { ktime_t expires; /* * The local CPU clockevent can be reprogrammed. Also get_target_base() * guarantees it is online. */ if (new_cpu_base == this_cpu_base) return true; /* * The offline local CPU can't be the default target if the * next remote target event is after this timer. Keep the * elected new base. An IPI will we issued to reprogram * it as a last resort. */ if (!hrtimer_base_is_online(this_cpu_base)) return true; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires >= new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { if (!hrtimer_base_is_online(base)) { int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER)); return &per_cpu(hrtimer_bases, cpu); } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq * code will take care of this when the timer function has * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ACCESS_PRIVATE((struct hrtimer *)addr, function); } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif static inline void debug_setup(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_setup(timer, clockid, mode); } static inline void debug_setup_on_stack(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init_on_stack(timer); trace_hrtimer_setup(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode); } static inline void debug_deactivate(struct hrtimer *timer) { debug_hrtimer_deactivate(timer); trace_hrtimer_cancel(timer); } static struct hrtimer_clock_base * __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) { unsigned int idx; if (!*active) return NULL; idx = __ffs(*active); *active &= ~(1U << idx); return &cpu_base->clock_base[idx]; } #define for_each_active_base(base, cpu_base, active) \ while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; struct hrtimer *timer; next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); if (timer == exclude) { /* Get to the next timer in the queue. */ next = timerqueue_iterate_next(next); if (!next) continue; timer = container_of(next, struct hrtimer, node); } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; /* Skip cpu_base update if a timer is being excluded. */ if (exclude) continue; if (timer->is_soft) cpu_base->softirq_next_timer = timer; else cpu_base->next_timer = timer; } } /* * clock_was_set() might have changed base->offset of any of * the clock bases so the result might be negative. Fix it up * to prevent a false positive in clockevents_program_event(). */ if (expires_next < 0) expires_next = 0; return expires_next; } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { unsigned int active; struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, expires_next); } return expires_next; } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active ? */ static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); } /* * Reprogram the event source with checking both queues for the * next event * Called with interrupts disabled and base->lock held */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { ktime_t expires_next; expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* * hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline int hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } /* * Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } #else static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. */ if (!hrtimer_hres_active(base) && !tick_nohz_active) return; raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); raw_spin_unlock(&base->lock); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* * If the hrtimer interrupt is running, then it will reevaluate the * clock bases and reprogram the clock event device. */ if (cpu_base->in_hrtirq) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* * If the remote CPU is currently handling an hrtimer interrupt, it * will reevaluate the first expiring timer of all clock bases * before reprogramming. Nothing to do here. */ if (cpu_base->in_hrtirq) return false; /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; next = timerqueue_getnext(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases); cpumask_var_t mask; int cpu; if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ cpus_read_lock(); for_each_online_cpu(cpu) { unsigned long flags; cpu_base = &per_cpu(hrtimer_bases, cpu); raw_spin_lock_irqsave(&cpu_base->lock, flags); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } preempt_disable(); smp_call_function_many(mask, retrigger_next_event, NULL, 1); preempt_enable(); cpus_read_unlock(); free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * * .. note:: * This only updates the timer expiry value and does not requeue the timer. * * There is also a variant of the function hrtimer_forward_now(). * * Context: Can be safely called from the callback function of @timer. If called * from other contexts @timer must neither be enqueued nor running the * callback and the caller needs to take care of serialization. * * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { u64 orun = 1; ktime_t delta; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires_tv64(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * * Returns true when the new timer is the leftmost timer in the tree. */ static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* * Note: If reprogram is false we do not update * cpu_base->next_timer. This happens when we remove the first * timer on a remote cpu. No harm as we never dereference * cpu_base->next_timer. So the worst thing what can happen is * an superfluous call to hrtimer_force_reprogram() on the * remote cpu later on if the same timer gets enqueued again. */ if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1); } /* * remove hrtimer, called with base lock held */ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* * If the timer is not restarted then reprogramming is * required if the timer is local. If it is local and about * to be restarted, avoid programming it twice (on removal * and a moment later when it's requeued). */ if (!restart) state = HRTIMER_STATE_INACTIVE; else reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires; /* * Find the next SOFT expiration. */ expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time than the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->*expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *new_base; bool force_local, first; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice * (on removal and on enqueue). To avoid that by prevent the * reprogram on removal, keep the timer local to the current CPU * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_base; force_local &= base->cpu_base->next_timer == timer; /* * Don't force local queuing if this enqueue happens on a unplugged * CPU after hrtimer_cpu_dying() has been invoked. */ force_local &= this_cpu_base->online; /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ if (!force_local) { new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); } else { new_base = base; } first = enqueue_hrtimer(timer, new_base, mode); if (!force_local) { /* * If the current CPU base is online, then the timer is * never queued on a remote CPU if it would be the first * expiring timer there. */ if (hrtimer_base_is_online(this_cpu_base)) return first; /* * Timer was enqueued remote because the current base is * already offline. If the timer is the first to expire, * kick the remote CPU to reprogram the clock event. */ if (first) { struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base; smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd); } return 0; } /* * Timer was forced to stay on the current CPU to avoid * reprogramming on removal and enqueue. Force reprogram the * hardware by evaluating the new first expiring timer. */ hrtimer_force_reprogram(new_base->cpu_base, 1); return 0; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } #ifdef CONFIG_SMP static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } #else static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } #endif /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling hrtimer_cancel() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long flags) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; expires = __hrtimer_next_event_base(cpu_base, exclude, active, KTIME_MAX); } active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; expires = __hrtimer_next_event_base(cpu_base, exclude, active, expires); } raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { switch (clock_id) { case CLOCK_REALTIME: return HRTIMER_BASE_REALTIME; case CLOCK_MONOTONIC: return HRTIMER_BASE_MONOTONIC; case CLOCK_BOOTTIME: return HRTIMER_BASE_BOOTTIME; case CLOCK_TAI: return HRTIMER_BASE_TAI; default: WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } } static void __hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); if (WARN_ON_ONCE(!function)) ACCESS_PRIVATE(timer, function) = hrtimer_dummy_timeout; else ACCESS_PRIVATE(timer, function) = function; } /** * hrtimer_setup - initialize a timer to the given clock * @timer: the timer to be initialized * @function: the callback function * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_setup(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup); /** * hrtimer_setup_on_stack - initialize a timer on stack memory * @timer: The timer to be initialized * @function: the callback function * @clock_id: The clock to be used * @mode: The timer mode * * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack * memory. */ void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_setup_on_stack(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->state and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); fn = ACCESS_PRIVATE(timer, function); /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { struct hrtimer_clock_base *base; unsigned int active = cpu_base->active_bases & active_mask; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *node; ktime_t basenow; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires_tv64(timer)) break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = 0; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via * the migration code. This does not affect enqueueing of * timers which run their callback and need to be requeued on * this CPU. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* Reevaluate the clock bases for the [soft] next expiry */ expires_next = hrtimer_update_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; cpu_base->in_hrtirq = 0; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); /* Reprogramming necessary ? */ if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. * * Acquire base lock for updating the offsets and retrieving * the current time. */ raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; /* * Give the system a chance to do something else than looping * here. We stored the entry time, so we know exactly how long * we spent here. We schedule the next event this amount of * time away. */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); delta = ktime_sub(now, entry_time); if ((unsigned int)delta > cpu_base->max_hang_time) cpu_base->max_hang_time = (unsigned int) delta; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. */ if (delta > 100 * NSEC_PER_MSEC) expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * __hrtimer_setup_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_setup_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_setup(&sl->timer, hrtimer_wakeup, clock_id, mode); sl->task = current; } /** * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_setup_on_stack(&sl->timer, clock_id, mode); __hrtimer_setup_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; hrtimer_setup_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_init_head(&clock_b->active); } cpu_base->cpu = cpu; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } int hrtimers_cpu_starting(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); /* Clear out any left over state from a CPU down operation */ cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->online = 1; return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct timerqueue_node *node; while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); } /* * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); hrtimers_cpu_starting(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } |
| 11 277 254 254 243 243 279 279 1 278 277 1 279 2 277 279 242 242 18 18 18 18 18 18 243 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * inode.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org> * * debugfs is for people to use instead of /proc or /sys. * See ./Documentation/core-api/kernel-api.rst for more details. */ #define pr_fmt(fmt) "debugfs: " fmt #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/kobject.h> #include <linux/namei.h> #include <linux/debugfs.h> #include <linux/fsnotify.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/security.h> #include "internal.h" #define DEBUGFS_DEFAULT_MODE 0700 static struct vfsmount *debugfs_mount; static int debugfs_mount_count; static bool debugfs_registered; static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; /* * Don't allow access attributes to be changed whilst the kernel is locked down * so that we can use the file mode as part of a heuristic to determine whether * to lock down individual files. */ static int debugfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { int ret; if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { ret = security_locked_down(LOCKDOWN_DEBUGFS); if (ret) return ret; } return simple_setattr(&nop_mnt_idmap, dentry, ia); } static const struct inode_operations debugfs_file_inode_operations = { .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_dir_inode_operations = { .lookup = simple_lookup, .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_symlink_inode_operations = { .get_link = simple_get_link, .setattr = debugfs_setattr, }; static struct inode *debugfs_get_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); } return inode; } struct debugfs_fs_info { kuid_t uid; kgid_t gid; umode_t mode; /* Opt_* bitfield. */ unsigned int opts; }; enum { Opt_uid, Opt_gid, Opt_mode, Opt_source, }; static const struct fs_parameter_spec debugfs_param_specs[] = { fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("mode", Opt_mode), fsparam_uid ("uid", Opt_uid), fsparam_string ("source", Opt_source), {} }; static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct debugfs_fs_info *opts = fc->s_fs_info; struct fs_parse_result result; int opt; opt = fs_parse(fc, debugfs_param_specs, param, &result); if (opt < 0) { /* * We might like to report bad mount options here; but * traditionally debugfs has ignored all mount options */ if (opt == -ENOPARAM) return 0; return opt; } switch (opt) { case Opt_uid: opts->uid = result.uid; break; case Opt_gid: opts->gid = result.gid; break; case Opt_mode: opts->mode = result.uint_32 & S_IALLUGO; break; case Opt_source: if (fc->source) return invalfc(fc, "Multiple sources specified"); fc->source = param->string; param->string = NULL; break; /* * We might like to report bad mount options here; * but traditionally debugfs has ignored all mount options */ } opts->opts |= BIT(opt); return 0; } static void _debugfs_apply_options(struct super_block *sb, bool remount) { struct debugfs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); /* * On remount, only reset mode/uid/gid if they were provided as mount * options. */ if (!remount || fsi->opts & BIT(Opt_mode)) { inode->i_mode &= ~S_IALLUGO; inode->i_mode |= fsi->mode; } if (!remount || fsi->opts & BIT(Opt_uid)) inode->i_uid = fsi->uid; if (!remount || fsi->opts & BIT(Opt_gid)) inode->i_gid = fsi->gid; } static void debugfs_apply_options(struct super_block *sb) { _debugfs_apply_options(sb, false); } static void debugfs_apply_options_remount(struct super_block *sb) { _debugfs_apply_options(sb, true); } static int debugfs_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct debugfs_fs_info *sb_opts = sb->s_fs_info; struct debugfs_fs_info *new_opts = fc->s_fs_info; if (!new_opts) return 0; sync_filesystem(sb); /* structure copy of new mount options to sb */ *sb_opts = *new_opts; debugfs_apply_options_remount(sb); return 0; } static int debugfs_show_options(struct seq_file *m, struct dentry *root) { struct debugfs_fs_info *fsi = root->d_sb->s_fs_info; if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, fsi->uid)); if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, fsi->gid)); if (fsi->mode != DEBUGFS_DEFAULT_MODE) seq_printf(m, ",mode=%o", fsi->mode); return 0; } static struct kmem_cache *debugfs_inode_cachep __ro_after_init; static void init_once(void *foo) { struct debugfs_inode_info *info = foo; inode_init_once(&info->vfs_inode); } static struct inode *debugfs_alloc_inode(struct super_block *sb) { struct debugfs_inode_info *info; info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL); if (!info) return NULL; return &info->vfs_inode; } static void debugfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode)); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .show_options = debugfs_show_options, .alloc_inode = debugfs_alloc_inode, .free_inode = debugfs_free_inode, }; static void debugfs_release_dentry(struct dentry *dentry) { struct debugfs_fsdata *fsd = dentry->d_fsdata; if (fsd) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { struct inode *inode = path->dentry->d_inode; return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private); } static const struct dentry_operations debugfs_dops = { .d_release = debugfs_release_dentry, .d_automount = debugfs_automount, }; static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr debug_files[] = {{""}}; int err; err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); if (err) return err; sb->s_op = &debugfs_super_operations; set_default_d_op(sb, &debugfs_dops); sb->s_d_flags |= DCACHE_DONTCACHE; debugfs_apply_options(sb); return 0; } static int debugfs_get_tree(struct fs_context *fc) { int err; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return -EPERM; err = get_tree_single(fc, debugfs_fill_super); if (err) return err; return debugfs_reconfigure(fc); } static void debugfs_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations debugfs_context_ops = { .free = debugfs_free_fc, .parse_param = debugfs_parse_param, .get_tree = debugfs_get_tree, .reconfigure = debugfs_reconfigure, }; static int debugfs_init_fs_context(struct fs_context *fc) { struct debugfs_fs_info *fsi; fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL); if (!fsi) return -ENOMEM; fsi->mode = DEBUGFS_DEFAULT_MODE; fc->s_fs_info = fsi; fc->ops = &debugfs_context_ops; return 0; } static struct file_system_type debug_fs_type = { .owner = THIS_MODULE, .name = "debugfs", .init_fs_context = debugfs_init_fs_context, .parameters = debugfs_param_specs, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("debugfs"); /** * debugfs_lookup() - look up an existing debugfs file * @name: a pointer to a string containing the name of the file to look up. * @parent: a pointer to the parent dentry of the file. * * This function will return a pointer to a dentry if it succeeds. If the file * doesn't exist or an error occurs, %NULL will be returned. The returned * dentry must be passed to dput() when it is no longer needed. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) { struct dentry *dentry; if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent)) return NULL; if (!parent) parent = debugfs_mount->mnt_root; dentry = lookup_noperm_positive_unlocked(&QSTR(name), parent); if (IS_ERR(dentry)) return NULL; return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); static struct dentry *start_creating(const char *name, struct dentry *parent) { struct dentry *dentry; int error; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return ERR_PTR(-EPERM); if (!debugfs_initialized()) return ERR_PTR(-ENOENT); pr_debug("creating file '%s'\n", name); if (IS_ERR(parent)) return parent; error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); if (error) { pr_err("Unable to pin filesystem for file '%s'\n", name); return ERR_PTR(error); } /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super * block. A pointer to that is in the struct vfsmount that we * have around. */ if (!parent) parent = debugfs_mount->mnt_root; dentry = simple_start_creating(parent, name); if (IS_ERR(dentry)) { if (dentry == ERR_PTR(-EEXIST)) pr_err("'%s' already exists in '%pd'\n", name, parent); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } return dentry; } static struct dentry *failed_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); return dentry; } static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct file_operations *proxy_fops, const void *real_fops) { struct dentry *dentry; struct inode *inode; if (!(mode & S_IFMT)) mode |= S_IFREG; BUG_ON(!S_ISREG(mode)); dentry = start_creating(name, parent); if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create file '%s'\n", name); return failed_creating(dentry); } inode->i_mode = mode; inode->i_private = data; inode->i_op = &debugfs_file_inode_operations; if (!real_fops) proxy_fops = &debugfs_noop_file_operations; inode->i_fop = proxy_fops; DEBUGFS_I(inode)->raw = real_fops; DEBUGFS_I(inode)->aux = (void *)aux; d_instantiate(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } struct dentry *debugfs_create_file_full(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, aux, &debugfs_full_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_full); struct dentry *debugfs_create_file_short(const char *name, umode_t mode, struct dentry *parent, void *data, const void *aux, const struct debugfs_short_fops *fops) { return __debugfs_create_file(name, mode, parent, data, aux, &debugfs_full_short_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); /** * debugfs_create_file_unsafe - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * * debugfs_create_file_unsafe() is completely analogous to * debugfs_create_file(), the only difference being that the fops * handed it will not get protected against file removals by the * debugfs core. * * It is your responsibility to protect your struct file_operation * methods against file removals by means of debugfs_file_get() * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of * DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and * thus, may be used here. */ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, NULL, &debugfs_open_proxy_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); /** * debugfs_create_file_size - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * @file_size: initial file size * * This is the basic "create a file" function for debugfs. It allows for a * wide range of flexibility in creating a file, or a directory (if you want * to create a directory, the debugfs_create_dir() function is * recommended to be used instead.) */ void debugfs_create_file_size(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops, loff_t file_size) { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); /** * debugfs_create_dir - create a directory in the debugfs filesystem * @name: a pointer to a string containing the name of the directory to * create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * directory will be created in the root of the debugfs filesystem. * * This function creates a directory in debugfs with the given name. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { struct dentry *dentry = start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create directory '%s'\n", name); return failed_creating(dentry); } inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; inode->i_op = &debugfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_dir); /** * debugfs_create_automount - create automount point in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @f: function to be called when pathname resolution steps on that one. * @data: opaque argument to pass to f(). * * @f should return what ->d_automount() would. */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, void *data) { struct dentry *dentry = start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); return failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; DEBUGFS_I(inode)->automount = f; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL(debugfs_create_automount); /** * debugfs_create_symlink- create a symbolic link in the debugfs filesystem * @name: a pointer to a string containing the name of the symbolic link to * create. * @parent: a pointer to the parent dentry for this symbolic link. This * should be a directory dentry if set. If this parameter is NULL, * then the symbolic link will be created in the root of the debugfs * filesystem. * @target: a pointer to a string containing the path to the target of the * symbolic link. * * This function creates a symbolic link with the given name in debugfs that * links to the given target path. