| 4173 4173 3 120 120 120 120 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "ipoib.h" #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> /* For ARPHRD_xxx */ #include <linux/ip.h> #include <linux/in.h> #include <linux/jhash.h> #include <net/arp.h> #include <net/addrconf.h> #include <net/netdev_lock.h> #include <net/pkt_sched.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("IP-over-InfiniBand net driver"); MODULE_LICENSE("Dual BSD/GPL"); int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE; int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE; module_param_named(send_queue_size, ipoib_sendq_size, int, 0444); MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue"); module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444); MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue"); #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG int ipoib_debug_level; module_param_named(debug_level, ipoib_debug_level, int, 0644); MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); #endif struct ipoib_path_iter { struct net_device *dev; struct ipoib_path path; }; static const u8 ipv4_bcast_addr[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0x12, 0x40, 0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff }; struct workqueue_struct *ipoib_workqueue; struct ib_sa_client ipoib_sa_client; static int ipoib_add_one(struct ib_device *device); static void ipoib_remove_one(struct ib_device *device, void *client_data); static void ipoib_neigh_reclaim(struct rcu_head *rp); static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); static int ipoib_set_mac(struct net_device *dev, void *addr); static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static struct ib_client ipoib_client = { .name = "ipoib", .add = ipoib_add_one, .remove = ipoib_remove_one, .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static int ipoib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *ni = ptr; struct net_device *dev = ni->dev; if (dev->netdev_ops->ndo_open != ipoib_open) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: ipoib_create_debug_files(dev); break; case NETDEV_CHANGENAME: ipoib_delete_debug_files(dev); ipoib_create_debug_files(dev); break; case NETDEV_UNREGISTER: ipoib_delete_debug_files(dev); break; } return NOTIFY_DONE; } #endif struct ipoib_ifupdown_work { struct work_struct work; struct net_device *dev; netdevice_tracker dev_tracker; bool up; }; static void ipoib_ifupdown_task(struct work_struct *work) { struct ipoib_ifupdown_work *pwork = container_of(work, struct ipoib_ifupdown_work, work); struct net_device *dev = pwork->dev; unsigned int flags; rtnl_lock(); flags = dev->flags; if (pwork->up) flags |= IFF_UP; else flags &= ~IFF_UP; if (dev->flags != flags) dev_change_flags(dev, flags, NULL); rtnl_unlock(); netdev_put(dev, &pwork->dev_tracker); kfree(pwork); } static void ipoib_schedule_ifupdown_task(struct net_device *dev, bool up) { struct ipoib_ifupdown_work *work; if ((up && (dev->flags & IFF_UP)) || (!up && !(dev->flags & IFF_UP))) return; work = kmalloc(sizeof(*work), GFP_KERNEL); if (!work) return; work->dev = dev; netdev_hold(dev, &work->dev_tracker, GFP_KERNEL); work->up = up; INIT_WORK(&work->work, ipoib_ifupdown_task); queue_work(ipoib_workqueue, &work->work); } int ipoib_open(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "bringing up interface\n"); netif_carrier_off(dev); set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; } ipoib_ib_dev_up(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring up any child interfaces too */ netdev_lock_ops_to_full(dev); list_for_each_entry(cpriv, &priv->child_intfs, list) ipoib_schedule_ifupdown_task(cpriv->dev, true); netdev_unlock_full_to_ops(dev); } else if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &ppriv->flags)) ipoib_dbg(priv, "parent device %s is not up, so child device may be not functioning.\n", ppriv->dev->name); } netif_start_queue(dev); return 0; err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); return -EINVAL; } static int ipoib_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "stopping interface\n"); clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); netif_stop_queue(dev); ipoib_ib_dev_down(dev); ipoib_ib_dev_stop(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring down any child interfaces too */ netdev_lock_ops_to_full(dev); list_for_each_entry(cpriv, &priv->child_intfs, list) ipoib_schedule_ifupdown_task(cpriv->dev, false); netdev_unlock_full_to_ops(dev); } return 0; } static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); return features; } static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = 0; /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { if (new_mtu > ipoib_cm_max_mtu(dev)) return -EINVAL; if (new_mtu > priv->mcast_mtu) ipoib_warn(priv, "mtu > %d will cause multicast packet drops.\n", priv->mcast_mtu); WRITE_ONCE(dev->mtu, new_mtu); return 0; } if (new_mtu < (ETH_MIN_MTU + IPOIB_ENCAP_LEN) || new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu)) return -EINVAL; priv->admin_mtu = new_mtu; if (priv->mcast_mtu < priv->admin_mtu) ipoib_dbg(priv, "MTU must be smaller than the underlying " "link layer MTU - 4 (%u)\n", priv->mcast_mtu); new_mtu = min(priv->mcast_mtu, priv->admin_mtu); if (priv->rn_ops->ndo_change_mtu) { bool carrier_status = netif_carrier_ok(dev); netif_carrier_off(dev); /* notify lower level on the real mtu */ ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu); if (carrier_status) netif_carrier_on(dev); } else { WRITE_ONCE(dev->mtu, new_mtu); } return ret; } static void ipoib_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (priv->rn_ops->ndo_get_stats64) priv->rn_ops->ndo_get_stats64(dev, stats); else netdev_stats_to_stats64(stats, &dev->stats); } /* Called with an RCU read lock taken */ static bool ipoib_is_dev_match_addr_rcu(const struct sockaddr *addr, struct net_device *dev) { struct net *net = dev_net(dev); struct in_device *in_dev; struct sockaddr_in *addr_in = (struct sockaddr_in *)addr; struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr; __be32 ret_addr; switch (addr->sa_family) { case AF_INET: in_dev = in_dev_get(dev); if (!in_dev) return false; ret_addr = inet_confirm_addr(net, in_dev, 0, addr_in->sin_addr.s_addr, RT_SCOPE_HOST); in_dev_put(in_dev); if (ret_addr) return true; break; case AF_INET6: if (IS_ENABLED(CONFIG_IPV6) && ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1)) return true; break; } return false; } /* * Find the master net_device on top of the given net_device. * @dev: base IPoIB net_device * * Returns the master net_device with a reference held, or the same net_device * if no master exists. */ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev) { struct net_device *master; rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); dev_hold(master); rcu_read_unlock(); if (master) return master; dev_hold(dev); return dev; } struct ipoib_walk_data { const struct sockaddr *addr; struct net_device *result; }; static int ipoib_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { dev_hold(upper); data->result = upper; ret = 1; } return ret; } /** * ipoib_get_net_dev_match_addr - Find a net_device matching * the given address, which is an upper device of the given net_device. * * @addr: IP address to look for. * @dev: base IPoIB net_device * * If found, returns the net_device with a reference held. Otherwise return * NULL. */ static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); data.result = dev; goto out; } netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; } /* returns the number of IPoIB netdevs on top a given ipoib device matching a * pkey_index and address, if one exists. * * @found_net_dev: contains a matching net_device if the return value >= 1, * with a reference held. */ static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv, const union ib_gid *gid, u16 pkey_index, const struct sockaddr *addr, int nesting, struct net_device **found_net_dev) { struct ipoib_dev_priv *child_priv; struct net_device *net_dev = NULL; int matches = 0; if (priv->pkey_index == pkey_index && (!gid || !memcmp(gid, &priv->local_gid, sizeof(*gid)))) { if (!addr) { net_dev = ipoib_get_master_net_dev(priv->dev); } else { /* Verify the net_device matches the IP address, as * IPoIB child devices currently share a GID. */ net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev); } if (net_dev) { if (!*found_net_dev) *found_net_dev = net_dev; else dev_put(net_dev); ++matches; } } if (test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return matches; /* Check child interfaces */ netdev_lock(priv->dev); list_for_each_entry(child_priv, &priv->child_intfs, list) { matches += ipoib_match_gid_pkey_addr(child_priv, gid, pkey_index, addr, nesting + 1, found_net_dev); if (matches > 1) break; } netdev_unlock(priv->dev); return matches; } /* Returns the number of matching net_devs found (between 0 and 2). Also * return the matching net_device in the @net_dev parameter, holding a * reference to the net_device, if the number of matches >= 1 */ static int __ipoib_get_net_dev_by_params(struct list_head *dev_list, u32 port, u16 pkey_index, const union ib_gid *gid, const struct sockaddr *addr, struct net_device **net_dev) { struct ipoib_dev_priv *priv; int matches = 0; *net_dev = NULL; list_for_each_entry(priv, dev_list, list) { if (priv->port != port) continue; matches += ipoib_match_gid_pkey_addr(priv, gid, pkey_index, addr, 0, net_dev); if (matches > 1) break; } return matches; } static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data) { struct net_device *net_dev; struct list_head *dev_list = client_data; u16 pkey_index; int matches; int ret; if (!rdma_protocol_ib(dev, port)) return NULL; ret = ib_find_cached_pkey(dev, port, pkey, &pkey_index); if (ret) return NULL; /* See if we can find a unique device matching the L2 parameters */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, NULL, &net_dev); switch (matches) { case 0: return NULL; case 1: return net_dev; } dev_put(net_dev); /* Couldn't find a unique device with L2 parameters only. Use L3 * address to uniquely match the net device */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, addr, &net_dev); switch (matches) { case 0: return NULL; default: dev_warn_ratelimited(&dev->dev, "duplicate IP address detected\n"); fallthrough; case 1: return net_dev; } } int ipoib_set_mode(struct net_device *dev, const char *buf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "connected\n")) || (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "datagram\n"))) { return 0; } /* flush paths if we switch modes so that connections are restarted */ if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) { set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); ipoib_warn(priv, "enabling connected mode " "will cause multicast packet drops\n"); netdev_lock_ops(dev); netdev_update_features(dev); netif_set_mtu(dev, ipoib_cm_max_mtu(dev)); netif_set_real_num_tx_queues(dev, 1); netdev_unlock_ops(dev); rtnl_unlock(); priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); netdev_lock_ops(dev); netdev_update_features(dev); netif_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); netif_set_real_num_tx_queues(dev, dev->num_tx_queues); netdev_unlock_ops(dev); rtnl_unlock(); ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; } struct ipoib_path *__path_find(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->path_tree.rb_node; struct ipoib_path *path; int ret; while (n) { path = rb_entry(n, struct ipoib_path, rb_node); ret = memcmp(gid, path->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = n->rb_left; else if (ret > 0) n = n->rb_right; else return path; } return NULL; } static int __path_add(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->path_tree.rb_node; struct rb_node *pn = NULL; struct ipoib_path *tpath; int ret; while (*n) { pn = *n; tpath = rb_entry(pn, struct ipoib_path, rb_node); ret = memcmp(path->pathrec.dgid.raw, tpath->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = &pn->rb_left; else if (ret > 0) n = &pn->rb_right; else return -EEXIST; } rb_link_node(&path->rb_node, pn, n); rb_insert_color(&path->rb_node, &priv->path_tree); list_add_tail(&path->list, &priv->path_list); return 0; } static void path_free(struct net_device *dev, struct ipoib_path *path) { struct sk_buff *skb; while ((skb = __skb_dequeue(&path->queue))) dev_kfree_skb_irq(skb); ipoib_dbg(ipoib_priv(dev), "%s\n", __func__); /* remove all neigh connected to this path */ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (path->ah) ipoib_put_ah(path->ah); kfree(path); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG struct ipoib_path_iter *ipoib_path_iter_init(struct net_device *dev) { struct ipoib_path_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return NULL; iter->dev = dev; memset(iter->path.pathrec.dgid.raw, 0, 16); if (ipoib_path_iter_next(iter)) { kfree(iter); return NULL; } return iter; } int ipoib_path_iter_next(struct ipoib_path_iter *iter) { struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_path *path; int ret = 1; spin_lock_irq(&priv->lock); n = rb_first(&priv->path_tree); while (n) { path = rb_entry(n, struct ipoib_path, rb_node); if (memcmp(iter->path.pathrec.dgid.raw, path->pathrec.dgid.raw, sizeof (union ib_gid)) < 0) { iter->path = *path; ret = 0; break; } n = rb_next(n); } spin_unlock_irq(&priv->lock); return ret; } void ipoib_path_iter_read(struct ipoib_path_iter *iter, struct ipoib_path *path) { *path = iter->path; } #endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */ void ipoib_mark_paths_invalid(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; spin_lock_irq(&priv->lock); list_for_each_entry_safe(path, tp, &priv->path_list, list) { ipoib_dbg(priv, "mark path LID 0x%08x GID %pI6 invalid\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec)), path->pathrec.dgid.raw); if (path->ah) path->ah->valid = 0; } spin_unlock_irq(&priv->lock); } static void push_pseudo_header(struct sk_buff *skb, const char *daddr) { struct ipoib_pseudo_header *phdr; phdr = skb_push(skb, sizeof(*phdr)); memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); } void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; LIST_HEAD(remove_list); unsigned long flags; netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->path_list, &remove_list); list_for_each_entry(path, &remove_list, list) rb_erase(&path->rb_node, &priv->path_tree); list_for_each_entry_safe(path, tp, &remove_list, list) { if (path->query) ib_sa_cancel_query(path->query_id, path->query); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); wait_for_completion(&path->done); path_free(dev, path); netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); } spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); } static void path_rec_completion(int status, struct sa_path_rec *pathrec, unsigned int num_prs, void *path_ptr) { struct ipoib_path *path = path_ptr; struct net_device *dev = path->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah = NULL; struct ipoib_ah *old_ah = NULL; struct ipoib_neigh *neigh, *tn; struct sk_buff_head skqueue; struct sk_buff *skb; unsigned long flags; if (!status) ipoib_dbg(priv, "PathRec LID 0x%04x for GID %pI6\n", be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->dgid.raw); else ipoib_dbg(priv, "PathRec status %d for GID %pI6\n", status, path->pathrec.dgid.raw); skb_queue_head_init(&skqueue); if (!status) { struct rdma_ah_attr av; if (!ib_init_ah_attr_from_path(priv->ca, priv->port, pathrec, &av, NULL)) { ah = ipoib_create_ah(dev, priv->pd, &av); rdma_destroy_ah_attr(&av); } } spin_lock_irqsave(&priv->lock, flags); if (!IS_ERR_OR_NULL(ah)) { /* * pathrec.dgid is used as the database key from the LLADDR, * it must remain unchanged even if the SA returns a different * GID to use in the AH. */ if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid))) { ipoib_dbg( priv, "%s got PathRec for gid %pI6 while asked for %pI6\n", dev->name, pathrec->dgid.raw, path->pathrec.dgid.raw); memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid)); } path->pathrec = *pathrec; old_ah = path->ah; path->ah = ah; ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n", ah, be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->sl); while ((skb = __skb_dequeue(&path->queue))) __skb_queue_tail(&skqueue, skb); list_for_each_entry_safe(neigh, tn, &path->neigh_list, list) { if (neigh->ah) { WARN_ON(neigh->ah != old_ah); /* * Dropping the ah reference inside * priv->lock is safe here, because we * will hold one more reference from * the original value of path->ah (ie * old_ah). */ ipoib_put_ah(neigh->ah); } kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); continue; } } while ((skb = __skb_dequeue(&neigh->queue))) __skb_queue_tail(&skqueue, skb); } path->ah->valid = 1; } path->query = NULL; complete(&path->done); spin_unlock_irqrestore(&priv->lock, flags); if (IS_ERR_OR_NULL(ah)) ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (old_ah) ipoib_put_ah(old_ah); while ((skb = __skb_dequeue(&skqueue))) { int ret; skb->dev = dev; ret = dev_queue_xmit(skb); if (ret) ipoib_warn(priv, "%s: dev_queue_xmit failed to re-queue packet, ret:%d\n", __func__, ret); } } static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path, void *gid) { path->dev = priv->dev; if (rdma_cap_opa_ah(priv->ca, priv->port)) path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; else path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid)); path->pathrec.sgid = priv->local_gid; path->pathrec.pkey = cpu_to_be16(priv->pkey); path->pathrec.numb_path = 1; path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; } static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; if (!priv->broadcast) return NULL; path = kzalloc(sizeof(*path), GFP_ATOMIC); if (!path) return NULL; skb_queue_head_init(&path->queue); INIT_LIST_HEAD(&path->neigh_list); init_path_rec(priv, path, gid); return path; } static int path_rec_start(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "Start path record lookup for %pI6\n", path->pathrec.dgid.raw); init_completion(&path->done); path->query_id = ib_sa_path_rec_get(&ipoib_sa_client, priv->ca, priv->port, &path->pathrec, IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_TRAFFIC_CLASS | IB_SA_PATH_REC_PKEY, 1000, GFP_ATOMIC, path_rec_completion, path, &path->query); if (path->query_id < 0) { ipoib_warn(priv, "ib_sa_path_rec_get failed: %d\n", path->query_id); path->query = NULL; complete(&path->done); return path->query_id; } return 0; } static void neigh_refresh_path(struct ipoib_neigh *neigh, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); path = __path_find(dev, daddr + 4); if (!path) goto out; if (!path->query) path_rec_start(dev, path); out: spin_unlock_irqrestore(&priv->lock, flags); } static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; struct ipoib_neigh *neigh; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); if (!neigh) { spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NULL; } /* To avoid race condition, make sure that the * neigh will be added only once. */ if (unlikely(!list_empty(&neigh->list))) { spin_unlock_irqrestore(&priv->lock, flags); return neigh; } path = __path_find(dev, daddr + 4); if (!path) { path = path_rec_create(dev, daddr + 4); if (!path) goto err_path; __path_add(dev, path); } list_add_tail(&neigh->list, &path->neigh_list); if (path->ah && path->ah->valid) { kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); goto err_drop; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; } } else { spin_unlock_irqrestore(&priv->lock, flags); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); return NULL; } } else { neigh->ah = NULL; if (!path->query && path_rec_start(dev, path)) goto err_path; if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { goto err_drop; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; err_path: ipoib_neigh_free(neigh); err_drop: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); /* no broadcast means that all paths are (going to be) not valid */ if (!priv->broadcast) goto drop_and_unlock; path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->ah || !path->ah->valid) { if (!path) { path = path_rec_create(dev, phdr->hwaddr + 4); if (!path) goto drop_and_unlock; __path_add(dev, path); } else { /* * make sure there are no changes in the existing * path record */ init_path_rec(priv, path, phdr->hwaddr + 4); } if (!path->query && path_rec_start(dev, path)) { goto drop_and_unlock; } if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); goto unlock; } else { goto drop_and_unlock; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_dbg(priv, "Send unicast ARP to %08x\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec))); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(phdr->hwaddr)); return; drop_and_unlock: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); unlock: spin_unlock_irqrestore(&priv->lock, flags); } static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_neigh *neigh; struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; phdr = (struct ipoib_pseudo_header *) skb->data; skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && (header->proto != htons(ETH_P_ARP)) && (header->proto != htons(ETH_P_RARP)) && (header->proto != htons(ETH_P_TIPC))) { /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; phdr->hwaddr[9] = priv->pkey & 0xff; neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } /* unicast, arrange "switch" according to probability */ switch (header->proto) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { neigh = neigh_add_path(skb, phdr->hwaddr, dev); if (likely(!neigh)) return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } send_using_neigh: /* note we now hold a ref to neigh */ if (ipoib_cm_get(neigh)) { if (ipoib_cm_up(neigh)) { ipoib_cm_send(dev, skb, ipoib_cm_get(neigh)); goto unref; } } else if (neigh->ah && neigh->ah->valid) { neigh->ah->last_send = rn->send(dev, skb, neigh->ah->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } else if (neigh->ah) { neigh_refresh_path(neigh, phdr->hwaddr, dev); } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } unref: ipoib_neigh_put(neigh); return NETDEV_TX_OK; } static void ipoib_timeout(struct net_device *dev, unsigned int txqueue) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); if (rn->tx_timeout) { rn->tx_timeout(dev, txqueue); return; } ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n", netif_queue_stopped(dev), priv->tx_head, priv->tx_tail, priv->global_tx_head, priv->global_tx_tail); schedule_work(&priv->tx_timeout_work); } void ipoib_ib_tx_timeout_work(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, tx_timeout_work); int err; rtnl_lock(); netdev_lock_ops(priv->dev); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) goto unlock; ipoib_stop(priv->dev); err = ipoib_open(priv->dev); if (err) { ipoib_warn(priv, "ipoib_open failed recovering from a tx_timeout, err(%d).\n", err); goto unlock; } netif_tx_wake_all_queues(priv->dev); unlock: netdev_unlock_ops(priv->dev); rtnl_unlock(); } static int ipoib_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ipoib_header *header; header = skb_push(skb, sizeof(*header)); header->proto = htons(type); header->reserved = 0; /* * we don't rely on dst_entry structure, always stuff the * destination address into skb hard header so we can figure out where * to send the packet later. */ push_pseudo_header(skb, daddr); return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set"); return; } queue_work(priv->wq, &priv->restart_task); } static int ipoib_get_iflink(const struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return READ_ONCE(dev->ifindex); /* child/vlan interface */ return READ_ONCE(priv->parent->ifindex); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) { /* * Use only the address parts that contributes to spreading * The subnet prefix is not used as one can not connect to * same remote port (GUID) using the same remote QPN via two * different subnets. */ /* qpn octets[1:4) & port GUID octets[12:20) */ u32 *d32 = (u32 *) daddr; u32 hv; hv = jhash_3words(d32[3], d32[4], IPOIB_QPN_MASK & d32[0], 0); return hv & htbl->mask; } struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh = NULL; u32 hash_val; rcu_read_lock_bh(); htbl = rcu_dereference_bh(ntbl->htbl); if (!htbl) goto out_unlock; hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_bh(htbl->buckets[hash_val]); neigh != NULL; neigh = rcu_dereference_bh(neigh->hnext)) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; goto out_unlock; } if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) neigh->alive = jiffies; goto out_unlock; } } out_unlock: rcu_read_unlock_bh(); return neigh; } static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long neigh_obsolete; unsigned long dt; unsigned long flags; int i; LIST_HEAD(remove_list); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; /* neigh is obsolete if it was idle for two GC periods */ dt = 2 * arp_tbl.gc_interval; neigh_obsolete = jiffies - dt; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { ipoib_check_and_add_mcast_sendonly(priv, neigh->daddr + 4, &remove_list); rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); ipoib_mcast_remove_list(&remove_list); } static void ipoib_reap_neigh(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, neigh_reap_task.work); __ipoib_reap_neigh(priv); queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); } static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr, struct net_device *dev) { struct ipoib_neigh *neigh; neigh = kzalloc(sizeof(*neigh), GFP_ATOMIC); if (!neigh) return NULL; neigh->dev = dev; memcpy(&neigh->daddr, daddr, sizeof(neigh->daddr)); skb_queue_head_init(&neigh->queue); INIT_LIST_HEAD(&neigh->list); ipoib_cm_set(neigh, NULL); /* one ref on behalf of the caller */ refcount_set(&neigh->refcnt, 1); return neigh; } struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) { neigh = NULL; goto out_unlock; } /* need to add a new neigh, but maybe some other thread succeeded? * recalc hash, maybe hash resize took place so we do a search */ hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock)); neigh != NULL; neigh = rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; break; } neigh->alive = jiffies; goto out_unlock; } } neigh = ipoib_neigh_ctor(daddr, dev); if (!neigh) goto out_unlock; /* one ref on behalf of the hash table */ refcount_inc(&neigh->refcnt); neigh->alive = jiffies; /* put in hash */ rcu_assign_pointer(neigh->hnext, rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock))); rcu_assign_pointer(htbl->buckets[hash_val], neigh); atomic_inc(&ntbl->entries); out_unlock: return neigh; } void ipoib_neigh_dtor(struct ipoib_neigh *neigh) { /* neigh reference count was dropprd to zero */ struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; if (neigh->ah) ipoib_put_ah(neigh->ah); while ((skb = __skb_dequeue(&neigh->queue))) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } if (ipoib_cm_get(neigh)) ipoib_cm_destroy_tx(ipoib_cm_get(neigh)); ipoib_dbg(ipoib_priv(dev), "neigh free for %06x %pI6\n", IPOIB_QPN(neigh->daddr), neigh->daddr + 4); kfree(neigh); if (atomic_dec_and_test(&priv->ntbl.entries)) { if (test_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags)) complete(&priv->ntbl.flushed); } } static void ipoib_neigh_reclaim(struct rcu_head *rp) { /* Called as a result of removal from hash table */ struct ipoib_neigh *neigh = container_of(rp, struct ipoib_neigh, rcu); /* note TX context may hold another ref */ ipoib_neigh_put(neigh); } void ipoib_neigh_free(struct ipoib_neigh *neigh) { struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **np; struct ipoib_neigh *n; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) return; hash_val = ipoib_addr_hash(htbl, neigh->daddr); np = &htbl->buckets[hash_val]; for (n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock)); n != NULL; n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) { if (n == neigh) { /* found */ rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); return; } else { np = &n->hnext; } } } static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **buckets; u32 size; clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); ntbl->htbl = NULL; htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); if (!htbl) return -ENOMEM; size = roundup_pow_of_two(arp_tbl.gc_thresh3); buckets = kvcalloc(size, sizeof(*buckets), GFP_KERNEL); if (!buckets) { kfree(htbl); return -ENOMEM; } htbl->size = size; htbl->mask = (size - 1); htbl->buckets = buckets; RCU_INIT_POINTER(ntbl->htbl, htbl); htbl->ntbl = ntbl; atomic_set(&ntbl->entries, 0); /* start garbage collection */ queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct ipoib_neigh_hash *htbl = container_of(head, struct ipoib_neigh_hash, rcu); struct ipoib_neigh __rcu **buckets = htbl->buckets; struct ipoib_neigh_table *ntbl = htbl->ntbl; kvfree(buckets); kfree(htbl); complete(&ntbl->deleted); } void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i; /* remove all neigh connected to a given path or mcast */ spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* delete neighs belong to this parent */ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; wait_flushed = atomic_read(&priv->ntbl.entries); if (!wait_flushed) goto free_htbl; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } } free_htbl: rcu_assign_pointer(ntbl->htbl, NULL); call_rcu(&htbl->rcu, neigh_hash_free_rcu); out_unlock: spin_unlock_irqrestore(&priv->lock, flags); if (wait_flushed) wait_for_completion(&priv->ntbl.flushed); } static void ipoib_neigh_hash_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "%s\n", __func__); init_completion(&priv->ntbl.deleted); cancel_delayed_work_sync(&priv->neigh_reap_task); ipoib_flush_neighs(priv); wait_for_completion(&priv->ntbl.deleted); } static void ipoib_napi_add(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_add_weight(dev, &priv->recv_napi, ipoib_rx_poll, IPOIB_NUM_WC); netif_napi_add_weight(dev, &priv->send_napi, ipoib_tx_poll, MAX_SEND_CQE); } static void ipoib_napi_del(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_del(&priv->recv_napi); netif_napi_del(&priv->send_napi); } static void ipoib_dev_uninit_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_transport_dev_cleanup(dev); ipoib_napi_del(dev); ipoib_cm_dev_cleanup(dev); kfree(priv->rx_ring); vfree(priv->tx_ring); priv->rx_ring = NULL; priv->tx_ring = NULL; } static int ipoib_dev_init_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); u8 addr_mod[3]; ipoib_napi_add(dev); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kcalloc(ipoib_recvq_size, sizeof(*priv->rx_ring), GFP_KERNEL); if (!priv->rx_ring) goto out; priv->tx_ring = vzalloc(array_size(ipoib_sendq_size, sizeof(*priv->tx_ring))); if (!priv->tx_ring) { pr_warn("%s: failed to allocate TX ring (%d entries)\n", priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } /* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */ if (ipoib_transport_dev_init(dev, priv->ca)) { pr_warn("%s: ipoib_transport_dev_init failed\n", priv->ca->name); goto out_tx_ring_cleanup; } /* after qp created set dev address */ addr_mod[0] = (priv->qp->qp_num >> 16) & 0xff; addr_mod[1] = (priv->qp->qp_num >> 8) & 0xff; addr_mod[2] = (priv->qp->qp_num) & 0xff; dev_addr_mod(priv->dev, 1, addr_mod, sizeof(addr_mod)); return 0; out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); out: ipoib_napi_del(dev); return -ENOMEM; } static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!priv->rn_ops->ndo_eth_ioctl) return -EOPNOTSUPP; return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } static int ipoib_dev_init(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = -ENOMEM; priv->qp = NULL; /* * the various IPoIB tasks assume they will never race against * themselves, so always use a single thread workqueue */ priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); if (!priv->wq) { pr_warn("%s: failed to allocate device WQ\n", dev->name); goto out; } /* create pd, which used both for control and datapath*/ priv->pd = ib_alloc_pd(priv->ca, 0); if (IS_ERR(priv->pd)) { pr_warn("%s: failed to allocate PD\n", priv->ca->name); goto clean_wq; } ret = priv->rn_ops->ndo_init(dev); if (ret) { pr_warn("%s failed to init HW resource\n", dev->name); goto out_free_pd; } ret = ipoib_neigh_hash_init(priv); if (ret) { pr_warn("%s failed to init neigh hash\n", dev->name); goto out_dev_uninit; } if (dev->flags & IFF_UP) { if (ipoib_ib_dev_open(dev)) { pr_warn("%s failed to open device\n", dev->name); ret = -ENODEV; goto out_hash_uninit; } } return 0; out_hash_uninit: ipoib_neigh_hash_uninit(dev); out_dev_uninit: ipoib_ib_dev_cleanup(dev); out_free_pd: if (priv->pd) { ib_dealloc_pd(priv->pd); priv->pd = NULL; } clean_wq: if (priv->wq) { destroy_workqueue(priv->wq); priv->wq = NULL; } out: return ret; } /* * This must be called before doing an unregister_netdev on a parent device to * shutdown the IB event handler. */ static void ipoib_parent_unregister_pre(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); /* * ipoib_set_mac checks netif_running before pushing work, clearing * running ensures the it will not add more work. */ rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL); rtnl_unlock(); /* ipoib_event() cannot be running once this returns */ ib_unregister_event_handler(&priv->event_handler); /* * Work on the queue grabs the rtnl lock, so this cannot be done while * also holding it. */ flush_workqueue(ipoib_workqueue); } static void ipoib_set_dev_features(struct ipoib_dev_priv *priv) { priv->hca_caps = priv->ca->attrs.device_cap_flags; priv->kernel_caps = priv->ca->attrs.kernel_cap_flags; if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) { priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM; if (priv->kernel_caps & IBK_UD_TSO) priv->dev->hw_features |= NETIF_F_TSO; priv->dev->features |= priv->dev->hw_features; } } static int ipoib_parent_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ib_port_attr attr; int result; result = ib_query_port(priv->ca, priv->port, &attr); if (result) { pr_warn("%s: ib_query_port %d failed\n", priv->ca->name, priv->port); return result; } priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr); result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey); if (result) { pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } result = rdma_query_gid(priv->ca, priv->port, 0, &priv->local_gid); if (result) { pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } dev_addr_mod(priv->dev, 4, priv->local_gid.raw, sizeof(union ib_gid)); SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent); priv->dev->dev_port = priv->port - 1; /* Let's set this one too for backwards compatibility. */ priv->dev->dev_id = priv->port - 1; return 0; } static void ipoib_child_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); priv->max_ib_mtu = ppriv->max_ib_mtu; set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags); if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN)) memcpy(&priv->local_gid, priv->dev->dev_addr + 4, sizeof(priv->local_gid)); else { __dev_addr_set(priv->dev, ppriv->dev->dev_addr, INFINIBAND_ALEN); memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); } } static int ipoib_ndo_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); int rc; struct rdma_netdev *rn = netdev_priv(ndev); if (priv->parent) { ipoib_child_init(ndev); } else { rc = ipoib_parent_init(ndev); if (rc) return rc; } /* MTU will be reset when mcast join happens */ ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = ndev->mtu; rn->mtu = priv->mcast_mtu; ndev->max_mtu = IPOIB_CM_MTU; ndev->neigh_priv_len = sizeof(struct ipoib_neigh); /* * Set the full membership bit, so that we join the right * broadcast group, etc. */ priv->pkey |= 0x8000; ndev->broadcast[8] = priv->pkey >> 8; ndev->broadcast[9] = priv->pkey & 0xff; set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); ipoib_set_dev_features(priv); rc = ipoib_dev_init(ndev); if (rc) { pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n", priv->ca->name, priv->dev->name, priv->port, rc); return rc; } if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); dev_hold(priv->parent); netdev_lock(priv->parent); list_add_tail(&priv->list, &ppriv->child_intfs); netdev_unlock(priv->parent); } return 0; } static void ipoib_ndo_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* * ipoib_remove_one guarantees the children are removed before the * parent, and that is the only place where a parent can be removed. */ WARN_ON(!list_empty(&priv->child_intfs)); if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); netdev_lock(ppriv->dev); list_del(&priv->list); netdev_unlock(ppriv->dev); } ipoib_neigh_hash_uninit(dev); ipoib_ib_dev_cleanup(dev); /* no more works over the priv->wq */ if (priv->wq) { /* See ipoib_mcast_carrier_on_task() */ WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); destroy_workqueue(priv->wq); priv->wq = NULL; } dev_put(priv->parent); } static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); } static int ipoib_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int err; err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); if (err) return err; ivf->vf = vf; memcpy(ivf->mac, dev->dev_addr, dev->addr_len); return 0; } static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) return -EINVAL; return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type); } static int ipoib_get_vf_guid(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid); } static int ipoib_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); } static const struct header_ops ipoib_header_ops = { .create = ipoib_hard_header, }; static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_set_vf_link_state = ipoib_set_vf_link_state, .ndo_get_vf_config = ipoib_get_vf_config, .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_get_vf_guid = ipoib_get_vf_guid, .