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is * unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR) * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *target) { struct dentry *dentry; struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); return dentry; } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create symlink '%s'\n", name); kfree(link); return failed_creating(dentry); } inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_op = &debugfs_symlink_inode_operations; inode->i_link = link; d_instantiate(dentry, inode); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_symlink); static void __debugfs_file_removed(struct dentry *dentry) { struct debugfs_fsdata *fsd; /* * Paired with the closing smp_mb() implied by a successful * cmpxchg() in debugfs_file_get(): either * debugfs_file_get() must see a dead dentry or we must see a * debugfs_fsdata instance at ->d_fsdata here (or both). */ smp_mb(); fsd = READ_ONCE(dentry->d_fsdata); if (!fsd) return; /* if this was the last reference, we're done */ if (refcount_dec_and_test(&fsd->active_users)) return; /* * If there's still a reference, the code that obtained it can * be in different states: * - The common case of not using cancellations, or already * after debugfs_leave_cancellation(), where we just need * to wait for debugfs_file_put() which signals the completion; * - inside a cancellation section, i.e. between * debugfs_enter_cancellation() and debugfs_leave_cancellation(), * in which case we need to trigger the ->cancel() function, * and then wait for debugfs_file_put() just like in the * previous case; * - before debugfs_enter_cancellation() (but obviously after * debugfs_file_get()), in which case we may not see the * cancellation in the list on the first round of the loop, * but debugfs_enter_cancellation() signals the completion * after adding it, so this code gets woken up to call the * ->cancel() function. */ while (refcount_read(&fsd->active_users)) { struct debugfs_cancellation *c; /* * Lock the cancellations. Note that the cancellations * structs are meant to be on the stack, so we need to * ensure we either use them here or don't touch them, * and debugfs_leave_cancellation() will wait for this * to be finished processing before exiting one. It may * of course win and remove the cancellation, but then * chances are we never even got into this bit, we only * do if the refcount isn't zero already. */ mutex_lock(&fsd->cancellations_mtx); while ((c = list_first_entry_or_null(&fsd->cancellations, typeof(*c), list))) { list_del_init(&c->list); c->cancel(dentry, c->cancel_data); } mutex_unlock(&fsd->cancellations_mtx); wait_for_completion(&fsd->active_users_drained); } } static void remove_one(struct dentry *victim) { if (d_is_reg(victim)) __debugfs_file_removed(victim); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } /** * debugfs_remove - recursively removes a directory * @dentry: a pointer to a the dentry of the directory to be removed. If this * parameter is NULL or an error value, nothing will be done. * * This function recursively removes a directory tree in debugfs that * was previously created with a call to another debugfs function * (like debugfs_create_file() or variants thereof.) * * This function is required to be called in order for the file to be * removed, no automatic cleanup of files will happen when a module is * removed, you are responsible here. */ void debugfs_remove(struct dentry *dentry) { if (IS_ERR_OR_NULL(dentry)) return; simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); simple_recursive_removal(dentry, remove_one); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it * @name: a pointer to a string containing the name of the item to look up. * @parent: a pointer to the parent dentry of the item. * * This is the equlivant of doing something like * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting * handled for the directory being looked up. */ void debugfs_lookup_and_remove(const char *name, struct dentry *parent) { struct dentry *dentry; dentry = debugfs_lookup(name, parent); if (!dentry) return; debugfs_remove(dentry); dput(dentry); } EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); /** * debugfs_change_name - rename a file/directory in the debugfs filesystem * @dentry: dentry of an object to be renamed. * @fmt: format for new name * * This function renames a file/directory in debugfs. The target must not * exist for rename to succeed. * * This function will return 0 on success and -E... on failure. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...) { int error = 0; const char *new_name; struct name_snapshot old_name; struct dentry *parent, *target; struct inode *dir; va_list ap; if (IS_ERR_OR_NULL(dentry)) return 0; va_start(ap, fmt); new_name = kvasprintf_const(GFP_KERNEL, fmt, ap); va_end(ap); if (!new_name) return -ENOMEM; parent = dget_parent(dentry); dir = d_inode(parent); inode_lock(dir); take_dentry_name_snapshot(&old_name, dentry); if (WARN_ON_ONCE(dentry->d_parent != parent)) { error = -EINVAL; goto out; } if (strcmp(old_name.name.name, new_name) == 0) goto out; target = lookup_noperm(&QSTR(new_name), parent); if (IS_ERR(target)) { error = PTR_ERR(target); goto out; } if (d_really_is_positive(target)) { dput(target); error = -EINVAL; goto out; } simple_rename_timestamp(dir, dentry, dir, target); d_move(dentry, target); dput(target); fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry); out: release_dentry_name_snapshot(&old_name); inode_unlock(dir); dput(parent); kfree_const(new_name); return error; } EXPORT_SYMBOL_GPL(debugfs_change_name); /** * debugfs_initialized - Tells whether debugfs has been registered */ bool debugfs_initialized(void) { return debugfs_registered; } EXPORT_SYMBOL_GPL(debugfs_initialized); static int __init debugfs_kernel(char *str) { if (str) { if (!strcmp(str, "on")) debugfs_allow = DEBUGFS_ALLOW_API | DEBUGFS_ALLOW_MOUNT; else if (!strcmp(str, "no-mount")) debugfs_allow = DEBUGFS_ALLOW_API; else if (!strcmp(str, "off")) debugfs_allow = 0; } return 0; } early_param("debugfs", debugfs_kernel); static int __init debugfs_init(void) { int retval; if (!(debugfs_allow & DEBUGFS_ALLOW_MOUNT)) return -EPERM; retval = sysfs_create_mount_point(kernel_kobj, "debug"); if (retval) return retval; debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache", sizeof(struct debugfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, init_once); if (debugfs_inode_cachep == NULL) { sysfs_remove_mount_point(kernel_kobj, "debug"); return -ENOMEM; } retval = register_filesystem(&debug_fs_type); if (retval) { // Really not going to happen sysfs_remove_mount_point(kernel_kobj, "debug"); kmem_cache_destroy(debugfs_inode_cachep); return retval; } debugfs_registered = true; return 0; } core_initcall(debugfs_init); |
| 137 | 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 |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __DSA_USER_H #define __DSA_USER_H #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/list.h> #include <linux/netpoll.h> #include <linux/types.h> #include <net/dsa.h> #include <net/gro_cells.h> struct net_device; struct netlink_ext_ack; extern struct notifier_block dsa_user_switchdev_notifier; extern struct notifier_block dsa_user_switchdev_blocking_notifier; struct dsa_user_priv { /* Copy of CPU port xmit for faster access in user transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); struct gro_cells gcells; /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif /* TC context */ struct list_head mall_tc_list; }; void dsa_user_mii_bus_init(struct dsa_switch *ds); int dsa_user_create(struct dsa_port *dp); void dsa_user_destroy(struct net_device *user_dev); int dsa_user_suspend(struct net_device *user_dev); int dsa_user_resume(struct net_device *user_dev); int dsa_user_register_notifier(void); void dsa_user_unregister_notifier(void); int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr); void dsa_user_host_uc_uninstall(struct net_device *dev); void dsa_user_sync_ha(struct net_device *dev); void dsa_user_unsync_ha(struct net_device *dev); void dsa_user_setup_tagger(struct net_device *user); int dsa_user_change_mtu(struct net_device *dev, int new_mtu); int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack); int dsa_user_manage_vlan_filtering(struct net_device *dev, bool vlan_filtering); static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); return p->dp; } static inline struct net_device * dsa_user_to_conduit(const struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return dsa_port_to_conduit(dp); } #endif |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/atomic.h> #include <linux/inetdevice.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_nat_masquerade.h> struct masq_dev_work { struct work_struct work; struct net *net; netns_tracker ns_tracker; union nf_inet_addr addr; int ifindex; int (*iter)(struct nf_conn *i, void *data); }; #define MAX_MASQ_WORKER_COUNT 16 static DEFINE_MUTEX(masq_mutex); static unsigned int masq_refcnt __read_mostly; static atomic_t masq_worker_count __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, const struct nf_nat_range2 *range, const struct net_device *out) { struct nf_conn *ct; struct nf_conn_nat *nat; enum ip_conntrack_info ctinfo; struct nf_nat_range2 newrange; const struct rtable *rt; __be32 newsrc, nh; WARN_ON(hooknum != NF_INET_POST_ROUTING); ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. */ if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0) return NF_ACCEPT; rt = skb_rtable(skb); nh = rt_nexthop(rt, ip_hdr(skb)->daddr); newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE); if (!newsrc) { pr_info("%s ate my IP address\n", out->name); return NF_DROP; } nat = nf_ct_nat_ext_add(ct); if (nat) nat->masq_index = out->ifindex; /* Transfer from original range. */ memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr.ip = newsrc; newrange.max_addr.ip = newsrc; newrange.min_proto = range->min_proto; newrange.max_proto = range->max_proto; /* Hand modified range to generic setup. */ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4); static void iterate_cleanup_work(struct work_struct *work) { struct nf_ct_iter_data iter_data = {}; struct masq_dev_work *w; w = container_of(work, struct masq_dev_work, work); iter_data.net = w->net; iter_data.data = (void *)w; nf_ct_iterate_cleanup_net(w->iter, &iter_data); put_net_track(w->net, &w->ns_tracker); kfree(w); atomic_dec(&masq_worker_count); module_put(THIS_MODULE); } /* Iterate conntrack table in the background and remove conntrack entries * that use the device/address being removed. * * In case too many work items have been queued already or memory allocation * fails iteration is skipped, conntrack entries will time out eventually. */ static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, int ifindex, int (*iter)(struct nf_conn *i, void *data), gfp_t gfp_flags) { struct masq_dev_work *w; if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT) return; net = maybe_get_net(net); if (!net) return; if (!try_module_get(THIS_MODULE)) goto err_module; w = kzalloc(sizeof(*w), gfp_flags); if (w) { /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */ atomic_inc(&masq_worker_count); INIT_WORK(&w->work, iterate_cleanup_work); w->ifindex = ifindex; w->net = net; netns_tracker_alloc(net, &w->ns_tracker, gfp_flags); w->iter = iter; if (addr) w->addr = *addr; schedule_work(&w->work); return; } module_put(THIS_MODULE); err_module: put_net(net); } static int device_cmp(struct nf_conn *i, void *arg) { const struct nf_conn_nat *nat = nfct_nat(i); const struct masq_dev_work *w = arg; if (!nat) return 0; return nat->masq_index == w->ifindex; } static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) { /* Device was downed. Search entire table for * conntracks which were associated with that device, * and forget them. */ nf_nat_masq_schedule(net, NULL, dev->ifindex, device_cmp, GFP_KERNEL); } return NOTIFY_DONE; } static int inet_cmp(struct nf_conn *ct, void *ptr) { struct nf_conntrack_tuple *tuple; struct masq_dev_work *w = ptr; if (!device_cmp(ct, ptr)) return 0; tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { const struct in_ifaddr *ifa = ptr; const struct in_device *idev; const struct net_device *dev; union nf_inet_addr addr; if (event != NETDEV_DOWN) return NOTIFY_DONE; /* The masq_dev_notifier will catch the case of the device going * down. So if the inetdev is dead and being destroyed we have * no work to do. Otherwise this is an individual address removal * and we have to perform the flush. */ idev = ifa->ifa_dev; if (idev->dead) return NOTIFY_DONE; memset(&addr, 0, sizeof(addr)); addr.ip = ifa->ifa_address; dev = idev->dev; nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex, inet_cmp, GFP_KERNEL); return NOTIFY_DONE; } static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; #if IS_ENABLED(CONFIG_IPV6) static int nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr) { #ifdef CONFIG_IPV6_MODULE const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); if (!v6_ops) return -EHOSTUNREACH; return v6_ops->dev_get_saddr(net, dev, daddr, srcprefs, saddr); #else return ipv6_dev_get_saddr(net, dev, daddr, srcprefs, saddr); #endif } unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out) { enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; struct in6_addr src; struct nf_conn *ct; struct nf_nat_range2 newrange; ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); if (nat_ipv6_dev_get_saddr(nf_ct_net(ct), out, &ipv6_hdr(skb)->daddr, 0, &src) < 0) return NF_DROP; nat = nf_ct_nat_ext_add(ct); if (nat) nat->masq_index = out->ifindex; newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr.in6 = src; newrange.max_addr.in6 = src; newrange.min_proto = range->min_proto; newrange.max_proto = range->max_proto; return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). * * Defer it to the system workqueue. * * As we can have 'a lot' of inet_events (depending on amount of ipv6 * addresses being deleted), we also need to limit work item queue. */ static int masq_inet6_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; union nf_inet_addr addr; if (event != NETDEV_DOWN) return NOTIFY_DONE; dev = ifa->idev->dev; memset(&addr, 0, sizeof(addr)); addr.in6 = ifa->addr; nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp, GFP_ATOMIC); return NOTIFY_DONE; } static struct notifier_block masq_inet6_notifier = { .notifier_call = masq_inet6_event, }; static int nf_nat_masquerade_ipv6_register_notifier(void) { return register_inet6addr_notifier(&masq_inet6_notifier); } #else static inline int nf_nat_masquerade_ipv6_register_notifier(void) { return 0; } #endif int nf_nat_masquerade_inet_register_notifiers(void) { int ret = 0; mutex_lock(&masq_mutex); if (WARN_ON_ONCE(masq_refcnt == UINT_MAX)) { ret = -EOVERFLOW; goto out_unlock; } /* check if the notifier was already set */ if (++masq_refcnt > 1) goto out_unlock; /* Register for device down reports */ ret = register_netdevice_notifier(&masq_dev_notifier); if (ret) goto err_dec; /* Register IP address change reports */ ret = register_inetaddr_notifier(&masq_inet_notifier); if (ret) goto err_unregister; ret = nf_nat_masquerade_ipv6_register_notifier(); if (ret) goto err_unreg_inet; mutex_unlock(&masq_mutex); return ret; err_unreg_inet: unregister_inetaddr_notifier(&masq_inet_notifier); err_unregister: unregister_netdevice_notifier(&masq_dev_notifier); err_dec: masq_refcnt--; out_unlock: mutex_unlock(&masq_mutex); return ret; } EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_register_notifiers); void nf_nat_masquerade_inet_unregister_notifiers(void) { mutex_lock(&masq_mutex); /* check if the notifiers still have clients */ if (--masq_refcnt > 0) goto out_unlock; unregister_netdevice_notifier(&masq_dev_notifier); unregister_inetaddr_notifier(&masq_inet_notifier); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&masq_inet6_notifier); #endif out_unlock: mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_unregister_notifiers); |