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_default_pf = { .ndo_init = ipoib_dev_init_default, .ndo_uninit = ipoib_dev_uninit_default, .ndo_open = ipoib_ib_dev_open_default, .ndo_stop = ipoib_ib_dev_stop_default, }; void ipoib_setup_common(struct net_device *dev) { dev->header_ops = &ipoib_header_ops; dev->netdev_ops = &ipoib_netdev_default_pf; ipoib_set_ethtool_ops(dev); dev->watchdog_timeo = 10 * HZ; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->features = (NETIF_F_VLAN_CHALLENGED | NETIF_F_HIGHDMA); netif_keep_dst(dev); memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); /* * unregister_netdev always frees the netdev, we use this mode * consistently to unify all the various unregister paths, including * those connected to rtnl_link_ops which require it. */ dev->needs_free_netdev = true; } static void ipoib_build_priv(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); priv->dev = dev; spin_lock_init(&priv->lock); mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); INIT_LIST_HEAD(&priv->dead_ahs); INIT_LIST_HEAD(&priv->multicast_list); INIT_DELAYED_WORK(&priv->mcast_task, ipoib_mcast_join_task); INIT_WORK(&priv->carrier_on_task, ipoib_mcast_carrier_on_task); INIT_WORK(&priv->reschedule_napi_work, ipoib_napi_schedule_work); INIT_WORK(&priv->flush_light, ipoib_ib_dev_flush_light); INIT_WORK(&priv->flush_normal, ipoib_ib_dev_flush_normal); INIT_WORK(&priv->flush_heavy, ipoib_ib_dev_flush_heavy); INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task); INIT_WORK(&priv->tx_timeout_work, ipoib_ib_tx_timeout_work); INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah); INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh); } static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP) return dev; dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!dev) return ERR_PTR(-ENOMEM); return dev; } int ipoib_intf_init(struct ib_device *hca, u32 port, const char *name, struct net_device *dev) { struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_dev_priv *priv; int rc; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->ca = hca; priv->port = port; rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common, dev); if (rc) { if (rc != -EOPNOTSUPP) goto out; rn->send = ipoib_send; rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; rc = netif_set_real_num_tx_queues(dev, 1); if (rc) goto out; rc = netif_set_real_num_rx_queues(dev, 1); if (rc) goto out; } priv->rn_ops = dev->netdev_ops; if (hca->attrs.kernel_cap_flags & IBK_VIRTUAL_FUNCTION) dev->netdev_ops = &ipoib_netdev_ops_vf; else dev->netdev_ops = &ipoib_netdev_ops_pf; rn->clnt_priv = priv; /* * Only the child register_netdev flows can handle priv_destructor * being set, so we force it to NULL here and handle manually until it * is safe to turn on. */ priv->next_priv_destructor = dev->priv_destructor; dev->priv_destructor = NULL; ipoib_build_priv(dev); return 0; out: kfree(priv); return rc; } struct net_device *ipoib_intf_alloc(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; int rc; dev = ipoib_alloc_netdev(hca, port, name); if (IS_ERR(dev)) return dev; rc = ipoib_intf_init(hca, port, name, dev); if (rc) { free_netdev(dev); return ERR_PTR(rc); } /* * Upon success the caller must ensure ipoib_intf_free is called or * register_netdevice succeed'd and priv_destructor is set to * ipoib_intf_free. */ return dev; } void ipoib_intf_free(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); dev->priv_destructor = priv->next_priv_destructor; if (dev->priv_destructor) dev->priv_destructor(dev); /* * There are some error flows around register_netdev failing that may * attempt to call priv_destructor twice, prevent that from happening. */ dev->priv_destructor = NULL; /* unregister/destroy is very complicated. Make bugs more obvious. */ rn->clnt_priv = NULL; kfree(priv); } static ssize_t pkey_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "0x%04x\n", priv->pkey); } static DEVICE_ATTR_RO(pkey); static ssize_t umcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags)); } void ipoib_set_umcast(struct net_device *ndev, int umcast_val) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); if (umcast_val > 0) { set_bit(IPOIB_FLAG_UMCAST, &priv->flags); ipoib_warn(priv, "ignoring multicast groups joined directly " "by userspace\n"); } else clear_bit(IPOIB_FLAG_UMCAST, &priv->flags); } static ssize_t umcast_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long umcast_val = simple_strtoul(buf, NULL, 0); ipoib_set_umcast(to_net_dev(dev), umcast_val); return count; } static DEVICE_ATTR_RW(umcast); int ipoib_add_umcast_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_umcast); } static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) { struct ipoib_dev_priv *child_priv; struct net_device *netdev = priv->dev; netif_addr_lock_bh(netdev); memcpy(&priv->local_gid.global.interface_id, &gid->global.interface_id, sizeof(gid->global.interface_id)); dev_addr_mod(netdev, 4, (u8 *)&priv->local_gid, sizeof(priv->local_gid)); clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); netif_addr_unlock_bh(netdev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { netdev_lock_ops_to_full(priv->dev); list_for_each_entry(child_priv, &priv->child_intfs, list) set_base_guid(child_priv, gid); netdev_unlock_full_to_ops(priv->dev); } } static int ipoib_check_lladdr(struct net_device *dev, struct sockaddr_storage *ss) { union ib_gid *gid = (union ib_gid *)(ss->__data + 4); int ret = 0; netif_addr_lock_bh(dev); /* Make sure the QPN, reserved and subnet prefix match the current * lladdr, it also makes sure the lladdr is unicast. */ if (memcmp(dev->dev_addr, ss->__data, 4 + sizeof(gid->global.subnet_prefix)) || gid->global.interface_id == 0) ret = -EINVAL; netif_addr_unlock_bh(dev); return ret; } static int ipoib_set_mac(struct net_device *dev, void *addr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sockaddr_storage *ss = addr; int ret; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; ret = ipoib_check_lladdr(dev, ss); if (ret) return ret; set_base_guid(priv, (union ib_gid *)(ss->__data + 4)); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; netdev_lock_ops_to_full(dev); list_for_each_entry(cpriv, &priv->child_intfs, list) queue_work(ipoib_workqueue, &cpriv->flush_light); netdev_unlock_full_to_ops(dev); } queue_work(ipoib_workqueue, &priv->flush_light); return 0; } static ssize_t create_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000) return -EINVAL; ret = ipoib_vlan_add(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(create_child); static ssize_t delete_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey < 0 || pkey > 0xffff) return -EINVAL; ret = ipoib_vlan_delete(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(delete_child); int ipoib_add_pkey_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_pkey); } /* * We erroneously exposed the iface's port number in the dev_id * sysfs field long after dev_port was introduced for that purpose[1], * and we need to stop everyone from relying on that. * Let's overload the shower routine for the dev_id file here * to gently bring the issue up. * * [1] https://www.spinics.net/lists/netdev/msg272123.html */ static ssize_t dev_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); /* * ndev->dev_port will be equal to 0 in old kernel prior to commit * 9b8b2a323008 ("IB/ipoib: Use dev_port to expose network interface * port numbers") Zero was chosen as special case for user space * applications to fallback and query dev_id to check if it has * different value or not. * * Don't print warning in such scenario. * * https://github.com/systemd/systemd/blob/master/src/udev/udev-builtin-net_id.c#L358 */ if (ndev->dev_port && ndev->dev_id == ndev->dev_port) netdev_info_once(ndev, "\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n", current->comm); return sysfs_emit(buf, "%#x\n", ndev->dev_id); } static DEVICE_ATTR_RO(dev_id); static int ipoib_intercept_dev_id_attr(struct net_device *dev) { device_remove_file(&dev->dev, &dev_attr_dev_id); return device_create_file(&dev->dev, &dev_attr_dev_id); } static struct net_device *ipoib_add_port(const char *format, struct ib_device *hca, u32 port) { struct rtnl_link_ops *ops = ipoib_get_link_ops(); struct rdma_netdev_alloc_params params; struct ipoib_dev_priv *priv; struct net_device *ndev; int result; ndev = ipoib_intf_alloc(hca, port, format); if (IS_ERR(ndev)) { pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port, PTR_ERR(ndev)); return ndev; } priv = ipoib_priv(ndev); INIT_IB_EVENT_HANDLER(&priv->event_handler, priv->ca, ipoib_event); ib_register_event_handler(&priv->event_handler); /* call event handler to ensure pkey in sync */ ipoib_queue_work(priv, IPOIB_FLUSH_HEAVY); ndev->rtnl_link_ops = ipoib_get_link_ops(); result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", hca->name, port, result); ipoib_parent_unregister_pre(ndev); ipoib_intf_free(ndev); free_netdev(ndev); return ERR_PTR(result); } if (hca->ops.rdma_netdev_get_params) { int rc = hca->ops.rdma_netdev_get_params(hca, port, RDMA_NETDEV_IPOIB, ¶ms); if (!rc && ops->priv_size < params.sizeof_priv) ops->priv_size = params.sizeof_priv; } /* * We cannot set priv_destructor before register_netdev because we * need priv to be always valid during the error flow to execute * ipoib_parent_unregister_pre(). Instead handle it manually and only * enter priv_destructor mode once we are completely registered. */ ndev->priv_destructor = ipoib_intf_free; if (ipoib_intercept_dev_id_attr(ndev)) goto sysfs_failed; if (ipoib_cm_add_mode_attr(ndev)) goto sysfs_failed; if (ipoib_add_pkey_attr(ndev)) goto sysfs_failed; if (ipoib_add_umcast_attr(ndev)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_create_child)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_delete_child)) goto sysfs_failed; return ndev; sysfs_failed: ipoib_parent_unregister_pre(ndev); unregister_netdev(ndev); return ERR_PTR(-ENOMEM); } static int ipoib_add_one(struct ib_device *device) { struct list_head *dev_list; struct net_device *dev; struct ipoib_dev_priv *priv; unsigned int p; int count = 0; dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL); if (!dev_list) return -ENOMEM; INIT_LIST_HEAD(dev_list); rdma_for_each_port (device, p) { if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { priv = ipoib_priv(dev); list_add_tail(&priv->list, dev_list); count++; } } if (!count) { kfree(dev_list); return -EOPNOTSUPP; } ib_set_client_data(device, &ipoib_client, dev_list); return 0; } static void ipoib_remove_one(struct ib_device *device, void *client_data) { struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv; struct list_head *dev_list = client_data; list_for_each_entry_safe(priv, tmp, dev_list, list) { LIST_HEAD(head); ipoib_parent_unregister_pre(priv->dev); rtnl_lock(); netdev_lock(priv->dev); list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) unregister_netdevice_queue(cpriv->dev, &head); netdev_unlock(priv->dev); unregister_netdevice_queue(priv->dev, &head); unregister_netdevice_many(&head); rtnl_unlock(); } kfree(dev_list); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static struct notifier_block ipoib_netdev_notifier = { .notifier_call = ipoib_netdev_event, }; #endif static int __init ipoib_init_module(void) { int ret; ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size); ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE); ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* * When copying small received packets, we only copy from the * linear data part of the SKB, so we rely on this condition. */ BUILD_BUG_ON(IPOIB_CM_COPYBREAK > IPOIB_CM_HEAD_SIZE); ipoib_register_debugfs(); /* * We create a global workqueue here that is used for all flush * operations. However, if you attempt to flush a workqueue * from a task on that same workqueue, it deadlocks the system. * We want to be able to flush the tasks associated with a * specific net device, so we also create a workqueue for each * netdevice. We queue up the tasks for that device only on * its private workqueue, and we only queue up flush events * on our global flush workqueue. This avoids the deadlocks. */ ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush", 0); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; } ib_sa_register_client(&ipoib_sa_client); ret = ib_register_client(&ipoib_client); if (ret) goto err_sa; ret = ipoib_netlink_init(); if (ret) goto err_client; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG register_netdevice_notifier(&ipoib_netdev_notifier); #endif return 0; err_client: ib_unregister_client(&ipoib_client); err_sa: ib_sa_unregister_client(&ipoib_sa_client); destroy_workqueue(ipoib_workqueue); err_fs: ipoib_unregister_debugfs(); return ret; } static void __exit ipoib_cleanup_module(void) { #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG unregister_netdevice_notifier(&ipoib_netdev_notifier); #endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); ipoib_unregister_debugfs(); destroy_workqueue(ipoib_workqueue); } module_init(ipoib_init_module); module_exit(ipoib_cleanup_module); |
| 84 1318 1313 1311 172 93 1305 3 893 12 12 12 12 12 12 12 12 12 1318 934 361 31 1295 20 1313 1318 1316 1318 1 78 5 10 92 186 1177 1330 1327 157 178 30 18 129 129 19 129 30 161 1219 1220 628 175 447 15 3 13 626 629 630 625 627 627 629 467 181 182 182 182 182 196 182 14 81 82 82 81 82 82 69 37 92 55 105 105 77 40 104 105 105 182 181 90 92 3 89 37 87 8 82 53 77 8 53 53 57 8 68 105 50 317 27 245 94 696 695 692 695 3 254 184 58 288 145 1 1 61 22 76 9 7 35 522 27 636 15 653 608 122 613 122 122 617 637 49 566 17 216 499 636 633 5 611 276 60 608 544 77 471 214 78 21 20 18 5 17 55 55 55 55 55 50 6 433 217 8 93 93 91 2 642 644 435 217 214 582 63 397 13 90 360 412 560 3 554 555 93 34 372 523 102 399 164 9 260 288 553 558 400 165 557 558 420 28 118 28 319 551 509 138 242 2 242 155 110 109 296 6 46 275 28 52 4 45 3 47 48 48 19 29 29 11 21 27 2 21 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The Internet Protocol (IP) output module. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <Alan.Cox@linux.org> * Richard Underwood * Stefan Becker, <stefanb@yello.ping.de> * Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Hirokazu Takahashi, <taka@valinux.co.jp> * * See ip_input.c for original log * * Fixes: * Alan Cox : Missing nonblock feature in ip_build_xmit. * Mike Kilburn : htons() missing in ip_build_xmit. * Bradford Johnson: Fix faulty handling of some frames when * no route is found. * Alexander Demenshin: Missing sk/skb free in ip_queue_xmit * (in case if packet not accepted by * output firewall rules) * Mike McLagan : Routing by source * Alexey Kuznetsov: use new route cache * Andi Kleen: Fix broken PMTU recovery and remove * some redundant tests. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Andi Kleen : Replace ip_reply with ip_send_reply. * Andi Kleen : Split fast and slow ip_build_xmit path * for decreased register pressure on x86 * and more readability. * Marc Boucher : When call_out_firewall returns FW_QUEUE, * silently drop skb instead of failing with -EPERM. * Detlev Wengorz : Copy protocol for fragments. * Hirokazu Takahashi: HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi: sendfile() on UDP works now. */ #include <linux/uaccess.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/xfrm.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/gso.h> #include <net/inetpeer.h> #include <net/lwtunnel.h> #include <net/inet_dscp.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } EXPORT_SYMBOL(ip_send_check); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS); iph_set_totlen(iph, skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(const struct inet_sock *inet, const struct dst_entry *dst) { int ttl = READ_ONCE(inet->uc_ttl); if (ttl < 0) ttl = ip4_dst_hoplimit(dst); return ttl; } /* * Add an ip header to a skbuff and send it out. * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos) { const struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct iphdr *iph; /* Build the IP header. */ skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; /* Do not bother generating IPID for small packets (eg SYNACK) */ if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; /* TCP packets here are SYNACK with fat IPv4/TCP options. * Avoid using the hashed IP ident generator. */ if (sk->sk_protocol == IPPROTO_TCP) iph->id = (__force __be16)get_random_u16(); else __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; ip_options_build(skb, &opt->opt, daddr, rt); } skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); /* OUTOCTETS should be counted after fragment */ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ res = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return res; } rcu_read_unlock(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return PTR_ERR(neigh); } static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* common case: seglen is <= mtu */ if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. * * This can happen in several cases: * - Forwarding of a TCP GRO skb, when DF flag is not set. * - Forwarding of an skb that arrived on a virtualization interface * (virtio-net/vhost/tap) with TSO/GSO size set by other network * stack. * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an * interface with a smaller MTU. * - Arriving GRO skb (or GSO skb in a virtualized environment) that is * bridged to a NETIF_F_TSO tunnel stacked over an interface with an * insufficient MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; } return ret; } static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); } static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: return __ip_finish_output(net, sk, skb); case NET_XMIT_CN: return __ip_finish_output(net, sk, skb) ? : ret; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *new_rt; bool do_cn = false; int ret, err; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_CN: do_cn = true; fallthrough; case NET_XMIT_SUCCESS: break; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, * see ipv4_pktinfo_prepare(). */ new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); if (new_rt) { new_rt->rt_iif = 0; skb_dst_drop(skb); skb_dst_set(skb, &new_rt->dst); } err = dev_loopback_xmit(net, sk, skb); return (do_cn && err) ? ret : err; } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; /* * If the indicated interface is up and running, send the packet. */ skb->dev = dev; skb->protocol = htons(ETH_P_IP); /* * Multicasts are looped back for other local users */ if (rt->rt_flags&RTCF_MULTICAST) { if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped by ip_mr_input in any case. Note, that local frames are looped back to be delivered to local recipients. This check is duplicated in ip_mr_input at the moment. */ && ((rt->rt_flags & RTCF_LOCAL) || !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } /* Multicasts with ttl 0 must not go beyond the host */ if (ip_hdr(skb)->ttl == 0) { kfree_skb(skb); return 0; } } if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } EXPORT_SYMBOL(ip_output); /* * copy saddr and daddr, possibly using 64bit load/stores * Equivalent to : * iph->saddr = fl4->saddr; * iph->daddr = fl4->daddr; */ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); iph->saddr = fl4->saddr; iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; struct rtable *rt; struct iphdr *iph; int res; /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); if (rt) goto packet_routed; /* Make sure we can route this packet. */ rt = dst_rtable(__sk_dst_check(sk, 0)); if (!rt) { inet_sk_init_flowi4(inet, fl4); /* sctp_v4_xmit() uses its own DSCP value */ fl4->flowi4_tos = tos & INET_DSCP_MASK; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); } skb_dst_set_noref(skb, &rt->dst); packet_routed: if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); /* Transport layer set skb->h.foo itself. */ if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt); } ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; no_route: rcu_read_unlock(); IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_IP_OUTNOROUTES); return -EHOSTUNREACH; } EXPORT_SYMBOL(__ip_queue_xmit); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos)); } EXPORT_SYMBOL(ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); #if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); } static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } return ip_do_fragment(net, sk, skb, output); } void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter) { unsigned int first_len = skb_pagelen(skb); iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->iph = iph; iter->hlen = hlen; skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_init); void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; struct iphdr *iph = iter->iph; struct sk_buff *frag; frag = iter->frag; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iph, hlen); iter->iph = ip_hdr(frag); iph = iter->iph; iph->tot_len = htons(frag->len); ip_copy_metadata(frag, skb); iter->offset += skb->len - hlen; iph->frag_off = htons(iter->offset >> 3); if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; state->not_last_frag = iph->frag_off & htons(IP_MF); } EXPORT_SYMBOL(ip_frag_init); static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, bool first_frag) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE * on the initial skb, so that all the following fragments * will inherit fixed options. */ if (first_frag) ip_options_fragment(from); } struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) { unsigned int len = state->left; struct sk_buff *skb2; struct iphdr *iph; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) { len &= ~7; } /* Allocate buffer */ skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip_copy_metadata(skb2, skb); skb_reserve(skb2, state->ll_rs); skb_put(skb2, len + state->hlen); skb_reset_network_header(skb2); skb2->transport_header = skb2->network_header + state->hlen; /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(skb2, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) BUG(); state->left -= len; /* * Fill in the new header fields. */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); if (state->DF) iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the * last fragment then keep MF on each bit */ if (state->left > 0 || state->not_last_frag) iph->frag_off |= htons(IP_MF); state->ptr += len; state->offset += len; iph->tot_len = htons(len + state->hlen); ip_send_check(iph); return skb2; } EXPORT_SYMBOL(ip_frag_next); /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus * a block of the data of the original IP data part) that will yet fit in a * single device frame, and queue such a frame for sending. */ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; struct sk_buff *skb2; u8 tstamp_type = skb->tstamp_type; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; /* * Point into the IP datagram header. */ iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. */ hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing * one, it is not prohibited. In this case fall back to copying. * * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ if (skb_has_frag_list(skb)) { struct sk_buff *frag, *frag2; unsigned int first_len = skb_pagelen(skb); if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || skb_cloned(skb) || skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { bool first_frag = (iter.offset == 0); IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); if (first_frag && IPCB(skb)->opt.optlen) { /* ipcb->opt is not populated for frags * coming from __ip_make_skb(), * ip_options_fragment() needs optlen */ IPCB(iter.frag)->opt.optlen = IPCB(skb)->opt.optlen; ip_options_fragment(iter.frag); ip_send_check(iter.iph); } } skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip_fraglist_next(&iter); } if (err == 0) { IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return 0; } kfree_skb_list(iter.frag); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { bool first_frag = (state.offset == 0); skb2 = ip_frag_next(skb, &state); if (IS_ERR(skb2)) { err = PTR_ERR(skb2); goto fail; } ip_frag_ipcb(skb, skb2, first_frag); /* * Put this fragment into the sending queue. */ skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, skb2); if (err) goto fail; IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); } consume_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return err; fail: kfree_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; } EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { if (!copy_from_iter_full(to, len, &msg->msg_iter)) return -EFAULT; } else { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } return 0; } EXPORT_SYMBOL(ip_generic_getfrag); static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; int mtu; int copy; int err; int offset = 0; bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = dst_rtable(cork->dst); bool paged, hold_tskey = false, extra_uref = false; unsigned int wmem_alloc_delta = 0; u32 tskey = 0; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } /* * transhdrlen > 0 means that this is the first fragment and we wish * it won't be fragmented in the future. */ if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && (!(flags & MSG_MORE) || cork->gso_size) && (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; if ((flags & MSG_ZEROCOPY) && length) { struct msghdr *msg = from; if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) return -EINVAL; /* Leave uarg NULL if can't zerocopy, callers should * be able to handle it. */ if ((rt->dst.dev->features & NETIF_F_SG) && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb), false); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; } else { uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } } else if ((flags & MSG_SPLICE_PAGES) && length) { if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) /* We need an empty buffer to attach stuff to */ paged = true; else flags &= ~MSG_SPLICE_PAGES; } cork->length += length; if (cork->tx_flags & SKBTX_ANY_TSTAMP && READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { if (cork->flags & IPCORK_TS_OPT_ID) { tskey = cork->ts_opt_id; } else { tskey = atomic_inc_return(&sk->sk_tskey) - 1; hold_tskey = true; } } /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, * each of segments is IP fragment ready for sending to network after * adding appropriate IP header. */ if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = mtu - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; if (skb_prev) fraggap = skb_prev->len - maxfraglen; else fraggap = 0; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len + 15; alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ if (datalen == length + fraggap) alloc_extra += rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = fragheaderlen + transhdrlen; pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap - pagedlen; /* [!] NOTE: copy will be negative if pagedlen>0 * because then the equation reduces to -fraggap. */ if (copy > 0 && INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } else if (flags & MSG_SPLICE_PAGES) { copy = 0; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; /* only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue. */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (flags & MSG_SPLICE_PAGES) { struct msghdr *msg = from; err = -EIO; if (WARN_ON_ONCE(copy > msg->msg_iter.count)) goto error; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) goto error; copy = err; wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb_len_add(skb, copy); wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); if (hold_tskey) atomic_dec(&sk->sk_tskey); return err; } static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ipcm_cookie *ipc, struct rtable **rtp) { struct ip_options_rcu *opt; struct rtable *rt; rt = *rtp; if (unlikely(!rt)) return -EFAULT; cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; /* * setup for corking. */ opt = ipc->opt; if (opt) { if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; /* We stole this route, caller should not release it. */ *rtp = NULL; cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; cork->priority = ipc->sockc.priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, &ipc->sockc, &cork->tx_flags); if (ipc->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) { cork->flags |= IPCORK_TS_OPT_ID; cork->ts_opt_id = ipc->sockc.ts_opt_id; } return 0; } /* * ip_append_data() can make one large IP datagram from many pieces of * data. Each piece will be held on the socket until * ip_push_pending_frames() is called. Each piece can be a page or * non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. * * LATER: length must be adjusted by pad at tail, when it is required. */ int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp); if (err) return err; } else { transhdrlen = 0; } return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags); } static void ip_cork_release(struct inet_cork *cork) { cork->flags &= ~IPCORK_OPT; kfree(cork->opt); cork->opt = NULL; dst_release(cork->dst); cork->dst = NULL; } /* * Combined all pending IP fragments on the socket as one IP datagram * and push them out. */ struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; struct rtable *rt = dst_rtable(cork->dst); struct iphdr *iph; u8 pmtudisc, ttl; __be16 df = 0; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Unless user demanded real pmtu discovery (IP_PMTUDISC_DO), we allow * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ skb->ignore_df = ip_sk_ignore_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If ignore_df is set too, we still allow to fragment this frame * locally. */ pmtudisc = READ_ONCE(inet->pmtudisc); if (pmtudisc == IP_PMTUDISC_DO || pmtudisc == IP_PMTUDISC_PROBE || (skb->len <= dst_mtu(&rt->dst) && ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); if (cork->flags & IPCORK_OPT) opt = cork->opt; if (cork->ttl != 0) ttl = cork->ttl; else if (rt->rt_type == RTN_MULTICAST) ttl = READ_ONCE(inet->mc_ttl); else ttl = ip_select_ttl(inet, &rt->dst); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = (cork->tos != -1) ? cork->tos : READ_ONCE(inet->tos); iph->frag_off = df; iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); ip_select_ident(net, skb, sk); if (opt) { iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt); } skb->priority = cork->priority; skb->mark = cork->mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); else skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid); /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount */ cork->dst = NULL; skb_dst_set(skb, &rt->dst); if (iph->protocol == IPPROTO_ICMP) { u8 icmp_type; /* For such sockets, transhdrlen is zero when do ip_append_data(), * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; icmp_out_count(net, icmp_type); } ip_cork_release(cork); out: return skb; } int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; err = ip_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); } return err; } int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) { struct sk_buff *skb; skb = ip_finish_skb(sk, fl4); if (!skb) return 0; /* Netfilter gets whole the not fragmented skb. */ return ip_send_skb(sock_net(sk), skb); } /* * Throw away all pending data on the socket. */ static void __ip_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) kfree_skb(skb); ip_cork_release(cork); } void ip_flush_pending_frames(struct sock *sk) { __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags) { struct sk_buff_head queue; int err; if (flags & MSG_PROBE) return NULL; __skb_queue_head_init(&queue); cork->flags = 0; cork->addr = 0; cork->opt = NULL; err = ip_setup_cork(sk, cork, ipc, rtp); if (err) return ERR_PTR(err); err = __ip_append_data(sk, fl4, &queue, cork, ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { __ip_flush_pending_frames(sk, &queue, cork); return ERR_PTR(err); } return __ip_make_skb(sk, fl4, &queue, cork); } /* * Fetch data from kernel space and fill in checksum if needed. */ static int ip_reply_glue_bits(void *dptr, char *to, int offset, int len, int odd, struct sk_buff *skb) { __wsum csum; csum = csum_partial_copy_nocheck(dptr+offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); return 0; } /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. */ void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len, u64 transmit_time, u32 txhash) { struct ip_options_data replyopts; struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct sk_buff *nskb; int err; int oif; if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt)) return; ipcm_init(&ipc); ipc.addr = daddr; ipc.sockc.transmit_time = transmit_time; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; if (replyopts.opt.opt.srr) daddr = replyopts.opt.opt.faddr; } oif = arg->bound_dev_if; if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, arg->tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) return; inet_sk(sk)->tos = arg->tos; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { ip_flush_pending_frames(sk); goto out; } nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) *((__sum16 *)skb_transport_header(nskb) + arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; if (orig_sk) skb_set_owner_edemux(nskb, (struct sock *)orig_sk); if (transmit_time) nskb->tstamp_type = SKB_CLOCK_MONOTONIC; if (txhash) skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); } out: ip_rt_put(rt); } void __init ip_init(void) { ip_rt_init(); inet_initpeers(); #if defined(CONFIG_IP_MULTICAST) igmp_mc_init(); #endif } |
| 16 17 1 3 3 32 1 33 36 17 18 11 28 8 23 31 17 8 17 6 17 30 17 16 30 8 16 31 31 31 31 17 30 33 33 12 6 6 7 4 2 33 16 26 21 5 5 30 19 29 26 21 19 20 21 3 5 32 28 30 30 31 11 28 30 24 30 30 29 33 28 22 33 16 33 16 16 16 31 3 31 31 33 32 30 33 17 33 33 33 33 33 33 33 33 33 33 33 5 5 4 1 25 25 27 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 | /* Bottleneck Bandwidth and RTT (BBR) congestion control * * BBR congestion control computes the sending rate based on the delivery * rate (throughput) estimated from ACKs. In a nutshell: * * On each ACK, update our model of the network path: * bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips) * min_rtt = windowed_min(rtt, 10 seconds) * pacing_rate = pacing_gain * bottleneck_bandwidth * cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4) * * The core algorithm does not react directly to packet losses or delays, * although BBR may adjust the size of next send per ACK when loss is * observed, or adjust the sending rate if it estimates there is a * traffic policer, in order to keep the drop rate reasonable. * * Here is a state transition diagram for BBR: * * | * V * +---> STARTUP ----+ * | | | * | V | * | DRAIN ----+ * | | | * | V | * +---> PROBE_BW ----+ * | ^ | | * | | | | * | +----+ | * | | * +---- PROBE_RTT <--+ * * A BBR flow starts in STARTUP, and ramps up its sending rate quickly. * When it estimates the pipe is full, it enters DRAIN to drain the queue. * In steady state a BBR flow only uses PROBE_BW and PROBE_RTT. * A long-lived BBR flow spends the vast majority of its time remaining * (repeatedly) in PROBE_BW, fully probing and utilizing the pipe's bandwidth * in a fair manner, with a small, bounded queue. *If* a flow has been * continuously sending for the entire min_rtt window, and hasn't seen an RTT * sample that matches or decreases its min_rtt estimate for 10 seconds, then * it briefly enters PROBE_RTT to cut inflight to a minimum value to re-probe * the path's two-way propagation delay (min_rtt). When exiting PROBE_RTT, if * we estimated that we reached the full bw of the pipe then we enter PROBE_BW; * otherwise we enter STARTUP to try to fill the pipe. * * BBR is described in detail in: * "BBR: Congestion-Based Congestion Control", * Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh, * Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016. * * There is a public e-mail list for discussing BBR development and testing: * https://groups.google.com/forum/#!forum/bbr-dev * * NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled, * otherwise TCP stack falls back to an internal pacing using one high * resolution timer per TCP socket and may use more resources. */ #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/module.h> #include <net/tcp.h> #include <linux/inet_diag.h> #include <linux/inet.h> #include <linux/random.h> #include <linux/win_minmax.h> /* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth * estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps. * This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32. * Since the minimum window is >=4 packets, the lower bound isn't * an issue. The upper bound isn't an issue with existing technologies. */ #define BW_SCALE 24 #define BW_UNIT (1 << BW_SCALE) #define BBR_SCALE 8 /* scaling factor for fractions in BBR (e.g. gains) */ #define BBR_UNIT (1 << BBR_SCALE) /* BBR has the following modes for deciding how fast to send: */ enum bbr_mode { BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */ BBR_DRAIN, /* drain any queue created during startup */ BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */ BBR_PROBE_RTT, /* cut inflight to min to probe min_rtt */ }; /* BBR congestion control block */ struct bbr { u32 min_rtt_us; /* min RTT in min_rtt_win_sec window */ u32 min_rtt_stamp; /* timestamp of min_rtt_us */ u32 probe_rtt_done_stamp; /* end time for BBR_PROBE_RTT mode */ struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ u32 rtt_cnt; /* count of packet-timed rounds elapsed */ u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ u64 cycle_mstamp; /* time of this cycle phase start */ u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ round_start:1, /* start of packet-timed tx->ack round? */ idle_restart:1, /* restarting after idle? */ probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ unused:13, lt_is_sampling:1, /* taking long-term ("LT") samples now? */ lt_rtt_cnt:7, /* round trips in long-term interval */ lt_use_bw:1; /* use lt_bw as our bw estimate? */ u32 lt_bw; /* LT est delivery rate in pkts/uS << 24 */ u32 lt_last_delivered; /* LT intvl start: tp->delivered */ u32 lt_last_stamp; /* LT intvl start: tp->delivered_mstamp */ u32 lt_last_lost; /* LT intvl start: tp->lost */ u32 pacing_gain:10, /* current gain for setting pacing rate */ cwnd_gain:10, /* current gain for setting cwnd */ full_bw_reached:1, /* reached full bw in Startup? */ full_bw_cnt:2, /* number of rounds without large bw gains */ cycle_idx:3, /* current index in pacing_gain cycle array */ has_seen_rtt:1, /* have we seen an RTT sample yet? */ unused_b:5; u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ u32 full_bw; /* recent bw, to estimate if pipe is full */ /* For tracking ACK aggregation: */ u64 ack_epoch_mstamp; /* start of ACK sampling epoch */ u16 extra_acked[2]; /* max excess data ACKed in epoch */ u32 ack_epoch_acked:20, /* packets (S)ACKed in sampling epoch */ extra_acked_win_rtts:5, /* age of extra_acked, in round trips */ extra_acked_win_idx:1, /* current index in extra_acked array */ unused_c:6; }; #define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */ /* Window length of bw filter (in rounds): */ static const int bbr_bw_rtts = CYCLE_LEN + 2; /* Window length of min_rtt filter (in sec): */ static const u32 bbr_min_rtt_win_sec = 10; /* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */ static const u32 bbr_probe_rtt_mode_ms = 200; /* Skip TSO below the following bandwidth (bits/sec): */ static const int bbr_min_tso_rate = 1200000; /* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck. * In order to help drive the network toward lower queues and low latency while * maintaining high utilization, the average pacing rate aims to be slightly * lower than the estimated bandwidth. This is an important aspect of the * design. */ static const int bbr_pacing_margin_percent = 1; /* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain * that will allow a smoothly increasing pacing rate that will double each RTT * and send the same number of packets per RTT that an un-paced, slow-starting * Reno or CUBIC flow would: */ static const int bbr_high_gain = BBR_UNIT * 2885 / 1000 + 1; /* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain * the queue created in BBR_STARTUP in a single round: */ static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885; /* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */ static const int bbr_cwnd_gain = BBR_UNIT * 2; /* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */ static const int bbr_pacing_gain[] = { BBR_UNIT * 5 / 4, /* probe for more available bw */ BBR_UNIT * 3 / 4, /* drain queue and/or yield bw to other flows */ BBR_UNIT, BBR_UNIT, BBR_UNIT, /* cruise at 1.0*bw to utilize pipe, */ BBR_UNIT, BBR_UNIT, BBR_UNIT /* without creating excess queue... */ }; /* Randomize the starting gain cycling phase over N phases: */ static const u32 bbr_cycle_rand = 7; /* Try to keep at least this many packets in flight, if things go smoothly. For * smooth functioning, a sliding window protocol ACKing every other packet * needs at least 4 packets in flight: */ static const u32 bbr_cwnd_min_target = 4; /* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */ /* If bw has increased significantly (1.25x), there may be more bw available: */ static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4; /* But after 3 rounds w/o significant bw growth, estimate pipe is full: */ static const u32 bbr_full_bw_cnt = 3; /* "long-term" ("LT") bandwidth estimator parameters... */ /* The minimum number of rounds in an LT bw sampling interval: */ static const u32 bbr_lt_intvl_min_rtts = 4; /* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */ static const u32 bbr_lt_loss_thresh = 50; /* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */ static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8; /* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */ static const u32 bbr_lt_bw_diff = 4000 / 8; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = 48; /* Gain factor for adding extra_acked to target cwnd: */ static const int bbr_extra_acked_gain = BBR_UNIT; /* Window length of extra_acked window. */ static const u32 bbr_extra_acked_win_rtts = 5; /* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */ static const u32 bbr_ack_epoch_acked_reset_thresh = 1U << 20; /* Time period for clamping cwnd increment due to ack aggregation */ static const u32 bbr_extra_acked_max_us = 100 * 1000; static void bbr_check_probe_rtt_done(struct sock *sk); /* Do we estimate that STARTUP filled the pipe? */ static bool bbr_full_bw_reached(const struct sock *sk) { const struct bbr *bbr = inet_csk_ca(sk); return bbr->full_bw_reached; } /* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */ static u32 bbr_max_bw(const struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); return minmax_get(&bbr->bw); } /* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */ static u32 bbr_bw(const struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk); } /* Return maximum extra acked in past k-2k round trips, * where k = bbr_extra_acked_win_rtts. */ static u16 bbr_extra_acked(const struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); return max(bbr->extra_acked[0], bbr->extra_acked[1]); } /* Return rate in bytes per second, optionally with a gain. * The order here is chosen carefully to avoid overflow of u64. This should * work for input rates of up to 2.9Tbit/sec and gain of 2.89x. */ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) { unsigned int mss = tcp_sk(sk)->mss_cache; rate *= mss; rate *= gain; rate >>= BBR_SCALE; rate *= USEC_PER_SEC / 100 * (100 - bbr_pacing_margin_percent); return rate >> BW_SCALE; } /* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */ static unsigned long bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain) { u64 rate = bw; rate = bbr_rate_bytes_per_sec(sk, rate, gain); rate = min_t(u64, rate, READ_ONCE(sk->sk_max_pacing_rate)); return rate; } /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ static void bbr_init_pacing_rate_from_rtt(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 bw; u32 rtt_us; if (tp->srtt_us) { /* any RTT sample yet? */ rtt_us = max(tp->srtt_us >> 3, 1U); bbr->has_seen_rtt = 1; } else { /* no RTT sample yet */ rtt_us = USEC_PER_MSEC; /* use nominal default RTT */ } bw = (u64)tcp_snd_cwnd(tp) * BW_UNIT; do_div(bw, rtt_us); WRITE_ONCE(sk->sk_pacing_rate, bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain)); } /* Pace using current bw estimate and a gain factor. */ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); unsigned long rate = bbr_bw_to_pacing_rate(sk, bw, gain); if (unlikely(!bbr->has_seen_rtt && tp->srtt_us)) bbr_init_pacing_rate_from_rtt(sk); if (bbr_full_bw_reached(sk) || rate > READ_ONCE(sk->sk_pacing_rate)) WRITE_ONCE(sk->sk_pacing_rate, rate); } /* override sysctl_tcp_min_tso_segs */ __bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk) { return READ_ONCE(sk->sk_pacing_rate) < (bbr_min_tso_rate >> 3) ? 