| 162 193 175 174 167 167 248 249 249 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/interval_tree.c - interval tree for mapping->i_mmap * * Copyright (C) 2012, Michel Lespinasse <walken@google.com> */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/rmap.h> #include <linux/interval_tree_generic.h> static inline unsigned long vma_start_pgoff(struct vm_area_struct *v) { return v->vm_pgoff; } static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) { return v->vm_pgoff + vma_pages(v) - 1; } INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff, /* empty */, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root) { struct rb_node **link; struct vm_area_struct *parent; unsigned long last = vma_last_pgoff(node); VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); if (!prev->shared.rb.rb_right) { parent = prev; link = &prev->shared.rb.rb_right; } else { parent = rb_entry(prev->shared.rb.rb_right, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; while (parent->shared.rb.rb_left) { parent = rb_entry(parent->shared.rb.rb_left, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; } link = &parent->shared.rb.rb_left; } node->shared.rb_subtree_last = last; rb_link_node(&node->shared.rb, &parent->shared.rb, link); rb_insert_augmented(&node->shared.rb, &root->rb_root, &vma_interval_tree_augment); } static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc) { return vma_start_pgoff(avc->vma); } static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc) { return vma_last_pgoff(avc->vma); } INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last, avc_start_pgoff, avc_last_pgoff, static inline, __anon_vma_interval_tree) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root) { #ifdef CONFIG_DEBUG_VM_RB node->cached_vma_start = avc_start_pgoff(node); node->cached_vma_last = avc_last_pgoff(node); #endif __anon_vma_interval_tree_insert(node, root); } void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root) { __anon_vma_interval_tree_remove(node, root); } struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_first(root, first, last); } struct anon_vma_chain * anon_vma_interval_tree_iter_next(struct anon_vma_chain *node, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_next(node, first, last); } #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node) { WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node)); WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node)); } #endif |
| 35 35 35 35 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_RCUREF_H #define _LINUX_RCUREF_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/limits.h> #include <linux/lockdep.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #define RCUREF_ONEREF 0x00000000U #define RCUREF_MAXREF 0x7FFFFFFFU #define RCUREF_SATURATED 0xA0000000U #define RCUREF_RELEASED 0xC0000000U #define RCUREF_DEAD 0xE0000000U #define RCUREF_NOREF 0xFFFFFFFFU /** * rcuref_init - Initialize a rcuref reference count with the given reference count * @ref: Pointer to the reference count * @cnt: The initial reference count typically '1' */ static inline void rcuref_init(rcuref_t *ref, unsigned int cnt) { atomic_set(&ref->refcnt, cnt - 1); } /** * rcuref_read - Read the number of held reference counts of a rcuref * @ref: Pointer to the reference count * * Return: The number of held references (0 ... N). The value 0 does not * indicate that it is safe to schedule the object, protected by this reference * counter, for deconstruction. * If you want to know if the reference counter has been marked DEAD (as * signaled by rcuref_put()) please use rcuread_is_dead(). */ static inline unsigned int rcuref_read(rcuref_t *ref) { unsigned int c = atomic_read(&ref->refcnt); /* Return 0 if within the DEAD zone. */ return c >= RCUREF_RELEASED ? 0 : c + 1; } /** * rcuref_is_dead - Check if the rcuref has been already marked dead * @ref: Pointer to the reference count * * Return: True if the object has been marked DEAD. This signals that a previous * invocation of rcuref_put() returned true on this reference counter meaning * the protected object can safely be scheduled for deconstruction. * Otherwise, returns false. */ static inline bool rcuref_is_dead(rcuref_t *ref) { unsigned int c = atomic_read(&ref->refcnt); return (c >= RCUREF_RELEASED) && (c < RCUREF_NOREF); } extern __must_check bool rcuref_get_slowpath(rcuref_t *ref); /** * rcuref_get - Acquire one reference on a rcuref reference count * @ref: Pointer to the reference count * * Similar to atomic_inc_not_zero() but saturates at RCUREF_MAXREF. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See documentation in lib/rcuref.c * * Return: * False if the attempt to acquire a reference failed. This happens * when the last reference has been put already * * True if a reference was successfully acquired */ static inline __must_check bool rcuref_get(rcuref_t *ref) { /* * Unconditionally increase the reference count. The saturation and * dead zones provide enough tolerance for this. */ if (likely(!atomic_add_negative_relaxed(1, &ref->refcnt))) return true; /* Handle the cases inside the saturation and dead zones */ return rcuref_get_slowpath(ref); } extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt); /* * Internal helper. Do not invoke directly. */ static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) { int cnt; RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), "suspicious rcuref_put_rcusafe() usage"); /* * Unconditionally decrease the reference count. The saturation and * dead zones provide enough tolerance for this. */ cnt = atomic_sub_return_release(1, &ref->refcnt); if (likely(cnt >= 0)) return false; /* * Handle the last reference drop and cases inside the saturation * and dead zones. */ return rcuref_put_slowpath(ref, cnt); } /** * rcuref_put_rcusafe -- Release one reference for a rcuref reference count RCU safe * @ref: Pointer to the reference count * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Can be invoked from contexts, which guarantee that no grace period can * happen which would free the object concurrently if the decrement drops * the last reference and the slowpath races against a concurrent get() and * put() pair. rcu_read_lock()'ed and atomic contexts qualify. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely release the * object which is protected by the reference counter. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * release the protected object. */ static inline __must_check bool rcuref_put_rcusafe(rcuref_t *ref) { return __rcuref_put(ref); } /** * rcuref_put -- Release one reference for a rcuref reference count * @ref: Pointer to the reference count * * Can be invoked from any context. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * 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. */ static inline __must_check bool rcuref_put(rcuref_t *ref) { bool released; preempt_disable(); released = __rcuref_put(ref); preempt_enable(); return released; } #endif |
| 485 216 210 204 286 55 | 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 | /* 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(const 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(const 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(const 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 |
| 105 243 243 232 135 243 135 232 232 1 232 243 13 13 13 12 18 18 16 13 18 13 16 16 16 18 18 255 255 254 255 254 254 255 255 255 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> #include <asm/sections.h> /* mutex to protect coming/going of the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); void jump_label_lock(void) { mutex_lock(&jump_label_mutex); } void jump_label_unlock(void) { mutex_unlock(&jump_label_mutex); } static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; const struct jump_entry *jeb = b; /* * Entrires are sorted by key. */ if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; /* * In the batching mode, entries should also be sorted by the code * inside the already sorted list of entries, enabling a bsearch in * the vector. */ if (jump_entry_code(jea) < jump_entry_code(jeb)) return -1; if (jump_entry_code(jea) > jump_entry_code(jeb)) return 1; return 0; } static void jump_label_swap(void *a, void *b, int size) { long delta = (unsigned long)a - (unsigned long)b; struct jump_entry *jea = a; struct jump_entry *jeb = b; struct jump_entry tmp = *jea; jea->code = jeb->code - delta; jea->target = jeb->target - delta; jea->key = jeb->key - delta; jeb->code = tmp.code + delta; jeb->target = tmp.target + delta; jeb->key = tmp.key + delta; } static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; void *swapfn = NULL; if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); /* * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h. * The use of 'atomic_read()' requires atomic.h and its problematic for some * kernel headers such as kernel.h and others. Since static_key_count() is not * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok * to have it be a function here. Similarly, for 