1 : 2; } static u32 bbr_tso_segs_goal(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 segs, bytes; /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ bytes = min_t(unsigned long, READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift), GSO_LEGACY_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); return min(segs, 0x7FU); } /* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ static void bbr_save_cwnd(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); if (bbr->prev_ca_state < TCP_CA_Recovery && bbr->mode != BBR_PROBE_RTT) bbr->prior_cwnd = tcp_snd_cwnd(tp); /* this cwnd is good enough */ else /* loss recovery or BBR_PROBE_RTT have temporarily cut cwnd */ bbr->prior_cwnd = max(bbr->prior_cwnd, tcp_snd_cwnd(tp)); } __bpf_kfunc static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); if (event == CA_EVENT_TX_START && tp->app_limited) { bbr->idle_restart = 1; bbr->ack_epoch_mstamp = tp->tcp_mstamp; bbr->ack_epoch_acked = 0; /* Avoid pointless buffer overflows: pace at est. bw if we don't * need more speed (we're restarting from idle and app-limited). */ if (bbr->mode == BBR_PROBE_BW) bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); else if (bbr->mode == BBR_PROBE_RTT) bbr_check_probe_rtt_done(sk); } } /* Calculate bdp based on min RTT and the estimated bottleneck bandwidth: * * bdp = ceil(bw * min_rtt * gain) * * The key factor, gain, controls the amount of queue. While a small gain * builds a smaller queue, it becomes more vulnerable to noise in RTT * measurements (e.g., delayed ACKs or other ACK compression effects). This * noise may cause BBR to under-estimate the rate. */ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) { struct bbr *bbr = inet_csk_ca(sk); u32 bdp; u64 w; /* If we've never had a valid RTT sample, cap cwnd at the initial * default. This should only happen when the connection is not using TCP * timestamps and has retransmitted all of the SYN/SYNACK/data packets * ACKed so far. In this case, an RTO can cut cwnd to 1, in which * case we need to slow-start up toward something safe: TCP_INIT_CWND. */ if (unlikely(bbr->min_rtt_us == ~0U)) /* no valid RTT samples yet? */ return TCP_INIT_CWND; /* be safe: cap at default initial cwnd*/ w = (u64)bw * bbr->min_rtt_us; /* Apply a gain to the given value, remove the BW_SCALE shift, and * round the value up to avoid a negative feedback loop. */ bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; return bdp; } /* To achieve full performance in high-speed paths, we budget enough cwnd to * fit full-sized skbs in-flight on both end hosts to fully utilize the path: * - one skb in sending host Qdisc, * - one skb in sending host TSO/GSO engine * - one skb being received by receiver host LRO/GRO/delayed-ACK engine * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, * which allows 2 outstanding 2-packet sequences, to try to keep pipe * full even with ACK-every-other-packet delayed ACKs. */ static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd) { struct bbr *bbr = inet_csk_ca(sk); /* Allow enough full-sized skbs in flight to utilize end systems. */ cwnd += 3 * bbr_tso_segs_goal(sk); /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0) cwnd += 2; return cwnd; } /* Find inflight based on min RTT and the estimated bottleneck bandwidth. */ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain) { u32 inflight; inflight = bbr_bdp(sk, bw, gain); inflight = bbr_quantization_budget(sk, inflight); return inflight; } /* With pacing at lower layers, there's often less data "in the network" than * "in flight". With TSQ and departure time pacing at lower layers (e.g. fq), * we often have several skbs queued in the pacing layer with a pre-scheduled * earliest departure time (EDT). BBR adapts its pacing rate based on the * inflight level that it estimates has already been "baked in" by previous * departure time decisions. We calculate a rough estimate of the number of our * packets that might be in the network at the earliest departure time for the * next skb scheduled: * in_network_at_edt = inflight_at_edt - (EDT - now) * bw * If we're increasing inflight, then we want to know if the transmit of the * EDT skb will push inflight above the target, so inflight_at_edt includes * bbr_tso_segs_goal() from the skb departing at EDT. If decreasing inflight, * then estimate if inflight will sink too low just before the EDT transmit. */ static u32 bbr_packets_in_net_at_edt(struct sock *sk, u32 inflight_now) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 now_ns, edt_ns, interval_us; u32 interval_delivered, inflight_at_edt; now_ns = tp->tcp_clock_cache; edt_ns = max(tp->tcp_wstamp_ns, now_ns); interval_us = div_u64(edt_ns - now_ns, NSEC_PER_USEC); interval_delivered = (u64)bbr_bw(sk) * interval_us >> BW_SCALE; inflight_at_edt = inflight_now; if (bbr->pacing_gain > BBR_UNIT) /* increasing inflight */ inflight_at_edt += bbr_tso_segs_goal(sk); /* include EDT skb */ if (interval_delivered >= inflight_at_edt) return 0; return inflight_at_edt - interval_delivered; } /* Find the cwnd increment based on estimate of ack aggregation */ static u32 bbr_ack_aggregation_cwnd(struct sock *sk) { u32 max_aggr_cwnd, aggr_cwnd = 0; if (bbr_extra_acked_gain && bbr_full_bw_reached(sk)) { max_aggr_cwnd = ((u64)bbr_bw(sk) * bbr_extra_acked_max_us) / BW_UNIT; aggr_cwnd = (bbr_extra_acked_gain * bbr_extra_acked(sk)) >> BBR_SCALE; aggr_cwnd = min(aggr_cwnd, max_aggr_cwnd); } return aggr_cwnd; } /* An optimization in BBR to reduce losses: On the first round of recovery, we * follow the packet conservation principle: send P packets per P packets acked. * After that, we slow-start and send at most 2*P packets per P packets acked. * After recovery finishes, or upon undo, we restore the cwnd we had when * recovery started (capped by the target cwnd based on estimated BDP). * * TODO(ycheng/ncardwell): implement a rate-based approach. */ static bool bbr_set_cwnd_to_recover_or_restore( struct sock *sk, const struct rate_sample *rs, u32 acked, u32 *new_cwnd) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u8 prev_state = bbr->prev_ca_state, state = inet_csk(sk)->icsk_ca_state; u32 cwnd = tcp_snd_cwnd(tp); /* An ACK for P pkts should release at most 2*P packets. We do this * in two steps. First, here we deduct the number of lost packets. * Then, in bbr_set_cwnd() we slow start up toward the target cwnd. */ if (rs->losses > 0) cwnd = max_t(s32, cwnd - rs->losses, 1); if (state == TCP_CA_Recovery && prev_state != TCP_CA_Recovery) { /* Starting 1st round of Recovery, so do packet conservation. */ bbr->packet_conservation = 1; bbr->next_rtt_delivered = tp->delivered; /* start round now */ /* Cut unused cwnd from app behavior, TSQ, or TSO deferral: */ cwnd = tcp_packets_in_flight(tp) + acked; } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { /* Exiting loss recovery; restore cwnd saved before recovery. */ cwnd = max(cwnd, bbr->prior_cwnd); bbr->packet_conservation = 0; } bbr->prev_ca_state = state; if (bbr->packet_conservation) { *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); return true; /* yes, using packet conservation */ } *new_cwnd = cwnd; return false; } /* Slow-start up toward target cwnd (if bw estimate is growing, or packet loss * has drawn us down below target), or snap down to target if we're above it. */ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, u32 acked, u32 bw, int gain) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u32 cwnd = tcp_snd_cwnd(tp), target_cwnd = 0; if (!acked) goto done; /* no packet fully ACKed; just apply caps */ if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) goto done; target_cwnd = bbr_bdp(sk, bw, gain); /* Increment the cwnd to account for excess ACKed data that seems * due to aggregation (of data and/or ACKs) visible in the ACK stream. */ target_cwnd += bbr_ack_aggregation_cwnd(sk); target_cwnd = bbr_quantization_budget(sk, target_cwnd); /* If we're below target cwnd, slow start cwnd toward target cwnd. */ if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ cwnd = min(cwnd + acked, target_cwnd); else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND) cwnd = cwnd + acked; cwnd = max(cwnd, bbr_cwnd_min_target); done: tcp_snd_cwnd_set(tp, min(cwnd, tp->snd_cwnd_clamp)); /* apply global cap */ if (bbr->mode == BBR_PROBE_RTT) /* drain queue, refresh min_rtt */ tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), bbr_cwnd_min_target)); } /* End cycle phase if it's time and/or we hit the phase's in-flight target. */ static bool bbr_is_next_cycle_phase(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool is_full_length = tcp_stamp_us_delta(tp->delivered_mstamp, bbr->cycle_mstamp) > bbr->min_rtt_us; u32 inflight, bw; /* The pacing_gain of 1.0 paces at the estimated bw to try to fully * use the pipe without increasing the queue. */ if (bbr->pacing_gain == BBR_UNIT) return is_full_length; /* just use wall clock time */ inflight = bbr_packets_in_net_at_edt(sk, rs->prior_in_flight); bw = bbr_max_bw(sk); /* A pacing_gain > 1.0 probes for bw by trying to raise inflight to at * least pacing_gain*BDP; this may take more than min_rtt if min_rtt is * small (e.g. on a LAN). We do not persist if packets are lost, since * a path with small buffers may not hold that much. */ if (bbr->pacing_gain > BBR_UNIT) return is_full_length && (rs->losses || /* perhaps pacing_gain*BDP won't fit */ inflight >= bbr_inflight(sk, bw, bbr->pacing_gain)); /* A pacing_gain < 1.0 tries to drain extra queue we added if bw * probing didn't find more bw. If inflight falls to match BDP then we * estimate queue is drained; persisting would underutilize the pipe. */ return is_full_length || inflight <= bbr_inflight(sk, bw, BBR_UNIT); } static void bbr_advance_cycle_phase(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); bbr->cycle_mstamp = tp->delivered_mstamp; } /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ static void bbr_update_cycle_phase(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs)) bbr_advance_cycle_phase(sk); } static void bbr_reset_startup_mode(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->mode = BBR_STARTUP; } static void bbr_reset_probe_bw_mode(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->mode = BBR_PROBE_BW; bbr->cycle_idx = CYCLE_LEN - 1 - get_random_u32_below(bbr_cycle_rand); bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */ } static void bbr_reset_mode(struct sock *sk) { if (!bbr_full_bw_reached(sk)) bbr_reset_startup_mode(sk); else bbr_reset_probe_bw_mode(sk); } /* Start a new long-term sampling interval. */ static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bbr->lt_last_stamp = div_u64(tp->delivered_mstamp, USEC_PER_MSEC); bbr->lt_last_delivered = tp->delivered; bbr->lt_last_lost = tp->lost; bbr->lt_rtt_cnt = 0; } /* Completely reset long-term bandwidth sampling. */ static void bbr_reset_lt_bw_sampling(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->lt_bw = 0; bbr->lt_use_bw = 0; bbr->lt_is_sampling = false; bbr_reset_lt_bw_sampling_interval(sk); } /* Long-term bw sampling interval is done. Estimate whether we're policed. */ static void bbr_lt_bw_interval_done(struct sock *sk, u32 bw) { struct bbr *bbr = inet_csk_ca(sk); u32 diff; if (bbr->lt_bw) { /* do we have bw from a previous interval? */ /* Is new bw close to the lt_bw from the previous interval? */ diff = abs(bw - bbr->lt_bw); if ((diff * BBR_UNIT <= bbr_lt_bw_ratio * bbr->lt_bw) || (bbr_rate_bytes_per_sec(sk, diff, BBR_UNIT) <= bbr_lt_bw_diff)) { /* All criteria are met; estimate we're policed. */ bbr->lt_bw = (bw + bbr->lt_bw) >> 1; /* avg 2 intvls */ bbr->lt_use_bw = 1; bbr->pacing_gain = BBR_UNIT; /* try to avoid drops */ bbr->lt_rtt_cnt = 0; return; } } bbr->lt_bw = bw; bbr_reset_lt_bw_sampling_interval(sk); } /* Token-bucket traffic policers are common (see "An Internet-Wide Analysis of * Traffic Policing", SIGCOMM 2016). BBR detects token-bucket policers and * explicitly models their policed rate, to reduce unnecessary losses. We * estimate that we're policed if we see 2 consecutive sampling intervals with * consistent throughput and high packet loss. If we think we're being policed, * set lt_bw to the "long-term" average delivery rate from those 2 intervals. */ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u32 lost, delivered; u64 bw; u32 t; if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ if (bbr->mode == BBR_PROBE_BW && bbr->round_start && ++bbr->lt_rtt_cnt >= bbr_lt_bw_max_rtts) { bbr_reset_lt_bw_sampling(sk); /* stop using lt_bw */ bbr_reset_probe_bw_mode(sk); /* restart gain cycling */ } return; } /* Wait for the first loss before sampling, to let the policer exhaust * its tokens and estimate the steady-state rate allowed by the policer. * Starting samples earlier includes bursts that over-estimate the bw. */ if (!bbr->lt_is_sampling) { if (!rs->losses) return; bbr_reset_lt_bw_sampling_interval(sk); bbr->lt_is_sampling = true; } /* To avoid underestimates, reset sampling if we run out of data. */ if (rs->is_app_limited) { bbr_reset_lt_bw_sampling(sk); return; } if (bbr->round_start) bbr->lt_rtt_cnt++; /* count round trips in this interval */ if (bbr->lt_rtt_cnt < bbr_lt_intvl_min_rtts) return; /* sampling interval needs to be longer */ if (bbr->lt_rtt_cnt > 4 * bbr_lt_intvl_min_rtts) { bbr_reset_lt_bw_sampling(sk); /* interval is too long */ return; } /* End sampling interval when a packet is lost, so we estimate the * policer tokens were exhausted. Stopping the sampling before the * tokens are exhausted under-estimates the policed rate. */ if (!rs->losses) return; /* Calculate packets lost and delivered in sampling interval. */ lost = tp->lost - bbr->lt_last_lost; delivered = tp->delivered - bbr->lt_last_delivered; /* Is loss rate (lost/delivered) >= lt_loss_thresh? If not, wait. */ if (!delivered || (lost << BBR_SCALE) < bbr_lt_loss_thresh * delivered) return; /* Find average delivery rate in this sampling interval. */ t = div_u64(tp->delivered_mstamp, USEC_PER_MSEC) - bbr->lt_last_stamp; if ((s32)t < 1) return; /* interval is less than one ms, so wait */ /* Check if can multiply without overflow */ if (t >= ~0U / USEC_PER_MSEC) { bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ return; } t *= USEC_PER_MSEC; bw = (u64)delivered * BW_UNIT; do_div(bw, t); bbr_lt_bw_interval_done(sk, bw); } /* Estimate the bandwidth based on how fast packets are delivered */ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 bw; bbr->round_start = 0; if (rs->delivered < 0 || rs->interval_us <= 0) return; /* Not a valid observation */ /* See if we've reached the next RTT */ if (!before(rs->prior_delivered, bbr->next_rtt_delivered)) { bbr->next_rtt_delivered = tp->delivered; bbr->rtt_cnt++; bbr->round_start = 1; bbr->packet_conservation = 0; } bbr_lt_bw_sampling(sk, rs); /* Divide delivered by the interval to find a (lower bound) bottleneck * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than * the available network rate. Such a sample could drag down estimated * bw, causing needless slow-down. Thus, to continue to send at the * last measured network rate, we filter out app-limited samples unless * they describe the path bw at least as well as our bw model. * * So the goal during app-limited phase is to proceed with the best * network rate no matter how long. We automatically leave this * phase when app writes faster than the network can deliver :) */ if (!rs->is_app_limited || bw >= bbr_max_bw(sk)) { /* Incorporate new sample into our max bw filter. */ minmax_running_max(&bbr->bw, bbr_bw_rtts, bbr->rtt_cnt, bw); } } /* Estimates the windowed max degree of ack aggregation. * This is used to provision extra in-flight data to keep sending during * inter-ACK silences. * * Degree of ack aggregation is estimated as extra data acked beyond expected. * * max_extra_acked = "maximum recent excess data ACKed beyond max_bw * interval" * cwnd += max_extra_acked * * Max extra_acked is clamped by cwnd and bw * bbr_extra_acked_max_us (100 ms). * Max filter is an approximate sliding window of 5-10 (packet timed) round * trips. */ static void bbr_update_ack_aggregation(struct sock *sk, const struct rate_sample *rs) { u32 epoch_us, expected_acked, extra_acked; struct bbr *bbr = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); if (!bbr_extra_acked_gain || rs->acked_sacked <= 0 || rs->delivered < 0 || rs->interval_us <= 0) return; if (bbr->round_start) { bbr->extra_acked_win_rtts = min(0x1F, bbr->extra_acked_win_rtts + 1); if (bbr->extra_acked_win_rtts >= bbr_extra_acked_win_rtts) { bbr->extra_acked_win_rtts = 0; bbr->extra_acked_win_idx = bbr->extra_acked_win_idx ? 0 : 1; bbr->extra_acked[bbr->extra_acked_win_idx] = 0; } } /* Compute how many packets we expected to be delivered over epoch. */ epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp, bbr->ack_epoch_mstamp); expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT; /* Reset the aggregation epoch if ACK rate is below expected rate or * significantly large no. of ack received since epoch (potentially * quite old epoch). */ if (bbr->ack_epoch_acked <= expected_acked || (bbr->ack_epoch_acked + rs->acked_sacked >= bbr_ack_epoch_acked_reset_thresh)) { bbr->ack_epoch_acked = 0; bbr->ack_epoch_mstamp = tp->delivered_mstamp; expected_acked = 0; } /* Compute excess data delivered, beyond what was expected. */ bbr->ack_epoch_acked = min_t(u32, 0xFFFFF, bbr->ack_epoch_acked + rs->acked_sacked); extra_acked = bbr->ack_epoch_acked - expected_acked; extra_acked = min(extra_acked, tcp_snd_cwnd(tp)); if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx]) bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked; } /* Estimate when the pipe is full, using the change in delivery rate: BBR * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited * rounds. Why 3 rounds: 1: rwin autotuning grows the rwin, 2: we fill the * higher rwin, 3: we get higher delivery rate samples. Or transient * cross-traffic or radio noise can go away. CUBIC Hystart shares a similar * design goal, but uses delay and inter-ACK spacing instead of bandwidth. */ static void bbr_check_full_bw_reached(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw_thresh; if (bbr_full_bw_reached(sk) || !bbr->round_start || rs->is_app_limited) return; bw_thresh = (u64)bbr->full_bw * bbr_full_bw_thresh >> BBR_SCALE; if (bbr_max_bw(sk) >= bw_thresh) { bbr->full_bw = bbr_max_bw(sk); bbr->full_bw_cnt = 0; return; } ++bbr->full_bw_cnt; bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt; } /* If pipe is probably full, drain the queue and then enter steady-state. */ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { bbr->mode = BBR_DRAIN; /* drain queue we created */ tcp_sk(sk)->snd_ssthresh = bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT); } /* fall through to check if in-flight is already small: */ if (bbr->mode == BBR_DRAIN && bbr_packets_in_net_at_edt(sk, tcp_packets_in_flight(tcp_sk(sk))) <= bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT)) bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ } static void bbr_check_probe_rtt_done(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); if (!(bbr->probe_rtt_done_stamp && after(tcp_jiffies32, bbr->probe_rtt_done_stamp))) return; bbr->min_rtt_stamp = tcp_jiffies32; /* wait a while until PROBE_RTT */ tcp_snd_cwnd_set(tp, max(tcp_snd_cwnd(tp), bbr->prior_cwnd)); bbr_reset_mode(sk); } /* The goal of PROBE_RTT mode is to have BBR flows cooperatively and * periodically drain the bottleneck queue, to converge to measure the true * min_rtt (unloaded propagation delay). This allows the flows to keep queues * small (reducing queuing delay and packet loss) and achieve fairness among * BBR flows. * * The min_rtt filter window is 10 seconds. When the min_rtt estimate expires, * we enter PROBE_RTT mode and cap the cwnd at bbr_cwnd_min_target=4 packets. * After at least bbr_probe_rtt_mode_ms=200ms and at least one packet-timed * round trip elapsed with that flight size <= 4, we leave PROBE_RTT mode and * re-enter the previous mode. BBR uses 200ms to approximately bound the * performance penalty of PROBE_RTT's cwnd capping to roughly 2% (200ms/10s). * * Note that flows need only pay 2% if they are busy sending over the last 10 * seconds. Interactive applications (e.g., Web, RPCs, video chunks) often have * natural silences or low-rate periods within 10 seconds where the rate is low * enough for long enough to drain its queue in the bottleneck. We pick up * these min RTT measurements opportunistically with our min_rtt filter. :-) */ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool filter_expired; /* Track min RTT seen in the min_rtt_win_sec filter window: */ filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && (rs->rtt_us < bbr->min_rtt_us || (filter_expired && !rs->is_ack_delayed))) { bbr->min_rtt_us = rs->rtt_us; bbr->min_rtt_stamp = tcp_jiffies32; } if (bbr_probe_rtt_mode_ms > 0 && filter_expired && !bbr->idle_restart && bbr->mode != BBR_PROBE_RTT) { bbr->mode = BBR_PROBE_RTT; /* dip, drain queue */ bbr_save_cwnd(sk); /* note cwnd so we can restore it */ bbr->probe_rtt_done_stamp = 0; } if (bbr->mode == BBR_PROBE_RTT) { /* Ignore low rate samples during this mode. */ tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; /* Maintain min packets in flight for max(200 ms, 1 round). */ if (!bbr->probe_rtt_done_stamp && tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) { bbr->probe_rtt_done_stamp = tcp_jiffies32 + msecs_to_jiffies(bbr_probe_rtt_mode_ms); bbr->probe_rtt_round_done = 0; bbr->next_rtt_delivered = tp->delivered; } else if (bbr->probe_rtt_done_stamp) { if (bbr->round_start) bbr->probe_rtt_round_done = 1; if (bbr->probe_rtt_round_done) bbr_check_probe_rtt_done(sk); } } /* Restart after idle ends only once we process a new S/ACK for data */ if (rs->delivered > 0) bbr->idle_restart = 0; } static void bbr_update_gains(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); switch (bbr->mode) { case BBR_STARTUP: bbr->pacing_gain = bbr_high_gain; bbr->cwnd_gain = bbr_high_gain; break; case BBR_DRAIN: bbr->pacing_gain = bbr_drain_gain; /* slow, to drain */ bbr->cwnd_gain = bbr_high_gain; /* keep cwnd */ break; case BBR_PROBE_BW: bbr->pacing_gain = (bbr->lt_use_bw ? BBR_UNIT : bbr_pacing_gain[bbr->cycle_idx]); bbr->cwnd_gain = bbr_cwnd_gain; break; case BBR_PROBE_RTT: bbr->pacing_gain = BBR_UNIT; bbr->cwnd_gain = BBR_UNIT; break; default: WARN_ONCE(1, "BBR bad mode: %u\n", bbr->mode); break; } } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) { bbr_update_bw(sk, rs); bbr_update_ack_aggregation(sk, rs); bbr_update_cycle_phase(sk, rs); bbr_check_full_bw_reached(sk, rs); bbr_check_drain(sk, rs); bbr_update_min_rtt(sk, rs); bbr_update_gains(sk); } __bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw; bbr_update_model(sk, rs); bw = bbr_bw(sk); bbr_set_pacing_rate(sk, bw, bbr->pacing_gain); bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); } __bpf_kfunc static void bbr_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bbr->prior_cwnd = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; bbr->rtt_cnt = 0; bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; bbr->packet_conservation = 0; bbr->probe_rtt_done_stamp = 0; bbr->probe_rtt_round_done = 0; bbr->min_rtt_us = tcp_min_rtt(tp); bbr->min_rtt_stamp = tcp_jiffies32; minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ bbr->has_seen_rtt = 0; bbr_init_pacing_rate_from_rtt(sk); bbr->round_start = 0; bbr->idle_restart = 0; bbr->full_bw_reached = 0; bbr->full_bw = 0; bbr->full_bw_cnt = 0; bbr->cycle_mstamp = 0; bbr->cycle_idx = 0; bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); bbr->ack_epoch_mstamp = tp->tcp_mstamp; bbr->ack_epoch_acked = 0; bbr->extra_acked_win_rtts = 0; bbr->extra_acked_win_idx = 0; bbr->extra_acked[0] = 0; bbr->extra_acked[1] = 0; cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } __bpf_kfunc static u32 bbr_sndbuf_expand(struct sock *sk) { /* Provision 3 * cwnd since BBR may slow-start even during recovery. */ return 3; } /* In theory BBR does not need to undo the cwnd since it does not * always reduce cwnd on losses (see bbr_main()). Keep it for now. */ __bpf_kfunc static u32 bbr_undo_cwnd(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */ bbr->full_bw_cnt = 0; bbr_reset_lt_bw_sampling(sk); return tcp_snd_cwnd(tcp_sk(sk)); } /* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ __bpf_kfunc static u32 bbr_ssthresh(struct sock *sk) { bbr_save_cwnd(sk); return tcp_sk(sk)->snd_ssthresh; } static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { if (ext & (1 << (INET_DIAG_BBRINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); u64 bw = bbr_bw(sk); bw = bw * tp->mss_cache * USEC_PER_SEC >> BW_SCALE; memset(&info->bbr, 0, sizeof(info->bbr)); info->bbr.bbr_bw_lo = (u32)bw; info->bbr.bbr_bw_hi = (u32)(bw >> 32); info->bbr.bbr_min_rtt = bbr->min_rtt_us; info->bbr.bbr_pacing_gain = bbr->pacing_gain; info->bbr.bbr_cwnd_gain = bbr->cwnd_gain; *attr = INET_DIAG_BBRINFO; return sizeof(info->bbr); } return 0; } __bpf_kfunc static void bbr_set_state(struct sock *sk, u8 new_state) { struct bbr *bbr = inet_csk_ca(sk); if (new_state == TCP_CA_Loss) { struct rate_sample rs = { .losses = 1 }; bbr->prev_ca_state = TCP_CA_Loss; bbr->full_bw = 0; bbr->round_start = 1; /* treat RTO like end of a round */ bbr_lt_bw_sampling(sk, &rs); } } static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .flags = TCP_CONG_NON_RESTRICTED, .name = "bbr", .owner = THIS_MODULE, .init = bbr_init, .cong_control = bbr_main, .sndbuf_expand = bbr_sndbuf_expand, .undo_cwnd = bbr_undo_cwnd, .cwnd_event = bbr_cwnd_event, .ssthresh = bbr_ssthresh, .min_tso_segs = bbr_min_tso_segs, .get_info = bbr_get_info, .set_state = bbr_set_state, }; BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) BTF_ID_FLAGS(func, bbr_init) BTF_ID_FLAGS(func, bbr_main) BTF_ID_FLAGS(func, bbr_sndbuf_expand) BTF_ID_FLAGS(func, bbr_undo_cwnd) BTF_ID_FLAGS(func, bbr_cwnd_event) BTF_ID_FLAGS(func, bbr_ssthresh) BTF_ID_FLAGS(func, bbr_min_tso_segs) BTF_ID_FLAGS(func, bbr_set_state) BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { .owner = THIS_MODULE, .set = &tcp_bbr_check_kfunc_ids, }; static int __init bbr_register(void) { int ret; BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_bbr_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&tcp_bbr_cong_ops); } static void __exit bbr_unregister(void) { tcp_unregister_congestion_control(&tcp_bbr_cong_ops); } module_init(bbr_register); module_exit(bbr_unregister); MODULE_AUTHOR("Van Jacobson <vanj@google.com>"); MODULE_AUTHOR("Neal Cardwell <ncardwell@google.com>"); MODULE_AUTHOR("Yuchung Cheng <ycheng@google.com>"); MODULE_AUTHOR("Soheil Hassas Yeganeh <soheil@google.com>"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("TCP BBR (Bottleneck Bandwidth and RTT)"); |
| 1316 19 1306 1306 295 282 422 1 58 58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * net busy poll support * Copyright(c) 2013 Intel Corporation. * * Author: Eliezer Tamir * * Contact Information: * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> */ #ifndef _LINUX_NET_BUSY_POLL_H #define _LINUX_NET_BUSY_POLL_H #include <linux/netdevice.h> #include <linux/sched/clock.h> #include <linux/sched/signal.h> #include <net/ip.h> #include <net/xdp.h> /* 0 - Reserved to indicate value not set * 1..NR_CPUS - Reserved for sender_cpu * NR_CPUS+1..~0 - Region available for NAPI IDs */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) static inline bool napi_id_valid(unsigned int napi_id) { return napi_id >= MIN_NAPI_ID; } #define BUSY_POLL_BUDGET 8 #ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct; extern unsigned int sysctl_net_busy_read __read_mostly; extern unsigned int sysctl_net_busy_poll __read_mostly; static inline bool net_busy_loop_on(void) { return READ_ONCE(sysctl_net_busy_poll); } static inline bool sk_can_busy_loop(const struct sock *sk) { return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current); } bool sk_busy_loop_end(void *p, unsigned long start_time); void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget); void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget); void napi_suspend_irqs(unsigned int napi_id); void napi_resume_irqs(unsigned int napi_id); #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) { return 0; } static inline bool sk_can_busy_loop(struct sock *sk) { return false; } #endif /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long busy_loop_current_time(void) { #ifdef CONFIG_NET_RX_BUSY_POLL return (unsigned long)(ktime_get_ns() >> 10); #else return 0; #endif } /* in poll/select we use the global sysctl_net_ll_poll value */ static inline bool busy_loop_timeout(unsigned long start_time) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } #endif return true; } static inline bool sk_busy_loop_timeout(struct sock *sk, unsigned long start_time) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } #endif return true; } static inline void sk_busy_loop(struct sock *sk, int nonblock) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int napi_id = READ_ONCE(sk->sk_napi_id); if (napi_id_valid(napi_id)) napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk, READ_ONCE(sk->sk_prefer_busy_poll), READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET); #endif } /* used in the NIC receive handler to mark the skb */ static inline void __skb_mark_napi_id(struct sk_buff *skb, const struct gro_node *gro) { #ifdef CONFIG_NET_RX_BUSY_POLL /* If the skb was already marked with a valid NAPI ID, avoid overwriting * it. */ if (!napi_id_valid(skb->napi_id)) skb->napi_id = gro->cached_napi_id; #endif } static inline void skb_mark_napi_id(struct sk_buff *skb, const struct napi_struct *napi) { __skb_mark_napi_id(skb, &napi->gro); } /* used in the protocol handler to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id)) WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif sk_rx_queue_update(sk, skb); } /* Variant of sk_mark_napi_id() for passive flow setup, * as sk->sk_napi_id and sk->sk_rx_queue_mapping content * needs to be set. */ static inline void sk_mark_napi_id_set(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif sk_rx_queue_set(sk, skb); } static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id) { #ifdef CONFIG_NET_RX_BUSY_POLL if (!READ_ONCE(sk->sk_napi_id)) WRITE_ONCE(sk->sk_napi_id, napi_id); #endif } /* variant used for unconnected sockets */ static inline void sk_mark_napi_id_once(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL __sk_mark_napi_id_once(sk, skb->napi_id); #endif } #endif /* _LINUX_NET_BUSY_POLL_H */ |
| 18726 637 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/bitops.h> #include <linux/wordpart.h> struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } #ifdef CONFIG_64BIT /* Keep the initial has_zero() value for both bitmask and size calc */ #define create_zero_mask(bits) (bits) static inline unsigned long zero_bytemask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } #define find_zero(bits) (__ffs(bits) >> 3) #else /* Create the final mask for both bytemask and size */ static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline unsigned long find_zero(unsigned long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret; asm volatile( "1: mov %[mem], %[ret]\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD) : [ret] "=r" (ret) : [mem] "m" (*(unsigned long *)addr)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_H */ |
| 10 10 3317 4 4 1 3 98 1021 1021 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_VERIFIER_H #define _LINUX_BPF_VERIFIER_H 1 #include <linux/bpf.h> /* for enum bpf_reg_type */ #include <linux/btf.h> /* for struct btf and btf_id() */ #include <linux/filter.h> /* for MAX_BPF_STACK */ #include <linux/tnum.h> /* Maximum variable offset umax_value permitted when resolving memory accesses. * In practice this is far bigger than any realistic pointer offset; this limit * ensures that umax_value + (int)off + (int)size cannot overflow a u64. */ #define BPF_MAX_VAR_OFF (1 << 29) /* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) /* size of tmp_str_buf in bpf_verifier. * we need at least 306 bytes to fit full stack mask representation * (in the "-8,-16,...,-512" form) */ #define TMP_STR_BUF_LEN 320 /* Patch buffer size */ #define INSN_BUF_SIZE 32 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that * "one of this state's descendants read this reg" (and therefore the reg is * relevant for states_equal() checks). * Write marks collect downwards and do not propagate; they record that "the * straight-line code that reached this state (from its parent) wrote this reg" * (and therefore that reads propagated from this state or its descendants * should not propagate to its parent). * A state with a write mark can receive read marks; it just won't propagate * them to its parent, since the write mark is a property, not of the state, * but of the link between it and its parent. See mark_reg_read() and * mark_stack_slot_read() in kernel/bpf/verifier.c. */ enum bpf_reg_liveness { REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ REG_LIVE_READ32 = 0x1, /* reg was read, so we're sensitive to initial value */ REG_LIVE_READ64 = 0x2, /* likewise, but full 64-bit content matters */ REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64, REG_LIVE_WRITTEN = 0x4, /* reg was written first, screening off later reads */ REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */ }; #define ITER_PREFIX "bpf_iter_" enum bpf_iter_state { BPF_ITER_STATE_INVALID, /* for non-first slot */ BPF_ITER_STATE_ACTIVE, BPF_ITER_STATE_DRAINED, }; struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; /* * Fixed part of pointer offset, pointer types only. * Or constant delta between "linked" scalars with the same ID. */ s32 off; union { /* valid when type == PTR_TO_PACKET */ int range; /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ struct { struct bpf_map *map_ptr; /* To distinguish map lookups from outer map * the map_uid is non-zero for registers * pointing to inner maps. */ u32 map_uid; }; /* for PTR_TO_BTF_ID */ struct { struct btf *btf; u32 btf_id; }; struct { /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ u32 mem_size; u32 dynptr_id; /* for dynptr slices */ }; /* For dynptr stack slots */ struct { enum bpf_dynptr_type type; /* A dynptr is 16 bytes so it takes up 2 stack slots. * We need to track which slot is the first slot * to protect against cases where the user may try to * pass in an address starting at the second slot of the * dynptr. */ bool first_slot; } dynptr; /* For bpf_iter stack slots */ struct { /* BTF container and BTF type ID describing * struct bpf_iter_<type> of an iterator state */ struct btf *btf; u32 btf_id; /* packing following two fields to fit iter state into 16 bytes */ enum bpf_iter_state state:2; int depth:30; } iter; /* For irq stack slots */ struct { enum { IRQ_NATIVE_KFUNC, IRQ_LOCK_KFUNC, } kfunc_class; } irq; /* Max size from any of the above. */ struct { unsigned long raw1; unsigned long raw2; } raw; u32 subprogno; /* for PTR_TO_FUNC */ }; /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset * from the pointed-to object, and is shared with all bpf_reg_states * with the same id as us. */ struct tnum var_off; /* Used to determine if any memory access using this register will * result in a bad access. * These refer to the same value as var_off, not necessarily the actual * contents of the register. */ s64 smin_value; /* minimum possible (s64)value */ s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ s32 s32_min_value; /* minimum possible (s32)value */ s32 s32_max_value; /* maximum possible (s32)value */ u32 u32_min_value; /* minimum possible (u32)value */ u32 u32_max_value; /* maximum possible (u32)value */ /* For PTR_TO_PACKET, used to find other pointers with the same variable * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. * For PTR_TO_MEM_OR_NULL this is used to identify memory allocation * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. * For stack slots that are dynptrs, this is used to track references to * the dynptr to determine proper reference freeing. * Similarly to dynptrs, we use ID to track "belonging" of a reference * to a specific instance of bpf_iter. */ /* * Upper bit of ID is used to remember relationship between "linked" * registers. Example: * r1 = r2; both will have r1->id == r2->id == N * r1 += 10; r1->id == N | BPF_ADD_CONST and r1->off == 10 */ #define BPF_ADD_CONST (1U << 31) u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned * from a pointer-cast helper, bpf_sk_fullsock() and * bpf_tcp_sock(). * * Consider the following where "sk" is a reference counted * pointer returned from "sk = bpf_sk_lookup_tcp();": * * 1: sk = bpf_sk_lookup_tcp(); * 2: if (!sk) { return 0; } * 3: fullsock = bpf_sk_fullsock(sk); * 4: if (!fullsock) { bpf_sk_release(sk); return 0; } * 5: tp = bpf_tcp_sock(fullsock); * 6: if (!tp) { bpf_sk_release(sk); return 0; } * 7: bpf_sk_release(sk); * 8: snd_cwnd = tp->snd_cwnd; // verifier will complain * * After bpf_sk_release(sk) at line 7, both "fullsock" ptr and * "tp" ptr should be invalidated also. In order to do that, * the reg holding "fullsock" and "sk" need to remember * the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id * such that the verifier can reset all regs which have * ref_obj_id matching the sk_reg->id. * * sk_reg->ref_obj_id is set to sk_reg->id at line 1. * sk_reg->id will stay as NULL-marking purpose only. * After NULL-marking is done, sk_reg->id can be reset to 0. * * After "fullsock = bpf_sk_fullsock(sk);" at line 3, * fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id. * * After "tp = bpf_tcp_sock(fullsock);" at line 5, * tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id * which is the same as sk_reg->ref_obj_id. * * From the verifier perspective, if sk, fullsock and tp * are not NULL, they are the same ptr with different * reg->type. In particular, bpf_sk_release(tp) is also * allowed and has the same effect as bpf_sk_release(sk). */ u32 ref_obj_id; /* parentage chain for liveness checking */ struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' * is used which is an index in bpf_verifier_state->frame[] array * pointing to bpf_func_state. */ u32 frameno; /* Tracks subreg definition. The stored value is the insn_idx of the * writing insn. This is safe because subreg_def is used before any insn * patching which only happens after main verification finished. */ s32 subreg_def; enum bpf_reg_liveness live; /* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */ bool precise; }; enum bpf_stack_slot_type { STACK_INVALID, /* nothing was stored in this stack slot */ STACK_SPILL, /* register spilled into stack */ STACK_MISC, /* BPF program wrote some data into this slot */ STACK_ZERO, /* BPF program wrote constant zero */ /* A dynptr is stored in this stack slot. The type of dynptr * is stored in bpf_stack_state->spilled_ptr.dynptr.type */ STACK_DYNPTR, STACK_ITER, STACK_IRQ_FLAG, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ #define BPF_REGMASK_ARGS ((1 << BPF_REG_1) | (1 << BPF_REG_2) | \ (1 << BPF_REG_3) | (1 << BPF_REG_4) | \ (1 << BPF_REG_5)) #define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) #define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) struct bpf_stack_state { struct bpf_reg_state spilled_ptr; u8 slot_type[BPF_REG_SIZE]; }; struct bpf_reference_state { /* Each reference object has a type. Ensure REF_TYPE_PTR is zero to * default to pointer reference on zero initialization of a state. */ enum ref_state_type { REF_TYPE_PTR = (1 << 1), REF_TYPE_IRQ = (1 << 2), REF_TYPE_LOCK = (1 << 3), REF_TYPE_RES_LOCK = (1 << 4), REF_TYPE_RES_LOCK_IRQ = (1 << 5), REF_TYPE_LOCK_MASK = REF_TYPE_LOCK | REF_TYPE_RES_LOCK | REF_TYPE_RES_LOCK_IRQ, } type; /* Track each reference created with a unique id, even if the same * instruction creates the reference multiple times (eg, via CALL). */ int id; /* Instruction where the allocation of this reference occurred. This * is used purely to inform the user of a reference leak. */ int insn_idx; /* Use to keep track of the source object of a lock, to ensure * it matches on unlock. */ void *ptr; }; struct bpf_retval_range { s32 minval; s32 maxval; }; /* state of the program: * type of all registers and stack info */ struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; /* index of call instruction that called into this func */ int callsite; /* stack frame number of this function state from pov of * enclosing bpf_verifier_state. * 0 = main function, 1 = first callee. */ u32 frameno; /* subprog number == index within subprog_info * zero == main subprog */ u32 subprogno; /* Every bpf_timer_start will increment async_entry_cnt. * It's used to distinguish: * void foo(void) { for(;;); } * void foo(void) { bpf_timer_set_callback(,foo); } */ u32 async_entry_cnt; struct bpf_retval_range callback_ret_range; bool in_callback_fn; bool in_async_callback_fn; bool in_exception_callback_fn; /* For callback calling functions that limit number of possible * callback executions (e.g. bpf_loop) keeps track of current * simulated iteration number. * Value in frame N refers to number of times callback with frame * N+1 was simulated, e.g. for the following call: * * bpf_loop(..., fn, ...); | suppose current frame is N * | fn would be simulated in frame N+1 * | number of simulations is tracked in frame N */ u32 callback_depth; /* The following fields should be last. See copy_func_state() */ /* The state of the stack. Each element of the array describes BPF_REG_SIZE * (i.e. 8) bytes worth of stack memory. * stack[0] represents bytes [*(r10-8)..*(r10-1)] * stack[1] represents bytes [*(r10-16)..*(r10-9)] * ... * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)] */ struct bpf_stack_state *stack; /* Size of the current stack, in bytes. The stack state is tracked below, in * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE. */ int allocated_stack; }; #define MAX_CALL_FRAMES 8 /* instruction history flags, used in bpf_insn_hist_entry.flags field */ enum { /* instruction references stack slot through PTR_TO_STACK register; * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8) * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512, * 8 bytes per slot, so slot index (spi) is [0, 63]) */ INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */ INSN_F_SPI_MASK = 0x3f, /* 6 bits */ INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */ INSN_F_STACK_ACCESS = BIT(9), INSN_F_DST_REG_STACK = BIT(10), /* dst_reg is PTR_TO_STACK */ INSN_F_SRC_REG_STACK = BIT(11), /* src_reg is PTR_TO_STACK */ /* total 12 bits are used now. */ }; static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES); static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8); struct bpf_insn_hist_entry { u32 idx; /* insn idx can't be bigger than 1 million */ u32 prev_idx : 20; /* special INSN_F_xxx flags */ u32 flags : 12; /* additional registers that need precision tracking when this * jump is backtracked, vector of six 10-bit records */ u64 linked_regs; }; /* Maximum number of register states that can exist at once */ #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES) struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; struct bpf_verifier_state *parent; /* Acquired reference states */ struct bpf_reference_state *refs; /* * 'branches' field is the number of branches left to explore: * 0 - all possible paths from this state reached bpf_exit or * were safely pruned * 1 - at least one path is being explored. * This state hasn't reached bpf_exit * 2 - at least two paths are being explored. * This state is an immediate parent of two children. * One is fallthrough branch with branches==1 and another * state is pushed into stack (to be explored later) also with * branches==1. The parent of this state has branches==1. * The verifier state tree connected via 'parent' pointer looks like: * 1 * 1 * 2 -> 1 (first 'if' pushed into stack) * 1 * 2 -> 1 (second 'if' pushed into stack) * 1 * 1 * 1 bpf_exit. * * Once do_check() reaches bpf_exit, it calls update_branch_counts() * and the verifier state tree will look: * 1 * 1 * 2 -> 1 (first 'if' pushed into stack) * 1 * 1 -> 1 (second 'if' pushed into stack) * 0 * 0 * 0 bpf_exit. * After pop_stack() the do_check() will resume at second 'if'. * * If is_state_visited() sees a state with branches > 0 it means * there is a loop. If such state is exactly equal to the current state * it's an infinite loop. Note states_equal() checks for states * equivalency, so two states being 'states_equal' does not mean * infinite loop. The exact comparison is provided by * states_maybe_looping() function. It's a stronger pre-check and * much faster than states_equal(). * * This algorithm may not find all possible infinite loops or * loop iteration count may be too high. * In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in. */ u32 branches; u32 insn_idx; u32 curframe; u32 acquired_refs; u32 active_locks; u32 active_preempt_locks; u32 active_irq_id; u32 active_lock_id; void *active_lock_ptr; bool active_rcu_lock; bool speculative; bool in_sleepable; /* first and last insn idx of this verifier state */ u32 first_insn_idx; u32 last_insn_idx; /* If this state is a part of states loop this field points to some * parent of this state such that: * - it is also a member of the same states loop; * - DFS states traversal starting from initial state visits loop_entry * state before this state. * Used to compute topmost loop entry for state loops. * State loops might appear because of open coded iterators logic. * See get_loop_entry() for more information. */ struct bpf_verifier_state *loop_entry; /* Sub-range of env->insn_hist[] corresponding to this state's * instruction history. * Backtracking is using it to go from last to first. * For most states instruction history is short, 0-3 instructions. * For loops can go up to ~40. */ u32 insn_hist_start; u32 insn_hist_end; u32 dfs_depth; u32 callback_unroll_depth; u32 may_goto_depth; /* If this state was ever pointed-to by other state's loop_entry field * this flag would be set to true. Used to avoid freeing such states * while they are still in use. */ u32 used_as_loop_entry; }; #define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ ((1 << frame->stack[slot].slot_type[BPF_REG_SIZE - 1]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ #define bpf_for_each_spilled_reg(iter, frame, reg, mask) \ for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask); \ iter < frame->allocated_stack / BPF_REG_SIZE; \ iter++, reg = bpf_get_spilled_reg(iter, frame, mask)) #define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr) \ ({ \ struct bpf_verifier_state *___vstate = __vst; \ int ___i, ___j; \ for (___i = 0; ___i <= ___vstate->curframe; ___i++) { \ struct bpf_reg_state *___regs; \ __state = ___vstate->frame[___i]; \ ___regs = __state->regs; \ for (___j = 0; ___j < MAX_BPF_REG; ___j++) { \ __reg = &___regs[___j]; \ (void)(__expr); \ } \ bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \ if (!