'static_key_enable()' and * 'static_key_disable()', which require bug.h. This should allow jump_label.h * to be included from most/all places for CONFIG_JUMP_LABEL. */ int static_key_count(struct static_key *key) { /* * -1 means the first static_key_slow_inc() is in progress. * static_key_enabled() must return true, so return 1 here. */ int n = atomic_read(&key->enabled); return n >= 0 ? n : 1; } EXPORT_SYMBOL_GPL(static_key_count); /* * static_key_fast_inc_not_disabled - adds a user for a static key * @key: static key that must be already enabled * * The caller must make sure that the static key can't get disabled while * in this function. It doesn't patch jump labels, only adds a user to * an already enabled static key. * * Returns true if the increment was done. Unlike refcount_t the ref counter * is not saturated, but will fail to increment on overflow. */ bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Negative key->enabled has a special meaning: it sends * static_key_slow_inc/dec() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). * * The INT_MAX overflow condition is either used by the networking * code to reset or detected in the slow path of * static_key_slow_inc_cpuslocked(). */ v = atomic_read(&key->enabled); do { if (v <= 0 || v == INT_MAX) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); bool static_key_slow_inc_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc/dec() calls; * later calls must wait for the first one to _finish_ the * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. */ if (static_key_fast_inc_not_disabled(key)) return true; guard(mutex)(&jump_label_mutex); /* Try to mark it as 'enabling in progress. */ if (!atomic_cmpxchg(&key->enabled, 0, -1)) { jump_label_update(key); /* * Ensure that when static_key_fast_inc_not_disabled() or * static_key_dec_not_one() observe the positive value, * they must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { /* * While holding the mutex this should never observe * anything else than a value >= 1 and succeed */ if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) return false; } return true; } bool static_key_slow_inc(struct static_key *key) { bool ret; cpus_read_lock(); ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * See static_key_slow_inc(). */ atomic_set_release(&key->enabled, 1); } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked); void static_key_enable(struct static_key *key) { cpus_read_lock(); static_key_enable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } jump_label_lock(); if (atomic_cmpxchg(&key->enabled, 1, 0) == 1) jump_label_update(key); jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked); void static_key_disable(struct static_key *key) { cpus_read_lock(); static_key_disable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable); static bool static_key_dec_not_one(struct static_key *key) { int v; /* * Go into the slow path if key::enabled is less than or equal than * one. One is valid to shut down the key, anything less than one * is an imbalance, which is handled at the call site. * * That includes the special case of '-1' which is set in * static_key_slow_inc_cpuslocked(), but that's harmless as it is * fully serialized in the slow path below. By the time this task * acquires the jump label lock the value is back to one and the * retry under the lock must succeed. */ v = atomic_read(&key->enabled); do { /* * Warn about the '-1' case though; since that means a * decrement is concurrent with a first (0->1) increment. IOW * people are trying to disable something that wasn't yet fully * enabled. This suggests an ordering problem on the user side. */ WARN_ON_ONCE(v < 0); /* * Warn about underflow, and lie about success in an attempt to * not make things worse. */ if (WARN_ON_ONCE(v == 0)) return true; if (v <= 1) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1))); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); int val; if (static_key_dec_not_one(key)) return; guard(mutex)(&jump_label_mutex); val = atomic_read(&key->enabled); /* * It should be impossible to observe -1 with jump_label_mutex held, * see static_key_slow_inc_cpuslocked(). */ if (WARN_ON_ONCE(val == -1)) return; /* * Cannot already be 0, something went sideways. */ if (WARN_ON_ONCE(val == 0)) return; if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); } static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key); } EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec_cpuslocked(key); } void __static_key_slow_dec_deferred(struct static_key *key, struct delayed_work *work, unsigned long timeout) { STATIC_KEY_CHECK_USE(key); if (static_key_dec_not_one(key)) return; schedule_delayed_work(work, timeout); } EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); flush_delayed_work(work); } EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { if (jump_entry_code(entry) <= (unsigned long)end && jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start) return 1; return 0; } static int __jump_label_text_reserved(struct jump_entry *iter_start, struct jump_entry *iter_stop, void *start, void *end, bool init) { struct jump_entry *iter; iter = iter_start; while (iter < iter_stop) { if (init || !jump_entry_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifndef arch_jump_label_transform_static static void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { /* nothing to do on most architectures */ } #endif static inline struct jump_entry *static_key_entries(struct static_key *key) { WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK); } static inline bool static_key_type(struct static_key *key) { return key->type & JUMP_TYPE_TRUE; } static inline bool static_key_linked(struct static_key *key) { return key->type & JUMP_TYPE_LINKED; } static inline void static_key_clear_linked(struct static_key *key) { key->type &= ~JUMP_TYPE_LINKED; } static inline void static_key_set_linked(struct static_key *key) { key->type |= JUMP_TYPE_LINKED; } /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in * turn point to 'struct jump_entry' tables. * * The two lower bits of the pointer are used to keep track of which pointer * type is in use and to store the initial branch direction, we use an access * function which preserves these bits. */ static void static_key_set_entries(struct static_key *key, struct jump_entry *entries) { unsigned long type; WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->entries = entries; key->type |= type; } static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; } static bool jump_label_can_update(struct jump_entry *entry, bool init) { /* * Cannot update code that was in an init text area. */ if (!init && jump_entry_is_init(entry)) return false; if (!kernel_text_address(jump_entry_code(entry))) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); return false; } return true; } #ifndef HAVE_JUMP_LABEL_BATCH static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (jump_label_can_update(entry, init)) arch_jump_label_transform(entry, jump_label_type(entry)); } } #else static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init)) continue; if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) { /* * Queue is full: Apply the current queue and try again. */ arch_jump_label_transform_apply(); BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry))); } } arch_jump_label_transform_apply(); } #endif void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct static_key *key = NULL; struct jump_entry *iter; /* * Since we are initializing the static_key.enabled field with * with the 'raw' int values (to avoid pulling in atomic.h) in * jump_label.h, let's make sure that is safe. There are only two * cases to check since we initialize to 0 or 1. */ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); if (static_key_initialized) return; cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); in_init = init_section_contains((void *)jump_entry_code(iter), 1); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; static_key_set_entries(key, iter); } static_key_initialized = true; jump_label_unlock(); cpus_read_unlock(); } static inline bool static_key_sealed(struct static_key *key) { return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); } static inline void static_key_seal(struct static_key *key) { unsigned long type = key->type & JUMP_TYPE_TRUE; key->type = JUMP_TYPE_LINKED | type; } void jump_label_init_ro(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct jump_entry *iter; if (WARN_ON_ONCE(!static_key_initialized)) return; cpus_read_lock(); jump_label_lock(); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk = jump_entry_key(iter); if (!is_kernel_ro_after_init((unsigned long)iterk)) continue; if (static_key_sealed(iterk)) continue; static_key_seal(iterk); } jump_label_unlock(); cpus_read_unlock(); } #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; } struct static_key_mod { struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; static inline struct static_key_mod *static_key_mod(struct static_key *key) { WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } /*** * key->type and key->next are the same via union. * This sets key->next and preserves the type bits. * * See additional comments above static_key_set_entries(). */ static void static_key_set_mod(struct static_key *key, struct static_key_mod *mod) { unsigned long type; WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->next = mod; key->type |= type; } static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; scoped_guard(rcu) { mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; } if (!mod) return 0; ret = __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static void __jump_label_mod_update(struct static_key *key) { struct static_key_mod *mod; for (mod = static_key_mod(key); mod; mod = mod->next) { struct jump_entry *stop; struct module *m; /* * NULL if the static_key is defined in a module * that does not use it */ if (!mod->entries) continue; m = mod->mod; if (!m) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; __jump_label_update(key, mod->entries, stop, m && m->state == MODULE_STATE_COMING); } } static int jump_label_add_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, *jlm2; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return 0; jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; in_init = within_module_init(jump_entry_code(iter), mod); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } /* * If the key was sealed at init, then there's no need to keep a * reference to its module entries - just patch them now and be * done with it. */ if (static_key_sealed(key)) goto do_poke; jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { jlm2 = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm2) { kfree(jlm); return -ENOMEM; } scoped_guard(rcu) jlm2->mod = __module_address((unsigned long)key); jlm2->entries = static_key_entries(key); jlm2->next = NULL; static_key_set_mod(key, jlm2); static_key_set_linked(key); } jlm->mod = mod; jlm->entries = iter; jlm->next = static_key_mod(key); static_key_set_mod(key, jlm); static_key_set_linked(key); /* Only update if we've changed from our initial state */ do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } return 0; } static void jump_label_del_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (jump_entry_key(iter) == key) continue; key = jump_entry_key(iter); if (within_module((unsigned long)key, mod)) continue; /* No @jlm allocated because key was sealed at init. */ if (static_key_sealed(key)) continue; /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; prev = &key->next; jlm = static_key_mod(key); while (jlm && jlm->mod != mod) { prev = &jlm->next; jlm = jlm->next; } /* No memory during module load */ if (WARN_ON(!jlm)) continue; if (prev == &key->next) static_key_set_mod(key, jlm->next); else *prev = jlm->next; kfree(jlm); jlm = static_key_mod(key); /* if only one etry is left, fold it back into the static_key */ if (jlm->next == NULL) { static_key_set_entries(key, jlm->entries); static_key_clear_linked(key); kfree(jlm); } } } static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); jump_label_lock(); switch (val) { case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; case MODULE_STATE_GOING: jump_label_del_module(mod); break; } jump_label_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, .priority = 1, /* higher than tracepoints */ }; static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ /*** * jump_label_text_reserved - check if addr range is reserved * @start: start text addr * @end: end text addr * * checks if the text addr located between @start and @end * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ int jump_label_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __jump_label_text_reserved(__start___jump_table, __stop___jump_table, start, end, init); if (ret) return ret; #ifdef CONFIG_MODULES ret = __jump_label_mod_text_reserved(start, end); #endif return ret; } static void jump_label_update(struct static_key *key) { struct jump_entry *stop = __stop___jump_table; bool init = system_state < SYSTEM_RUNNING; struct jump_entry *entry; #ifdef CONFIG_MODULES struct module *mod; if (static_key_linked(key)) { __jump_label_mod_update(key); return; } scoped_guard(rcu) { mod = __module_address((unsigned long)key); if (mod) { stop = mod->jump_entries + mod->num_jump_entries; init = mod->state == MODULE_STATE_COMING; } } #endif entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) __jump_label_update(key, entry, stop, init); } #ifdef CONFIG_STATIC_KEYS_SELFTEST static DEFINE_STATIC_KEY_TRUE(sk_true); static DEFINE_STATIC_KEY_FALSE(sk_false); static __init int jump_label_test(void) { int i; for (i = 0; i < 2; i++) { WARN_ON(static_key_enabled(&sk_true.key) != true); WARN_ON(static_key_enabled(&sk_false.key) != false); WARN_ON(!static_branch_likely(&sk_true)); WARN_ON(!static_branch_unlikely(&sk_true)); WARN_ON(static_branch_likely(&sk_false)); WARN_ON(static_branch_unlikely(&sk_false)); static_branch_disable(&sk_true); static_branch_enable(&sk_false); WARN_ON(static_key_enabled(&sk_true.key) == true); WARN_ON(static_key_enabled(&sk_false.key) == false); WARN_ON(static_branch_likely(&sk_true)); WARN_ON(static_branch_unlikely(&sk_true)); WARN_ON(!static_branch_likely(&sk_false)); WARN_ON(!static_branch_unlikely(&sk_false)); static_branch_enable(&sk_true); static_branch_disable(&sk_false); } return 0; } early_initcall(jump_label_test); #endif /* STATIC_KEYS_SELFTEST */ |
| 2 4 2 2 9 3 1 1 1 3 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2020 Arm Ltd. #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <kvm/arm_hypercalls.h> #define ARM_SMCCC_TRNG_VERSION_1_0 0x10000UL /* Those values are deliberately separate from the generic SMCCC definitions. */ #define TRNG_SUCCESS 0UL #define TRNG_NOT_SUPPORTED ((unsigned long)-1) #define TRNG_INVALID_PARAMETER ((unsigned long)-2) #define TRNG_NO_ENTROPY ((unsigned long)-3) #define TRNG_MAX_BITS64 192 static const uuid_t arm_smc_trng_uuid __aligned(4) = UUID_INIT( 0x0d21e000, 0x4384, 0x11eb, 0x80, 0x70, 0x52, 0x44, 0x55, 0x4e, 0x5a, 0x4c); static int kvm_trng_do_rnd(struct kvm_vcpu *vcpu, int size) { DECLARE_BITMAP(bits, TRNG_MAX_BITS64); u32 num_bits = smccc_get_arg1(vcpu); int i; if (num_bits > 3 * size) { smccc_set_retval(vcpu, TRNG_INVALID_PARAMETER, 0, 0, 0); return 1; } /* get as many bits as we need to fulfil the request */ for (i = 0; i < DIV_ROUND_UP(num_bits, BITS_PER_LONG); i++) bits[i] = get_random_long(); bitmap_clear(bits, num_bits, TRNG_MAX_BITS64 - num_bits); if (size == 32) smccc_set_retval(vcpu, TRNG_SUCCESS, lower_32_bits(bits[1]), upper_32_bits(bits[0]), lower_32_bits(bits[0])); else smccc_set_retval(vcpu, TRNG_SUCCESS, bits[2], bits[1], bits[0]); memzero_explicit(bits, sizeof(bits)); return 1; } int kvm_trng_call(struct kvm_vcpu *vcpu) { const __le32 *u = (__le32 *)arm_smc_trng_uuid.b; u32 func_id = smccc_get_function(vcpu); unsigned long val = TRNG_NOT_SUPPORTED; int size = 64; switch (func_id) { case ARM_SMCCC_TRNG_VERSION: val = ARM_SMCCC_TRNG_VERSION_1_0; break; case ARM_SMCCC_TRNG_FEATURES: switch (smccc_get_arg1(vcpu)) { case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: val = TRNG_SUCCESS; } break; case ARM_SMCCC_TRNG_GET_UUID: smccc_set_retval(vcpu, le32_to_cpu(u[0]), le32_to_cpu(u[1]), le32_to_cpu(u[2]), le32_to_cpu(u[3])); return 1; case ARM_SMCCC_TRNG_RND32: size = 32; fallthrough; case ARM_SMCCC_TRNG_RND64: return kvm_trng_do_rnd(vcpu, size); } smccc_set_retval(vcpu, val, 0, 0, 0); return 1; } |
| 4 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 | // 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 |