__reg) \ continue; \ (void)(__expr); \ } \ } \ }) /* Invoke __expr over regsiters in __vst, setting __state and __reg */ #define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr) /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; struct list_head node; u32 miss_cnt; u32 hit_cnt:31; u32 in_free_list:1; }; struct bpf_loop_inline_state { unsigned int initialized:1; /* set to true upon first entry */ unsigned int fit_for_inline:1; /* true if callback function is the same * at each call and flags are always zero */ u32 callback_subprogno; /* valid when fit_for_inline is true */ }; /* pointer and state for maps */ struct bpf_map_ptr_state { struct bpf_map *map_ptr; bool poison; bool unpriv; }; /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) #define BPF_ALU_NEG_VALUE (1U << 2) #define BPF_ALU_NON_POINTER (1U << 3) #define BPF_ALU_IMMEDIATE (1U << 4) #define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \ BPF_ALU_SANITIZE_DST) struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ struct bpf_map_ptr_state map_ptr_state; s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { u32 map_index; /* index into used_maps[] */ u32 map_off; /* offset from value base address */ }; struct { enum bpf_reg_type reg_type; /* type of pseudo_btf_id */ union { struct { struct btf *btf; u32 btf_id; /* btf_id for struct typed var */ }; u32 mem_size; /* mem_size for non-struct typed var */ }; } btf_var; /* if instruction is a call to bpf_loop this field tracks * the state of the relevant registers to make decision about inlining */ struct bpf_loop_inline_state loop_inline_state; }; union { /* remember the size of type passed to bpf_obj_new to rewrite R1 */ u64 obj_new_size; /* remember the offset of node field within type to rewrite */ u64 insert_off; }; struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ bool needs_zext; /* alu op needs to clear upper bits */ bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */ bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */ bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ u8 alu_state; /* used in combination with alu_limit */ /* true if STX or LDX instruction is a part of a spill/fill * pattern for a bpf_fastcall call. */ u8 fastcall_pattern:1; /* for CALL instructions, a number of spill/fill pairs in the * bpf_fastcall pattern. */ u8 fastcall_spills_num:3; u8 arg_prog:4; /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ bool jmp_point; bool prune_point; /* ensure we check state equivalence and save state checkpoint and * this instruction, regardless of any heuristics */ bool force_checkpoint; /* true if instruction is a call to a helper function that * accepts callback function as a parameter. */ bool calls_callback; /* registers alive before this instruction. */ u16 live_regs_before; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ #define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */ #define BPF_VERIFIER_TMP_LOG_SIZE 1024 struct bpf_verifier_log { /* Logical start and end positions of a "log window" of the verifier log. * start_pos == 0 means we haven't truncated anything. * Once truncation starts to happen, start_pos + len_total == end_pos, * except during log reset situations, in which (end_pos - start_pos) * might get smaller than len_total (see bpf_vlog_reset()). * Generally, (end_pos - start_pos) gives number of useful data in * user log buffer. */ u64 start_pos; u64 end_pos; char __user *ubuf; u32 level; u32 len_total; u32 len_max; char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; }; #define BPF_LOG_LEVEL1 1 #define BPF_LOG_LEVEL2 2 #define BPF_LOG_STATS 4 #define BPF_LOG_FIXED 8 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS | BPF_LOG_FIXED) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { return log && log->level; } #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_arg_info { enum bpf_arg_type arg_type; union { u32 mem_size; u32 btf_id; }; }; enum priv_stack_mode { PRIV_STACK_UNKNOWN, NO_PRIV_STACK, PRIV_STACK_ADAPTIVE, }; struct bpf_subprog_info { /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ u16 stack_extra; /* offsets in range [stack_depth .. fastcall_stack_off) * are used for bpf_fastcall spills and fills. */ s16 fastcall_stack_off; bool has_tail_call: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; bool is_cb: 1; bool is_async_cb: 1; bool is_exception_cb: 1; bool args_cached: 1; /* true if bpf_fastcall stack region is used by functions that can't be inlined */ bool keep_fastcall_stack: 1; bool changes_pkt_data: 1; bool might_sleep: 1; enum priv_stack_mode priv_stack_mode; u8 arg_cnt; struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; }; struct bpf_verifier_env; struct backtrack_state { struct bpf_verifier_env *env; u32 frame; u32 reg_masks[MAX_CALL_FRAMES]; u64 stack_masks[MAX_CALL_FRAMES]; }; struct bpf_id_pair { u32 old; u32 cur; }; struct bpf_idmap { u32 tmp_id_gen; struct bpf_id_pair map[BPF_ID_MAP_SIZE]; }; struct bpf_idset { u32 count; u32 ids[BPF_ID_MAP_SIZE]; }; /* single container for all structs * one verifier_env per bpf_check() call */ struct bpf_verifier_env { u32 insn_idx; u32 prev_insn_idx; struct bpf_prog *prog; /* eBPF program being verified */ const struct bpf_verifier_ops *ops; struct module *attach_btf_mod; /* The owner module of prog->aux->attach_btf */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ bool test_state_freq; /* test verifier with different pruning frequency */ bool test_reg_invariants; /* fail verification on register invariants violations */ struct bpf_verifier_state *cur_state; /* current verifier state */ /* Search pruning optimization, array of list_heads for * lists of struct bpf_verifier_state_list. */ struct list_head *explored_states; struct list_head free_list; /* list of struct bpf_verifier_state_list */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */ u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ u32 hidden_subprog_cnt; /* number of hidden subprogs */ int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; /* Allow access to uninitialized stack memory. Writes with fixed offset are * always allowed, so this refers to reads (with fixed or variable offset), * to writes with variable offset and to indirect (helper) accesses. */ bool allow_uninit_stack; bool bpf_capable; bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; bool seen_exception; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */ union { struct bpf_idmap idmap_scratch; struct bpf_idset idset_scratch; }; struct { int *insn_state; int *insn_stack; /* vector of instruction indexes sorted in post-order */ int *insn_postorder; int cur_stack; /* current position in the insn_postorder vector */ int cur_postorder; } cfg; struct backtrack_state bt; struct bpf_insn_hist_entry *insn_hist; struct bpf_insn_hist_entry *cur_hist_ent; u32 insn_hist_cap; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ u32 prev_insn_processed, insn_processed; /* number of jmps, calls, exits analyzed so far */ u32 prev_jmps_processed, jmps_processed; /* total verification time */ u64 verification_time; /* maximum number of verifier states kept in 'branching' instructions */ u32 max_states_per_insn; /* total number of allocated verifier states */ u32 total_states; /* some states are freed during program analysis. * this is peak number of states. this number dominates kernel * memory consumption during verification */ u32 peak_states; /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; u32 free_list_size; u32 explored_states_size; bpfptr_t fd_array; /* bit mask to keep track of whether a register has been accessed * since the last time the function state was printed */ u32 scratched_regs; /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; /* buffer used to temporary hold constants as scalar registers */ struct bpf_reg_state fake_reg[2]; /* buffer used to generate temporary string representations, * e.g., in reg_type_str() to generate reg_type string */ char tmp_str_buf[TMP_STR_BUF_LEN]; struct bpf_insn insn_buf[INSN_BUF_SIZE]; struct bpf_insn epilogue_buf[INSN_BUF_SIZE]; }; static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) { return &env->prog->aux->func_info_aux[subprog]; } static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog) { return &env->subprog_info[subprog]; } __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...); int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, char __user *log_buf, u32 log_size); void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...); #define verifier_bug_if(cond, env, fmt, args...) \ ({ \ bool __cond = (cond); \ if (unlikely(__cond)) { \ BPF_WARN_ONCE(1, "verifier bug: " fmt "(" #cond ")\n", ##args); \ bpf_log(&env->log, "verifier bug: " fmt "(" #cond ")\n", ##args); \ } \ (__cond); \ }) #define verifier_bug(env, fmt, args...) verifier_bug_if(1, env, fmt, ##args) static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; return cur->frame[cur->curframe]; } static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) { return cur_func(env)->regs; } int bpf_prog_offload_verifier_prep(struct bpf_prog *prog); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int bpf_prog_offload_finalize(struct bpf_verifier_env *env); void bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, struct bpf_insn *insn); void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, struct btf *btf, u32 btf_id) { if (tgt_prog) return ((u64)tgt_prog->aux->id << 32) | btf_id; else return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id; } /* unpack the IDs from the key as constructed above */ static inline void bpf_trampoline_unpack_key(u64 key, u32 *obj_id, u32 *btf_id) { if (obj_id) *obj_id = key >> 32; if (btf_id) *btf_id = key & 0x7FFFFFFF; } int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *prog, const struct bpf_prog *tgt_prog, u32 btf_id, struct bpf_attach_target_info *tgt_info); void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); int mark_chain_precision(struct bpf_verifier_env *env, int regno); #define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0) /* extract base type from bpf_{arg, return, reg}_type. */ static inline u32 base_type(u32 type) { return type & BPF_BASE_TYPE_MASK; } /* extract flags from an extended type. See bpf_type_flag in bpf.h. */ static inline u32 type_flag(u32 type) { return type & ~BPF_BASE_TYPE_MASK; } /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) { switch (resolve_prog_type(prog)) { case BPF_PROG_TYPE_TRACING: return prog->expected_attach_type != BPF_TRACE_ITER; case BPF_PROG_TYPE_STRUCT_OPS: return prog->aux->jits_use_priv_stack; case BPF_PROG_TYPE_LSM: return false; default: return true; } } #define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED | NON_OWN_REF) static inline bool bpf_type_has_unsafe_modifiers(u32 type) { return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS; } static inline bool type_is_ptr_alloc_obj(u32 type) { return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; } static inline bool type_is_non_owning_ref(u32 type) { return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF; } static inline bool type_is_pkt_pointer(enum bpf_reg_type type) { type = base_type(type); return type == PTR_TO_PACKET || type == PTR_TO_PACKET_META; } static inline bool type_is_sk_pointer(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_SOCK_COMMON || type == PTR_TO_TCP_SOCK || type == PTR_TO_XDP_SOCK; } static inline bool type_may_be_null(u32 type) { return type & PTR_MAYBE_NULL; } static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) { env->scratched_regs |= 1U << regno; } static inline void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) { env->scratched_stack_slots |= 1ULL << spi; } static inline bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) { return (env->scratched_regs >> regno) & 1; } static inline bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) { return (env->scratched_stack_slots >> regno) & 1; } static inline bool verifier_state_scratched(const struct bpf_verifier_env *env) { return env->scratched_regs || env->scratched_stack_slots; } static inline void mark_verifier_state_clean(struct bpf_verifier_env *env) { env->scratched_regs = 0U; env->scratched_stack_slots = 0ULL; } /* Used for printing the entire verifier state. */ static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env) { env->scratched_regs = ~0U; env->scratched_stack_slots = ~0ULL; } static inline bool bpf_stack_narrow_access_ok(int off, int fill_size, int spill_size) { #ifdef __BIG_ENDIAN off -= spill_size - fill_size; #endif return !(off % BPF_REG_SIZE); } const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type); const char *dynptr_type_str(enum bpf_dynptr_type type); const char *iter_type_str(const struct btf *btf, u32 btf_id); const char *iter_state_str(enum bpf_iter_state state); void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno, bool print_all); void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno); #endif /* _LINUX_BPF_VERIFIER_H */ |
| 109 25 100 1 161 160 160 160 20 158 27 5 3 125 159 143 138 149 148 128 116 116 10 162 162 140 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/isofs/namei.c * * (C) 1992 Eric Youngdale Modified for ISO 9660 filesystem. * * (C) 1991 Linus Torvalds - minix filesystem */ #include <linux/gfp.h> #include "isofs.h" /* * ok, we cannot use strncmp, as the name is not in our data space. * Thus we'll have to use isofs_match. No big problem. Match also makes * some sanity tests. */ static int isofs_cmp(struct dentry *dentry, const char *compare, int dlen) { struct qstr qstr; qstr.name = compare; qstr.len = dlen; if (likely(!dentry->d_op)) return dentry->d_name.len != dlen || memcmp(dentry->d_name.name, compare, dlen); return dentry->d_op->d_compare(NULL, dentry->d_name.len, dentry->d_name.name, &qstr); } /* * isofs_find_entry() * * finds an entry in the specified directory with the wanted name. It * returns the inode number of the found entry, or 0 on error. */ static unsigned long isofs_find_entry(struct inode *dir, struct dentry *dentry, unsigned long *block_rv, unsigned long *offset_rv, char *tmpname, struct iso_directory_record *tmpde) { unsigned long bufsize = ISOFS_BUFFER_SIZE(dir); unsigned char bufbits = ISOFS_BUFFER_BITS(dir); unsigned long block, f_pos, offset, block_saved, offset_saved; struct buffer_head *bh = NULL; struct isofs_sb_info *sbi = ISOFS_SB(dir->i_sb); if (!ISOFS_I(dir)->i_first_extent) return 0; f_pos = 0; offset = 0; block = 0; while (f_pos < dir->i_size) { struct iso_directory_record *de; int de_len, match, i, dlen; char *dpnt; if (!bh) { bh = isofs_bread(dir, block); if (!bh) return 0; } de = (struct iso_directory_record *) (bh->b_data + offset); de_len = *(unsigned char *) de; if (!de_len) { brelse(bh); bh = NULL; f_pos = (f_pos + ISOFS_BLOCK_SIZE) & ~(ISOFS_BLOCK_SIZE - 1); block = f_pos >> bufbits; offset = 0; continue; } block_saved = bh->b_blocknr; offset_saved = offset; offset += de_len; f_pos += de_len; /* Make sure we have a full directory entry */ if (offset >= bufsize) { int slop = bufsize - offset + de_len; memcpy(tmpde, de, slop); offset &= bufsize - 1; block++; brelse(bh); bh = NULL; if (offset) { bh = isofs_bread(dir, block); if (!bh) return 0; memcpy((void *) tmpde + slop, bh->b_data, offset); } de = tmpde; } dlen = de->name_len[0]; dpnt = de->name; /* Basic sanity check, whether name doesn't exceed dir entry */ if (de_len < dlen + sizeof(struct iso_directory_record)) { printk(KERN_NOTICE "iso9660: Corrupted directory entry" " in block %lu of inode %lu\n", block, dir->i_ino); brelse(bh); return 0; } if (sbi->s_rock && ((i = get_rock_ridge_filename(de, tmpname, dir)))) { dlen = i; /* possibly -1 */ dpnt = tmpname; #ifdef CONFIG_JOLIET } else if (sbi->s_joliet_level) { dlen = get_joliet_filename(de, tmpname, dir); dpnt = tmpname; #endif } else if (sbi->s_mapping == 'a') { dlen = get_acorn_filename(de, tmpname, dir); dpnt = tmpname; } else if (sbi->s_mapping == 'n') { dlen = isofs_name_translate(de, tmpname, dir); dpnt = tmpname; } /* * Skip hidden or associated files unless hide or showassoc, * respectively, is set */ match = 0; if (dlen > 0 && (!sbi->s_hide || (!(de->flags[-sbi->s_high_sierra] & 1))) && (sbi->s_showassoc || (!(de->flags[-sbi->s_high_sierra] & 4)))) { if (dpnt && (dlen > 1 || dpnt[0] > 1)) match = (isofs_cmp(dentry, dpnt, dlen) == 0); } if (match) { isofs_normalize_block_and_offset(de, &block_saved, &offset_saved); *block_rv = block_saved; *offset_rv = offset_saved; brelse(bh); return 1; } } brelse(bh); return 0; } struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int found; unsigned long block; unsigned long offset; struct inode *inode; struct page *page; page = alloc_page(GFP_USER); if (!page) return ERR_PTR(-ENOMEM); found = isofs_find_entry(dir, dentry, &block, &offset, page_address(page), 1024 + page_address(page)); __free_page(page); inode = found ? isofs_iget(dir->i_sb, block, offset) : NULL; return d_splice_alias(inode, dentry); } |
| 83 83 79 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "ratelimiter.h" #include <linux/siphash.h> #include <linux/mm.h> #include <linux/slab.h> #include <net/ip.h> static struct kmem_cache *entry_cache; static hsiphash_key_t key; static spinlock_t table_lock = __SPIN_LOCK_UNLOCKED("ratelimiter_table_lock"); static DEFINE_MUTEX(init_lock); static u64 init_refcnt; /* Protected by init_lock, hence not atomic. */ static atomic_t total_entries = ATOMIC_INIT(0); static unsigned int max_entries, table_size; static void wg_ratelimiter_gc_entries(struct work_struct *); static DECLARE_DEFERRABLE_WORK(gc_work, wg_ratelimiter_gc_entries); static struct hlist_head *table_v4; #if IS_ENABLED(CONFIG_IPV6) static struct hlist_head *table_v6; #endif struct ratelimiter_entry { u64 last_time_ns, tokens, ip; void *net; spinlock_t lock; struct hlist_node hash; struct rcu_head rcu; }; enum { PACKETS_PER_SECOND = 20, PACKETS_BURSTABLE = 5, PACKET_COST = NSEC_PER_SEC / PACKETS_PER_SECOND, TOKEN_MAX = PACKET_COST * PACKETS_BURSTABLE }; static void entry_free(struct rcu_head *rcu) { kmem_cache_free(entry_cache, container_of(rcu, struct ratelimiter_entry, rcu)); atomic_dec(&total_entries); } static void entry_uninit(struct ratelimiter_entry *entry) { hlist_del_rcu(&entry->hash); call_rcu(&entry->rcu, entry_free); } /* Calling this function with a NULL work uninits all entries. */ static void wg_ratelimiter_gc_entries(struct work_struct *work) { const u64 now = ktime_get_coarse_boottime_ns(); struct ratelimiter_entry *entry; struct hlist_node *temp; unsigned int i; for (i = 0; i < table_size; ++i) { spin_lock(&table_lock); hlist_for_each_entry_safe(entry, temp, &table_v4[i], hash) { if (unlikely(!work) || now - entry->last_time_ns > NSEC_PER_SEC) entry_uninit(entry); } #if IS_ENABLED(CONFIG_IPV6) hlist_for_each_entry_safe(entry, temp, &table_v6[i], hash) { if (unlikely(!work) || now - entry->last_time_ns > NSEC_PER_SEC) entry_uninit(entry); } #endif spin_unlock(&table_lock); if (likely(work)) cond_resched(); } if (likely(work)) queue_delayed_work(system_power_efficient_wq, &gc_work, HZ); } bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net) { /* We only take the bottom half of the net pointer, so that we can hash * 3 words in the end. This way, siphash's len param fits into the final * u32, and we don't incur an extra round. */ const u32 net_word = (unsigned long)net; struct ratelimiter_entry *entry; struct hlist_head *bucket; u64 ip; if (skb->protocol == htons(ETH_P_IP)) { ip = (u64 __force)ip_hdr(skb)->saddr; bucket = &table_v4[hsiphash_2u32(net_word, ip, &key) & (table_size - 1)]; } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { /* Only use 64 bits, so as to ratelimit the whole /64. */ memcpy(&ip, &ipv6_hdr(skb)->saddr, sizeof(ip)); bucket = &table_v6[hsiphash_3u32(net_word, ip >> 32, ip, &key) & (table_size - 1)]; } #endif else return false; rcu_read_lock(); hlist_for_each_entry_rcu(entry, bucket, hash) { if (entry->net == net && entry->ip == ip) { u64 now, tokens; bool ret; /* Quasi-inspired by nft_limit.c, but this is actually a * slightly different algorithm. Namely, we incorporate * the burst as part of the maximum tokens, rather than * as part of the rate. */ spin_lock(&entry->lock); now = ktime_get_coarse_boottime_ns(); tokens = min_t(u64, TOKEN_MAX, entry->tokens + now - entry->last_time_ns); entry->last_time_ns = now; ret = tokens >= PACKET_COST; entry->tokens = ret ? tokens - PACKET_COST : tokens; spin_unlock(&entry->lock); rcu_read_unlock(); return ret; } } rcu_read_unlock(); if (atomic_inc_return(&total_entries) > max_entries) goto err_oom; entry = kmem_cache_alloc(entry_cache, GFP_KERNEL); if (unlikely(!entry)) goto err_oom; entry->net = net; entry->ip = ip; INIT_HLIST_NODE(&entry->hash); spin_lock_init(&entry->lock); entry->last_time_ns = ktime_get_coarse_boottime_ns(); entry->tokens = TOKEN_MAX - PACKET_COST; spin_lock(&table_lock); hlist_add_head_rcu(&entry->hash, bucket); spin_unlock(&table_lock); return true; err_oom: atomic_dec(&total_entries); return false; } int wg_ratelimiter_init(void) { mutex_lock(&init_lock); if (++init_refcnt != 1) goto out; entry_cache = KMEM_CACHE(ratelimiter_entry, 0); if (!entry_cache) goto err; /* xt_hashlimit.c uses a slightly different algorithm for ratelimiting, * but what it shares in common is that it uses a massive hashtable. So, * we borrow their wisdom about good table sizes on different systems * dependent on RAM. This calculation here comes from there. */ table_size = (totalram_pages() > (1U << 30) / PAGE_SIZE) ? 8192 : max_t(unsigned long, 16, roundup_pow_of_two( (totalram_pages() << PAGE_SHIFT) / (1U << 14) / sizeof(struct hlist_head))); max_entries = table_size * 8; table_v4 = kvcalloc(table_size, sizeof(*table_v4), GFP_KERNEL); if (unlikely(!table_v4)) goto err_kmemcache; #if IS_ENABLED(CONFIG_IPV6) table_v6 = kvcalloc(table_size, sizeof(*table_v6), GFP_KERNEL); if (unlikely(!table_v6)) { kvfree(table_v4); goto err_kmemcache; } #endif queue_delayed_work(system_power_efficient_wq, &gc_work, HZ); get_random_bytes(&key, sizeof(key)); out: mutex_unlock(&init_lock); return 0; err_kmemcache: kmem_cache_destroy(entry_cache); err: --init_refcnt; mutex_unlock(&init_lock); return -ENOMEM; } void wg_ratelimiter_uninit(void) { mutex_lock(&init_lock); if (!init_refcnt || --init_refcnt) goto out; cancel_delayed_work_sync(&gc_work); wg_ratelimiter_gc_entries(NULL); rcu_barrier(); kvfree(table_v4); #if IS_ENABLED(CONFIG_IPV6) kvfree(table_v6); #endif kmem_cache_destroy(entry_cache); out: mutex_unlock(&init_lock); } #include "selftest/ratelimiter.c" |
| 3933 2791 1605 265 1866 2884 805 1739 1992 3328 40 40 3328 945 2496 906 2543 946 3329 3035 298 2548 947 2495 907 2428 945 220 157 3323 93 317 3322 741 93 3325 1959 1502 3275 93 2 86 3928 2 3928 42 41 42 41 42 3 40 652 652 651 3325 7 7 4 3 86 86 86 73 14 3327 43 86 81 6 340 1 2091 683 2105 416 2030 1736 48 1598 2378 88 29 12 5 15 6 5 1927 332 885 1062 888 1713 443 762 212 117 76 337 492 763 3 4 3 10 1410 38 13 2 22 10 1 28 1315 1412 51 28 4 7 12 60 3 2 3326 54 2 2 2 2 2 3327 3326 3330 3324 3330 3328 3283 54 3323 3327 3330 3102 935 2390 2423 36 28 1739 1562 89 171 29 15 1468 65 305 2630 2032 33 40 26 48 33 40 58 7 5 12 24 22 27 8 63 33 39 76 40 49 248 3 245 8 5 4 8 8 7 7 2 2 7 2 6 6 2 1 2 2 17 7 50 2 68 11 146 142 282 121 305 769 10 10 762 768 9 9 9 9 5 51 2085 43 2094 40 2096 40 86 7 397 16 66 674 320 191 196 543 161 92 200 373 266 58 89 26 1036 167 167 507 128 10 119 17 1 380 383 3 3 310 274 3325 3330 3329 3325 3326 3329 3330 157 643 644 643 1 157 157 157 156 157 157 645 54 3325 317 3322 3282 54 317 3321 3326 3325 3328 3324 3326 3329 317 3019 3327 317 3325 3326 3326 3906 108 55 2560 37 20 32 2 18 2 30 32 55 2651 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * BPF JIT compiler * * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com) * Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/netdevice.h> #include <linux/filter.h> #include <linux/if_vlan.h> #include <linux/bpf.h> #include <linux/memory.h> #include <linux/sort.h> #include <asm/extable.h> #include <asm/ftrace.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> #include <asm/text-patching.h> #include <asm/unwind.h> #include <asm/cfi.h> static bool all_callee_regs_used[4] = {true, true, true, true}; static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { if (len == 1) *ptr = bytes; else if (len == 2) *(u16 *)ptr = bytes; else { *(u32 *)ptr = bytes; barrier(); } return ptr + len; } #define EMIT(bytes, len) \ do { prog = emit_code(prog, bytes, len); } while (0) #define EMIT1(b1) EMIT(b1, 1) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) #define EMIT5(b1, b2, b3, b4, b5) \ do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0) #define EMIT1_off32(b1, off) \ do { EMIT1(b1); EMIT(off, 4); } while (0) #define EMIT2_off32(b1, b2, off) \ do { EMIT2(b1, b2); EMIT(off, 4); } while (0) #define EMIT3_off32(b1, b2, b3, off) \ do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0) #define EMIT4_off32(b1, b2, b3, b4, off) \ do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) #ifdef CONFIG_X86_KERNEL_IBT #define EMIT_ENDBR() EMIT(gen_endbr(), 4) #define EMIT_ENDBR_POISON() EMIT(gen_endbr_poison(), 4) #else #define EMIT_ENDBR() #define EMIT_ENDBR_POISON() #endif static bool is_imm8(int value) { return value <= 127 && value >= -128; } /* * Let us limit the positive offset to be <= 123. * This is to ensure eventual jit convergence For the following patterns: * ... * pass4, final_proglen=4391: * ... * 20e: 48 85 ff test rdi,rdi * 211: 74 7d je 0x290 * 213: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] * ... * 289: 48 85 ff test rdi,rdi * 28c: 74 17 je 0x2a5 * 28e: e9 7f ff ff ff jmp 0x212 * 293: bf 03 00 00 00 mov edi,0x3 * Note that insn at 0x211 is 2-byte cond jump insn for offset 0x7d (-125) * and insn at 0x28e is 5-byte jmp insn with offset -129. * * pass5, final_proglen=4392: * ... * 20e: 48 85 ff test rdi,rdi * 211: 0f 84 80 00 00 00 je 0x297 * 217: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] * ... * 28d: 48 85 ff test rdi,rdi * 290: 74 1a je 0x2ac * 292: eb 84 jmp 0x218 * 294: bf 03 00 00 00 mov edi,0x3 * Note that insn at 0x211 is 6-byte cond jump insn now since its offset * becomes 0x80 based on previous round (0x293 - 0x213 = 0x80). * At the same time, insn at 0x292 is a 2-byte insn since its offset is * -124. * * pass6 will repeat the same code as in pass4 and this will prevent * eventual convergence. * * To fix this issue, we need to break je (2->6 bytes) <-> jmp (5->2 bytes) * cycle in the above. In the above example je offset <= 0x7c should work. * * For other cases, je <-> je needs offset <= 0x7b to avoid no convergence * issue. For jmp <-> je and jmp <-> jmp cases, jmp offset <= 0x7c should * avoid no convergence issue. * * Overall, let us limit the positive offset for 8bit cond/uncond jmp insn * to maximum 123 (0x7b). This way, the jit pass can eventually converge. */ static bool is_imm8_jmp_offset(int value) { return value <= 123 && value >= -128; } static bool is_simm32(s64 value) { return value == (s64)(s32)value; } static bool is_uimm32(u64 value) { return value == (u64)(u32)value; } /* mov dst, src */ #define EMIT_mov(DST, SRC) \ do { \ if (DST != SRC) \ EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \ } while (0) static int bpf_size_to_x86_bytes(int bpf_size) { if (bpf_size == BPF_W) return 4; else if (bpf_size == BPF_H) return 2; else if (bpf_size == BPF_B) return 1; else if (bpf_size == BPF_DW) return 4; /* imm32 */ else return 0; } /* * List of x86 cond jumps opcodes (. + s8) * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32) */ #define X86_JB 0x72 #define X86_JAE 0x73 #define X86_JE 0x74 #define X86_JNE 0x75 #define X86_JBE 0x76 #define X86_JA 0x77 #define X86_JL 0x7C #define X86_JGE 0x7D #define X86_JLE 0x7E #define X86_JG 0x7F /* Pick a register outside of BPF range for JIT internal work */ #define AUX_REG (MAX_BPF_JIT_REG + 1) #define X86_REG_R9 (MAX_BPF_JIT_REG + 2) #define X86_REG_R12 (MAX_BPF_JIT_REG + 3) /* * The following table maps BPF registers to x86-64 registers. * * x86-64 register R12 is unused, since if used as base address * register in load/store instructions, it always needs an * extra byte of encoding and is callee saved. * * x86-64 register R9 is not used by BPF programs, but can be used by BPF * trampoline. x86-64 register R10 is used for blinding (if enabled). */ static const int reg2hex[] = { [BPF_REG_0] = 0, /* RAX */ [BPF_REG_1] = 7, /* RDI */ [BPF_REG_2] = 6, /* RSI */ [BPF_REG_3] = 2, /* RDX */ [BPF_REG_4] = 1, /* RCX */ [BPF_REG_5] = 0, /* R8 */ [BPF_REG_6] = 3, /* RBX callee saved */ [BPF_REG_7] = 5, /* R13 callee saved */ [BPF_REG_8] = 6, /* R14 callee saved */ [BPF_REG_9] = 7, /* R15 callee saved */ [BPF_REG_FP] = 5, /* RBP readonly */ [BPF_REG_AX] = 2, /* R10 temp register */ [AUX_REG] = 3, /* R11 temp register */ [X86_REG_R9] = 1, /* R9 register, 6th function argument */ [X86_REG_R12] = 4, /* R12 callee saved */ }; static const int reg2pt_regs[] = { [BPF_REG_0] = offsetof(struct pt_regs, ax), [BPF_REG_1] = offsetof(struct pt_regs, di), [BPF_REG_2] = offsetof(struct pt_regs, si), [BPF_REG_3] = offsetof(struct pt_regs, dx), [BPF_REG_4] = offsetof(struct pt_regs, cx), [BPF_REG_5] = offsetof(struct pt_regs, r8), [BPF_REG_6] = offsetof(struct pt_regs, bx), [BPF_REG_7] = offsetof(struct pt_regs, r13), [BPF_REG_8] = offsetof(struct pt_regs, r14), [BPF_REG_9] = offsetof(struct pt_regs, r15), }; /* * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15 * which need extra byte of encoding. * rax,rcx,...,rbp have simpler encoding */ static bool is_ereg(u32 reg) { return (1 << reg) & (BIT(BPF_REG_5) | BIT(AUX_REG) | BIT(BPF_REG_7) | BIT(BPF_REG_8) | BIT(BPF_REG_9) | BIT(X86_REG_R9) | BIT(X86_REG_R12) | BIT(BPF_REG_AX)); } /* * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64 * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte * of encoding. al,cl,dl,bl have simpler encoding. */ static bool is_ereg_8l(u32 reg) { return is_ereg(reg) || (1 << reg) & (BIT(BPF_REG_1) | BIT(BPF_REG_2) | BIT(BPF_REG_FP)); } static bool is_axreg(u32 reg) { return reg == BPF_REG_0; } /* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */ static u8 add_1mod(u8 byte, u32 reg) { if (is_ereg(reg)) byte |= 1; return byte; } static u8 add_2mod(u8 byte, u32 r1, u32 r2) { if (is_ereg(r1)) byte |= 1; if (is_ereg(r2)) byte |= 4; return byte; } static u8 add_3mod(u8 byte, u32 r1, u32 r2, u32 index) { if (is_ereg(r1)) byte |= 1; if (is_ereg(index)) byte |= 2; if (is_ereg(r2)) byte |= 4; return byte; } /* Encode 'dst_reg' register into x86-64 opcode 'byte' */ static u8 add_1reg(u8 byte, u32 dst_reg) { return byte + reg2hex[dst_reg]; } /* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) { return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3); } /* Some 1-byte opcodes for binary ALU operations */ static u8 simple_alu_opcodes[] = { [BPF_ADD] = 0x01, [BPF_SUB] = 0x29, [BPF_AND] = 0x21, [BPF_OR] = 0x09, [BPF_XOR] = 0x31, [BPF_LSH] = 0xE0, [BPF_RSH] = 0xE8, [BPF_ARSH] = 0xF8, }; static void jit_fill_hole(void *area, unsigned int size) { /* Fill whole space with INT3 instructions */ memset(area, 0xcc, size); } int bpf_arch_text_invalidate(void *dst, size_t len) { return IS_ERR_OR_NULL(text_poke_set(dst, 0xcc, len)); } struct jit_context { int cleanup_addr; /* Epilogue code offset */ /* * Program specific offsets of labels in the code; these rely on the * JIT doing at least 2 passes, recording the position on the first * pass, only to generate the correct offset on the second pass. */ int tail_call_direct_label; int tail_call_indirect_label; }; /* Maximum number of bytes emitted while JITing one eBPF insn */ #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 /* Number of bytes emit_patch() needs to generate instructions */ #define X86_PATCH_SIZE 5 /* Number of bytes that will be skipped on tailcall */ #define X86_TAIL_CALL_OFFSET (12 + ENDBR_INSN_SIZE) static void push_r9(u8 **pprog) { u8 *prog = *pprog; EMIT2(0x41, 0x51); /* push r9 */ *pprog = prog; } static void pop_r9(u8 **pprog) { u8 *prog = *pprog; EMIT2(0x41, 0x59); /* pop r9 */ *pprog = prog; } static void push_r12(u8 **pprog) { u8 *prog = *pprog; EMIT2(0x41, 0x54); /* push r12 */ *pprog = prog; } static void push_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; if (callee_regs_used[0]) EMIT1(0x53); /* push rbx */ if (callee_regs_used[1]) EMIT2(0x41, 0x55); /* push r13 */ if (callee_regs_used[2]) EMIT2(0x41, 0x56); /* push r14 */ if (callee_regs_used[3]) EMIT2(0x41, 0x57); /* push r15 */ *pprog = prog; } static void pop_r12(u8 **pprog) { u8 *prog = *pprog; EMIT2(0x41, 0x5C); /* pop r12 */ *pprog = prog; } static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; if (callee_regs_used[3]) EMIT2(0x41, 0x5F); /* pop r15 */ if (callee_regs_used[2]) EMIT2(0x41, 0x5E); /* pop r14 */ if (callee_regs_used[1]) EMIT2(0x41, 0x5D); /* pop r13 */ if (callee_regs_used[0]) EMIT1(0x5B); /* pop rbx */ *pprog = prog; } static void emit_nops(u8 **pprog, int len) { u8 *prog = *pprog; int i, noplen; while (len > 0) { noplen = len; if (noplen > ASM_NOP_MAX) noplen = ASM_NOP_MAX; for (i = 0; i < noplen; i++) EMIT1(x86_nops[noplen][i]); len -= noplen; } *pprog = prog; } /* * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT * in arch/x86/kernel/alternative.c */ static int emit_call(u8 **prog, void *func, void *ip); static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity) { u8 *prog = *pprog; EMIT_ENDBR(); EMIT3_off32(0x41, 0x81, 0xea, hash); /* subl $hash, %r10d */ if (cfi_bhi) { emit_call(&prog, __bhi_args[arity], ip + 11); } else { EMIT2(0x75, 0xf9); /* jne.d8 .-7 */ EMIT3(0x0f, 0x1f, 0x00); /* nop3 */ } EMIT_ENDBR_POISON(); *pprog = prog; } static void emit_kcfi(u8 **pprog, u32 hash) { u8 *prog = *pprog; EMIT1_off32(0xb8, hash); /* movl $hash, %eax */ #ifdef CONFIG_CALL_PADDING EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); EMIT1(0x90); #endif EMIT_ENDBR(); *pprog = prog; } static void emit_cfi(u8 **pprog, u8 *ip, u32 hash, int arity) { u8 *prog = *pprog; switch (cfi_mode) { case CFI_FINEIBT: emit_fineibt(&prog, ip, hash, arity); break; case CFI_KCFI: emit_kcfi(&prog, hash); break; default: EMIT_ENDBR(); break; } *pprog = prog; } static void emit_prologue_tail_call(u8 **pprog, bool is_subprog) { u8 *prog = *pprog; if (!is_subprog) { /* cmp rax, MAX_TAIL_CALL_CNT */ EMIT4(0x48, 0x83, 0xF8, MAX_TAIL_CALL_CNT); EMIT2(X86_JA, 6); /* ja 6 */ /* rax is tail_call_cnt if <= MAX_TAIL_CALL_CNT. * case1: entry of main prog. * case2: tail callee of main prog. */ EMIT1(0x50); /* push rax */ /* Make rax as tail_call_cnt_ptr. */ EMIT3(0x48, 0x89, 0xE0); /* mov rax, rsp */ EMIT2(0xEB, 1); /* jmp 1 */ /* rax is tail_call_cnt_ptr if > MAX_TAIL_CALL_CNT. * case: tail callee of subprog. */ EMIT1(0x50); /* push rax */ /* push tail_call_cnt_ptr */ EMIT1(0x50); /* push rax */ } else { /* is_subprog */ /* rax is tail_call_cnt_ptr. */ EMIT1(0x50); /* push rax */ EMIT1(0x50); /* push rax */ } *pprog = prog; } /* * Emit x86-64 prologue code for BPF program. * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes * while jumping to another program */ static void emit_prologue(u8 **pprog, u8 *ip, u32 stack_depth, bool ebpf_from_cbpf, bool tail_call_reachable, bool is_subprog, bool is_exception_cb) { u8 *prog = *pprog; if (is_subprog) { emit_cfi(&prog, ip, cfi_bpf_subprog_hash, 5); } else { emit_cfi(&prog, ip, cfi_bpf_hash, 1); } /* BPF trampoline can be made to work without these nops, * but let's waste 5 bytes for now and optimize later */ emit_nops(&prog, X86_PATCH_SIZE); if (!ebpf_from_cbpf) { if (tail_call_reachable && !is_subprog) /* When it's the entry of the whole tailcall context, * zeroing rax means initialising tail_call_cnt. */ EMIT3(0x48, 0x31, 0xC0); /* xor rax, rax */ else /* Keep the same instruction layout. */ emit_nops(&prog, 3); /* nop3 */ } /* Exception callback receives FP as third parameter */ if (is_exception_cb) { EMIT3(0x48, 0x89, 0xF4); /* mov rsp, rsi */ EMIT3(0x48, 0x89, 0xD5); /* mov rbp, rdx */ /* The main frame must have exception_boundary as true, so we * first restore those callee-saved regs from stack, before * reusing the stack frame. */ pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); /* Reset the stack frame. */ EMIT3(0x48, 0x89, 0xEC); /* mov rsp, rbp */ } else { EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ } /* X86_TAIL_CALL_OFFSET is here */ EMIT_ENDBR(); /* sub rsp, rounded_stack_depth */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8)); if (tail_call_reachable) emit_prologue_tail_call(&prog, is_subprog); *pprog = prog; } static int emit_patch(u8 **pprog, void *func, void *ip, u8 opcode) { u8 *prog = *pprog; s64 offset; offset = func - (ip + X86_PATCH_SIZE); if (!is_simm32(offset)) { pr_err("Target call %p is out of range\n", func); return -ERANGE; } EMIT1_off32(opcode, offset); *pprog = prog; return 0; } static int emit_call(u8 **pprog, void *func, void *ip) { return emit_patch(pprog, func, ip, 0xE8); } static int emit_rsb_call(u8 **pprog, void *func, void *ip) { OPTIMIZER_HIDE_VAR(func); ip += x86_call_depth_emit_accounting(pprog, func, ip); return emit_patch(pprog, func, ip, 0xE8); } static int emit_jump(u8 **pprog, void *func, void *ip) { return emit_patch(pprog, func, ip, 0xE9); } static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { const u8 *nop_insn = x86_nops[5]; u8 old_insn[X86_PATCH_SIZE]; u8 new_insn[X86_PATCH_SIZE]; u8 *prog; int ret; memcpy(old_insn, nop_insn, X86_PATCH_SIZE); if (old_addr) { prog = old_insn; ret = t == BPF_MOD_CALL ? emit_call(&prog, old_addr, ip) : emit_jump(&prog, old_addr, ip); if (ret) return ret; } memcpy(new_insn, nop_insn, X86_PATCH_SIZE); if (new_addr) { prog = new_insn; ret = t == BPF_MOD_CALL ? emit_call(&prog, new_addr, ip) : emit_jump(&prog, new_addr, ip); if (ret) return ret; } ret = -EBUSY; mutex_lock(&text_mutex); if (memcmp(ip, old_insn, X86_PATCH_SIZE)) goto out; ret = 1; if (memcmp(ip, new_insn, X86_PATCH_SIZE)) { smp_text_poke_single(ip, new_insn, X86_PATCH_SIZE, NULL); ret = 0; } out: mutex_unlock(&text_mutex); return ret; } int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { if (!is_kernel_text((long)ip) && !is_bpf_text_address((long)ip)) /* BPF poking in modules is not supported */ return -EINVAL; /* * See emit_prologue(), for IBT builds the trampoline hook is preceded * with an ENDBR instruction. */ if (is_endbr(ip)) ip += ENDBR_INSN_SIZE; return __bpf_arch_text_poke(ip, t, old_addr, new_addr); } #define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8) static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { u8 *prog = *pprog; if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) { OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, its_static_thunk(reg), ip); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { OPTIMIZER_HIDE_VAR(reg); if (cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) emit_jump(&prog, &__x86_indirect_jump_thunk_array[reg], ip); else emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else { EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */ if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || IS_ENABLED(CONFIG_MITIGATION_SLS)) EMIT1(0xCC); /* int3 */ } *pprog = prog; } static void emit_return(u8 **pprog, u8 *ip) { u8 *prog = *pprog; if (cpu_wants_rethunk()) { emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ if (IS_ENABLED(CONFIG_MITIGATION_SLS)) EMIT1(0xCC); /* int3 */ } *pprog = prog; } #define BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack) (-16 - round_up(stack, 8)) /* * Generate the following code: * * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... * if (index >= array->map.max_entries) * goto out; * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT) * goto out; * prog = array->ptrs[index]; * if (prog == NULL) * goto out; * goto *(prog->bpf_func + prologue_size); * out: */ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, u8 **pprog, bool *callee_regs_used, u32 stack_depth, u8 *ip, struct jit_context *ctx) { int tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack_depth); u8 *prog = *pprog, *start = *pprog; int offset; /* * rdi - pointer to ctx * rsi - pointer to bpf_array * rdx - index in bpf_array */ /* * if (index >= array->map.max_entries) * goto out; */ EMIT2(0x89, 0xD2); /* mov edx, edx */ EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); offset = ctx->tail_call_indirect_label - (prog + 2 - start); EMIT2(X86_JBE, offset); /* jbe out */ /* * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT3_off32(0x48, 0x8B, 0x85, tcc_ptr_off); /* mov rax, qword ptr [rbp - tcc_ptr_off] */ EMIT4(0x48, 0x83, 0x38, MAX_TAIL_CALL_CNT); /* cmp qword ptr [rax], MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_indirect_label - (prog + 2 - start); EMIT2(X86_JAE, offset); /* jae out */ /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6, /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */ offsetof(struct bpf_array, ptrs)); /* * if (prog == NULL) * goto out; */ EMIT3(0x48, 0x85, 0xC9); /* test rcx,rcx */ offset = ctx->tail_call_indirect_label - (prog + 2 - start); EMIT2(X86_JE, offset); /* je out */ /* Inc tail_call_cnt if the slot is populated. */ EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */ if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena)) pop_r12(&prog); } /* Pop tail_call_cnt_ptr. */ EMIT1(0x58); /* pop rax */ /* Pop tail_call_cnt, if it's main prog. * Pop tail_call_cnt_ptr, if it's subprog. */ EMIT1(0x58); /* pop rax */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, /* add rsp, sd */ round_up(stack_depth, 8)); /* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */ EMIT4(0x48, 0x8B, 0x49, /* mov rcx, qword ptr [rcx + 32] */ offsetof(struct bpf_prog, bpf_func)); EMIT4(0x48, 0x83, 0xC1, /* add rcx, X86_TAIL_CALL_OFFSET */ X86_TAIL_CALL_OFFSET); /* * Now we're ready to jump into next BPF program * rdi == ctx (1st arg) * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET */ emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start)); /* out: */ ctx->tail_call_indirect_label = prog - start; *pprog = prog; } static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, struct bpf_jit_poke_descriptor *poke, u8 **pprog, u8 *ip, bool *callee_regs_used, u32 stack_depth, struct jit_context *ctx) { int tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack_depth); u8 *prog = *pprog, *start = *pprog; int offset; /* * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT3_off32(0x48, 0x8B, 0x85, tcc_ptr_off); /* mov rax, qword ptr [rbp - tcc_ptr_off] */ EMIT4(0x48, 0x83, 0x38, MAX_TAIL_CALL_CNT); /* cmp qword ptr [rax], MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_direct_label - (prog + 2 - start); EMIT2(X86_JAE, offset); /* jae out */ poke->tailcall_bypass = ip + (prog - start); poke->adj_off = X86_TAIL_CALL_OFFSET; poke->tailcall_target = ip + ctx->tail_call_direct_label - X86_PATCH_SIZE; poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE; emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE, poke->tailcall_bypass); /* Inc tail_call_cnt if the slot is populated. */ EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */ if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena)) pop_r12(&prog); } /* Pop tail_call_cnt_ptr. */ EMIT1(0x58); /* pop rax */ /* Pop tail_call_cnt, if it's main prog. * Pop tail_call_cnt_ptr, if it's subprog. */ EMIT1(0x58); /* pop rax */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8)); emit_nops(&prog, X86_PATCH_SIZE); /* out: */ ctx->tail_call_direct_label = prog - start; *pprog = prog; } static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) { struct bpf_jit_poke_descriptor *poke; struct bpf_array *array; struct bpf_prog *target; int i, ret; for (i = 0; i < prog->aux->size_poke_tab; i++) { poke = &prog->aux->poke_tab[i]; if (poke->aux && poke->aux != prog->aux) continue; WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable)); if (poke->reason != BPF_POKE_REASON_TAIL_CALL) continue; array = container_of(poke->tail_call.map, struct bpf_array, map); mutex_lock(&array->aux->poke_mutex); target = array->ptrs[poke->tail_call.key]; if (target) { ret = __bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, NULL, (u8 *)target->bpf_func + poke->adj_off); BUG_ON(ret < 0); ret = __bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, (u8 *)poke->tailcall_target + X86_PATCH_SIZE, NULL); BUG_ON(ret < 0); } WRITE_ONCE(poke->tailcall_target_stable, true); mutex_unlock(&array->aux->poke_mutex); } } static void emit_mov_imm32(u8 **pprog, bool sign_propagate, u32 dst_reg, const u32 imm32) { u8 *prog = *pprog; u8 b1, b2, b3; /* * Optimization: if imm32 is positive, use 'mov %eax, imm32' * (which zero-extends imm32) to save 2 bytes. */ if (sign_propagate && (s32)imm32 < 0) { /* 'mov %rax, imm32' sign extends imm32 */ b1 = add_1mod(0x48, dst_reg); b2 = 0xC7; b3 = 0xC0; EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32); goto done; } /* * Optimization: if imm32 is zero, use 'xor %eax, %eax' * to save 3 bytes. */ if (imm32 == 0) { if (is_ereg(dst_reg)) EMIT1(add_2mod(0x40, dst_reg, dst_reg)); b2 = 0x31; /* xor */ b3 = 0xC0; EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); goto done; } /* mov %eax, imm32 */ if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); EMIT1_off32(add_1reg(0xB8, dst_reg), imm32); done: *pprog = prog; } static void emit_mov_imm64(u8 **pprog, u32 dst_reg, const u32 imm32_hi, const u32 imm32_lo) { u64 imm64 = ((u64)imm32_hi << 32) | (u32)imm32_lo; u8 *prog = *pprog; if (is_uimm32(imm64)) { /* * For emitting plain u32, where sign bit must not be * propagated LLVM tends to load imm64 over mov32 * directly, so save couple of bytes by just doing * 'mov %eax, imm32' instead. */ emit_mov_imm32(&prog, false, dst_reg, imm32_lo); } else if (is_simm32(imm64)) { emit_mov_imm32(&prog, true, dst_reg, imm32_lo); } else { /* movabsq rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); EMIT(imm32_lo, 4); EMIT(imm32_hi, 4); } *pprog = prog; } static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) { u8 *prog = *pprog; if (is64) { /* mov dst, src */ EMIT_mov(dst_reg, src_reg); } else { /* mov32 dst, src */ if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT1(add_2mod(0x40, dst_reg, src_reg)); EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg)); } *pprog = prog; } static void emit_movsx_reg(u8 **pprog, int num_bits, bool is64, u32 dst_reg, u32 src_reg) { u8 *prog = *pprog; if (is64) { /* movs[b,w,l]q dst, src */ if (num_bits == 8) EMIT4(add_2mod(0x48, src_reg, dst_reg), 0x0f, 0xbe, add_2reg(0xC0, src_reg, dst_reg)); else if (num_bits == 16) EMIT4(add_2mod(0x48, src_reg, dst_reg), 0x0f, 0xbf, add_2reg(0xC0, src_reg, dst_reg)); else if (num_bits == 32) EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x63, add_2reg(0xC0, src_reg, dst_reg)); } else { /* movs[b,w]l dst, src */ if (num_bits == 8) { EMIT4(add_2mod(0x40, src_reg, dst_reg), 0x0f, 0xbe, add_2reg(0xC0, src_reg, dst_reg)); } else if (num_bits == 16) { if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT1(add_2mod(0x40, src_reg, dst_reg)); EMIT3(add_2mod(0x0f, src_reg, dst_reg), 0xbf, add_2reg(0xC0, src_reg, dst_reg)); } } *pprog = prog; } /* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */ static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off) { u8 *prog = *pprog; if (is_imm8(off)) { /* 1-byte signed displacement. * * If off == 0 we could skip this and save one extra byte, but * special case of x86 R13 which always needs an offset is not * worth the hassle */ EMIT2(add_2reg(0x40, ptr_reg, val_reg), off); } else { /* 4-byte signed displacement */ EMIT1_off32(add_2reg(0x80, ptr_reg, val_reg), off); } *pprog = prog; } static void emit_insn_suffix_SIB(u8 **pprog, u32 ptr_reg, u32 val_reg, u32 index_reg, int off) { u8 *prog = *pprog; if (is_imm8(off)) { EMIT3(add_2reg(0x44, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off); } else { EMIT2_off32(add_2reg(0x84, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off); } *pprog = prog; } /* * Emit a REX byte if it will be necessary to address these registers */ static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64) { u8 *prog = *pprog; if (is64) EMIT1(add_2mod(0x48, dst_reg, src_reg)); else if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT1(add_2mod(0x40, dst_reg, src_reg)); *pprog = prog; } /* * Similar version of maybe_emit_mod() for a single register */ static void maybe_emit_1mod(u8 **pprog, u32 reg, bool is64) { u8 *prog = *pprog; if (is64) EMIT1(add_1mod(0x48, reg)); else if (is_ereg(reg)) EMIT1(add_1mod(0x40, reg)); *pprog = prog; } /* LDX: dst_reg = *(u8*)(src_reg + off) */ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { u8 *prog = *pprog; switch (size) { case BPF_B: /* Emit 'movzx rax, byte ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6); break; case BPF_H: /* Emit 'movzx rax, word ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7); break; case BPF_W: /* Emit 'mov eax, dword ptr [rax+0x14]' */ if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B); else EMIT1(0x8B); break; case BPF_DW: /* Emit 'mov rax, qword ptr [rax+0x14]' */ EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); break; } emit_insn_suffix(&prog, src_reg, dst_reg, off); *pprog = prog; } /* LDSX: dst_reg = *(s8*)(src_reg + off) */ static void emit_ldsx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { u8 *prog = *pprog; switch (size) { case BPF_B: /* Emit 'movsx rax, byte ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBE); break; case BPF_H: /* Emit 'movsx rax, word ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xBF); break; case BPF_W: /* Emit 'movsx rax, dword ptr [rax+0x14]' */ EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x63); break; } emit_insn_suffix(&prog, src_reg, dst_reg, off); *pprog = prog; } static void emit_ldx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) { u8 *prog = *pprog; switch (size) { case BPF_B: /* movzx rax, byte ptr [rax + r12 + off] */ EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB6); break; case BPF_H: /* movzx rax, word ptr [rax + r12 + off] */ EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB7); break; case BPF_W: /* mov eax, dword ptr [rax + r12 + off] */ EMIT2(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x8B); break; case BPF_DW: /* mov rax, qword ptr [rax + r12 + off] */ EMIT2(add_3mod(0x48, src_reg, dst_reg, index_reg), 0x8B); break; } emit_insn_suffix_SIB(&prog, src_reg, dst_reg, index_reg, off); *pprog = prog; } static void emit_ldx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { emit_ldx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off); } /* STX: *(u8*)(dst_reg + off) = src_reg */ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { u8 *prog = *pprog; switch (size) { case BPF_B: /* Emit 'mov byte ptr [rax + off], al' */ if (is_ereg(dst_reg) || is_ereg_8l(src_reg)) /* Add extra byte for eregs or SIL,DIL,BPL in src_reg */ EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else EMIT1(0x88); break; case BPF_H: if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89); else EMIT2(0x66, 0x89); break; case BPF_W: if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89); else EMIT1(0x89); break; case BPF_DW: EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89); break; } emit_insn_suffix(&prog, dst_reg, src_reg, off); *pprog = prog; } /* STX: *(u8*)(dst_reg + index_reg + off) = src_reg */ static void emit_stx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) { u8 *prog = *pprog; switch (size) { case BPF_B: /* mov byte ptr [rax + r12 + off], al */ EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x88); break; case BPF_H: /* mov word ptr [rax + r12 + off], ax */ EMIT3(0x66, add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89); break; case BPF_W: /* mov dword ptr [rax + r12 + 1], eax */ EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89); break; case BPF_DW: /* mov qword ptr [rax + r12 + 1], rax */ EMIT2(add_3mod(0x48, dst_reg, src_reg, index_reg), 0x89); break; } emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off); *pprog = prog; } static void emit_stx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { emit_stx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off); } /* ST: *(u8*)(dst_reg + index_reg + off) = imm32 */ static void emit_st_index(u8 **pprog, u32 size, u32 dst_reg, u32 index_reg, int off, int imm) { u8 *prog = *pprog; switch (size) { case BPF_B: /* mov byte ptr [rax + r12 + off], imm8 */ EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC6); break; case BPF_H: /* mov word ptr [rax + r12 + off], imm16 */ EMIT3(0x66, add_3mod(0x40, dst_reg, 0, index_reg), 0xC7); break; case BPF_W: /* mov dword ptr [rax + r12 + 1], imm32 */ EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC7); break; case BPF_DW: /* mov qword ptr [rax + r12 + 1], imm32 */ EMIT2(add_3mod(0x48, dst_reg, 0, index_reg), 0xC7); break; } emit_insn_suffix_SIB(&prog, dst_reg, 0, index_reg, off); EMIT(imm, bpf_size_to_x86_bytes(size)); *pprog = prog; } static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm) { emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm); } static int emit_atomic_rmw(u8 **pprog, u32 atomic_op, u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) { u8 *prog = *pprog; EMIT1(0xF0); /* lock prefix */ maybe_emit_mod(&prog, dst_reg, src_reg, bpf_size == BPF_DW); /* emit opcode */ switch (atomic_op) { case BPF_ADD: case BPF_AND: case BPF_OR: case BPF_XOR: /* lock *(u32/u64*)(dst_reg + off) <op>= src_reg */ EMIT1(simple_alu_opcodes[atomic_op]); break; case BPF_ADD | BPF_FETCH: /* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */ EMIT2(0x0F, 0xC1); break; case BPF_XCHG: /* src_reg = atomic_xchg(dst_reg + off, src_reg); */ EMIT1(0x87); break; case BPF_CMPXCHG: /* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */ EMIT2(0x0F, 0xB1); break; default: pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); return -EFAULT; } emit_insn_suffix(&prog, dst_reg, src_reg, off); *pprog = prog; return 0; } static int emit_atomic_rmw_index(u8 **pprog, u32 atomic_op, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) { u8 *prog = *pprog; EMIT1(0xF0); /* lock prefix */ switch (size) { case BPF_W: EMIT1(add_3mod(0x40, dst_reg, src_reg, index_reg)); break; case BPF_DW: EMIT1(add_3mod(0x48, dst_reg, src_reg, index_reg)); break; default: pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n"); return -EFAULT; } /* emit opcode */ switch (atomic_op) { case BPF_ADD: case BPF_AND: case BPF_OR: case BPF_XOR: /* lock *(u32/u64*)(dst_reg + idx_reg + off) <op>= src_reg */ EMIT1(simple_alu_opcodes[atomic_op]); break; case BPF_ADD | BPF_FETCH: /* src_reg = atomic_fetch_add(dst_reg + idx_reg + off, src_reg); */ EMIT2(0x0F, 0xC1); break; case BPF_XCHG: /* src_reg = atomic_xchg(dst_reg + idx_reg + off, src_reg); */ EMIT1(0x87); break; case BPF_CMPXCHG: /* r0 = atomic_cmpxchg(dst_reg + idx_reg + off, r0, src_reg); */ EMIT2(0x0F, 0xB1); break; default: pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op); return -EFAULT; } emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off); *pprog = prog; return 0; } static int emit_atomic_ld_st(u8 **pprog, u32 atomic_op, u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) { switch (atomic_op) { case BPF_LOAD_ACQ: /* dst_reg = smp_load_acquire(src_reg + off16) */ emit_ldx(pprog, bpf_size, dst_reg, src_reg, off); break; case BPF_STORE_REL: /* smp_store_release(dst_reg + off16, src_reg) */ emit_stx(pprog, bpf_size, dst_reg, src_reg, off); break; default: pr_err("bpf_jit: unknown atomic load/store opcode %02x\n", atomic_op); return -EFAULT; } return 0; } static int emit_atomic_ld_st_index(u8 **pprog, u32 atomic_op, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) { switch (atomic_op) { case BPF_LOAD_ACQ: /* dst_reg = smp_load_acquire(src_reg + idx_reg + off16) */ emit_ldx_index(pprog, size, dst_reg, src_reg, index_reg, off); break; case BPF_STORE_REL: /* smp_store_release(dst_reg + idx_reg + off16, src_reg) */ emit_stx_index(pprog, size, dst_reg, src_reg, index_reg, off); break; default: pr_err("bpf_jit: unknown atomic load/store opcode %02x\n", atomic_op); return -EFAULT; } return 0; } #define DONT_CLEAR 1 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs) { u32 reg = x->fixup >> 8; /* jump over faulting load and clear dest register */ if (reg != DONT_CLEAR) *(unsigned long *)((void *)regs + reg) = 0; regs->ip += x->fixup & 0xff; return true; } static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt, bool *regs_used) { int i; for (i = 1; i <= insn_cnt; i++, insn++) { if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6) regs_used[0] = true; if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7) regs_used[1] = true; if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8) regs_used[2] = true; if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9) regs_used[3] = true; } } /* emit the 3-byte VEX prefix * * r: same as rex.r, extra bit for ModRM reg field * x: same as rex.x, extra bit for SIB index field * b: same as rex.b, extra bit for ModRM r/m, or SIB base * m: opcode map select, encoding escape bytes e.g. 0x0f38 * w: same as rex.w (32 bit or 64 bit) or opcode specific * src_reg2: additional source reg (encoded as BPF reg) * l: vector length (128 bit or 256 bit) or reserved * pp: opcode prefix (none, 0x66, 0xf2 or 0xf3) */ static void emit_3vex(u8 **pprog, bool r, bool x, bool b, u8 m, bool w, u8 src_reg2, bool l, u8 pp) { u8 *prog = *pprog; const u8 b0 = 0xc4; /* first byte of 3-byte VEX prefix */ u8 b1, b2; u8 vvvv = reg2hex[src_reg2]; /* reg2hex gives only the lower 3 bit of vvvv */ if (is_ereg(src_reg2)) vvvv |= 1 << 3; /* * 2nd byte of 3-byte VEX prefix * ~ means bit inverted encoding * * 7 0 * +---+---+---+---+---+---+---+---+ * |~R |~X |~B | m | * +---+---+---+---+---+---+---+---+ */ b1 = (!r << 7) | (!x << 6) | (!b << 5) | (m & 0x1f); /* * 3rd byte of 3-byte VEX prefix * * 7 0 * +---+---+---+---+---+---+---+---+ * | W | ~vvvv | L | pp | * +---+---+---+---+---+---+---+---+ */ b2 = (w << 7) | ((~vvvv & 0xf) << 3) | (l << 2) | (pp & 3); EMIT3(b0, b1, b2); *pprog = prog; } /* emit BMI2 shift instruction */ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op) { u8 *prog = *pprog; bool r = is_ereg(dst_reg); u8 m = 2; /* escape code 0f38 */ emit_3vex(&prog, r, false, r, m, is64, src_reg, false, op); EMIT2(0xf7, add_2reg(0xC0, dst_reg, dst_reg)); *pprog = prog; } static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr) { u8 *prog = *pprog; /* movabs r9, priv_frame_ptr */ emit_mov_imm64(&prog, X86_REG_R9, (__force long) priv_frame_ptr >> 32, (u32) (__force long) priv_frame_ptr); #ifdef CONFIG_SMP /* add <r9>, gs:[<off>] */ EMIT2(0x65, 0x4c); EMIT3(0x03, 0x0c, 0x25); EMIT((u32)(unsigned long)&this_cpu_off, 4); #endif *pprog = prog; } #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) #define __LOAD_TCC_PTR(off) \ EMIT3_off32(0x48, 0x8B, 0x85, off) /* mov rax, qword ptr [rbp - rounded_stack_depth - 16] */ #define LOAD_TAIL_CALL_CNT_PTR(stack) \ __LOAD_TCC_PTR(BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack)) /* Memory size/value to protect private stack overflow/underflow */ #define PRIV_STACK_GUARD_SZ 8 #define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip, struct bpf_prog *bpf_prog) { u8 *prog = *pprog; u8 *func; if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) { /* The clearing sequence clobbers eax and ecx. */ EMIT1(0x50); /* push rax */ EMIT1(0x51); /* push rcx */ ip += 2; func = (u8 *)clear_bhb_loop; ip += x86_call_depth_emit_accounting(&prog, func, ip); if (emit_call(&prog, func, ip)) return -EINVAL; EMIT1(0x59); /* pop rcx */ EMIT1(0x58); /* pop rax */ } /* Insert IBHF instruction */ if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) && cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) || cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) { /* * Add an Indirect Branch History Fence (IBHF). IBHF acts as a * fence preventing branch history from before the fence from * affecting indirect branches after the fence. This is * specifically used in cBPF jitted code to prevent Intra-mode * BHI attacks. The IBHF instruction is designed to be a NOP on * hardware that doesn't need or support it. The REP and REX.W * prefixes are required by the microcode, and they also ensure * that the NOP is unlikely to be used in existing code. * * IBHF is not a valid instruction in 32-bit mode. */ EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */ } *pprog = prog; return 0; } static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { bool tail_call_reachable = bpf_prog->aux->tail_call_reachable; struct bpf_insn *insn = bpf_prog->insnsi; bool callee_regs_used[4] = {}; int insn_cnt = bpf_prog->len; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; void __percpu *priv_frame_ptr = NULL; u64 arena_vm_start, user_vm_start; void __percpu *priv_stack_ptr; int i, excnt = 0; int ilen, proglen = 0; u8 *prog = temp; u32 stack_depth; int err; stack_depth = bpf_prog->aux->stack_depth; priv_stack_ptr = bpf_prog->aux->priv_stack_ptr; if (priv_stack_ptr) { priv_frame_ptr = priv_stack_ptr + PRIV_STACK_GUARD_SZ + round_up(stack_depth, 8); stack_depth = 0; } arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena); user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena); detect_reg_usage(insn, insn_cnt, callee_regs_used); emit_prologue(&prog, image, stack_depth, bpf_prog_was_classic(bpf_prog), tail_call_reachable, bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb); /* Exception callback will clobber callee regs for its own use, and * restore the original callee regs from main prog's stack frame. */ if (bpf_prog->aux->exception_boundary) { /* We also need to save r12, which is not mapped to any BPF * register, as we throw after entry into the kernel, which may * overwrite r12. */ push_r12(&prog); push_callee_regs(&prog, all_callee_regs_used); } else { if (arena_vm_start) push_r12(&prog); push_callee_regs(&prog, callee_regs_used); } if (arena_vm_start) emit_mov_imm64(&prog, X86_REG_R12, arena_vm_start >> 32, (u32) arena_vm_start); if (priv_frame_ptr) emit_priv_frame_ptr(&prog, priv_frame_ptr); ilen = prog - temp; if (rw_image) memcpy(rw_image + proglen, temp, ilen); proglen += ilen; addrs[0] = proglen; prog = temp; for (i = 1; i <= insn_cnt; i++, insn++) { const s32 imm32 = insn->imm; u32 dst_reg = insn->dst_reg; u32 src_reg = insn->src_reg; u8 b2 = 0, b3 = 0; u8 *start_of_ldx; s64 jmp_offset; s16 insn_off; u8 jmp_cond; u8 *func; int nops; if (priv_frame_ptr) { if (src_reg == BPF_REG_FP) src_reg = X86_REG_R9; if (dst_reg == BPF_REG_FP) dst_reg = X86_REG_R9; } switch (insn->code) { /* ALU */ case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU64 | BPF_ADD | BPF_X: case BPF_ALU64 | BPF_SUB | BPF_X: case BPF_ALU64 | BPF_AND | BPF_X: case BPF_ALU64 | BPF_OR | BPF_X: case BPF_ALU64 | BPF_XOR | BPF_X: maybe_emit_mod(&prog, dst_reg, src_reg, BPF_CLASS(insn->code) == BPF_ALU64); b2 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg)); break; case BPF_ALU64 | BPF_MOV | BPF_X: if (insn_is_cast_user(insn)) { if (dst_reg != src_reg) /* 32-bit mov */ emit_mov_reg(&prog, false, dst_reg, src_reg); /* shl dst_reg, 32 */ maybe_emit_1mod(&prog, dst_reg, true); EMIT3(0xC1, add_1reg(0xE0, dst_reg), 32); /* or dst_reg, user_vm_start */ maybe_emit_1mod(&prog, dst_reg, true); if (is_axreg(dst_reg)) EMIT1_off32(0x0D, user_vm_start >> 32); else EMIT2_off32(0x81, add_1reg(0xC8, dst_reg), user_vm_start >> 32); /* rol dst_reg, 32 */ maybe_emit_1mod(&prog, dst_reg, true); EMIT3(0xC1, add_1reg(0xC0, dst_reg), 32); /* xor r11, r11 */ EMIT3(0x4D, 0x31, 0xDB); /* test dst_reg32, dst_reg32; check if lower 32-bit are zero */ maybe_emit_mod(&prog, dst_reg, dst_reg, false); EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); /* cmove r11, dst_reg; if so, set dst_reg to zero */ /* WARNING: Intel swapped src/dst register encoding in CMOVcc !!! */ maybe_emit_mod(&prog, AUX_REG, dst_reg, true); EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg)); break; } else if (insn_is_mov_percpu_addr(insn)) { /* mov <dst>, <src> (if necessary) */ EMIT_mov(dst_reg, src_reg); #ifdef CONFIG_SMP /* add <dst>, gs:[<off>] */ EMIT2(0x65, add_1mod(0x48, dst_reg)); EMIT3(0x03, add_2reg(0x04, 0, dst_reg), 0x25); EMIT((u32)(unsigned long)&this_cpu_off, 4); #endif break; } fallthrough; case BPF_ALU | BPF_MOV | BPF_X: if (insn->off == 0) emit_mov_reg(&prog, BPF_CLASS(insn->code) == BPF_ALU64, dst_reg, src_reg); else emit_movsx_reg(&prog, insn->off, BPF_CLASS(insn->code) == BPF_ALU64, dst_reg, src_reg); break; /* neg dst */ case BPF_ALU | BPF_NEG: case BPF_ALU64 | BPF_NEG: maybe_emit_1mod(&prog, dst_reg, BPF_CLASS(insn->code) == BPF_ALU64); EMIT2(0xF7, add_1reg(0xD8, dst_reg)); break; case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: maybe_emit_1mod(&prog, dst_reg, BPF_CLASS(insn->code) == BPF_ALU64); /* * b3 holds 'normal' opcode, b2 short form only valid * in case dst is eax/rax. */ switch (BPF_OP(insn->code)) { case BPF_ADD: b3 = 0xC0; b2 = 0x05; break; case BPF_SUB: b3 = 0xE8; b2 = 0x2D; break; case BPF_AND: b3 = 0xE0; b2 = 0x25; break; case BPF_OR: b3 = 0xC8; b2 = 0x0D; break; case BPF_XOR: b3 = 0xF0; b2 = 0x35; break; } if (is_imm8(imm32)) EMIT3(0x83, add_1reg(b3, dst_reg), imm32); else if (is_axreg(dst_reg)) EMIT1_off32(b2, imm32); else EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32); break; case BPF_ALU64 | BPF_MOV | BPF_K: case BPF_ALU | BPF_MOV | BPF_K: emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64, dst_reg, imm32); break; case BPF_LD | BPF_IMM | BPF_DW: emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm); insn++; i++; break; /* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */ case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; if (dst_reg != BPF_REG_0) EMIT1(0x50); /* push rax */ if (dst_reg != BPF_REG_3) EMIT1(0x52); /* push rdx */ if (BPF_SRC(insn->code) == BPF_X) { if (src_reg == BPF_REG_0 || src_reg == BPF_REG_3) { /* mov r11, src_reg */ EMIT_mov(AUX_REG, src_reg); src_reg = AUX_REG; } } else { /* mov r11, imm32 */ EMIT3_off32(0x49, 0xC7, 0xC3, imm32); src_reg = AUX_REG; } if (dst_reg != BPF_REG_0) /* mov rax, dst_reg */ emit_mov_reg(&prog, is64, BPF_REG_0, dst_reg); if (insn->off == 0) { /* * xor edx, edx * equivalent to 'xor rdx, rdx', but one byte less */ EMIT2(0x31, 0xd2); /* div src_reg */ maybe_emit_1mod(&prog, src_reg, is64); EMIT2(0xF7, add_1reg(0xF0, src_reg)); } else { if (BPF_CLASS(insn->code) == BPF_ALU) EMIT1(0x99); /* cdq */ else EMIT2(0x48, 0x99); /* cqo */ /* idiv src_reg */ maybe_emit_1mod(&prog, src_reg, is64); EMIT2(0xF7, add_1reg(0xF8, src_reg)); } if (BPF_OP(insn->code) == BPF_MOD && dst_reg != BPF_REG_3) /* mov dst_reg, rdx */ emit_mov_reg(&prog, is64, dst_reg, BPF_REG_3); else if (BPF_OP(insn->code) == BPF_DIV && dst_reg != BPF_REG_0) /* mov dst_reg, rax */ emit_mov_reg(&prog, is64, dst_reg, BPF_REG_0); if (dst_reg != BPF_REG_3) EMIT1(0x5A); /* pop rdx */ if (dst_reg != BPF_REG_0) EMIT1(0x58); /* pop rax */ break; } case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: maybe_emit_mod(&prog, dst_reg, dst_reg, BPF_CLASS(insn->code) == BPF_ALU64); if (is_imm8(imm32)) /* imul dst_reg, dst_reg, imm8 */ EMIT3(0x6B, add_2reg(0xC0, dst_reg, dst_reg), imm32); else /* imul dst_reg, dst_reg, imm32 */ EMIT2_off32(0x69, add_2reg(0xC0, dst_reg, dst_reg), imm32); break; case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU64 | BPF_MUL | BPF_X: maybe_emit_mod(&prog, src_reg, dst_reg, BPF_CLASS(insn->code) == BPF_ALU64); /* imul dst_reg, src_reg */ EMIT3(0x0F, 0xAF, add_2reg(0xC0, src_reg, dst_reg)); break; /* Shifts */ case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_ARSH | BPF_K: case BPF_ALU64 | BPF_LSH | BPF_K: case BPF_ALU64 | BPF_RSH | BPF_K: case BPF_ALU64 | BPF_ARSH | BPF_K: maybe_emit_1mod(&prog, dst_reg, BPF_CLASS(insn->code) == BPF_ALU64); b3 = simple_alu_opcodes[BPF_OP(insn->code)]; if (imm32 == 1) EMIT2(0xD1, add_1reg(b3, dst_reg)); else EMIT3(0xC1, add_1reg(b3, dst_reg), imm32); break; case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_ARSH | BPF_X: case BPF_ALU64 | BPF_LSH | BPF_X: case BPF_ALU64 | BPF_RSH | BPF_X: case BPF_ALU64 | BPF_ARSH | BPF_X: /* BMI2 shifts aren't better when shift count is already in rcx */ if (boot_cpu_has(X86_FEATURE_BMI2) && src_reg != BPF_REG_4) { /* shrx/sarx/shlx dst_reg, dst_reg, src_reg */ bool w = (BPF_CLASS(insn->code) == BPF_ALU64); u8 op; switch (BPF_OP(insn->code)) { case BPF_LSH: op = 1; /* prefix 0x66 */ break; case BPF_RSH: op = 3; /* prefix 0xf2 */ break; case BPF_ARSH: op = 2; /* prefix 0xf3 */ break; } emit_shiftx(&prog, dst_reg, src_reg, w, op); break; } if (src_reg != BPF_REG_4) { /* common case */ /* Check for bad case when dst_reg == rcx */ if (dst_reg == BPF_REG_4) { /* mov r11, dst_reg */ EMIT_mov(AUX_REG, dst_reg); dst_reg = AUX_REG; } else { EMIT1(0x51); /* push rcx */ } /* mov rcx, src_reg */ EMIT_mov(BPF_REG_4, src_reg); } /* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */ maybe_emit_1mod(&prog, dst_reg, BPF_CLASS(insn->code) == BPF_ALU64); b3 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(0xD3, add_1reg(b3, dst_reg)); if (src_reg != BPF_REG_4) { if (insn->dst_reg == BPF_REG_4) /* mov dst_reg, r11 */ EMIT_mov(insn->dst_reg, AUX_REG); else EMIT1(0x59); /* pop rcx */ } break; case BPF_ALU | BPF_END | BPF_FROM_BE: case BPF_ALU64 | BPF_END | BPF_FROM_LE: switch (imm32) { case 16: /* Emit 'ror %ax, 8' to swap lower 2 bytes */ EMIT1(0x66); if (is_ereg(dst_reg)) EMIT1(0x41); EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8); /* Emit 'movzwl eax, ax' */ if (is_ereg(dst_reg)) EMIT3(0x45, 0x0F, 0xB7); else EMIT2(0x0F, 0xB7); EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); break; case 32: /* Emit 'bswap eax' to swap lower 4 bytes */ if (is_ereg(dst_reg)) EMIT2(0x41, 0x0F); else EMIT1(0x0F); EMIT1(add_1reg(0xC8, dst_reg)); break; case 64: /* Emit 'bswap rax' to swap 8 bytes */ EMIT3(add_1mod(0x48, dst_reg), 0x0F, add_1reg(0xC8, dst_reg)); break; } break; case BPF_ALU | BPF_END | BPF_FROM_LE: switch (imm32) { case 16: /* * Emit 'movzwl eax, ax' to zero extend 16-bit * into 64 bit */ if (is_ereg(dst_reg)) EMIT3(0x45, 0x0F, 0xB7); else EMIT2(0x0F, 0xB7); EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); break; case 32: /* Emit 'mov eax, eax' to clear upper 32-bits */ if (is_ereg(dst_reg)) EMIT1(0x45); EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg)); break; case 64: /* nop */ break; } break; /* speculation barrier */ case BPF_ST | BPF_NOSPEC: EMIT_LFENCE(); break; /* ST: *(u8*)(dst_reg + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: if (is_ereg(dst_reg)) EMIT2(0x41, 0xC6); else EMIT1(0xC6); goto st; case BPF_ST | BPF_MEM | BPF_H: if (is_ereg(dst_reg)) EMIT3(0x66, 0x41, 0xC7); else EMIT2(0x66, 0xC7); goto st; case BPF_ST | BPF_MEM | BPF_W: if (is_ereg(dst_reg)) EMIT2(0x41, 0xC7); else EMIT1(0xC7); goto st; case BPF_ST | BPF_MEM | BPF_DW: EMIT2(add_1mod(0x48, dst_reg), 0xC7); st: if (is_imm8(insn->off)) EMIT2(add_1reg(0x40, dst_reg), insn->off); else EMIT1_off32(add_1reg(0x80, dst_reg), insn->off); EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code))); break; /* STX: *(u8*)(dst_reg + off) = src_reg */ case BPF_STX | BPF_MEM | BPF_B: case BPF_STX | BPF_MEM | BPF_H: case BPF_STX | BPF_MEM | BPF_W: case BPF_STX | BPF_MEM | BPF_DW: emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); break; case BPF_ST | BPF_PROBE_MEM32 | BPF_B: case BPF_ST | BPF_PROBE_MEM32 | BPF_H: case BPF_ST | BPF_PROBE_MEM32 | BPF_W: case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: start_of_ldx = prog; emit_st_r12(&prog, BPF_SIZE(insn->code), dst_reg, insn->off, insn->imm); goto populate_extable; /* LDX: dst_reg = *(u8*)(src_reg + r12 + off) */ case BPF_LDX | BPF_PROBE_MEM32 | BPF_B: case BPF_LDX | BPF_PROBE_MEM32 | BPF_H: case BPF_LDX | BPF_PROBE_MEM32 | BPF_W: case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW: case BPF_STX | BPF_PROBE_MEM32 | BPF_B: case BPF_STX | BPF_PROBE_MEM32 | BPF_H: case BPF_STX | BPF_PROBE_MEM32 | BPF_W: case BPF_STX | BPF_PROBE_MEM32 | BPF_DW: start_of_ldx = prog; if (BPF_CLASS(insn->code) == BPF_LDX) emit_ldx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); else emit_stx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); populate_extable: { struct exception_table_entry *ex; u8 *_insn = image + proglen + (start_of_ldx - temp); s64 delta; if (!bpf_prog->aux->extable) break; if (excnt >= bpf_prog->aux->num_exentries) { pr_err("mem32 extable bug\n"); return -EFAULT; } ex = &bpf_prog->aux->extable[excnt++]; delta = _insn - (u8 *)&ex->insn; /* switch ex to rw buffer for writes */ ex = (void *)rw_image + ((void *)ex - (void *)image); ex->insn = delta; ex->data = EX_TYPE_BPF; ex->fixup = (prog - start_of_ldx) | ((BPF_CLASS(insn->code) == BPF_LDX ? reg2pt_regs[dst_reg] : DONT_CLEAR) << 8); } break; /* LDX: dst_reg = *(u8*)(src_reg + off) */ case BPF_LDX | BPF_MEM | BPF_B: case BPF_LDX | BPF_PROBE_MEM | BPF_B: case BPF_LDX | BPF_MEM | BPF_H: case BPF_LDX | BPF_PROBE_MEM | BPF_H: case BPF_LDX | BPF_MEM | BPF_W: case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: /* LDXS: dst_reg = *(s8*)(src_reg + off) */ case BPF_LDX | BPF_MEMSX | BPF_B: case BPF_LDX | BPF_MEMSX | BPF_H: case BPF_LDX | BPF_MEMSX | BPF_W: case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: insn_off = insn->off; if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE * and * src_reg + insn->off < VSYSCALL_ADDR */ u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR; u8 *end_of_jmp; /* movabsq r10, VSYSCALL_ADDR */ emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32, (u32)(long)VSYSCALL_ADDR); /* mov src_reg, r11 */ EMIT_mov(AUX_REG, src_reg); if (insn->off) { /* add r11, insn->off */ maybe_emit_1mod(&prog, AUX_REG, true); EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); } /* sub r11, r10 */ maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); /* movabsq r10, limit */ emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32, (u32)(long)limit); /* cmp r10, r11 */ maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); /* if unsigned '>', goto load */ EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ emit_mov_imm32(&prog, false, dst_reg, 0); /* jmp byte_after_ldx */ EMIT2(0xEB, 0); /* populate jmp_offset for JAE above to jump to start_of_ldx */ start_of_ldx = prog; end_of_jmp[-1] = start_of_ldx - end_of_jmp; } if (BPF_MODE(insn->code) == BPF_PROBE_MEMSX || BPF_MODE(insn->code) == BPF_MEMSX) emit_ldsx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off); else emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn_off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { struct exception_table_entry *ex; u8 *_insn = image + proglen + (start_of_ldx - temp); s64 delta; /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; if (!bpf_prog->aux->extable) break; if (excnt >= bpf_prog->aux->num_exentries) { pr_err("ex gen bug\n"); return -EFAULT; } ex = &bpf_prog->aux->extable[excnt++]; delta = _insn - (u8 *)&ex->insn; if (!is_simm32(delta)) { pr_err("extable->insn doesn't fit into 32-bit\n"); return -EFAULT; } /* switch ex to rw buffer for writes */ ex = (void *)rw_image + ((void *)ex - (void *)image); ex->insn = delta; ex->data = EX_TYPE_BPF; if (dst_reg > BPF_REG_9) { pr_err("verifier error\n"); return -EFAULT; } /* * Compute size of x86 insn and its target dest x86 register. * ex_handler_bpf() will use lower 8 bits to adjust * pt_regs->ip to jump over this x86 instruction * and upper bits to figure out which pt_regs to zero out. * End result: x86 insn "mov rbx, qword ptr [rax+0x14]" * of 4 bytes will be ignored and rbx will be zero inited. */ ex->fixup = (prog - start_of_ldx) | (reg2pt_regs[dst_reg] << 8); } break; case BPF_STX | BPF_ATOMIC | BPF_B: case BPF_STX | BPF_ATOMIC | BPF_H: if (!bpf_atomic_is_load_store(insn)) { pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n"); return -EFAULT; } fallthrough; case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: if (insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH)) { bool is64 = BPF_SIZE(insn->code) == BPF_DW; u32 real_src_reg = src_reg; u32 real_dst_reg = dst_reg; u8 *branch_target; /* * Can't be implemented with a single x86 insn. * Need to do a CMPXCHG loop. */ /* Will need RAX as a CMPXCHG operand so save R0 */ emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0); if (src_reg == BPF_REG_0) real_src_reg = BPF_REG_AX; if (dst_reg == BPF_REG_0) real_dst_reg = BPF_REG_AX; branch_target = prog; /* Load old value */ emit_ldx(&prog, BPF_SIZE(insn->code), BPF_REG_0, real_dst_reg, insn->off); /* * Perform the (commutative) operation locally, * put the result in the AUX_REG. */ emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0); maybe_emit_mod(&prog, AUX_REG, real_src_reg, is64); EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)], add_2reg(0xC0, AUX_REG, real_src_reg)); /* Attempt to swap in new value */ err = emit_atomic_rmw(&prog, BPF_CMPXCHG, real_dst_reg, AUX_REG, insn->off, BPF_SIZE(insn->code)); if (WARN_ON(err)) return err; /* * ZF tells us whether we won the race. If it's * cleared we need to try again. */ EMIT2(X86_JNE, -(prog - branch_target) - 2); /* Return the pre-modification value */ emit_mov_reg(&prog, is64, real_src_reg, BPF_REG_0); /* Restore R0 after clobbering RAX */ emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX); break; } if (bpf_atomic_is_load_store(insn)) err = emit_atomic_ld_st(&prog, insn->imm, dst_reg, src_reg, insn->off, BPF_SIZE(insn->code)); else err = emit_atomic_rmw(&prog, insn->imm, dst_reg, src_reg, insn->off, BPF_SIZE(insn->code)); if (err) return err; break; case BPF_STX | BPF_PROBE_ATOMIC | BPF_B: case BPF_STX | BPF_PROBE_ATOMIC | BPF_H: if (!bpf_atomic_is_load_store(insn)) { pr_err("bpf_jit: 1- and 2-byte RMW atomics are not supported\n"); return -EFAULT; } fallthrough; case BPF_STX | BPF_PROBE_ATOMIC | BPF_W: case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW: start_of_ldx = prog; if (bpf_atomic_is_load_store(insn)) err = emit_atomic_ld_st_index(&prog, insn->imm, BPF_SIZE(insn->code), dst_reg, src_reg, X86_REG_R12, insn->off); else err = emit_atomic_rmw_index(&prog, insn->imm, BPF_SIZE(insn->code), dst_reg, src_reg, X86_REG_R12, insn->off); if (err) return err; goto populate_extable; /* call */ case BPF_JMP | BPF_CALL: { u8 *ip = image + addrs[i - 1]; func = (u8 *) __bpf_call_base + imm32; if (src_reg == BPF_PSEUDO_CALL && tail_call_reachable) { LOAD_TAIL_CALL_CNT_PTR(stack_depth); ip += 7; } if (!imm32) return -EINVAL; if (priv_frame_ptr) { push_r9(&prog); ip += 2; } ip += x86_call_depth_emit_accounting(&prog, func, ip); if (emit_call(&prog, func, ip)) return -EINVAL; if (priv_frame_ptr) pop_r9(&prog); break; } case BPF_JMP | BPF_TAIL_CALL: if (imm32) emit_bpf_tail_call_direct(bpf_prog, &bpf_prog->aux->poke_tab[imm32 - 1], &prog, image + addrs[i - 1], callee_regs_used, stack_depth, ctx); else emit_bpf_tail_call_indirect(bpf_prog, &prog, callee_regs_used, stack_depth, image + addrs[i - 1], ctx); break; /* cond jump */ case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JSGT | BPF_X: case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: case BPF_JMP | BPF_JSLE | BPF_X: case BPF_JMP32 | BPF_JEQ | BPF_X: case BPF_JMP32 | BPF_JNE | BPF_X: case BPF_JMP32 | BPF_JGT | BPF_X: case BPF_JMP32 | BPF_JLT | BPF_X: case BPF_JMP32 | BPF_JGE | BPF_X: case BPF_JMP32 | BPF_JLE | BPF_X: case BPF_JMP32 | BPF_JSGT | BPF_X: case BPF_JMP32 | BPF_JSLT | BPF_X: case BPF_JMP32 | BPF_JSGE | BPF_X: case BPF_JMP32 | BPF_JSLE | BPF_X: /* cmp dst_reg, src_reg */ maybe_emit_mod(&prog, dst_reg, src_reg, BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x39, add_2reg(0xC0, dst_reg, src_reg)); goto emit_cond_jmp; case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: /* test dst_reg, src_reg */ maybe_emit_mod(&prog, dst_reg, src_reg, BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x85, add_2reg(0xC0, dst_reg, src_reg)); goto emit_cond_jmp; case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: /* test dst_reg, imm32 */ maybe_emit_1mod(&prog, dst_reg, BPF_CLASS(insn->code) == BPF_JMP); EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32); goto emit_cond_jmp; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP32 | BPF_JEQ | BPF_K: case BPF_JMP32 | BPF_JNE | BPF_K: case BPF_JMP32 | BPF_JGT | BPF_K: case BPF_JMP32 | BPF_JLT | BPF_K: case BPF_JMP32 | BPF_JGE | BPF_K: case BPF_JMP32 | BPF_JLE | BPF_K: case BPF_JMP32 | BPF_JSGT | BPF_K: case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: /* test dst_reg, dst_reg to save one extra byte */ if (imm32 == 0) { maybe_emit_mod(&prog, dst_reg, dst_reg, BPF_CLASS(insn->code) == BPF_JMP); EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); goto emit_cond_jmp; } /* cmp dst_reg, imm8/32 */ maybe_emit_1mod(&prog, dst_reg, BPF_CLASS(insn->code) == BPF_JMP); if (is_imm8(imm32)) EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32); else EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32); emit_cond_jmp: /* Convert BPF opcode to x86 */ switch (BPF_OP(insn->code)) { case BPF_JEQ: jmp_cond = X86_JE; break; case BPF_JSET: case BPF_JNE: jmp_cond = X86_JNE; break; case BPF_JGT: /* GT is unsigned '>', JA in x86 */ jmp_cond = X86_JA; break; case BPF_JLT: /* LT is unsigned '<', JB in x86 */ jmp_cond = X86_JB; break; case BPF_JGE: /* GE is unsigned '>=', JAE in x86 */ jmp_cond = X86_JAE; break; case BPF_JLE: /* LE is unsigned '<=', JBE in x86 */ jmp_cond = X86_JBE; break; case BPF_JSGT: /* Signed '>', GT in x86 */ jmp_cond = X86_JG; break; case BPF_JSLT: /* Signed '<', LT in x86 */ jmp_cond = X86_JL; break; case BPF_JSGE: /* Signed '>=', GE in x86 */ jmp_cond = X86_JGE; break; case BPF_JSLE: /* Signed '<=', LE in x86 */ jmp_cond = X86_JLE; break; default: /* to silence GCC warning */ return -EFAULT; } jmp_offset = addrs[i + insn->off] - addrs[i]; if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To keep the jmp_offset valid, the extra bytes are * padded before the jump insn, so we subtract the * 2 bytes of jmp_cond insn from INSN_SZ_DIFF. * * If the previous pass already emits an imm8 * jmp_cond, then this BPF insn won't shrink, so * "nops" is 0. * * On the other hand, if the previous pass emits an * imm32 jmp_cond, the extra 4 bytes(*) is padded to * keep the image from shrinking further. * * (*) imm32 jmp_cond is 6 bytes, and imm8 jmp_cond * is 2 bytes, so the size difference is 4 bytes. */ nops = INSN_SZ_DIFF - 2; if (nops != 0 && nops != 4) { pr_err("unexpected jmp_cond padding: %d bytes\n", nops); return -EFAULT; } emit_nops(&prog, nops); } EMIT2(jmp_cond, jmp_offset); } else if (is_simm32(jmp_offset)) { EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); } else { pr_err("cond_jmp gen bug %llx\n", jmp_offset); return -EFAULT; } break; case BPF_JMP | BPF_JA: case BPF_JMP32 | BPF_JA: if (BPF_CLASS(insn->code) == BPF_JMP) { if (insn->off == -1) /* -1 jmp instructions will always jump * backwards two bytes. Explicitly handling * this case avoids wasting too many passes * when there are long sequences of replaced * dead code. */ jmp_offset = -2; else jmp_offset = addrs[i + insn->off] - addrs[i]; } else { if (insn->imm == -1) jmp_offset = -2; else jmp_offset = addrs[i + insn->imm] - addrs[i]; } if (!jmp_offset) { /* * If jmp_padding is enabled, the extra nops will * be inserted. Otherwise, optimize out nop jumps. */ if (jmp_padding) { /* There are 3 possible conditions. * (1) This BPF_JA is already optimized out in * the previous run, so there is no need * to pad any extra byte (0 byte). * (2) The previous pass emits an imm8 jmp, * so we pad 2 bytes to match the previous * insn size. * (3) Similarly, the previous pass emits an * imm32 jmp, and 5 bytes is padded. */ nops = INSN_SZ_DIFF; if (nops != 0 && nops != 2 && nops != 5) { pr_err("unexpected nop jump padding: %d bytes\n", nops); return -EFAULT; } emit_nops(&prog, nops); } break; } emit_jmp: if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To avoid breaking jmp_offset, the extra bytes * are padded before the actual jmp insn, so * 2 bytes is subtracted from INSN_SZ_DIFF. * * If the previous pass already emits an imm8 * jmp, there is nothing to pad (0 byte). * * If it emits an imm32 jmp (5 bytes) previously * and now an imm8 jmp (2 bytes), then we pad * (5 - 2 = 3) bytes to stop the image from * shrinking further. */ nops = INSN_SZ_DIFF - 2; if (nops != 0 && nops != 3) { pr_err("unexpected jump padding: %d bytes\n", nops); return -EFAULT; } emit_nops(&prog, INSN_SZ_DIFF - 2); } EMIT2(0xEB, jmp_offset); } else if (is_simm32(jmp_offset)) { EMIT1_off32(0xE9, jmp_offset); } else { pr_err("jmp gen bug %llx\n", jmp_offset); return -EFAULT; } break; case BPF_JMP | BPF_EXIT: if (seen_exit) { jmp_offset = ctx->cleanup_addr - addrs[i]; goto emit_jmp; } seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; if (bpf_prog_was_classic(bpf_prog) && !capable(CAP_SYS_ADMIN)) { u8 *ip = image + addrs[i - 1]; if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog)) return -EINVAL; } if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); if (arena_vm_start) pop_r12(&prog); } EMIT1(0xC9); /* leave */ emit_return(&prog, image + addrs[i - 1] + (prog - temp)); break; default: /* * By design x86-64 JIT should support all BPF instructions. * This error will be seen if new instruction was added * to the interpreter, but not to the JIT, or if there is * junk in bpf_prog. */ pr_err("bpf_jit: unknown opcode %02x\n", insn->code); return -EINVAL; } ilen = prog - temp; if (ilen > BPF_MAX_INSN_SIZE) { pr_err("bpf_jit: fatal insn size error\n"); return -EFAULT; } if (image) { /* * When populating the image, assert that: * * i) We do not write beyond the allocated space, and * ii) addrs[i] did not change from the prior run, in order * to validate assumptions made for computing branch * displacements. */ if (unlikely(proglen + ilen > oldproglen || proglen + ilen != addrs[i])) { pr_err("bpf_jit: fatal error\n"); return -EFAULT; } memcpy(rw_image + proglen, temp, ilen); } proglen += ilen; addrs[i] = proglen; prog = temp; } if (image && excnt != bpf_prog->aux->num_exentries) { pr_err("extable is not populated\n"); return -EFAULT; } return proglen; } static void clean_stack_garbage(const struct btf_func_model *m, u8 **pprog, int nr_stack_slots, int stack_size) { int arg_size, off; u8 *prog; /* Generally speaking, the compiler will pass the arguments * on-stack with "push" instruction, which will take 8-byte * on the stack. In this case, there won't be garbage values * while we copy the arguments from origin stack frame to current * in BPF_DW. * * However, sometimes the compiler will only allocate 4-byte on * the stack for the arguments. For now, this case will only * happen if there is only one argument on-stack and its size * not more than 4 byte. In this case, there will be garbage * values on the upper 4-byte where we store the argument on * current stack frame. * * arguments on origin stack: * * stack_arg_1(4-byte) xxx(4-byte) * * what we copy: * * stack_arg_1(8-byte): stack_arg_1(origin) xxx * * and the xxx is the garbage values which we should clean here. */ if (nr_stack_slots != 1) return; /* the size of the last argument */ arg_size = m->arg_size[m->nr_args - 1]; if (arg_size <= 4) { off = -(stack_size - 4); prog = *pprog; /* mov DWORD PTR [rbp + off], 0 */ if (!is_imm8(off)) EMIT2_off32(0xC7, 0x85, off); else EMIT3(0xC7, 0x45, off); EMIT(0, 4); *pprog = prog; } } /* get the count of the regs that are used to pass arguments */ static int get_nr_used_regs(const struct btf_func_model *m) { int i, arg_regs, nr_used_regs = 0; for (i = 0; i < min_t(int, m->nr_args, MAX_BPF_FUNC_ARGS); i++) { arg_regs = (m->arg_size[i] + 7) / 8; if (nr_used_regs + arg_regs <= 6) nr_used_regs += arg_regs; if (nr_used_regs >= 6) break; } return nr_used_regs; } static void save_args(const struct btf_func_model *m, u8 **prog, int stack_size, bool for_call_origin) { int arg_regs, first_off = 0, nr_regs = 0, nr_stack_slots = 0; int i, j; /* Store function arguments to stack. * For a function that accepts two pointers the sequence will be: * mov QWORD PTR [rbp-0x10],rdi * mov QWORD PTR [rbp-0x8],rsi */ for (i = 0; i < min_t(int, m->nr_args, MAX_BPF_FUNC_ARGS); i++) { arg_regs = (m->arg_size[i] + 7) / 8; /* According to the research of Yonghong, struct members * should be all in register or all on the stack. * Meanwhile, the compiler will pass the argument on regs * if the remaining regs can hold the argument. * * Disorder of the args can happen. For example: * * struct foo_struct { * long a; * int b; * }; * int foo(char, char, char, char, char, struct foo_struct, * char); * * the arg1-5,arg7 will be passed by regs, and arg6 will * by stack. */ if (nr_regs + arg_regs > 6) { /* copy function arguments from origin stack frame * into current stack frame. * * The starting address of the arguments on-stack * is: * rbp + 8(push rbp) + * 8(return addr of origin call) + * 8(return addr of the caller) * which means: rbp + 24 */ for (j = 0; j < arg_regs; j++) { emit_ldx(prog, BPF_DW, BPF_REG_0, BPF_REG_FP, nr_stack_slots * 8 + 0x18); emit_stx(prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -stack_size); if (!nr_stack_slots) first_off = stack_size; stack_size -= 8; nr_stack_slots++; } } else { /* Only copy the arguments on-stack to current * 'stack_size' and ignore the regs, used to * prepare the arguments on-stack for origin call. */ if (for_call_origin) { nr_regs += arg_regs; continue; } /* copy the arguments from regs into stack */ for (j = 0; j < arg_regs; j++) { emit_stx(prog, BPF_DW, BPF_REG_FP, nr_regs == 5 ? X86_REG_R9 : BPF_REG_1 + nr_regs, -stack_size); stack_size -= 8; nr_regs++; } } } clean_stack_garbage(m, prog, nr_stack_slots, first_off); } static void restore_regs(const struct btf_func_model *m, u8 **prog, int stack_size) { int i, j, arg_regs, nr_regs = 0; /* Restore function arguments from stack. * For a function that accepts two pointers the sequence will be: * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10] * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8] * * The logic here is similar to what we do in save_args() */ for (i = 0; i < min_t(int, m->nr_args, MAX_BPF_FUNC_ARGS); i++) { arg_regs = (m->arg_size[i] + 7) / 8; if (nr_regs + arg_regs <= 6) { for (j = 0; j < arg_regs; j++) { emit_ldx(prog, BPF_DW, nr_regs == 5 ? X86_REG_R9 : BPF_REG_1 + nr_regs, BPF_REG_FP, -stack_size); stack_size -= 8; nr_regs++; } } else { stack_size -= 8 * arg_regs; } if (nr_regs >= 6) break; } } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, int run_ctx_off, bool save_ret, void *image, void *rw_image) { u8 *prog = *pprog; u8 *jmp_insn; int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); struct bpf_prog *p = l->link.prog; u64 cookie = l->cookie; /* mov rdi, cookie */ emit_mov_imm64(&prog, BPF_REG_1, (long) cookie >> 32, (u32) (long) cookie); /* Prepare struct bpf_tramp_run_ctx. * * bpf_tramp_run_ctx is already preserved by * arch_prepare_bpf_trampoline(). * * mov QWORD PTR [rbp - run_ctx_off + ctx_cookie_off], rdi */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off); /* arg1: mov rdi, progs[i] */ emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); /* arg2: lea rsi, [rbp - ctx_cookie_off] */ if (!is_imm8(-run_ctx_off)) EMIT3_off32(0x48, 0x8D, 0xB5, -run_ctx_off); else EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); if (emit_rsb_call(&prog, bpf_trampoline_enter(p), image + (prog - (u8 *)rw_image))) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); /* if (__bpf_prog_enter*(prog) == 0) * goto skip_exec_of_prog; */ EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ /* emit 2 nops that will be replaced with JE insn */ jmp_insn = prog; emit_nops(&prog, 2); /* arg1: lea rdi, [rbp - stack_size] */ if (!is_imm8(-stack_size)) EMIT3_off32(0x48, 0x8D, 0xBD, -stack_size); else EMIT4(0x48, 0x8D, 0x7D, -stack_size); /* arg2: progs[i]->insnsi for interpreter */ if (!p->jited) emit_mov_imm64(&prog, BPF_REG_2, (long) p->insnsi >> 32, (u32) (long) p->insnsi); /* call JITed bpf program or interpreter */ if (emit_rsb_call(&prog, p->bpf_func, image + (prog - (u8 *)rw_image))) return -EINVAL; /* * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return * of the previous call which is then passed on the stack to * the next BPF program. * * BPF_TRAMP_FENTRY trampoline may need to return the return * value of BPF_PROG_TYPE_STRUCT_OPS prog. */ if (save_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); /* replace 2 nops with JE insn, since jmp target is known */ jmp_insn[0] = X86_JE; jmp_insn[1] = prog - jmp_insn - 2; /* arg1: mov rdi, progs[i] */ emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); /* arg2: mov rsi, rbx <- start time in nsec */ emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); /* arg3: lea rdx, [rbp - run_ctx_off] */ if (!is_imm8(-run_ctx_off)) EMIT3_off32(0x48, 0x8D, 0x95, -run_ctx_off); else EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); if (emit_rsb_call(&prog, bpf_trampoline_exit(p), image + (prog - (u8 *)rw_image))) return -EINVAL; *pprog = prog; return 0; } static void emit_align(u8 **pprog, u32 align) { u8 *target, *prog = *pprog; target = PTR_ALIGN(prog, align); if (target != prog) emit_nops(&prog, target - prog); *pprog = prog; } static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) { u8 *prog = *pprog; s64 offset; offset = func - (ip + 2 + 4); if (!is_simm32(offset)) { pr_err("Target %p is out of range\n", func); return -EINVAL; } EMIT2_off32(0x0F, jmp_cond + 0x10, offset); *pprog = prog; return 0; } static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, int run_ctx_off, bool save_ret, void *image, void *rw_image) { int i; u8 *prog = *pprog; for (i = 0; i < tl->nr_links; i++) { if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, save_ret, image, rw_image)) return -EINVAL; } *pprog = prog; return 0; } static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, int run_ctx_off, u8 **branches, void *image, void *rw_image) { u8 *prog = *pprog; int i; /* The first fmod_ret program will receive a garbage return value. * Set this to 0 to avoid confusing the program. */ emit_mov_imm32(&prog, false, BPF_REG_0, 0); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); for (i = 0; i < tl->nr_links; i++) { if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true, image, rw_image)) return -EINVAL; /* mod_ret prog stored return value into [rbp - 8]. Emit: * if (*(u64 *)(rbp - 8) != 0) * goto do_fexit; */ /* cmp QWORD PTR [rbp - 0x8], 0x0 */ EMIT4(0x48, 0x83, 0x7d, 0xf8); EMIT1(0x00); /* Save the location of the branch and Generate 6 nops * (4 bytes for an offset and 2 bytes for the jump) These nops * are replaced with a conditional jump once do_fexit (i.e. the * start of the fexit invocation) is finalized. */ branches[i] = prog; emit_nops(&prog, 4 + 2); } *pprog = prog; return 0; } /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ #define LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack) \ __LOAD_TCC_PTR(-round_up(stack, 8) - 8) /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 * The assembly code when eth_type_trans is executing after trampoline: * * push rbp * mov rbp, rsp * sub rsp, 16 // space for skb and dev * push rbx // temp regs to pass start time * mov qword ptr [rbp - 16], rdi // save skb pointer to stack * mov qword ptr [rbp - 8], rsi // save dev pointer to stack * call __bpf_prog_enter // rcu_read_lock and preempt_disable * mov rbx, rax // remember start time in bpf stats are enabled * lea rdi, [rbp - 16] // R1==ctx of bpf prog * call addr_of_jited_FENTRY_prog * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off * mov rsi, rbx // prog start time * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math * mov rdi, qword ptr [rbp - 16] // restore skb pointer from stack * mov rsi, qword ptr [rbp - 8] // restore dev pointer from stack * pop rbx * leave * ret * * eth_type_trans has 5 byte nop at the beginning. These 5 bytes will be * replaced with 'call generated_bpf_trampoline'. When it returns * eth_type_trans will continue executing with original skb and dev pointers. * * The assembly code when eth_type_trans is called from trampoline: * * push rbp * mov rbp, rsp * sub rsp, 24 // space for skb, dev, return value * push rbx // temp regs to pass start time * mov qword ptr [rbp - 24], rdi // save skb pointer to stack * mov qword ptr [rbp - 16], rsi // save dev pointer to stack * call __bpf_prog_enter // rcu_read_lock and preempt_disable * mov rbx, rax // remember start time if bpf stats are enabled * lea rdi, [rbp - 24] // R1==ctx of bpf prog * call addr_of_jited_FENTRY_prog // bpf prog can access skb and dev * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off * mov rsi, rbx // prog start time * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math * mov rdi, qword ptr [rbp - 24] // restore skb pointer from stack * mov rsi, qword ptr [rbp - 16] // restore dev pointer from stack * call eth_type_trans+5 // execute body of eth_type_trans * mov qword ptr [rbp - 8], rax // save return value * call __bpf_prog_enter // rcu_read_lock and preempt_disable * mov rbx, rax // remember start time in bpf stats are enabled * lea rdi, [rbp - 24] // R1==ctx of bpf prog * call addr_of_jited_FEXIT_prog // bpf prog can access skb, dev, return value * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off * mov rsi, rbx // prog start time * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math * mov rax, qword ptr [rbp - 8] // restore eth_type_trans's return value * pop rbx * leave * add rsp, 8 // skip eth_type_trans's frame * ret // return to its caller */ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image, void *rw_image_end, void *image, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { int i, ret, nr_regs = m->nr_args, stack_size = 0; int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; void *orig_call = func_addr; u8 **branches = NULL; u8 *prog; bool save_ret; /* * F_INDIRECT is only compatible with F_RET_FENTRY_RET, it is * explicitly incompatible with F_CALL_ORIG | F_SKIP_FRAME | F_IP_ARG * because @func_addr. */ WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) && (flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET))); /* extra registers for struct arguments */ for (i = 0; i < m->nr_args; i++) { if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) nr_regs += (m->arg_size[i] + 7) / 8 - 1; } /* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6 * are passed through regs, the remains are through stack. */ if (nr_regs > MAX_BPF_FUNC_ARGS) return -ENOTSUPP; /* Generated trampoline stack layout: * * RBP + 8 [ return address ] * RBP + 0 [ RBP ] * * RBP - 8 [ return value ] BPF_TRAMP_F_CALL_ORIG or * BPF_TRAMP_F_RET_FENTRY_RET flags * * [ reg_argN ] always * [ ... ] * RBP - regs_off [ reg_arg1 ] program's ctx pointer * * RBP - nregs_off [ regs count ] always * * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * * RBP - rbx_off [ rbx value ] always * * RBP - run_ctx_off [ bpf_tramp_run_ctx ] * * [ stack_argN ] BPF_TRAMP_F_CALL_ORIG * [ ... ] * [ stack_arg2 ] * RBP - arg_stack_off [ stack_arg1 ] * RSP [ tail_call_cnt_ptr ] BPF_TRAMP_F_TAIL_CALL_CTX */ /* room for return value of orig_call or fentry prog */ save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); if (save_ret) stack_size += 8; stack_size += nr_regs * 8; regs_off = stack_size; /* regs count */ stack_size += 8; nregs_off = stack_size; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ ip_off = stack_size; stack_size += 8; rbx_off = stack_size; stack_size += (sizeof(struct bpf_tramp_run_ctx) + 7) & ~0x7; run_ctx_off = stack_size; if (nr_regs > 6 && (flags & BPF_TRAMP_F_CALL_ORIG)) { /* the space that used to pass arguments on-stack */ stack_size += (nr_regs - get_nr_used_regs(m)) * 8; /* make sure the stack pointer is 16-byte aligned if we * need pass arguments on stack, which means * [stack_size + 8(rbp) + 8(rip) + 8(origin rip)] * should be 16-byte aligned. Following code depend on * that stack_size is already 8-byte aligned. */ stack_size += (stack_size % 16) ? 0 : 8; } arg_stack_off = stack_size; if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* skip patched call instruction and point orig_call to actual * body of the kernel function. */ if (is_endbr(orig_call)) orig_call += ENDBR_INSN_SIZE; orig_call += X86_PATCH_SIZE; } prog = rw_image; if (flags & BPF_TRAMP_F_INDIRECT) { /* * Indirect call for bpf_struct_ops */ emit_cfi(&prog, image, cfi_get_func_hash(func_addr), cfi_get_func_arity(func_addr)); } else { /* * Direct-call fentry stub, as such it needs accounting for the * __fentry__ call. */ x86_call_depth_emit_accounting(&prog, NULL, image); } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ if (!is_imm8(stack_size)) { /* sub rsp, stack_size */ EMIT3_off32(0x48, 0x81, 0xEC, stack_size); } else { /* sub rsp, stack_size */ EMIT4(0x48, 0x83, 0xEC, stack_size); } if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) EMIT1(0x50); /* push rax */ /* mov QWORD PTR [rbp - rbx_off], rbx */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_6, -rbx_off); /* Store number of argument registers of the traced function: * mov rax, nr_regs * mov QWORD PTR [rbp - nregs_off], rax */ emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_regs); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -nregs_off); if (flags & BPF_TRAMP_F_IP_ARG) { /* Store IP address of the traced function: * movabsq rax, func_addr * mov QWORD PTR [rbp - ip_off], rax */ emit_mov_imm64(&prog, BPF_REG_0, (long) func_addr >> 32, (u32) (long) func_addr); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off); } save_args(m, &prog, regs_off, false); if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); if (emit_rsb_call(&prog, __bpf_tramp_enter, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } if (fentry->nr_links) { if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off, flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image)) return -EINVAL; } if (fmod_ret->nr_links) { branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *), GFP_KERNEL); if (!branches) return -ENOMEM; if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off, run_ctx_off, branches, image, rw_image)) { ret = -EINVAL; goto cleanup; } } if (flags & BPF_TRAMP_F_CALL_ORIG) { restore_regs(m, &prog, regs_off); save_args(m, &prog, arg_stack_off, true); if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { /* Before calling the original function, load the * tail_call_cnt_ptr from stack to rax. */ LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack_size); } if (flags & BPF_TRAMP_F_ORIG_STACK) { emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8); EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ if (emit_rsb_call(&prog, orig_call, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); im->ip_after_call = image + (prog - (u8 *)rw_image); emit_nops(&prog, X86_PATCH_SIZE); } if (fmod_ret->nr_links) { /* From Intel 64 and IA-32 Architectures Optimization * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler * Coding Rule 11: All branch targets should be 16-byte * aligned. */ emit_align(&prog, 16); /* Update the branches saved in invoke_bpf_mod_ret with the * aligned address of do_fexit. */ for (i = 0; i < fmod_ret->nr_links; i++) { emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image), image + (branches[i] - (u8 *)rw_image), X86_JNE); } } if (fexit->nr_links) { if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false, image, rw_image)) { ret = -EINVAL; goto cleanup; } } if (flags & BPF_TRAMP_F_RESTORE_REGS) restore_regs(m, &prog, regs_off); /* This needs to be done regardless. If there were fmod_ret programs, * the return value is only updated on the stack and still needs to be * restored to R0. */ if (flags & BPF_TRAMP_F_CALL_ORIG) { im->ip_epilogue = image + (prog - (u8 *)rw_image); /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); if (emit_rsb_call(&prog, __bpf_tramp_exit, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { /* Before running the original function, load the * tail_call_cnt_ptr from stack to rax. */ LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack_size); } /* restore return value of orig_call or fentry prog back into RAX */ if (save_ret) emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off); EMIT1(0xC9); /* leave */ if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* skip our return address and return to parent */ EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ } emit_return(&prog, image + (prog - (u8 *)rw_image)); /* Make sure the trampoline generation logic doesn't overflow */ if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) { ret = -EFAULT; goto cleanup; } ret = prog - (u8 *)rw_image + BPF_INSN_SAFETY; cleanup: kfree(branches); return ret; } void *arch_alloc_bpf_trampoline(unsigned int size) { return bpf_prog_pack_alloc(size, jit_fill_hole); } void arch_free_bpf_trampoline(void *image, unsigned int size) { bpf_prog_pack_free(image, size); } int arch_protect_bpf_trampoline(void *image, unsigned int size) { return 0; } int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { void *rw_image, *tmp; int ret; u32 size = image_end - image; /* rw_image doesn't need to be in module memory range, so we can * use kvmalloc. */ rw_image = kvmalloc(size, GFP_KERNEL); if (!rw_image) return -ENOMEM; ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m, flags, tlinks, func_addr); if (ret < 0) goto out; tmp = bpf_arch_text_copy(image, rw_image, size); if (IS_ERR(tmp)) ret = PTR_ERR(tmp); out: kvfree(rw_image); return ret; } int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { struct bpf_tramp_image im; void *image; int ret; /* Allocate a temporary buffer for __arch_prepare_bpf_trampoline(). * This will NOT cause fragmentation in direct map, as we do not * call set_memory_*() on this buffer. * * We cannot use kvmalloc here, because we need image to be in * module memory range. */ image = bpf_jit_alloc_exec(PAGE_SIZE); if (!image) return -ENOMEM; ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image, m, flags, tlinks, func_addr); bpf_jit_free_exec(image); return ret; } static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf) { u8 *jg_reloc, *prog = *pprog; int pivot, err, jg_bytes = 1; s64 jg_offset; if (a == b) { /* Leaf node of recursion, i.e. not a range of indices * anymore. */ EMIT1(add_1mod(0x48, BPF_REG_3)); /* cmp rdx,func */ if (!is_simm32(progs[a])) return -1; EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3), progs[a]); err = emit_cond_near_jump(&prog, /* je func */ (void *)progs[a], image + (prog - buf), X86_JE); if (err) return err; emit_indirect_jump(&prog, 2 /* rdx */, image + (prog - buf)); *pprog = prog; return 0; } /* Not a leaf node, so we pivot, and recursively descend into * the lower and upper ranges. */ pivot = (b - a) / 2; EMIT1(add_1mod(0x48, BPF_REG_3)); /* cmp rdx,func */ if (!is_simm32(progs[a + pivot])) return -1; EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3), progs[a + pivot]); if (pivot > 2) { /* jg upper_part */ /* Require near jump. */ jg_bytes = 4; EMIT2_off32(0x0F, X86_JG + 0x10, 0); } else { EMIT2(X86_JG, 0); } jg_reloc = prog; err = emit_bpf_dispatcher(&prog, a, a + pivot, /* emit lower_part */ progs, image, buf); if (err) return err; /* From Intel 64 and IA-32 Architectures Optimization * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler * Coding Rule 11: All branch targets should be 16-byte * aligned. */ emit_align(&prog, 16); jg_offset = prog - jg_reloc; emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes); err = emit_bpf_dispatcher(&prog, a + pivot + 1, /* emit upper_part */ b, progs, image, buf); if (err) return err; *pprog = prog; return 0; } static int cmp_ips(const void *a, const void *b) { const s64 *ipa = a; const s64 *ipb = b; if (*ipa > *ipb) return 1; if (*ipa < *ipb) return -1; return 0; } int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs) { u8 *prog = buf; sort(funcs, num_funcs, sizeof(funcs[0]), cmp_ips, NULL); return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf); } static const char *bpf_get_prog_name(struct bpf_prog *prog) { if (prog->aux->ksym.prog) return prog->aux->ksym.name; return prog->aux->name; } static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size) { int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3; u64 *stack_ptr; for_each_possible_cpu(cpu) { stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu); stack_ptr[0] = PRIV_STACK_GUARD_VAL; stack_ptr[underflow_idx] = PRIV_STACK_GUARD_VAL; } } static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size, struct bpf_prog *prog) { int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3; u64 *stack_ptr; for_each_possible_cpu(cpu) { stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu); if (stack_ptr[0] != PRIV_STACK_GUARD_VAL || stack_ptr[underflow_idx] != PRIV_STACK_GUARD_VAL) { pr_err("BPF private stack overflow/underflow detected for prog %sx\n", bpf_get_prog_name(prog)); break; } } } struct x64_jit_data { struct bpf_binary_header *rw_header; struct bpf_binary_header *header; int *addrs; u8 *image; int proglen; struct jit_context ctx; }; #define MAX_PASSES 20 #define PADDING_PASSES (MAX_PASSES - 5) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { struct bpf_binary_header *rw_header = NULL; struct bpf_binary_header *header = NULL; struct bpf_prog *tmp, *orig_prog = prog; void __percpu *priv_stack_ptr = NULL; struct x64_jit_data *jit_data; int priv_stack_alloc_sz; int proglen, oldproglen = 0; struct jit_context ctx = {}; bool tmp_blinded = false; bool extra_pass = false; bool padding = false; u8 *rw_image = NULL; u8 *image = NULL; int *addrs; int pass; int i; if (!prog->jit_requested) return orig_prog; tmp = bpf_jit_blind_constants(prog); /* * If blinding was requested and we failed during blinding, * we must fall back to the interpreter. */ if (IS_ERR(tmp)) return orig_prog; if (tmp != prog) { tmp_blinded = true; prog = tmp; } jit_data = prog->aux->jit_data; if (!jit_data) { jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); if (!jit_data) { prog = orig_prog; goto out; } prog->aux->jit_data = jit_data; } priv_stack_ptr = prog->aux->priv_stack_ptr; if (!priv_stack_ptr && prog->aux->jits_use_priv_stack) { /* Allocate actual private stack size with verifier-calculated * stack size plus two memory guards to protect overflow and * underflow. */ priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) + 2 * PRIV_STACK_GUARD_SZ; priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_sz, 8, GFP_KERNEL); if (!priv_stack_ptr) { prog = orig_prog; goto out_priv_stack; } priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_sz); prog->aux->priv_stack_ptr = priv_stack_ptr; } addrs = jit_data->addrs; if (addrs) { ctx = jit_data->ctx; oldproglen = jit_data->proglen; image = jit_data->image; header = jit_data->header; rw_header = jit_data->rw_header; rw_image = (void *)rw_header + ((void *)image - (void *)header); extra_pass = true; padding = true; goto skip_init_addrs; } addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL); if (!addrs) { prog = orig_prog; goto out_addrs; } /* * Before first pass, make a rough estimation of addrs[] * each BPF instruction is translated to less than 64 bytes */ for (proglen = 0, i = 0; i <= prog->len; i++) { proglen += 64; addrs[i] = proglen; } ctx.cleanup_addr = proglen; skip_init_addrs: /* * JITed image shrinks with every pass and the loop iterates * until the image stops shrinking. Very large BPF programs * may converge on the last pass. In such case do one more * pass to emit the final image. */ for (pass = 0; pass < MAX_PASSES || image; pass++) { if (!padding && pass >= PADDING_PASSES) padding = true; proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding); if (proglen <= 0) { out_image: image = NULL; if (header) { bpf_arch_text_copy(&header->size, &rw_header->size, sizeof(rw_header->size)); bpf_jit_binary_pack_free(header, rw_header); } /* Fall back to interpreter mode */ prog = orig_prog; if (extra_pass) { prog->bpf_func = NULL; prog->jited = 0; prog->jited_len = 0; } goto out_addrs; } if (image) { if (proglen != oldproglen) { pr_err("bpf_jit: proglen=%d != oldproglen=%d\n", proglen, oldproglen); goto out_image; } break; } if (proglen == oldproglen) { /* * The number of entries in extable is the number of BPF_LDX * insns that access kernel memory via "pointer to BTF type". * The verifier changed their opcode from LDX|MEM|size * to LDX|PROBE_MEM|size to make JITing easier. */ u32 align = __alignof__(struct exception_table_entry); u32 extable_size = prog->aux->num_exentries * sizeof(struct exception_table_entry); /* allocate module memory for x86 insns and extable */ header = bpf_jit_binary_pack_alloc(roundup(proglen, align) + extable_size, &image, align, &rw_header, &rw_image, jit_fill_hole); if (!header) { prog = orig_prog; goto out_addrs; } prog->aux->extable = (void *) image + roundup(proglen, align); } oldproglen = proglen; cond_resched(); } if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, proglen, pass + 1, rw_image); if (image) { if (!prog->is_func || extra_pass) { /* * bpf_jit_binary_pack_finalize fails in two scenarios: * 1) header is not pointing to proper module memory; * 2) the arch doesn't support bpf_arch_text_copy(). * * Both cases are serious bugs and justify WARN_ON. */ if (WARN_ON(bpf_jit_binary_pack_finalize(header, rw_header))) { /* header has been freed */ header = NULL; goto out_image; } bpf_tail_call_direct_fixup(prog); } else { jit_data->addrs = addrs; jit_data->ctx = ctx; jit_data->proglen = proglen; jit_data->image = image; jit_data->header = header; jit_data->rw_header = rw_header; } /* * ctx.prog_offset is used when CFI preambles put code *before* * the function. See emit_cfi(). For FineIBT specifically this code * can also be executed and bpf_prog_kallsyms_add() will * generate an additional symbol to cover this, hence also * decrement proglen. */ prog->bpf_func = (void *)image + cfi_get_offset(); prog->jited = 1; prog->jited_len = proglen - cfi_get_offset(); } else { prog = orig_prog; } if (!image || !prog->is_func || extra_pass) { if (image) bpf_prog_fill_jited_linfo(prog, addrs + 1); out_addrs: kvfree(addrs); if (!image && priv_stack_ptr) { free_percpu(priv_stack_ptr); prog->aux->priv_stack_ptr = NULL; } out_priv_stack: kfree(jit_data); prog->aux->jit_data = NULL; } out: if (tmp_blinded) bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); return prog; } bool bpf_jit_supports_kfunc_call(void) { return true; } void *bpf_arch_text_copy(void *dst, void *src, size_t len) { if (text_poke_copy(dst, src, len) == NULL) return ERR_PTR(-EINVAL); return dst; } /* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */ bool bpf_jit_supports_subprog_tailcalls(void) { return true; } bool bpf_jit_supports_percpu_insn(void) { return true; } void bpf_jit_free(struct bpf_prog *prog) { if (prog->jited) { struct x64_jit_data *jit_data = prog->aux->jit_data; struct bpf_binary_header *hdr; void __percpu *priv_stack_ptr; int priv_stack_alloc_sz; /* * If we fail the final pass of JIT (from jit_subprogs), * the program may not be finalized yet. Call finalize here * before freeing it. */ if (jit_data) { bpf_jit_binary_pack_finalize(jit_data->header, jit_data->rw_header); kvfree(jit_data->addrs); kfree(jit_data); } prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset(); hdr = bpf_jit_binary_pack_hdr(prog); bpf_jit_binary_pack_free(hdr, NULL); priv_stack_ptr = prog->aux->priv_stack_ptr; if (priv_stack_ptr) { priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) + 2 * PRIV_STACK_GUARD_SZ; priv_stack_check_guard(priv_stack_ptr, priv_stack_alloc_sz, prog); free_percpu(prog->aux->priv_stack_ptr); } WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog)); } bpf_prog_unlock_free(prog); } bool bpf_jit_supports_exceptions(void) { /* We unwind through both kernel frames (starting from within bpf_throw * call) and BPF frames. Therefore we require ORC unwinder to be enabled * to walk kernel frames and reach BPF frames in the stack trace. */ return IS_ENABLED(CONFIG_UNWINDER_ORC); } bool bpf_jit_supports_private_stack(void) { return true; } void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) { #if defined(CONFIG_UNWINDER_ORC) struct unwind_state state; unsigned long addr; for (unwind_start(&state, current, NULL, NULL); !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || !consume_fn(cookie, (u64)addr, (u64)state.sp, (u64)state.bp)) break; } return; #endif WARN(1, "verification of programs using bpf_throw should have failed\n"); } void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, struct bpf_prog *new, struct bpf_prog *old) { u8 *old_addr, *new_addr, *old_bypass_addr; int ret; old_bypass_addr = old ? NULL : poke->bypass_addr; old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; /* * On program loading or teardown, the program's kallsym entry * might not be in place, so we use __bpf_arch_text_poke to skip * the kallsyms check. */ if (new) { ret = __bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, old_addr, new_addr); BUG_ON(ret < 0); if (!old) { ret = __bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, poke->bypass_addr, NULL); BUG_ON(ret < 0); } } else { ret = __bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, old_bypass_addr, poke->bypass_addr); BUG_ON(ret < 0); /* let other CPUs finish the execution of program * so that it will not possible to expose them * to invalid nop, stack unwind, nop state */ if (!ret) synchronize_rcu(); ret = __bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, old_addr, NULL); BUG_ON(ret < 0); } } bool bpf_jit_supports_arena(void) { return true; } bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) { if (!in_arena) return true; switch (insn->code) { case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: if (insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH)) return false; } return true; } bool bpf_jit_supports_ptr_xchg(void) { return true; } /* x86-64 JIT emits its own code to filter user addresses so return 0 here */ u64 bpf_arch_uaddress_limit(void) { return 0; } bool bpf_jit_supports_timed_may_goto(void) { return true; } |
| 157 2 128 120 120 120 16 5 120 138 124 1 7 4 123 128 120 128 128 128 128 120 120 120 120 120 120 120 120 120 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 | // SPDX-License-Identifier: GPL-2.0-or-later /* Decoder for ASN.1 BER/DER/CER encoded bytestream * * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/asn1_decoder.h> #include <linux/asn1_ber_bytecode.h> static const unsigned char asn1_op_lengths[ASN1_OP__NR] = { /* OPC TAG JMP ACT */ [ASN1_OP_MATCH] = 1 + 1, [ASN1_OP_MATCH_OR_SKIP] = 1 + 1, [ASN1_OP_MATCH_ACT] = 1 + 1 + 1, [ASN1_OP_MATCH_ACT_OR_SKIP] = 1 + 1 + 1, [ASN1_OP_MATCH_JUMP] = 1 + 1 + 1, [ASN1_OP_MATCH_JUMP_OR_SKIP] = 1 + 1 + 1, [ASN1_OP_MATCH_ANY] = 1, [ASN1_OP_MATCH_ANY_OR_SKIP] = 1, [ASN1_OP_MATCH_ANY_ACT] = 1 + 1, [ASN1_OP_MATCH_ANY_ACT_OR_SKIP] = 1 + 1, [ASN1_OP_COND_MATCH_OR_SKIP] = 1 + 1, [ASN1_OP_COND_MATCH_ACT_OR_SKIP] = 1 + 1 + 1, [ASN1_OP_COND_MATCH_JUMP_OR_SKIP] = 1 + 1 + 1, [ASN1_OP_COND_MATCH_ANY] = 1, [ASN1_OP_COND_MATCH_ANY_OR_SKIP] = 1, [ASN1_OP_COND_MATCH_ANY_ACT] = 1 + 1, [ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP] = 1 + 1, [ASN1_OP_COND_FAIL] = 1, [ASN1_OP_COMPLETE] = 1, [ASN1_OP_ACT] = 1 + 1, [ASN1_OP_MAYBE_ACT] = 1 + 1, [ASN1_OP_RETURN] = 1, [ASN1_OP_END_SEQ] = 1, [ASN1_OP_END_SEQ_OF] = 1 + 1, [ASN1_OP_END_SET] = 1, [ASN1_OP_END_SET_OF] = 1 + 1, [ASN1_OP_END_SEQ_ACT] = 1 + 1, [ASN1_OP_END_SEQ_OF_ACT] = 1 + 1 + 1, [ASN1_OP_END_SET_ACT] = 1 + 1, [ASN1_OP_END_SET_OF_ACT] = 1 + 1 + 1, }; /* * Find the length of an indefinite length object * @data: The data buffer * @datalen: The end of the innermost containing element in the buffer * @_dp: The data parse cursor (updated before returning) * @_len: Where to return the size of the element. * @_errmsg: Where to return a pointer to an error message on error */ static int asn1_find_indefinite_length(const unsigned char *data, size_t datalen, size_t *_dp, size_t *_len, const char **_errmsg) { unsigned char tag, tmp; size_t dp = *_dp, len, n; int indef_level = 1; next_tag: if (unlikely(datalen - dp < 2)) { if (datalen == dp) goto missing_eoc; goto data_overrun_error; } /* Extract a tag from the data */ tag = data[dp++]; if (tag == ASN1_EOC) { /* It appears to be an EOC. */ if (data[dp++] != 0) goto invalid_eoc; if (--indef_level <= 0) { *_len = dp - *_dp; *_dp = dp; return 0; } goto next_tag; } if (unlikely((tag & 0x1f) == ASN1_LONG_TAG)) { do { if (unlikely(datalen - dp < 2)) goto data_overrun_error; tmp = data[dp++]; } while (tmp & 0x80); } /* Extract the length */ len = data[dp++]; if (len <= 0x7f) goto check_length; if (unlikely(len == ASN1_INDEFINITE_LENGTH)) { /* Indefinite length */ if (unlikely((tag & ASN1_CONS_BIT) == ASN1_PRIM << 5)) goto indefinite_len_primitive; indef_level++; goto next_tag; } n = len - 0x80; if (unlikely(n > sizeof(len) - 1)) goto length_too_long; if (unlikely(n > datalen - dp)) goto data_overrun_error; len = 0; for (; n > 0; n--) { len <<= 8; len |= data[dp++]; } check_length: if (len > datalen - dp) goto data_overrun_error; dp += len; goto next_tag; length_too_long: *_errmsg = "Unsupported length"; goto error; indefinite_len_primitive: *_errmsg = "Indefinite len primitive not permitted"; goto error; invalid_eoc: *_errmsg = "Invalid length EOC"; goto error; data_overrun_error: *_errmsg = "Data overrun error"; goto error; missing_eoc: *_errmsg = "Missing EOC in indefinite len cons"; error: *_dp = dp; return -1; } /** * asn1_ber_decoder - Decoder BER/DER/CER ASN.1 according to pattern * @decoder: The decoder definition (produced by asn1_compiler) * @context: The caller's context (to be passed to the action functions) * @data: The encoded data * @datalen: The size of the encoded data * * Decode BER/DER/CER encoded ASN.1 data according to a bytecode pattern * produced by asn1_compiler. Action functions are called on marked tags to * allow the caller to retrieve significant data. * * LIMITATIONS: * * To keep down the amount of stack used by this function, the following limits * have been imposed: * * (1) This won't handle datalen > 65535 without increasing the size of the * cons stack elements and length_too_long checking. * * (2) The stack of constructed types is 10 deep. If the depth of non-leaf * constructed types exceeds this, the decode will fail. * * (3) The SET type (not the SET OF type) isn't really supported as tracking * what members of the set have been seen is a pain. */ int asn1_ber_decoder(const struct asn1_decoder *decoder, void *context, const unsigned char *data, size_t datalen) { const unsigned char *machine = decoder->machine; const asn1_action_t *actions = decoder->actions; size_t machlen = decoder->machlen; enum asn1_opcode op; unsigned char tag = 0, csp = 0, jsp = 0, optag = 0, hdr = 0; const char *errmsg; size_t pc = 0, dp = 0, tdp = 0, len = 0; int ret; unsigned char flags = 0; #define FLAG_INDEFINITE_LENGTH 0x01 #define FLAG_MATCHED 0x02 #define FLAG_LAST_MATCHED 0x04 /* Last tag matched */ #define FLAG_CONS 0x20 /* Corresponds to CONS bit in the opcode tag * - ie. whether or not we are going to parse * a compound type. */ #define NR_CONS_STACK 10 unsigned short cons_dp_stack[NR_CONS_STACK]; unsigned short cons_datalen_stack[NR_CONS_STACK]; unsigned char cons_hdrlen_stack[NR_CONS_STACK]; #define NR_JUMP_STACK 10 unsigned char jump_stack[NR_JUMP_STACK]; if (datalen > 65535) return -EMSGSIZE; next_op: pr_debug("next_op: pc=\e[32m%zu\e[m/%zu dp=\e[33m%zu\e[m/%zu C=%d J=%d\n", pc, machlen, dp, datalen, csp, jsp); if (unlikely(pc >= machlen)) goto machine_overrun_error; op = machine[pc]; if (unlikely(pc + asn1_op_lengths[op] > machlen)) goto machine_overrun_error; /* If this command is meant to match a tag, then do that before * evaluating the command. */ if (op <= ASN1_OP__MATCHES_TAG) { unsigned char tmp; /* Skip conditional matches if possible */ if ((op & ASN1_OP_MATCH__COND && flags & FLAG_MATCHED) || (op & ASN1_OP_MATCH__SKIP && dp == datalen)) { flags &= ~FLAG_LAST_MATCHED; pc += asn1_op_lengths[op]; goto next_op; } flags = 0; hdr = 2; /* Extract a tag from the data */ if (unlikely(datalen - dp < 2)) goto data_overrun_error; tag = data[dp++]; if (unlikely((tag & 0x1f) == ASN1_LONG_TAG)) goto long_tag_not_supported; if (op & ASN1_OP_MATCH__ANY) { pr_debug("- any %02x\n", tag); } else { /* Extract the tag from the machine * - Either CONS or PRIM are permitted in the data if * CONS is not set in the op stream, otherwise CONS * is mandatory. */ optag = machine[pc + 1]; flags |= optag & FLAG_CONS; /* Determine whether the tag matched */ tmp = optag ^ tag; tmp &= ~(optag & ASN1_CONS_BIT); pr_debug("- match? %02x %02x %02x\n", tag, optag, tmp); if (tmp != 0) { /* All odd-numbered tags are MATCH_OR_SKIP. */ if (op & ASN1_OP_MATCH__SKIP) { pc += asn1_op_lengths[op]; dp--; goto next_op; } goto tag_mismatch; } } flags |= FLAG_MATCHED; len = data[dp++]; if (len > 0x7f) { if (unlikely(len == ASN1_INDEFINITE_LENGTH)) { /* Indefinite length */ if (unlikely(!(tag & ASN1_CONS_BIT))) goto indefinite_len_primitive; flags |= FLAG_INDEFINITE_LENGTH; if (unlikely(2 > datalen - dp)) goto data_overrun_error; } else { int n = len - 0x80; if (unlikely(n > 2)) goto length_too_long; if (unlikely(n > datalen - dp)) goto data_overrun_error; hdr += n; for (len = 0; n > 0; n--) { len <<= 8; len |= data[dp++]; } if (unlikely(len > datalen - dp)) goto data_overrun_error; } } else { if (unlikely(len > datalen - dp)) goto data_overrun_error; } if (flags & FLAG_CONS) { /* For expected compound forms, we stack the positions * of the start and end of the data. */ if (unlikely(csp >= NR_CONS_STACK)) goto cons_stack_overflow; cons_dp_stack[csp] = dp; cons_hdrlen_stack[csp] = hdr; if (!(flags & FLAG_INDEFINITE_LENGTH)) { cons_datalen_stack[csp] = datalen; datalen = dp + len; } else { cons_datalen_stack[csp] = 0; } csp++; } pr_debug("- TAG: %02x %zu%s\n", tag, len, flags & FLAG_CONS ? " CONS" : ""); tdp = dp; } /* Decide how to handle the operation */ switch (op) { case ASN1_OP_MATCH: case ASN1_OP_MATCH_OR_SKIP: case ASN1_OP_MATCH_ACT: case ASN1_OP_MATCH_ACT_OR_SKIP: case ASN1_OP_MATCH_ANY: case ASN1_OP_MATCH_ANY_OR_SKIP: case ASN1_OP_MATCH_ANY_ACT: case ASN1_OP_MATCH_ANY_ACT_OR_SKIP: case ASN1_OP_COND_MATCH_OR_SKIP: case ASN1_OP_COND_MATCH_ACT_OR_SKIP: case ASN1_OP_COND_MATCH_ANY: case ASN1_OP_COND_MATCH_ANY_OR_SKIP: case ASN1_OP_COND_MATCH_ANY_ACT: case ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP: if (!(flags & FLAG_CONS)) { if (flags & FLAG_INDEFINITE_LENGTH) { size_t tmp = dp; ret = asn1_find_indefinite_length( data, datalen, &tmp, &len, &errmsg); if (ret < 0) goto error; } pr_debug("- LEAF: %zu\n", len); } if (op & ASN1_OP_MATCH__ACT) { unsigned char act; if (op & ASN1_OP_MATCH__ANY) act = machine[pc + 1]; else act = machine[pc + 2]; ret = actions[act](context, hdr, tag, data + dp, len); if (ret < 0) return ret; } if (!(flags & FLAG_CONS)) dp += len; pc += asn1_op_lengths[op]; goto next_op; case ASN1_OP_MATCH_JUMP: case ASN1_OP_MATCH_JUMP_OR_SKIP: case ASN1_OP_COND_MATCH_JUMP_OR_SKIP: pr_debug("- MATCH_JUMP\n"); if (unlikely(jsp == NR_JUMP_STACK)) goto jump_stack_overflow; jump_stack[jsp++] = pc + asn1_op_lengths[op]; pc = machine[pc + 2]; goto next_op; case ASN1_OP_COND_FAIL: if (unlikely(!(flags & FLAG_MATCHED))) goto tag_mismatch; pc += asn1_op_lengths[op]; goto next_op; case ASN1_OP_COMPLETE: if (unlikely(jsp != 0 || csp != 0)) { pr_err("ASN.1 decoder error: Stacks not empty at completion (%u, %u)\n", jsp, csp); return -EBADMSG; } return 0; case ASN1_OP_END_SET: case ASN1_OP_END_SET_ACT: if (unlikely(!(flags & FLAG_MATCHED))) goto tag_mismatch; fallthrough; case ASN1_OP_END_SEQ: case ASN1_OP_END_SET_OF: case ASN1_OP_END_SEQ_OF: case ASN1_OP_END_SEQ_ACT: case ASN1_OP_END_SET_OF_ACT: case ASN1_OP_END_SEQ_OF_ACT: if (unlikely(csp <= 0)) goto cons_stack_underflow; csp--; tdp = cons_dp_stack[csp]; hdr = cons_hdrlen_stack[csp]; len = datalen; datalen = cons_datalen_stack[csp]; pr_debug("- end cons t=%zu dp=%zu l=%zu/%zu\n", tdp, dp, len, datalen); if (datalen == 0) { /* Indefinite length - check for the EOC. */ datalen = len; if (unlikely(datalen - dp < 2)) goto data_overrun_error; if (data[dp++] != 0) { if (op & ASN1_OP_END__OF) { dp--; csp++; pc = machine[pc + 1]; pr_debug("- continue\n"); goto next_op; } goto missing_eoc; } if (data[dp++] != 0) goto invalid_eoc; len = dp - tdp - 2; } else { if (dp < len && (op & ASN1_OP_END__OF)) { datalen = len; csp++; pc = machine[pc + 1]; pr_debug("- continue\n"); goto next_op; } if (dp != len) goto cons_length_error; len -= tdp; pr_debug("- cons len l=%zu d=%zu\n", len, dp - tdp); } if (op & ASN1_OP_END__ACT) { unsigned char act; if (op & ASN1_OP_END__OF) act = machine[pc + 2]; else act = machine[pc + 1]; ret = actions[act](context, hdr, 0, data + tdp, len); if (ret < 0) return ret; } pc += asn1_op_lengths[op]; goto next_op; case ASN1_OP_MAYBE_ACT: if (!(flags & FLAG_LAST_MATCHED)) { pc += asn1_op_lengths[op]; goto next_op; } fallthrough; case ASN1_OP_ACT: ret = actions[machine[pc + 1]](context, hdr, tag, data + tdp, len); if (ret < 0) return ret; pc += asn1_op_lengths[op]; goto next_op; case ASN1_OP_RETURN: if (unlikely(jsp <= 0)) goto jump_stack_underflow; pc = jump_stack[--jsp]; flags |= FLAG_MATCHED | FLAG_LAST_MATCHED; goto next_op; default: break; } /* Shouldn't reach here */ pr_err("ASN.1 decoder error: Found reserved opcode (%u) pc=%zu\n", op, pc); return -EBADMSG; data_overrun_error: errmsg = "Data overrun error"; goto error; machine_overrun_error: errmsg = "Machine overrun error"; goto error; jump_stack_underflow: errmsg = "Jump stack underflow"; goto error; jump_stack_overflow: errmsg = "Jump stack overflow"; goto error; cons_stack_underflow: errmsg = "Cons stack underflow"; goto error; cons_stack_overflow: errmsg = "Cons stack overflow"; goto error; cons_length_error: errmsg = "Cons length error"; goto error; missing_eoc: errmsg = "Missing EOC in indefinite len cons"; goto error; invalid_eoc: errmsg = "Invalid length EOC"; goto error; length_too_long: errmsg = "Unsupported length"; goto error; indefinite_len_primitive: errmsg = "Indefinite len primitive not permitted"; goto error; tag_mismatch: errmsg = "Unexpected tag"; goto error; long_tag_not_supported: errmsg = "Long tag not supported"; error: pr_debug("\nASN1: %s [m=%zu d=%zu ot=%02x t=%02x l=%zu]\n", errmsg, pc, dp, optag, tag, len); return -EBADMSG; } EXPORT_SYMBOL_GPL(asn1_ber_decoder); MODULE_DESCRIPTION("Decoder for ASN.1 BER/DER/CER encoded bytestream"); MODULE_LICENSE("GPL"); |
| 483 58 128 128 48 620 620 35 616 1 2443 2446 1041 231 105 115 1144 1143 241 315 1091 314 1090 517 516 1 517 517 1250 5 5 5 1358 1358 516 516 1148 1133 1145 176 1149 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux network device link state notification * * Author: * Stefan Rompf <sux@loplof.de> */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/if.h> #include <net/sock.h> #include <net/pkt_sched.h> #include <linux/rtnetlink.h> #include <linux/jiffies.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/bitops.h> #include <linux/types.h> #include "dev.h" enum lw_bits { LW_URGENT = 0, }; static unsigned long linkwatch_flags; static unsigned long linkwatch_nextevent; static void linkwatch_event(struct work_struct *dummy); static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event); static LIST_HEAD(lweventlist); static DEFINE_SPINLOCK(lweventlist_lock); static unsigned int default_operstate(const struct net_device *dev) { if (netif_testing(dev)) return IF_OPER_TESTING; /* Some uppers (DSA) have additional sources for being down, so * first check whether lower is indeed the source of its down state. */ if (!netif_carrier_ok(dev)) { struct net_device *peer; int iflink; /* If called from netdev_run_todo()/linkwatch_sync_dev(), * dev_net(dev) can be already freed, and RTNL is not held. */ if (dev->reg_state <= NETREG_REGISTERED) iflink = dev_get_iflink(dev); else iflink = dev->ifindex; if (iflink == dev->ifindex) return IF_OPER_DOWN; ASSERT_RTNL(); peer = __dev_get_by_index(dev_net(dev), iflink); if (!peer) return IF_OPER_DOWN; return netif_carrier_ok(peer) ? IF_OPER_DOWN : IF_OPER_LOWERLAYERDOWN; } if (netif_dormant(dev)) return IF_OPER_DORMANT; return IF_OPER_UP; } static void rfc2863_policy(struct net_device *dev) { unsigned int operstate = default_operstate(dev); if (operstate == READ_ONCE(dev->operstate)) return; switch(dev->link_mode) { case IF_LINK_MODE_TESTING: if (operstate == IF_OPER_UP) operstate = IF_OPER_TESTING; break; case IF_LINK_MODE_DORMANT: if (operstate == IF_OPER_UP) operstate = IF_OPER_DORMANT; break; case IF_LINK_MODE_DEFAULT: default: break; } WRITE_ONCE(dev->operstate, operstate); } void linkwatch_init_dev(struct net_device *dev) { /* Handle pre-registration link state changes */ if (!netif_carrier_ok(dev) || netif_dormant(dev) || netif_testing(dev)) rfc2863_policy(dev); } static bool linkwatch_urgent_event(struct net_device *dev) { if (!netif_running(dev)) return false; if (dev->ifindex != dev_get_iflink(dev)) return true; if (netif_is_lag_port(dev) || netif_is_lag_master(dev)) return true; return netif_carrier_ok(dev) && qdisc_tx_changing(dev); } static void linkwatch_add_event(struct net_device *dev) { unsigned long flags; spin_lock_irqsave(&lweventlist_lock, flags); if (list_empty(&dev->link_watch_list)) { list_add_tail(&dev->link_watch_list, &lweventlist); netdev_hold(dev, &dev->linkwatch_dev_tracker, GFP_ATOMIC); } spin_unlock_irqrestore(&lweventlist_lock, flags); } static void linkwatch_schedule_work(int urgent) { unsigned long delay = linkwatch_nextevent - jiffies; if (test_bit(LW_URGENT, &linkwatch_flags)) return; /* Minimise down-time: drop delay for up event. */ if (urgent) { if (test_and_set_bit(LW_URGENT, &linkwatch_flags)) return; delay = 0; } /* If we wrap around we'll delay it by at most HZ. */ if (delay > HZ) delay = 0; /* * If urgent, schedule immediate execution; otherwise, don't * override the existing timer. */ if (test_bit(LW_URGENT, &linkwatch_flags)) mod_delayed_work(system_unbound_wq, &linkwatch_work, 0); else queue_delayed_work(system_unbound_wq, &linkwatch_work, delay); } static void linkwatch_do_dev(struct net_device *dev) { /* * Make sure the above read is complete since it can be * rewritten as soon as we clear the bit below. */ smp_mb__before_atomic(); /* We are about to handle this device, * so new events can be accepted */ clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); rfc2863_policy(dev); if (dev->flags & IFF_UP) { if (netif_carrier_ok(dev)) dev_activate(dev); else dev_deactivate(dev); netif_state_change(dev); } /* Note: our callers are responsible for calling netdev_tracker_free(). * This is the reason we use __dev_put() instead of dev_put(). */ __dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) { #define MAX_DO_DEV_PER_LOOP 100 int do_dev = MAX_DO_DEV_PER_LOOP; /* Use a local list here since we add non-urgent * events back to the global one when called with * urgent_only=1. */ LIST_HEAD(wrk); /* Give urgent case more budget */ if (urgent_only) do_dev += MAX_DO_DEV_PER_LOOP; /* * Limit the number of linkwatch events to one * per second so that a runaway driver does not * cause a storm of messages on the netlink * socket. This limit does not apply to up events * while the device qdisc is down. */ if (!urgent_only) linkwatch_nextevent = jiffies + HZ; /* Limit wrap-around effect on delay. */ else if (time_after(linkwatch_nextevent, jiffies + HZ)) linkwatch_nextevent = jiffies; clear_bit(LW_URGENT, &linkwatch_flags); spin_lock_irq(&lweventlist_lock); list_splice_init(&lweventlist, &wrk); while (!list_empty(&wrk) && do_dev > 0) { struct net_device *dev; dev = list_first_entry(&wrk, struct net_device, link_watch_list); list_del_init(&dev->link_watch_list); if (!netif_device_present(dev) || (urgent_only && !linkwatch_urgent_event(dev))) { list_add_tail(&dev->link_watch_list, &lweventlist); continue; } /* We must free netdev tracker under * the spinlock protection. */ netdev_tracker_free(dev, &dev->linkwatch_dev_tracker); spin_unlock_irq(&lweventlist_lock); netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); do_dev--; spin_lock_irq(&lweventlist_lock); } /* Add the remaining work back to lweventlist */ list_splice_init(&wrk, &lweventlist); if (!list_empty(&lweventlist)) linkwatch_schedule_work(0); spin_unlock_irq(&lweventlist_lock); } static bool linkwatch_clean_dev(struct net_device *dev) { unsigned long flags; bool clean = false; spin_lock_irqsave(&lweventlist_lock, flags); if (!list_empty(&dev->link_watch_list)) { list_del_init(&dev->link_watch_list); clean = true; /* We must release netdev tracker under * the spinlock protection. */ netdev_tracker_free(dev, &dev->linkwatch_dev_tracker); } spin_unlock_irqrestore(&lweventlist_lock, flags); return clean; } void __linkwatch_sync_dev(struct net_device *dev) { netdev_ops_assert_locked(dev); if (linkwatch_clean_dev(dev)) linkwatch_do_dev(dev); } void linkwatch_sync_dev(struct net_device *dev) { if (linkwatch_clean_dev(dev)) { netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); } } /* Must be called with the rtnl semaphore held */ void linkwatch_run_queue(void) { __linkwatch_run_queue(0); } static void linkwatch_event(struct work_struct *dummy) { rtnl_lock(); __linkwatch_run_queue(time_after(linkwatch_nextevent, jiffies)); rtnl_unlock(); } void linkwatch_fire_event(struct net_device *dev) { bool urgent = linkwatch_urgent_event(dev); if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { linkwatch_add_event(dev); } else if (!urgent) return; linkwatch_schedule_work(urgent); } EXPORT_SYMBOL(linkwatch_fire_event); |
| 4 10 1 9 9 5 5 5 5 4169 6 6 1 2 30 30 1 25 13 14 32 32 32 32 30 32 69 69 58 60 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Frame handler other utility functions for HSR and PRP. */ #include "hsr_slave.h" #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_forward.h" #include "hsr_framereg.h" bool hsr_invalid_dan_ingress_frame(__be16 protocol) { return (protocol != htons(ETH_P_PRP) && protocol != htons(ETH_P_HSR)); } static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; struct hsr_priv *hsr; __be16 protocol; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); return RX_HANDLER_PASS; } port = hsr_port_get_rcu(skb->dev); if (!port) goto finish_pass; hsr = port->hsr; if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { /* Directly kill frames sent by ourselves */ kfree_skb(skb); goto finish_consume; } /* For HSR, only tagged frames are expected (unless the device offloads * HSR tag removal), but for PRP there could be non tagged frames as * well from Single attached nodes (SANs). */ protocol = eth_hdr(skb)->h_proto; if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && port->type != HSR_PT_INTERLINK && hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || protocol == htons(ETH_P_HSR)) skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); skb_reset_mac_len(skb); /* Only the frames received over the interlink port will assign a * sequence number and require synchronisation vs other sender. */ if (port->type == HSR_PT_INTERLINK) { spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); } else { hsr_forward_skb(skb, port); } finish_consume: return RX_HANDLER_CONSUMED; finish_pass: return RX_HANDLER_PASS; } bool hsr_port_exists(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame; } static int hsr_check_dev_ok(struct net_device *dev, struct netlink_ext_ack *extack) { /* Don't allow HSR on non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) { NL_SET_ERR_MSG_MOD(extack, "Cannot use loopback or non-ethernet device as HSR slave."); return -EINVAL; } /* Don't allow enslaving hsr devices */ if (is_hsr_master(dev)) { NL_SET_ERR_MSG_MOD(extack, "Cannot create trees of HSR devices."); return -EINVAL; } if (hsr_port_exists(dev)) { NL_SET_ERR_MSG_MOD(extack, "This device is already a HSR slave."); return -EINVAL; } if (is_vlan_dev(dev)) { NL_SET_ERR_MSG_MOD(extack, "HSR on top of VLAN is not yet supported in this driver."); return -EINVAL; } if (dev->priv_flags & IFF_DONT_BRIDGE) { NL_SET_ERR_MSG_MOD(extack, "This device does not support bridging."); return -EOPNOTSUPP; } /* HSR over bonded devices has not been tested, but I'm not sure it * won't work... */ return 0; } /* Setup device to be added to the HSR bridge. */ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, struct hsr_port *port, struct netlink_ext_ack *extack) { struct net_device *hsr_dev; struct hsr_port *master; int res; /* Don't use promiscuous mode for offload since L2 frame forward * happens at the offloaded hardware. */ if (!port->hsr->fwd_offloaded) { res = dev_set_promiscuity(dev, 1); if (res) return res; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr_dev = master->dev; res = netdev_upper_dev_link(dev, hsr_dev, extack); if (res) goto fail_upper_dev_link; res = netdev_rx_handler_register(dev, hsr_handle_frame, port); if (res) goto fail_rx_handler; dev_disable_lro(dev); return 0; fail_rx_handler: netdev_upper_dev_unlink(dev, hsr_dev); fail_upper_dev_link: if (!port->hsr->fwd_offloaded) dev_set_promiscuity(dev, -1); return res; } int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type type, struct netlink_ext_ack *extack) { struct hsr_port *port, *master; int res; if (type != HSR_PT_MASTER) { res = hsr_check_dev_ok(dev, extack); if (res) return res; } port = hsr_port_get_hsr(hsr, type); if (port) return -EBUSY; /* This port already exists */ port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; port->hsr = hsr; port->dev = dev; port->type = type; ether_addr_copy(port->original_macaddress, dev->dev_addr); if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(hsr, dev, port, extack); if (res) goto fail_dev_setup; } list_add_tail_rcu(&port->port_list, &hsr->ports); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); return 0; fail_dev_setup: kfree(port); return res; } void hsr_del_port(struct hsr_port *port) { struct hsr_priv *hsr; struct hsr_port *master; hsr = port->hsr; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); list_del_rcu(&port->port_list); if (port != master) { netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); if (!port->hsr->fwd_offloaded) dev_set_promiscuity(port->dev, -1); netdev_upper_dev_unlink(port->dev, master->dev); eth_hw_addr_set(port->dev, port->original_macaddress); } kfree_rcu(port, rcu); } |
| 48 14 34 23 1 1 29 1 25 2 1 1 19 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 | // SPDX-License-Identifier: GPL-2.0-only /* * Input device TTY line discipline * * Copyright (c) 1999-2002 Vojtech Pavlik * * This is a module that converts a tty line into a much simpler * 'serial io port' abstraction that the input device drivers use. */ #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/serio.h> #include <linux/tty.h> #include <linux/compat.h> MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); MODULE_DESCRIPTION("Input device TTY line discipline"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_MOUSE); #define SERPORT_BUSY 1 #define SERPORT_ACTIVE 2 #define SERPORT_DEAD 3 struct serport { struct tty_struct *tty; wait_queue_head_t wait; struct serio *serio; struct serio_device_id id; spinlock_t lock; unsigned long flags; }; /* * Callback functions from the serio code. */ static int serport_serio_write(struct serio *serio, unsigned char data) { struct serport *serport = serio->port_data; return -(serport->tty->ops->write(serport->tty, &data, 1) != 1); } static int serport_serio_open(struct serio *serio) { struct serport *serport = serio->port_data; guard(spinlock_irqsave)(&serport->lock); set_bit(SERPORT_ACTIVE, &serport->flags); return 0; } static void serport_serio_close(struct serio *serio) { struct serport *serport = serio->port_data; guard(spinlock_irqsave)(&serport->lock); clear_bit(SERPORT_ACTIVE, &serport->flags); } /* * serport_ldisc_open() is the routine that is called upon setting our line * discipline on a tty. It prepares the serio struct. */ static int serport_ldisc_open(struct tty_struct *tty) { struct serport *serport; if (!capable(CAP_SYS_ADMIN)) return -EPERM; serport = kzalloc(sizeof(*serport), GFP_KERNEL); if (!serport) return -ENOMEM; serport->tty = tty; spin_lock_init(&serport->lock); init_waitqueue_head(&serport->wait); tty->disc_data = serport; tty->receive_room = 256; set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); return 0; } /* * serport_ldisc_close() is the opposite of serport_ldisc_open() */ static void serport_ldisc_close(struct tty_struct *tty) { struct serport *serport = tty->disc_data; kfree(serport); } /* * serport_ldisc_receive() is called by the low level tty driver when characters * are ready for us. We forward the characters and flags, one by one to the * 'interrupt' routine. */ static void serport_ldisc_receive(struct tty_struct *tty, const u8 *cp, const u8 *fp, size_t count) { struct serport *serport = tty->disc_data; unsigned int ch_flags = 0; int i; guard(spinlock_irqsave)(&serport->lock); if (!test_bit(SERPORT_ACTIVE, &serport->flags)) return; for (i = 0; i < count; i++) { if (fp) { switch (fp[i]) { case TTY_FRAME: ch_flags = SERIO_FRAME; break; case TTY_PARITY: ch_flags = SERIO_PARITY; break; default: ch_flags = 0; break; } } serio_interrupt(serport->serio, cp[i], ch_flags); } } /* * serport_ldisc_read() just waits indefinitely if everything goes well. * However, when the serio driver closes the serio port, it finishes, * returning 0 characters. */ static ssize_t serport_ldisc_read(struct tty_struct * tty, struct file * file, u8 *kbuf, size_t nr, void **cookie, unsigned long offset) { struct serport *serport = tty->disc_data; struct serio *serio; if (test_and_set_bit(SERPORT_BUSY, &serport->flags)) return -EBUSY; serport->serio = serio = kzalloc(sizeof(*serio), GFP_KERNEL); if (!serio) return -ENOMEM; strscpy(serio->name, "Serial port", sizeof(serio->name)); snprintf(serio->phys, sizeof(serio->phys), "%s/serio0", tty_name(tty)); serio->id = serport->id; serio->id.type = SERIO_RS232; serio->write = serport_serio_write; serio->open = serport_serio_open; serio->close = serport_serio_close; serio->port_data = serport; serio->dev.parent = tty->dev; serio_register_port(serport->serio); printk(KERN_INFO "serio: Serial port %s\n", tty_name(tty)); wait_event_interruptible(serport->wait, test_bit(SERPORT_DEAD, &serport->flags)); serio_unregister_port(serport->serio); serport->serio = NULL; clear_bit(SERPORT_DEAD, &serport->flags); clear_bit(SERPORT_BUSY, &serport->flags); return 0; } static void serport_set_type(struct tty_struct *tty, unsigned long type) { struct serport *serport = tty->disc_data; serport->id.proto = type & 0x000000ff; serport->id.id = (type & 0x0000ff00) >> 8; serport->id.extra = (type & 0x00ff0000) >> 16; } /* * serport_ldisc_ioctl() allows to set the port protocol, and device ID */ static int serport_ldisc_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { if (cmd == SPIOCSTYPE) { unsigned long type; if (get_user(type, (unsigned long __user *) arg)) return -EFAULT; serport_set_type(tty, type); return 0; } return -EINVAL; } #ifdef CONFIG_COMPAT #define COMPAT_SPIOCSTYPE _IOW('q', 0x01, compat_ulong_t) static int serport_ldisc_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { if (cmd == COMPAT_SPIOCSTYPE) { void __user *uarg = compat_ptr(arg); compat_ulong_t compat_type; if (get_user(compat_type, (compat_ulong_t __user *)uarg)) return -EFAULT; serport_set_type(tty, compat_type); return 0; } return -EINVAL; } #endif static void serport_ldisc_hangup(struct tty_struct *tty) { struct serport *serport = tty->disc_data; scoped_guard(spinlock_irqsave, &serport->lock) set_bit(SERPORT_DEAD, &serport->flags); wake_up_interruptible(&serport->wait); } static void serport_ldisc_write_wakeup(struct tty_struct * tty) { struct serport *serport = tty->disc_data; guard(spinlock_irqsave)(&serport->lock); if (test_bit(SERPORT_ACTIVE, &serport->flags)) serio_drv_write_wakeup(serport->serio); } /* * The line discipline structure. */ static struct tty_ldisc_ops serport_ldisc = { .owner = THIS_MODULE, .num = N_MOUSE, .name = "input", .open = serport_ldisc_open, .close = serport_ldisc_close, .read = serport_ldisc_read, .ioctl = serport_ldisc_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = serport_ldisc_compat_ioctl, #endif .receive_buf = serport_ldisc_receive, .hangup = serport_ldisc_hangup, .write_wakeup = serport_ldisc_write_wakeup }; /* * The functions for insering/removing us as a module. */ static int __init serport_init(void) { int retval; retval = tty_register_ldisc(&serport_ldisc); if (retval) printk(KERN_ERR "serport.c: Error registering line discipline.\n"); return retval; } static void __exit serport_exit(void) { tty_unregister_ldisc(&serport_ldisc); } module_init(serport_init); module_exit(serport_exit); |
| 509 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 | // SPDX-License-Identifier: GPL-2.0+ /* * linux/net/sunrpc/gss_rpc_upcall.c * * Copyright (C) 2012 Simo Sorce <simo@redhat.com> */ #include <linux/types.h> #include <linux/un.h> #include <linux/sunrpc/svcauth.h> #include "gss_rpc_upcall.h" #define GSSPROXY_SOCK_PATHNAME "/var/run/gssproxy.sock" #define GSSPROXY_PROGRAM (400112u) #define GSSPROXY_VERS_1 (1u) /* * Encoding/Decoding functions */ enum { GSSX_NULL = 0, /* Unused */ GSSX_INDICATE_MECHS = 1, GSSX_GET_CALL_CONTEXT = 2, GSSX_IMPORT_AND_CANON_NAME = 3, GSSX_EXPORT_CRED = 4, GSSX_IMPORT_CRED = 5, GSSX_ACQUIRE_CRED = 6, GSSX_STORE_CRED = 7, GSSX_INIT_SEC_CONTEXT = 8, GSSX_ACCEPT_SEC_CONTEXT = 9, GSSX_RELEASE_HANDLE = 10, GSSX_GET_MIC = 11, GSSX_VERIFY = 12, GSSX_WRAP = 13, GSSX_UNWRAP = 14, GSSX_WRAP_SIZE_LIMIT = 15, }; #define PROC(proc, name) \ [GSSX_##proc] = { \ .p_proc = GSSX_##proc, \ .p_encode = gssx_enc_##name, \ .p_decode = gssx_dec_##name, \ .p_arglen = GSSX_ARG_##name##_sz, \ .p_replen = GSSX_RES_##name##_sz, \ .p_statidx = GSSX_##proc, \ .p_name = #proc, \ } static const struct rpc_procinfo gssp_procedures[] = { PROC(INDICATE_MECHS, indicate_mechs), PROC(GET_CALL_CONTEXT, get_call_context), PROC(IMPORT_AND_CANON_NAME, import_and_canon_name), PROC(EXPORT_CRED, export_cred), PROC(IMPORT_CRED, import_cred), PROC(ACQUIRE_CRED, acquire_cred), PROC(STORE_CRED, store_cred), PROC(INIT_SEC_CONTEXT, init_sec_context), PROC(ACCEPT_SEC_CONTEXT, accept_sec_context), PROC(RELEASE_HANDLE, release_handle), PROC(GET_MIC, get_mic), PROC(VERIFY, verify), PROC(WRAP, wrap), PROC(UNWRAP, unwrap), PROC(WRAP_SIZE_LIMIT, wrap_size_limit), }; /* * Common transport functions */ static const struct rpc_program gssp_program; static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) { static const struct sockaddr_un gssp_localaddr = { .sun_family = AF_LOCAL, .sun_path = GSSPROXY_SOCK_PATHNAME, }; struct rpc_create_args args = { .net = net, .protocol = XPRT_TRANSPORT_LOCAL, .address = (struct sockaddr *)&gssp_localaddr, .addrsize = sizeof(gssp_localaddr), .servername = "localhost", .program = &gssp_program, .version = GSSPROXY_VERS_1, .authflavor = RPC_AUTH_NULL, /* * Note we want connection to be done in the caller's * filesystem namespace. We therefore turn off the idle * timeout, which would result in reconnections being * done without the correct namespace: */ .flags = RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_CONNECTED | RPC_CLNT_CREATE_NO_IDLE_TIMEOUT }; struct rpc_clnt *clnt; int result = 0; clnt = rpc_create(&args); if (IS_ERR(clnt)) { dprintk("RPC: failed to create AF_LOCAL gssproxy " "client (errno %ld).\n", PTR_ERR(clnt)); result = PTR_ERR(clnt); *_clnt = NULL; goto out; } dprintk("RPC: created new gssp local client (gssp_local_clnt: " "%p)\n", clnt); *_clnt = clnt; out: return result; } void init_gssp_clnt(struct sunrpc_net *sn) { mutex_init(&sn->gssp_lock); sn->gssp_clnt = NULL; } int set_gssp_clnt(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_clnt *clnt; int ret; mutex_lock(&sn->gssp_lock); ret = gssp_rpc_create(net, &clnt); if (!ret) { if (sn->gssp_clnt) rpc_shutdown_client(sn->gssp_clnt); sn->gssp_clnt = clnt; } mutex_unlock(&sn->gssp_lock); return ret; } void clear_gssp_clnt(struct sunrpc_net *sn) { mutex_lock(&sn->gssp_lock); if (sn->gssp_clnt) { rpc_shutdown_client(sn->gssp_clnt); sn->gssp_clnt = NULL; } mutex_unlock(&sn->gssp_lock); } static struct rpc_clnt *get_gssp_clnt(struct sunrpc_net *sn) { struct rpc_clnt *clnt; mutex_lock(&sn->gssp_lock); clnt = sn->gssp_clnt; if (clnt) refcount_inc(&clnt->cl_count); mutex_unlock(&sn->gssp_lock); return clnt; } static int gssp_call(struct net *net, struct rpc_message *msg) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_clnt *clnt; int status; clnt = get_gssp_clnt(sn); if (!clnt) return -EIO; status = rpc_call_sync(clnt, msg, 0); if (status < 0) { dprintk("gssp: rpc_call returned error %d\n", -status); switch (status) { case -EPROTONOSUPPORT: status = -EINVAL; break; case -ECONNREFUSED: case -ETIMEDOUT: case -ENOTCONN: status = -EAGAIN; break; case -ERESTARTSYS: if (signalled ()) status = -EINTR; break; default: break; } } rpc_release_client(clnt); return status; } static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg) { unsigned int i; for (i = 0; i < arg->npages && arg->pages[i]; i++) __free_page(arg->pages[i]); kfree(arg->pages); } static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg) { unsigned int i; arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE); arg->pages = kcalloc(arg->npages, sizeof(struct page *), GFP_KERNEL); if (!arg->pages) return -ENOMEM; for (i = 0; i < arg->npages; i++) { arg->pages[i] = alloc_page(GFP_KERNEL); if (!arg->pages[i]) { gssp_free_receive_pages(arg); return -ENOMEM; } } return 0; } static char *gssp_stringify(struct xdr_netobj *netobj) { return kmemdup_nul(netobj->data, netobj->len, GFP_KERNEL); } static void gssp_hostbased_service(char **principal) { char *c; if (!*principal) return; /* terminate and remove realm part */ c = strchr(*principal, '@'); if (c) { *c = '\0'; /* change service-hostname delimiter */ c = strchr(*principal, '/'); if (c) *c = '@'; } if (!c) { /* not a service principal */ kfree(*principal); *principal = NULL; } } /* * Public functions */ /* numbers somewhat arbitrary but large enough for current needs */ #define GSSX_MAX_OUT_HANDLE 128 #define GSSX_MAX_SRC_PRINC 256 #define GSSX_KMEMBUF (GSSX_max_output_handle_sz + \ GSSX_max_oid_sz + \ GSSX_max_princ_sz + \ sizeof(struct svc_cred)) int gssp_accept_sec_context_upcall(struct net *net, struct gssp_upcall_data *data) { struct gssx_ctx ctxh = { .state = data->in_handle }; struct gssx_arg_accept_sec_context arg = { .input_token = data->in_token, }; struct gssx_ctx rctxh = { /* * pass in the max length we expect for each of these * buffers but let the xdr code kmalloc them: */ .exported_context_token.len = GSSX_max_output_handle_sz, .mech.len = GSS_OID_MAX_LEN, .targ_name.display_name.len = GSSX_max_princ_sz, .src_name.display_name.len = GSSX_max_princ_sz }; struct gssx_res_accept_sec_context res = { .context_handle = &rctxh, .output_token = &data->out_token }; struct rpc_message msg = { .rpc_proc = &gssp_procedures[GSSX_ACCEPT_SEC_CONTEXT], .rpc_argp = &arg, .rpc_resp = &res, .rpc_cred = NULL, /* FIXME ? */ }; struct xdr_netobj client_name = { 0 , NULL }; struct xdr_netobj target_name = { 0, NULL }; int ret; if (data->in_handle.len != 0) arg.context_handle = &ctxh; res.output_token->len = GSSX_max_output_token_sz; ret = gssp_alloc_receive_pages(&arg); if (ret) return ret; ret = gssp_call(net, &msg); gssp_free_receive_pages(&arg); /* we need to fetch all data even in case of error so * that we can free special strctures is they have been allocated */ data->major_status = res.status.major_status; data->minor_status = res.status.minor_status; if (res.context_handle) { data->out_handle = rctxh.exported_context_token; data->mech_oid.len = rctxh.mech.len; if (rctxh.mech.data) { memcpy(data->mech_oid.data, rctxh.mech.data, data->mech_oid.len); kfree(rctxh.mech.data); } client_name = rctxh.src_name.display_name; target_name = rctxh.targ_name.display_name; } if (res.options.count == 1) { gssx_buffer *value = &res.options.data[0].value; /* Currently we only decode CREDS_VALUE, if we add * anything else we'll have to loop and match on the * option name */ if (value->len == 1) { /* steal group info from struct svc_cred */ data->creds = *(struct svc_cred *)value->data; data->found_creds = 1; } /* whether we use it or not, free data */ kfree(value->data); } if (res.options.count != 0) { kfree(res.options.data); } /* convert to GSS_NT_HOSTBASED_SERVICE form and set into creds */ if (data->found_creds) { if (client_name.data) { data->creds.cr_raw_principal = gssp_stringify(&client_name); data->creds.cr_principal = gssp_stringify(&client_name); gssp_hostbased_service(&data->creds.cr_principal); } if (target_name.data) { data->creds.cr_targ_princ = gssp_stringify(&target_name); gssp_hostbased_service(&data->creds.cr_targ_princ); } } kfree(client_name.data); kfree(target_name.data); return ret; } void gssp_free_upcall_data(struct gssp_upcall_data *data) { kfree(data->in_handle.data); kfree(data->out_handle.data); kfree(data->out_token.data); free_svc_cred(&data->creds); } /* * Initialization stuff */ static unsigned int gssp_version1_counts[ARRAY_SIZE(gssp_procedures)]; static const struct rpc_version gssp_version1 = { .number = GSSPROXY_VERS_1, .nrprocs = ARRAY_SIZE(gssp_procedures), .procs = gssp_procedures, .counts = gssp_version1_counts, }; static const struct rpc_version *gssp_version[] = { NULL, &gssp_version1, }; static struct rpc_stat gssp_stats; static const struct rpc_program gssp_program = { .name = "gssproxy", .number = GSSPROXY_PROGRAM, .nrvers = ARRAY_SIZE(gssp_version), .version = gssp_version, .stats = &gssp_stats, }; |
| 901 862 271 862 585 471 458 75 464 282 13244 2597 856 970 1795 1502 323 1292 192 1289 401 4486 381 807 3 4 1 5640 134 272 5771 5 322 118 13237 13251 17 13243 13237 13242 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 | // SPDX-License-Identifier: GPL-2.0-only /* * common LSM auditing functions * * Based on code written for SELinux by : * Stephen Smalley * James Morris <jmorris@redhat.com> * Author : Etienne Basset, <etienne.basset@ensta.org> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/fs.h> #include <linux/init.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <linux/ip.h> #include <net/ip.h> #include <net/ipv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/lsm_audit.h> #include <linux/security.h> /** * ipv4_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv4_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int ret = 0; struct iphdr *ih; ih = ip_hdr(skb); ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; if (proto) *proto = ih->protocol; /* non initial fragment */ if (ntohs(ih->frag_off) & IP_OFFSET) return 0; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr *th = tcp_hdr(skb); ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr *uh = udp_hdr(skb); ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_SCTP: { struct sctphdr *sh = sctp_hdr(skb); ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #if IS_ENABLED(CONFIG_IPV6) /** * ipv6_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv6_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ret = 0; struct ipv6hdr *ip6; u8 nexthdr; __be16 frag_off; ip6 = ipv6_hdr(skb); ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; /* IPv6 can have several extension header before the Transport header * skip them */ offset = skb_network_offset(skb); offset += sizeof(*ip6); nexthdr = ip6->nexthdr; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) return 0; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #endif static inline void print_ipv6_addr(struct audit_buffer *ab, const struct in6_addr *addr, __be16 port, const char *name1, const char *name2) { if (!ipv6_addr_any(addr)) audit_log_format(ab, " %s=%pI6c", name1, addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr, __be16 port, const char *name1, const char *name2) { if (addr) audit_log_format(ab, " %s=%pI4", name1, &addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } /** * audit_log_lsm_data - helper to log common LSM audit data * @ab : the audit buffer * @a : common audit data */ void audit_log_lsm_data(struct audit_buffer *ab, const struct common_audit_data *a) { /* * To keep stack sizes in check force programmers to notice if they * start making this union too large! See struct lsm_network_audit * as an example of how to deal with large data. */ BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2); switch (a->type) { case LSM_AUDIT_DATA_NONE: return; case LSM_AUDIT_DATA_IPC: audit_log_format(ab, " ipc_key=%d ", a->u.ipc_id); break; case LSM_AUDIT_DATA_CAP: audit_log_format(ab, " capability=%d ", a->u.cap); break; case LSM_AUDIT_DATA_PATH: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.path); inode = d_backing_inode(a->u.path.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_FILE: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.file->f_path); inode = file_inode(a->u.file); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_IOCTL_OP: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.op->path); inode = a->u.op->path.dentry->d_inode; if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd); break; } case LSM_AUDIT_DATA_DENTRY: { struct inode *inode; audit_log_format(ab, " name="); spin_lock(&a->u.dentry->d_lock); audit_log_untrustedstring(ab, a->u.dentry->d_name.name); spin_unlock(&a->u.dentry->d_lock); inode = d_backing_inode(a->u.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_INODE: { struct dentry *dentry; struct inode *inode; rcu_read_lock(); inode = a->u.inode; dentry = d_find_alias_rcu(inode); if (dentry) { audit_log_format(ab, " name="); spin_lock(&dentry->d_lock); audit_log_untrustedstring(ab, dentry->d_name.name); spin_unlock(&dentry->d_lock); } audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); rcu_read_unlock(); break; } case LSM_AUDIT_DATA_TASK: { struct task_struct *tsk = a->u.tsk; if (tsk) { pid_t pid = task_tgid_nr(tsk); if (pid) { char tskcomm[sizeof(tsk->comm)]; audit_log_format(ab, " opid=%d ocomm=", pid); audit_log_untrustedstring(ab, get_task_comm(tskcomm, tsk)); } } break; } case LSM_AUDIT_DATA_NET: if (a->u.net->sk) { const struct sock *sk = a->u.net->sk; const struct unix_sock *u; struct unix_address *addr; int len = 0; char *p = NULL; switch (sk->sk_family) { case AF_INET: { const struct inet_sock *inet = inet_sk(sk); print_ipv4_addr(ab, inet->inet_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv4_addr(ab, inet->inet_daddr, inet->inet_dport, "faddr", "fport"); break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { const struct inet_sock *inet = inet_sk(sk); print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv6_addr(ab, &sk->sk_v6_daddr, inet->inet_dport, "faddr", "fport"); break; } #endif case AF_UNIX: u = unix_sk(sk); addr = smp_load_acquire(&u->addr); if (!addr) break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } len = addr->len-sizeof(short); p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); else audit_log_n_hex(ab, p, len); break; } } switch (a->u.net->family) { case AF_INET: print_ipv4_addr(ab, a->u.net->v4info.saddr, a->u.net->sport, "saddr", "src"); print_ipv4_addr(ab, a->u.net->v4info.daddr, a->u.net->dport, "daddr", "dest"); break; case AF_INET6: print_ipv6_addr(ab, &a->u.net->v6info.saddr, a->u.net->sport, "saddr", "src"); print_ipv6_addr(ab, &a->u.net->v6info.daddr, a->u.net->dport, "daddr", "dest"); break; } if (a->u.net->netif > 0) { struct net_device *dev; /* NOTE: we always use init's namespace */ dev = dev_get_by_index(&init_net, a->u.net->netif); if (dev) { audit_log_format(ab, " netif=%s", dev->name); dev_put(dev); } } break; #ifdef CONFIG_KEYS case LSM_AUDIT_DATA_KEY: audit_log_format(ab, " key_serial=%u", a->u.key_struct.key); if (a->u.key_struct.key_desc) { audit_log_format(ab, " key_desc="); audit_log_untrustedstring(ab, a->u.key_struct.key_desc); } break; #endif case LSM_AUDIT_DATA_KMOD: audit_log_format(ab, " kmod="); audit_log_untrustedstring(ab, a->u.kmod_name); break; case LSM_AUDIT_DATA_IBPKEY: { struct in6_addr sbn_pfx; memset(&sbn_pfx.s6_addr, 0, sizeof(sbn_pfx.s6_addr)); memcpy(&sbn_pfx.s6_addr, &a->u.ibpkey->subnet_prefix, sizeof(a->u.ibpkey->subnet_prefix)); audit_log_format(ab, " pkey=0x%x subnet_prefix=%pI6c", a->u.ibpkey->pkey, &sbn_pfx); break; } case LSM_AUDIT_DATA_IBENDPORT: audit_log_format(ab, " device=%s port_num=%u", a->u.ibendport->dev_name, a->u.ibendport->port); break; case LSM_AUDIT_DATA_LOCKDOWN: audit_log_format(ab, " lockdown_reason=\"%s\"", lockdown_reasons[a->u.reason]); break; case LSM_AUDIT_DATA_ANONINODE: audit_log_format(ab, " anonclass=%s", a->u.anonclass); break; case LSM_AUDIT_DATA_NLMSGTYPE: audit_log_format(ab, " nl-msgtype=%hu", a->u.nlmsg_type); break; } /* switch (a->type) */ } /** * dump_common_audit_data - helper to dump common audit data * @ab : the audit buffer * @a : common audit data */ static void dump_common_audit_data(struct audit_buffer *ab, const struct common_audit_data *a) { char comm[sizeof(current->comm)]; audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current)); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_lsm_data(ab, a); } /** * common_lsm_audit - generic LSM auditing function * @a: auxiliary audit data * @pre_audit: lsm-specific pre-audit callback * @post_audit: lsm-specific post-audit callback * * setup the audit buffer for common security information * uses callback to print LSM specific information */ void common_lsm_audit(struct common_audit_data *a, void (*pre_audit)(struct audit_buffer *, void *), void (*post_audit)(struct audit_buffer *, void *)) { struct audit_buffer *ab; if (a == NULL) return; /* we use GFP_ATOMIC so we won't sleep */ ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN, AUDIT_AVC); if (ab == NULL) return; if (pre_audit) pre_audit(ab, a); dump_common_audit_data(ab, a); if (post_audit) post_audit(ab, a); audit_log_end(ab); } |
| 86 19 71 69 63 45 57 57 57 52 52 22 52 132 85 66 9 4 57 45 57 66 82 30 52 29 52 21 20 1 71 10 61 61 60 87 65 22 86 12 468 467 468 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3: Garbage Collector For AF_UNIX sockets * * Garbage Collector: * Copyright (C) Barak A. Pearlmutter. * * Chopped about by Alan Cox 22/3/96 to make it fit the AF_UNIX socket problem. * If it doesn't work blame me, it worked when Barak sent it. * * Assumptions: * * - object w/ a bit * - free list * * Current optimizations: * * - explicit stack instead of recursion * - tail recurse on first born instead of immediate push/pop * - we gather the stuff that should not be killed into tree * and stack is just a path from root to the current pointer. * * Future optimizations: * * - don't just push entire root set; process in place * * Fixes: * Alan Cox 07 Sept 1997 Vmalloc internal stack as needed. * Cope with changing max_files. * Al Viro 11 Oct 1998 * Graph may have cycles. That is, we can send the descriptor * of foo to bar and vice versa. Current code chokes on that. * Fix: move SCM_RIGHTS ones into the separate list and then * skb_free() them all instead of doing explicit fput's. * Another problem: since fput() may block somebody may * create a new unix_socket when we are in the middle of sweep * phase. Fix: revert the logic wrt MARKED. Mark everything * upon the beginning and unmark non-junk ones. * * [12 Oct 1998] AAARGH! New code purges all SCM_RIGHTS * sent to connect()'ed but still not accept()'ed sockets. * Fixed. Old code had slightly different problem here: * extra fput() in situation when we passed the descriptor via * such socket and closed it (descriptor). That would happen on * each unix_gc() until the accept(). Since the struct file in * question would go to the free list and might be reused... * That might be the reason of random oopses on filp_close() * in unrelated processes. * * AV 28 Feb 1999 * Kill the explicit allocation of stack. Now we keep the tree * with root in dummy + pointer (gc_current) to one of the nodes. * Stack is represented as path from gc_current to dummy. Unmark * now means "add to tree". Push == "make it a son of gc_current". * Pop == "move gc_current to parent". We keep only pointers to * parents (->gc_tree). * AV 1 Mar 1999 * Damn. Added missing check for ->dead in listen queues scanning. * * Miklos Szeredi 25 Jun 2007 * Reimplement with a cycle collecting algorithm. This should * solve several problems with the previous code, like being racy * wrt receive and holding up unrelated socket operations. */ #include <linux/fs.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/workqueue.h> #include <net/af_unix.h> #include <net/scm.h> #include <net/tcp_states.h> #include "af_unix.h" struct unix_vertex { struct list_head edges; struct list_head entry; struct list_head scc_entry; unsigned long out_degree; unsigned long index; unsigned long scc_index; }; struct unix_edge { struct unix_sock *predecessor; struct unix_sock *successor; struct list_head vertex_entry; struct list_head stack_entry; }; struct unix_sock *unix_get_socket(struct file *filp) { struct inode *inode = file_inode(filp); /* Socket ? */ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); const struct proto_ops *ops; struct sock *sk = sock->sk; ops = READ_ONCE(sock->ops); /* PF_UNIX ? */ if (sk && ops && ops->family == PF_UNIX) return unix_sk(sk); } return NULL; } static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) { /* If an embryo socket has a fd, * the listener indirectly holds the fd's refcnt. */ if (edge->successor->listener) return unix_sk(edge->successor->listener)->vertex; return edge->successor->vertex; } static bool unix_graph_maybe_cyclic; static bool unix_graph_grouped; static void unix_update_graph(struct unix_vertex *vertex) { /* If the receiver socket is not inflight, no cyclic * reference could be formed. */ if (!vertex) return; unix_graph_maybe_cyclic = true; unix_graph_grouped = false; } static LIST_HEAD(unix_unvisited_vertices); enum unix_vertex_index { UNIX_VERTEX_INDEX_MARK1, UNIX_VERTEX_INDEX_MARK2, UNIX_VERTEX_INDEX_START, }; static unsigned long unix_vertex_unvisited_index = UNIX_VERTEX_INDEX_MARK1; static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) { struct unix_vertex *vertex = edge->predecessor->vertex; if (!vertex) { vertex = list_first_entry(&fpl->vertices, typeof(*vertex), entry); vertex->index = unix_vertex_unvisited_index; vertex->out_degree = 0; INIT_LIST_HEAD(&vertex->edges); INIT_LIST_HEAD(&vertex->scc_entry); list_move_tail(&vertex->entry, &unix_unvisited_vertices); edge->predecessor->vertex = vertex; } vertex->out_degree++; list_add_tail(&edge->vertex_entry, &vertex->edges); unix_update_graph(unix_edge_successor(edge)); } static void unix_del_edge(struct scm_fp_list *fpl, struct unix_edge *edge) { struct unix_vertex *vertex = edge->predecessor->vertex; if (!fpl->dead) unix_update_graph(unix_edge_successor(edge)); list_del(&edge->vertex_entry); vertex->out_degree--; if (!vertex->out_degree) { edge->predecessor->vertex = NULL; list_move_tail(&vertex->entry, &fpl->vertices); } } static void unix_free_vertices(struct scm_fp_list *fpl) { struct unix_vertex *vertex, *next_vertex; list_for_each_entry_safe(vertex, next_vertex, &fpl->vertices, entry) { list_del(&vertex->entry); kfree(vertex); } } static DEFINE_SPINLOCK(unix_gc_lock); unsigned int unix_tot_inflight; void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) { int i = 0, j = 0; spin_lock(&unix_gc_lock); if (!fpl->count_unix) goto out; do { struct unix_sock *inflight = unix_get_socket(fpl->fp[j++]); struct unix_edge *edge; if (!inflight) continue; edge = fpl->edges + i++; edge->predecessor = inflight; edge->successor = receiver; unix_add_edge(fpl, edge); } while (i < fpl->count_unix); receiver->scm_stat.nr_unix_fds += fpl->count_unix; WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); spin_unlock(&unix_gc_lock); fpl->inflight = true; unix_free_vertices(fpl); } void unix_del_edges(struct scm_fp_list *fpl) { struct unix_sock *receiver; int i = 0; spin_lock(&unix_gc_lock); if (!fpl->count_unix) goto out; do { struct unix_edge *edge = fpl->edges + i++; unix_del_edge(fpl, edge); } while (i < fpl->count_unix); if (!fpl->dead) { receiver = fpl->edges[0].successor; receiver->scm_stat.nr_unix_fds -= fpl->count_unix; } WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); spin_unlock(&unix_gc_lock); fpl->inflight = false; } void unix_update_edges(struct unix_sock *receiver) { /* nr_unix_fds is only updated under unix_state_lock(). * If it's 0 here, the embryo socket is not part of the * inflight graph, and GC will not see it, so no lock needed. */ if (!receiver->scm_stat.nr_unix_fds) { receiver->listener = NULL; } else { spin_lock(&unix_gc_lock); unix_update_graph(unix_sk(receiver->listener)->vertex); receiver->listener = NULL; spin_unlock(&unix_gc_lock); } } int unix_prepare_fpl(struct scm_fp_list *fpl) { struct unix_vertex *vertex; int i; if (!fpl->count_unix) return 0; for (i = 0; i < fpl->count_unix; i++) { vertex = kmalloc(sizeof(*vertex), GFP_KERNEL); if (!vertex) goto err; list_add(&vertex->entry, &fpl->vertices); } fpl->edges = kvmalloc_array(fpl->count_unix, sizeof(*fpl->edges), GFP_KERNEL_ACCOUNT); if (!fpl->edges) goto err; return 0; err: unix_free_vertices(fpl); return -ENOMEM; } void unix_destroy_fpl(struct scm_fp_list *fpl) { if (fpl->inflight) unix_del_edges(fpl); kvfree(fpl->edges); unix_free_vertices(fpl); } static bool unix_vertex_dead(struct unix_vertex *vertex) { struct unix_edge *edge; struct unix_sock *u; long total_ref; list_for_each_entry(edge, &vertex->edges, vertex_entry) { struct unix_vertex *next_vertex = unix_edge_successor(edge); /* The vertex's fd can be received by a non-inflight socket. */ if (!next_vertex) return false; /* The vertex's fd can be received by an inflight socket in * another SCC. */ if (next_vertex->scc_index != vertex->scc_index) return false; } /* No receiver exists out of the same SCC. */ edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); u = edge->predecessor; total_ref = file_count(u->sk.sk_socket->file); /* If not close()d, total_ref > out_degree. */ if (total_ref != vertex->out_degree) return false; return true; } static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) { struct unix_vertex *vertex; list_for_each_entry_reverse(vertex, scc, scc_entry) { struct sk_buff_head *queue; struct unix_edge *edge; struct unix_sock *u; edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); u = edge->predecessor; queue = &u->sk.sk_receive_queue; spin_lock(&queue->lock); if (u->sk.sk_state == TCP_LISTEN) { struct sk_buff *skb; skb_queue_walk(queue, skb) { struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; spin_lock(&embryo_queue->lock); skb_queue_splice_init(embryo_queue, hitlist); spin_unlock(&embryo_queue->lock); } } else { skb_queue_splice_init(queue, hitlist); } spin_unlock(&queue->lock); } } static bool unix_scc_cyclic(struct list_head *scc) { struct unix_vertex *vertex; struct unix_edge *edge; /* SCC containing multiple vertices ? */ if (!list_is_singular(scc)) return true; vertex = list_first_entry(scc, typeof(*vertex), scc_entry); /* Self-reference or a embryo-listener circle ? */ list_for_each_entry(edge, &vertex->edges, vertex_entry) { if (unix_edge_successor(edge) == vertex) return true; } return false; } static LIST_HEAD(unix_visited_vertices); static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, struct sk_buff_head *hitlist) { LIST_HEAD(vertex_stack); struct unix_edge *edge; LIST_HEAD(edge_stack); next_vertex: /* Push vertex to vertex_stack and mark it as on-stack * (index >= UNIX_VERTEX_INDEX_START). * The vertex will be popped when finalising SCC later. */ list_add(&vertex->scc_entry, &vertex_stack); vertex->index = *last_index; vertex->scc_index = *last_index; (*last_index)++; /* Explore neighbour vertices (receivers of the current vertex's fd). */ list_for_each_entry(edge, &vertex->edges, vertex_entry) { struct unix_vertex *next_vertex = unix_edge_successor(edge); if (!next_vertex) continue; if (next_vertex->index == unix_vertex_unvisited_index) { /* Iterative deepening depth first search * * 1. Push a forward edge to edge_stack and set * the successor to vertex for the next iteration. */ list_add(&edge->stack_entry, &edge_stack); vertex = next_vertex; goto next_vertex; /* 2. Pop the edge directed to the current vertex * and restore the ancestor for backtracking. */ prev_vertex: edge = list_first_entry(&edge_stack, typeof(*edge), stack_entry); list_del_init(&edge->stack_entry); next_vertex = vertex; vertex = edge->predecessor->vertex; /* If the successor has a smaller scc_index, two vertices * are in the same SCC, so propagate the smaller scc_index * to skip SCC finalisation. */ vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); } else if (next_vertex->index != unix_vertex_grouped_index) { /* Loop detected by a back/cross edge. * * The successor is on vertex_stack, so two vertices are in * the same SCC. If the successor has a smaller *scc_index*, * propagate it to skip SCC finalisation. */ vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); } else { /* The successor was already grouped as another SCC */ } } if (vertex->index == vertex->scc_index) { struct unix_vertex *v; struct list_head scc; bool scc_dead = true; /* SCC finalised. * * If the scc_index was not updated, all the vertices above on * vertex_stack are in the same SCC. Group them using scc_entry. */ __list_cut_position(&scc, &vertex_stack, &vertex->scc_entry); list_for_each_entry_reverse(v, &scc, scc_entry) { /* Don't restart DFS from this vertex in unix_walk_scc(). */ list_move_tail(&v->entry, &unix_visited_vertices); /* Mark vertex as off-stack. */ v->index = unix_vertex_grouped_index; if (scc_dead) scc_dead = unix_vertex_dead(v); } if (scc_dead) unix_collect_skb(&scc, hitlist); else if (!unix_graph_maybe_cyclic) unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); list_del(&scc); } /* Need backtracking ? */ if (!list_empty(&edge_stack)) goto prev_vertex; } static void unix_walk_scc(struct sk_buff_head *hitlist) { unsigned long last_index = UNIX_VERTEX_INDEX_START; unix_graph_maybe_cyclic = false; /* Visit every vertex exactly once. * __unix_walk_scc() moves visited vertices to unix_visited_vertices. */ while (!list_empty(&unix_unvisited_vertices)) { struct unix_vertex *vertex; vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); __unix_walk_scc(vertex, &last_index, hitlist); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); unix_graph_grouped = true; } static void unix_walk_scc_fast(struct sk_buff_head *hitlist) { unix_graph_maybe_cyclic = false; while (!list_empty(&unix_unvisited_vertices)) { struct unix_vertex *vertex; struct list_head scc; bool scc_dead = true; vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); list_add(&scc, &vertex->scc_entry); list_for_each_entry_reverse(vertex, &scc, scc_entry) { list_move_tail(&vertex->entry, &unix_visited_vertices); if (scc_dead) scc_dead = unix_vertex_dead(vertex); } if (scc_dead) unix_collect_skb(&scc, hitlist); else if (!unix_graph_maybe_cyclic) unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); list_del(&scc); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); } static bool gc_in_progress; static void __unix_gc(struct work_struct *work) { struct sk_buff_head hitlist; struct sk_buff *skb; spin_lock(&unix_gc_lock); if (!unix_graph_maybe_cyclic) { spin_unlock(&unix_gc_lock); goto skip_gc; } __skb_queue_head_init(&hitlist); if (unix_graph_grouped) unix_walk_scc_fast(&hitlist); else unix_walk_scc(&hitlist); spin_unlock(&unix_gc_lock); skb_queue_walk(&hitlist, skb) { if (UNIXCB(skb).fp) UNIXCB(skb).fp->dead = true; } __skb_queue_purge_reason(&hitlist, SKB_DROP_REASON_SOCKET_CLOSE); skip_gc: WRITE_ONCE(gc_in_progress, false); } static DECLARE_WORK(unix_gc_work, __unix_gc); void unix_gc(void) { WRITE_ONCE(gc_in_progress, true); queue_work(system_unbound_wq, &unix_gc_work); } #define UNIX_INFLIGHT_TRIGGER_GC 16000 #define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) void wait_for_unix_gc(struct scm_fp_list *fpl) { /* If number of inflight sockets is insane, * force a garbage collect right now. * * Paired with the WRITE_ONCE() in unix_inflight(), * unix_notinflight(), and __unix_gc(). */ if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && !READ_ONCE(gc_in_progress)) unix_gc(); /* Penalise users who want to send AF_UNIX sockets * but whose sockets have not been received yet. */ if (!fpl || !fpl->count_unix || READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) return; if (READ_ONCE(gc_in_progress)) flush_work(&unix_gc_work); } |
| 11 3 8 81 81 1 4 1 2 2 2 2 2 81 81 8 8 8 87 2 1 85 6 81 1 81 6 57 56 57 2 2 1 52 3 1 2 3 2 1 18 18 12 6 6 56 1 2 1 1 1 2 1 1 52 4 4 1 3 20 20 81 81 77 4 1 66 66 1 1 2 1 1 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 | // SPDX-License-Identifier: GPL-2.0-only /* * File: socket.c * * Phonet sockets * * Copyright (C) 2008 Nokia Corporation. * * Authors: Sakari Ailus <sakari.ailus@nokia.com> * Rémi Denis-Courmont */ #include <linux/gfp.h> #include <linux/kernel.h> #include <linux/net.h> #include <linux/poll.h> #include <linux/sched/signal.h> #include <net/sock.h> #include <net/tcp_states.h> #include <linux/phonet.h> #include <linux/export.h> #include <net/phonet/phonet.h> #include <net/phonet/pep.h> #include <net/phonet/pn_dev.h> static int pn_socket_release(struct socket *sock) { struct sock *sk = sock->sk; if (sk) { sock->sk = NULL; sk->sk_prot->close(sk, 0); } return 0; } #define PN_HASHSIZE 16 #define PN_HASHMASK (PN_HASHSIZE-1) static struct { struct hlist_head hlist[PN_HASHSIZE]; struct mutex lock; } pnsocks; void __init pn_sock_init(void) { unsigned int i; for (i = 0; i < PN_HASHSIZE; i++) INIT_HLIST_HEAD(pnsocks.hlist + i); mutex_init(&pnsocks.lock); } static struct hlist_head *pn_hash_list(u16 obj) { return pnsocks.hlist + (obj & PN_HASHMASK); } /* * Find address based on socket address, match only certain fields. * Also grab sock if it was found. Remember to sock_put it later. */ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) { struct sock *sknode; struct sock *rval = NULL; u16 obj = pn_sockaddr_get_object(spn); u8 res = spn->spn_resource; struct hlist_head *hlist = pn_hash_list(obj); rcu_read_lock(); sk_for_each_rcu(sknode, hlist) { struct pn_sock *pn = pn_sk(sknode); BUG_ON(!pn->sobject); /* unbound socket */ if (!net_eq(sock_net(sknode), net)) continue; if (pn_port(obj)) { /* Look up socket by port */ if (pn_port(pn->sobject) != pn_port(obj)) continue; } else { /* If port is zero, look up by resource */ if (pn->resource != res) continue; } if (pn_addr(pn->sobject) && pn_addr(pn->sobject) != pn_addr(obj)) continue; rval = sknode; sock_hold(sknode); break; } rcu_read_unlock(); return rval; } /* Deliver a broadcast packet (only in bottom-half) */ void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) { struct hlist_head *hlist = pnsocks.hlist; unsigned int h; rcu_read_lock(); for (h = 0; h < PN_HASHSIZE; h++) { struct sock *sknode; sk_for_each(sknode, hlist) { struct sk_buff *clone; if (!net_eq(sock_net(sknode), net)) continue; if (!sock_flag(sknode, SOCK_BROADCAST)) continue; clone = skb_clone(skb, GFP_ATOMIC); if (clone) { sock_hold(sknode); sk_receive_skb(sknode, clone, 0); } } hlist++; } rcu_read_unlock(); } int pn_sock_hash(struct sock *sk) { struct hlist_head *hlist = pn_hash_list(pn_sk(sk)->sobject); mutex_lock(&pnsocks.lock); sk_add_node_rcu(sk, hlist); mutex_unlock(&pnsocks.lock); return 0; } EXPORT_SYMBOL(pn_sock_hash); void pn_sock_unhash(struct sock *sk) { mutex_lock(&pnsocks.lock); sk_del_node_init_rcu(sk); mutex_unlock(&pnsocks.lock); pn_sock_unbind_all_res(sk); synchronize_rcu(); } EXPORT_SYMBOL(pn_sock_unhash); static DEFINE_MUTEX(port_mutex); static int pn_socket_bind(struct socket *sock, struct sockaddr *addr, int len) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); struct sockaddr_pn *spn = (struct sockaddr_pn *)addr; int err; u16 handle; u8 saddr; if (sk->sk_prot->bind) return sk->sk_prot->bind(sk, addr, len); if (len < sizeof(struct sockaddr_pn)) return -EINVAL; if (spn->spn_family != AF_PHONET) return -EAFNOSUPPORT; handle = pn_sockaddr_get_object((struct sockaddr_pn *)addr); saddr = pn_addr(handle); if (saddr && phonet_address_lookup(sock_net(sk), saddr)) return -EADDRNOTAVAIL; lock_sock(sk); if (sk->sk_state != TCP_CLOSE || pn_port(pn->sobject)) { err = -EINVAL; /* attempt to rebind */ goto out; } WARN_ON(sk_hashed(sk)); mutex_lock(&port_mutex); err = sk->sk_prot->get_port(sk, pn_port(handle)); if (err) goto out_port; /* get_port() sets the port, bind() sets the address if applicable */ pn->sobject = pn_object(saddr, pn_port(pn->sobject)); pn->resource = spn->spn_resource; /* Enable RX on the socket */ err = sk->sk_prot->hash(sk); out_port: mutex_unlock(&port_mutex); out: release_sock(sk); return err; } static int pn_socket_autobind(struct socket *sock) { struct sockaddr_pn sa; int err; memset(&sa, 0, sizeof(sa)); sa.spn_family = AF_PHONET; err = pn_socket_bind(sock, (struct sockaddr *)&sa, sizeof(struct sockaddr_pn)); if (err != -EINVAL) return err; BUG_ON(!pn_port(pn_sk(sock->sk)->sobject)); return 0; /* socket was already bound */ } static int pn_socket_connect(struct socket *sock, struct sockaddr *addr, int len, int flags) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); struct sockaddr_pn *spn = (struct sockaddr_pn *)addr; struct task_struct *tsk = current; long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); int err; if (pn_socket_autobind(sock)) return -ENOBUFS; if (len < sizeof(struct sockaddr_pn)) return -EINVAL; if (spn->spn_family != AF_PHONET) return -EAFNOSUPPORT; lock_sock(sk); switch (sock->state) { case SS_UNCONNECTED: if (sk->sk_state != TCP_CLOSE) { err = -EISCONN; goto out; } break; case SS_CONNECTING: err = -EALREADY; goto out; default: err = -EISCONN; goto out; } pn->dobject = pn_sockaddr_get_object(spn); pn->resource = pn_sockaddr_get_resource(spn); sock->state = SS_CONNECTING; err = sk->sk_prot->connect(sk, addr, len); if (err) { sock->state = SS_UNCONNECTED; pn->dobject = 0; goto out; } while (sk->sk_state == TCP_SYN_SENT) { DEFINE_WAIT(wait); if (!timeo) { err = -EINPROGRESS; goto out; } if (signal_pending(tsk)) { err = sock_intr_errno(timeo); goto out; } prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); finish_wait(sk_sleep(sk), &wait); } if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED)) err = 0; else if (sk->sk_state == TCP_CLOSE_WAIT) err = -ECONNRESET; else err = -ECONNREFUSED; sock->state = err ? SS_UNCONNECTED : SS_CONNECTED; out: release_sock(sk); return err; } static int pn_socket_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *sk = sock->sk; struct sock *newsk; if (unlikely(sk->sk_state != TCP_LISTEN)) return -EINVAL; newsk = sk->sk_prot->accept(sk, arg); if (!newsk) return arg->err; lock_sock(newsk); sock_graft(newsk, newsock); newsock->state = SS_CONNECTED; release_sock(newsk); return 0; } static int pn_socket_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); memset(addr, 0, sizeof(struct sockaddr_pn)); addr->sa_family = AF_PHONET; if (!peer) /* Race with bind() here is userland's problem. */ pn_sockaddr_set_object((struct sockaddr_pn *)addr, pn->sobject); return sizeof(struct sockaddr_pn); } static __poll_t pn_socket_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct pep_sock *pn = pep_sk(sk); __poll_t mask = 0; poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == TCP_CLOSE) return EPOLLERR; if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (!skb_queue_empty_lockless(&pn->ctrlreq_queue)) mask |= EPOLLPRI; if (!mask && sk->sk_state == TCP_CLOSE_WAIT) return EPOLLHUP; if (sk->sk_state == TCP_ESTABLISHED && refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf && atomic_read(&pn->tx_credits)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; } static int pn_socket_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); if (cmd == SIOCPNGETOBJECT) { struct net_device *dev; u16 handle; u8 saddr; if (get_user(handle, (__u16 __user *)arg)) return -EFAULT; lock_sock(sk); if (sk->sk_bound_dev_if) dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if); else dev = phonet_device_get(sock_net(sk)); if (dev && (dev->flags & IFF_UP)) saddr = phonet_address_get(dev, pn_addr(handle)); else saddr = PN_NO_ADDR; release_sock(sk); dev_put(dev); if (saddr == PN_NO_ADDR) return -EHOSTUNREACH; handle = pn_object(saddr, pn_port(pn->sobject)); return put_user(handle, (__u16 __user *)arg); } return sk_ioctl(sk, cmd, (void __user *)arg); } static int pn_socket_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int err = 0; if (pn_socket_autobind(sock)) return -ENOBUFS; lock_sock(sk); if (sock->state != SS_UNCONNECTED) { err = -EINVAL; goto out; } if (sk->sk_state != TCP_LISTEN) { sk->sk_state = TCP_LISTEN; sk->sk_ack_backlog = 0; } sk->sk_max_ack_backlog = backlog; out: release_sock(sk); return err; } static int pn_socket_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; if (pn_socket_autobind(sock)) return -EAGAIN; return sk->sk_prot->sendmsg(sk, m, total_len); } const struct proto_ops phonet_dgram_ops = { .family = AF_PHONET, .owner = THIS_MODULE, .release = pn_socket_release, .bind = pn_socket_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = pn_socket_getname, .poll = datagram_poll, .ioctl = pn_socket_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = pn_socket_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, }; const struct proto_ops phonet_stream_ops = { .family = AF_PHONET, .owner = THIS_MODULE, .release = pn_socket_release, .bind = pn_socket_bind, .connect = pn_socket_connect, .socketpair = sock_no_socketpair, .accept = pn_socket_accept, .getname = pn_socket_getname, .poll = pn_socket_poll, .ioctl = pn_socket_ioctl, .listen = pn_socket_listen, .shutdown = sock_no_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = pn_socket_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, }; EXPORT_SYMBOL(phonet_stream_ops); /* allocate port for a socket */ int pn_sock_get_port(struct sock *sk, unsigned short sport) { static int port_cur; struct net *net = sock_net(sk); struct pn_sock *pn = pn_sk(sk); struct sockaddr_pn try_sa; struct sock *tmpsk; memset(&try_sa, 0, sizeof(struct sockaddr_pn)); try_sa.spn_family = AF_PHONET; WARN_ON(!mutex_is_locked(&port_mutex)); if (!sport) { /* search free port */ int port, pmin, pmax; phonet_get_local_port_range(&pmin, &pmax); for (port = pmin; port <= pmax; port++) { port_cur++; if (port_cur < pmin || port_cur > pmax) port_cur = pmin; pn_sockaddr_set_port(&try_sa, port_cur); tmpsk = pn_find_sock_by_sa(net, &try_sa); if (tmpsk == NULL) { sport = port_cur; goto found; } else sock_put(tmpsk); } } else { /* try to find specific port */ pn_sockaddr_set_port(&try_sa, sport); tmpsk = pn_find_sock_by_sa(net, &try_sa); if (tmpsk == NULL) /* No sock there! We can use that port... */ goto found; else sock_put(tmpsk); } /* the port must be in use already */ return -EADDRINUSE; found: pn->sobject = pn_object(pn_addr(pn->sobject), sport); return 0; } EXPORT_SYMBOL(pn_sock_get_port); #ifdef CONFIG_PROC_FS static struct sock *pn_sock_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); struct hlist_head *hlist = pnsocks.hlist; struct sock *sknode; unsigned int h; for (h = 0; h < PN_HASHSIZE; h++) { sk_for_each_rcu(sknode, hlist) { if (!net_eq(net, sock_net(sknode))) continue; if (!pos) return sknode; pos--; } hlist++; } return NULL; } static struct sock *pn_sock_get_next(struct seq_file *seq, struct sock *sk) { struct net *net = seq_file_net(seq); do sk = sk_next(sk); while (sk && !net_eq(net, sock_net(sk))); return sk; } static void *pn_sock_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? pn_sock_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *pn_sock_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; if (v == SEQ_START_TOKEN) sk = pn_sock_get_idx(seq, 0); else sk = pn_sock_get_next(seq, v); (*pos)++; return sk; } static void pn_sock_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { rcu_read_unlock(); } static int pn_sock_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) seq_puts(seq, "pt loc rem rs st tx_queue rx_queue " " uid inode ref pointer drops"); else { struct sock *sk = v; struct pn_sock *pn = pn_sk(sk); seq_printf(seq, "%2d %04X:%04X:%02X %02X %08X:%08X %5d %lu " "%d %pK %u", sk->sk_protocol, pn->sobject, pn->dobject, pn->resource, sk->sk_state, sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk), from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), refcount_read(&sk->sk_refcnt), sk, atomic_read(&sk->sk_drops)); } seq_pad(seq, '\n'); return 0; } const struct seq_operations pn_sock_seq_ops = { .start = pn_sock_seq_start, .next = pn_sock_seq_next, .stop = pn_sock_seq_stop, .show = pn_sock_seq_show, }; #endif static struct { struct sock *sk[256]; } pnres; /* * Find and hold socket based on resource. */ struct sock *pn_find_sock_by_res(struct net *net, u8 res) { struct sock *sk; if (!net_eq(net, &init_net)) return NULL; rcu_read_lock(); sk = rcu_dereference(pnres.sk[res]); if (sk) sock_hold(sk); rcu_read_unlock(); return sk; } static DEFINE_MUTEX(resource_mutex); int pn_sock_bind_res(struct sock *sk, u8 res) { int ret = -EADDRINUSE; if (!net_eq(sock_net(sk), &init_net)) return -ENOIOCTLCMD; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (pn_socket_autobind(sk->sk_socket)) return -EAGAIN; mutex_lock(&resource_mutex); if (pnres.sk[res] == NULL) { sock_hold(sk); rcu_assign_pointer(pnres.sk[res], sk); ret = 0; } mutex_unlock(&resource_mutex); return ret; } int pn_sock_unbind_res(struct sock *sk, u8 res) { int ret = -ENOENT; if (!capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&resource_mutex); if (pnres.sk[res] == sk) { RCU_INIT_POINTER(pnres.sk[res], NULL); ret = 0; } mutex_unlock(&resource_mutex); if (ret == 0) { synchronize_rcu(); sock_put(sk); } return ret; } void pn_sock_unbind_all_res(struct sock *sk) { unsigned int res, match = 0; mutex_lock(&resource_mutex); for (res = 0; res < 256; res++) { if (pnres.sk[res] == sk) { RCU_INIT_POINTER(pnres.sk[res], NULL); match++; } } mutex_unlock(&resource_mutex); while (match > 0) { __sock_put(sk); match--; } /* Caller is responsible for RCU sync before final sock_put() */ } #ifdef CONFIG_PROC_FS static struct sock **pn_res_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); unsigned int i; if (!net_eq(net, &init_net)) return NULL; for (i = 0; i < 256; i++) { if (pnres.sk[i] == NULL) continue; if (!pos) return pnres.sk + i; pos--; } return NULL; } static struct sock **pn_res_get_next(struct seq_file *seq, struct sock **sk) { struct net *net = seq_file_net(seq); unsigned int i; BUG_ON(!net_eq(net, &init_net)); for (i = (sk - pnres.sk) + 1; i < 256; i++) if (pnres.sk[i]) return pnres.sk + i; return NULL; } static void *pn_res_seq_start(struct seq_file *seq, loff_t *pos) __acquires(resource_mutex) { mutex_lock(&resource_mutex); return *pos ? pn_res_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *pn_res_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock **sk; if (v == SEQ_START_TOKEN) sk = pn_res_get_idx(seq, 0); else sk = pn_res_get_next(seq, v); (*pos)++; return sk; } static void pn_res_seq_stop(struct seq_file *seq, void *v) __releases(resource_mutex) { mutex_unlock(&resource_mutex); } static int pn_res_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 63); if (v == SEQ_START_TOKEN) seq_puts(seq, "rs uid inode"); else { struct sock **psk = v; struct sock *sk = *psk; seq_printf(seq, "%02X %5u %lu", (int) (psk - pnres.sk), from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk)); } seq_pad(seq, '\n'); return 0; } const struct seq_operations pn_res_seq_ops = { .start = pn_res_seq_start, .next = pn_res_seq_next, .stop = pn_res_seq_stop, .show = pn_res_seq_show, }; #endif |
| 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file holds USB constants and structures that are needed for * USB device APIs. These are used by the USB device model, which is * defined in chapter 9 of the USB 2.0 specification and in the * Wireless USB 1.0 spec (now defunct). Linux has several APIs in C that * need these: * * - the master/host side Linux-USB kernel driver API; * - the "usbfs" user space API; and * - the Linux "gadget" slave/device/peripheral side driver API. * * USB 2.0 adds an additional "On The Go" (OTG) mode, which lets systems * act either as a USB master/host or as a USB slave/device. That means * the master and slave side APIs benefit from working well together. * * Note all descriptors are declared '__attribute__((packed))' so that: * * [a] they never get padded, either internally (USB spec writers * probably handled that) or externally; * * [b] so that accessing bigger-than-a-bytes fields will never * generate bus errors on any platform, even when the location of * its descriptor inside a bundle isn't "naturally aligned", and * * [c] for consistency, removing all doubt even when it appears to * someone that the two other points are non-issues for that * particular descriptor type. */ #ifndef _UAPI__LINUX_USB_CH9_H #define _UAPI__LINUX_USB_CH9_H #include <linux/types.h> /* __u8 etc */ #include <asm/byteorder.h> /* le16_to_cpu */ /*-------------------------------------------------------------------------*/ /* CONTROL REQUEST SUPPORT */ /* * USB directions * * This bit flag is used in endpoint descriptors' bEndpointAddress field. * It's also one of three fields in control requests bRequestType. */ #define USB_DIR_OUT 0 /* to device */ #define USB_DIR_IN 0x80 /* to host */ /* * USB types, the second of three bRequestType fields */ #define USB_TYPE_MASK (0x03 << 5) #define USB_TYPE_STANDARD (0x00 << 5) #define USB_TYPE_CLASS (0x01 << 5) #define USB_TYPE_VENDOR (0x02 << 5) #define USB_TYPE_RESERVED (0x03 << 5) /* * USB recipients, the third of three bRequestType fields */ #define USB_RECIP_MASK 0x1f #define USB_RECIP_DEVICE 0x00 #define USB_RECIP_INTERFACE 0x01 #define USB_RECIP_ENDPOINT 0x02 #define USB_RECIP_OTHER 0x03 /* From Wireless USB 1.0 */ #define USB_RECIP_PORT 0x04 #define USB_RECIP_RPIPE 0x05 /* * Standard requests, for the bRequest field of a SETUP packet. * * These are qualified by the bRequestType field, so that for example * TYPE_CLASS or TYPE_VENDOR specific feature flags could be retrieved * by a GET_STATUS request. */ #define USB_REQ_GET_STATUS 0x00 #define USB_REQ_CLEAR_FEATURE 0x01 #define USB_REQ_SET_FEATURE 0x03 #define USB_REQ_SET_ADDRESS 0x05 #define USB_REQ_GET_DESCRIPTOR 0x06 #define USB_REQ_SET_DESCRIPTOR 0x07 #define USB_REQ_GET_CONFIGURATION 0x08 #define USB_REQ_SET_CONFIGURATION 0x09 #define USB_REQ_GET_INTERFACE 0x0A #define USB_REQ_SET_INTERFACE 0x0B #define USB_REQ_SYNCH_FRAME 0x0C #define USB_REQ_SET_SEL 0x30 #define USB_REQ_SET_ISOCH_DELAY 0x31 #define USB_REQ_SET_ENCRYPTION 0x0D /* Wireless USB */ #define USB_REQ_GET_ENCRYPTION 0x0E #define USB_REQ_RPIPE_ABORT 0x0E #define USB_REQ_SET_HANDSHAKE 0x0F #define USB_REQ_RPIPE_RESET 0x0F #define USB_REQ_GET_HANDSHAKE 0x10 #define USB_REQ_SET_CONNECTION 0x11 #define USB_REQ_SET_SECURITY_DATA 0x12 #define USB_REQ_GET_SECURITY_DATA 0x13 #define USB_REQ_SET_WUSB_DATA 0x14 #define USB_REQ_LOOPBACK_DATA_WRITE 0x15 #define USB_REQ_LOOPBACK_DATA_READ 0x16 #define USB_REQ_SET_INTERFACE_DS 0x17 /* specific requests for USB Power Delivery */ #define USB_REQ_GET_PARTNER_PDO 20 #define USB_REQ_GET_BATTERY_STATUS 21 #define USB_REQ_SET_PDO 22 #define USB_REQ_GET_VDM 23 #define USB_REQ_SEND_VDM 24 /* The Link Power Management (LPM) ECN defines USB_REQ_TEST_AND_SET command, * used by hubs to put ports into a new L1 suspend state, except that it * forgot to define its number ... */ /* * USB feature flags are written using USB_REQ_{CLEAR,SET}_FEATURE, and * are read as a bit array returned by USB_REQ_GET_STATUS. (So there * are at most sixteen features of each type.) Hubs may also support a * new USB_REQ_TEST_AND_SET_FEATURE to put ports into L1 suspend. */ #define USB_DEVICE_SELF_POWERED 0 /* (read only) */ #define USB_DEVICE_REMOTE_WAKEUP 1 /* dev may initiate wakeup */ #define USB_DEVICE_TEST_MODE 2 /* (wired high speed only) */ #define USB_DEVICE_BATTERY 2 /* (wireless) */ #define USB_DEVICE_B_HNP_ENABLE 3 /* (otg) dev may initiate HNP */ #define USB_DEVICE_WUSB_DEVICE 3 /* (wireless)*/ #define USB_DEVICE_A_HNP_SUPPORT 4 /* (otg) RH port supports HNP */ #define USB_DEVICE_A_ALT_HNP_SUPPORT 5 /* (otg) other RH port does */ #define USB_DEVICE_DEBUG_MODE 6 /* (special devices only) */ /* * Test Mode Selectors * See USB 2.0 spec Table 9-7 */ #define USB_TEST_J 1 #define USB_TEST_K 2 #define USB_TEST_SE0_NAK 3 #define USB_TEST_PACKET 4 #define USB_TEST_FORCE_ENABLE 5 /* Status Type */ #define USB_STATUS_TYPE_STANDARD 0 #define USB_STATUS_TYPE_PTM 1 /* * New Feature Selectors as added by USB 3.0 * See USB 3.0 spec Table 9-7 */ #define USB_DEVICE_U1_ENABLE 48 /* dev may initiate U1 transition */ #define USB_DEVICE_U2_ENABLE 49 /* dev may initiate U2 transition */ #define USB_DEVICE_LTM_ENABLE 50 /* dev may send LTM */ #define USB_INTRF_FUNC_SUSPEND 0 /* function suspend */ #define USB_INTR_FUNC_SUSPEND_OPT_MASK 0xFF00 /* * Suspend Options, Table 9-8 USB 3.0 spec */ #define USB_INTRF_FUNC_SUSPEND_LP (1 << (8 + 0)) #define USB_INTRF_FUNC_SUSPEND_RW (1 << (8 + 1)) /* * Interface status, Figure 9-5 USB 3.0 spec */ #define USB_INTRF_STAT_FUNC_RW_CAP 1 #define USB_INTRF_STAT_FUNC_RW 2 #define USB_ENDPOINT_HALT 0 /* IN/OUT will STALL */ /* Bit array elements as returned by the USB_REQ_GET_STATUS request. */ #define USB_DEV_STAT_U1_ENABLED 2 /* transition into U1 state */ #define USB_DEV_STAT_U2_ENABLED 3 /* transition into U2 state */ #define USB_DEV_STAT_LTM_ENABLED 4 /* Latency tolerance messages */ /* * Feature selectors from Table 9-8 USB Power Delivery spec */ #define USB_DEVICE_BATTERY_WAKE_MASK 40 #define USB_DEVICE_OS_IS_PD_AWARE 41 #define USB_DEVICE_POLICY_MODE 42 #define USB_PORT_PR_SWAP 43 #define USB_PORT_GOTO_MIN 44 #define USB_PORT_RETURN_POWER 45 #define USB_PORT_ACCEPT_PD_REQUEST 46 #define USB_PORT_REJECT_PD_REQUEST 47 #define USB_PORT_PORT_PD_RESET 48 #define USB_PORT_C_PORT_PD_CHANGE 49 #define USB_PORT_CABLE_PD_RESET 50 #define USB_DEVICE_CHARGING_POLICY 54 /** * struct usb_ctrlrequest - SETUP data for a USB device control request * @bRequestType: matches the USB bmRequestType field * @bRequest: matches the USB bRequest field * @wValue: matches the USB wValue field (le16 byte order) * @wIndex: matches the USB wIndex field (le16 byte order) * @wLength: matches the USB wLength field (le16 byte order) * * This structure is used to send control requests to a USB device. It matches * the different fields of the USB 2.0 Spec section 9.3, table 9-2. See the * USB spec for a fuller description of the different fields, and what they are * used for. * * Note that the driver for any interface can issue control requests. * For most devices, interfaces don't coordinate with each other, so * such requests may be made at any time. */ struct usb_ctrlrequest { __u8 bRequestType; __u8 bRequest; __le16 wValue; __le16 wIndex; __le16 wLength; } __attribute__ ((packed)); /*-------------------------------------------------------------------------*/ /* * STANDARD DESCRIPTORS ... as returned by GET_DESCRIPTOR, or * (rarely) accepted by SET_DESCRIPTOR. * * Note that all multi-byte values here are encoded in little endian * byte order "on the wire". Within the kernel and when exposed * through the Linux-USB APIs, they are not converted to cpu byte * order; it is the responsibility of the client code to do this. * The single exception is when device and configuration descriptors (but * not other descriptors) are read from character devices * (i.e. /dev/bus/usb/BBB/DDD); * in this case the fields are converted to host endianness by the kernel. */ /* * Descriptor types ... USB 2.0 spec table 9.5 */ #define USB_DT_DEVICE 0x01 #define USB_DT_CONFIG 0x02 #define USB_DT_STRING 0x03 #define USB_DT_INTERFACE 0x04 #define USB_DT_ENDPOINT 0x05 #define USB_DT_DEVICE_QUALIFIER 0x06 #define USB_DT_OTHER_SPEED_CONFIG 0x07 #define USB_DT_INTERFACE_POWER 0x08 /* these are from a minor usb 2.0 revision (ECN) */ #define USB_DT_OTG 0x09 #define USB_DT_DEBUG 0x0a #define USB_DT_INTERFACE_ASSOCIATION 0x0b /* these are from the Wireless USB spec */ #define USB_DT_SECURITY 0x0c #define USB_DT_KEY 0x0d #define USB_DT_ENCRYPTION_TYPE 0x0e #define USB_DT_BOS 0x0f #define USB_DT_DEVICE_CAPABILITY 0x10 #define USB_DT_WIRELESS_ENDPOINT_COMP 0x11 /* From the eUSB2 spec */ #define USB_DT_EUSB2_ISOC_ENDPOINT_COMP 0x12 /* From Wireless USB spec */ #define USB_DT_WIRE_ADAPTER 0x21 /* From USB Device Firmware Upgrade Specification, Revision 1.1 */ #define USB_DT_DFU_FUNCTIONAL 0x21 /* these are from the Wireless USB spec */ #define USB_DT_RPIPE 0x22 #define USB_DT_CS_RADIO_CONTROL 0x23 /* From the T10 UAS specification */ #define USB_DT_PIPE_USAGE 0x24 /* From the USB 3.0 spec */ #define USB_DT_SS_ENDPOINT_COMP 0x30 /* From the USB 3.1 spec */ #define USB_DT_SSP_ISOC_ENDPOINT_COMP 0x31 /* Conventional codes for class-specific descriptors. The convention is * defined in the USB "Common Class" Spec (3.11). Individual class specs * are authoritative for their usage, not the "common class" writeup. */ #define USB_DT_CS_DEVICE (USB_TYPE_CLASS | USB_DT_DEVICE) #define USB_DT_CS_CONFIG (USB_TYPE_CLASS | USB_DT_CONFIG) #define USB_DT_CS_STRING (USB_TYPE_CLASS | USB_DT_STRING) #define USB_DT_CS_INTERFACE (USB_TYPE_CLASS | USB_DT_INTERFACE) #define USB_DT_CS_ENDPOINT (USB_TYPE_CLASS | USB_DT_ENDPOINT) /* All standard descriptors have these 2 fields at the beginning */ struct usb_descriptor_header { __u8 bLength; __u8 bDescriptorType; } __attribute__ ((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_DEVICE: Device descriptor */ struct usb_device_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 bcdUSB; __u8 bDeviceClass; __u8 bDeviceSubClass; __u8 bDeviceProtocol; __u8 bMaxPacketSize0; __le16 idVendor; __le16 idProduct; __le16 bcdDevice; __u8 iManufacturer; __u8 iProduct; __u8 iSerialNumber; __u8 bNumConfigurations; } __attribute__ ((packed)); #define USB_DT_DEVICE_SIZE 18 /* * Device and/or Interface Class codes * as found in bDeviceClass or bInterfaceClass * and defined by www.usb.org documents */ #define USB_CLASS_PER_INTERFACE 0 /* for DeviceClass */ #define USB_CLASS_AUDIO 1 #define USB_CLASS_COMM 2 #define USB_CLASS_HID 3 #define USB_CLASS_PHYSICAL 5 #define USB_CLASS_STILL_IMAGE 6 #define USB_CLASS_PRINTER 7 #define USB_CLASS_MASS_STORAGE 8 #define USB_CLASS_HUB 9 #define USB_CLASS_CDC_DATA 0x0a #define USB_CLASS_CSCID 0x0b /* chip+ smart card */ #define USB_CLASS_CONTENT_SEC 0x0d /* content security */ #define USB_CLASS_VIDEO 0x0e #define USB_CLASS_WIRELESS_CONTROLLER 0xe0 #define USB_CLASS_PERSONAL_HEALTHCARE 0x0f #define USB_CLASS_AUDIO_VIDEO 0x10 #define USB_CLASS_BILLBOARD 0x11 #define USB_CLASS_USB_TYPE_C_BRIDGE 0x12 #define USB_CLASS_MCTP 0x14 #define USB_CLASS_MISC 0xef #define USB_CLASS_APP_SPEC 0xfe #define USB_SUBCLASS_DFU 0x01 #define USB_CLASS_VENDOR_SPEC 0xff #define USB_SUBCLASS_VENDOR_SPEC 0xff /*-------------------------------------------------------------------------*/ /* USB_DT_CONFIG: Configuration descriptor information. * * USB_DT_OTHER_SPEED_CONFIG is the same descriptor, except that the * descriptor type is different. Highspeed-capable devices can look * different depending on what speed they're currently running. Only * devices with a USB_DT_DEVICE_QUALIFIER have any OTHER_SPEED_CONFIG * descriptors. */ struct usb_config_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wTotalLength; __u8 bNumInterfaces; __u8 bConfigurationValue; __u8 iConfiguration; __u8 bmAttributes; __u8 bMaxPower; } __attribute__ ((packed)); #define USB_DT_CONFIG_SIZE 9 /* from config descriptor bmAttributes */ #define USB_CONFIG_ATT_ONE (1 << 7) /* must be set */ #define USB_CONFIG_ATT_SELFPOWER (1 << 6) /* self powered */ #define USB_CONFIG_ATT_WAKEUP (1 << 5) /* can wakeup */ #define USB_CONFIG_ATT_BATTERY (1 << 4) /* battery powered */ /*-------------------------------------------------------------------------*/ /* USB String descriptors can contain at most 126 characters. */ #define USB_MAX_STRING_LEN 126 /* USB_DT_STRING: String descriptor */ struct usb_string_descriptor { __u8 bLength; __u8 bDescriptorType; union { __le16 legacy_padding; __DECLARE_FLEX_ARRAY(__le16, wData); /* UTF-16LE encoded */ }; } __attribute__ ((packed)); /* note that "string" zero is special, it holds language codes that * the device supports, not Unicode characters. */ /*-------------------------------------------------------------------------*/ /* USB_DT_INTERFACE: Interface descriptor */ struct usb_interface_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bInterfaceNumber; __u8 bAlternateSetting; __u8 bNumEndpoints; __u8 bInterfaceClass; __u8 bInterfaceSubClass; __u8 bInterfaceProtocol; __u8 iInterface; } __attribute__ ((packed)); #define USB_DT_INTERFACE_SIZE 9 /*-------------------------------------------------------------------------*/ /* USB_DT_ENDPOINT: Endpoint descriptor */ struct usb_endpoint_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bEndpointAddress; __u8 bmAttributes; __le16 wMaxPacketSize; __u8 bInterval; /* NOTE: these two are _only_ in audio endpoints. */ /* use USB_DT_ENDPOINT*_SIZE in bLength, not sizeof. */ __u8 bRefresh; __u8 bSynchAddress; } __attribute__ ((packed)); #define USB_DT_ENDPOINT_SIZE 7 #define USB_DT_ENDPOINT_AUDIO_SIZE 9 /* Audio extension */ /* * Endpoints */ #define USB_ENDPOINT_NUMBER_MASK 0x0f /* in bEndpointAddress */ #define USB_ENDPOINT_DIR_MASK 0x80 #define USB_ENDPOINT_XFERTYPE_MASK 0x03 /* in bmAttributes */ #define USB_ENDPOINT_XFER_CONTROL 0 #define USB_ENDPOINT_XFER_ISOC 1 #define USB_ENDPOINT_XFER_BULK 2 #define USB_ENDPOINT_XFER_INT 3 #define USB_ENDPOINT_MAX_ADJUSTABLE 0x80 #define USB_ENDPOINT_MAXP_MASK 0x07ff #define USB_EP_MAXP_MULT_SHIFT 11 #define USB_EP_MAXP_MULT_MASK (3 << USB_EP_MAXP_MULT_SHIFT) #define USB_EP_MAXP_MULT(m) \ (((m) & USB_EP_MAXP_MULT_MASK) >> USB_EP_MAXP_MULT_SHIFT) /* The USB 3.0 spec redefines bits 5:4 of bmAttributes as interrupt ep type. */ #define USB_ENDPOINT_INTRTYPE 0x30 #define USB_ENDPOINT_INTR_PERIODIC (0 << 4) #define USB_ENDPOINT_INTR_NOTIFICATION (1 << 4) #define USB_ENDPOINT_SYNCTYPE 0x0c #define USB_ENDPOINT_SYNC_NONE (0 << 2) #define USB_ENDPOINT_SYNC_ASYNC (1 << 2) #define USB_ENDPOINT_SYNC_ADAPTIVE (2 << 2) #define USB_ENDPOINT_SYNC_SYNC (3 << 2) #define USB_ENDPOINT_USAGE_MASK 0x30 #define USB_ENDPOINT_USAGE_DATA 0x00 #define USB_ENDPOINT_USAGE_FEEDBACK 0x10 #define USB_ENDPOINT_USAGE_IMPLICIT_FB 0x20 /* Implicit feedback Data endpoint */ /*-------------------------------------------------------------------------*/ /** * usb_endpoint_num - get the endpoint's number * @epd: endpoint to be checked * * Returns @epd's number: 0 to 15. */ static inline int usb_endpoint_num(const struct usb_endpoint_descriptor *epd) { return epd->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK; } /** * usb_endpoint_type - get the endpoint's transfer type * @epd: endpoint to be checked * * Returns one of USB_ENDPOINT_XFER_{CONTROL, ISOC, BULK, INT} according * to @epd's transfer type. */ static inline int usb_endpoint_type(const struct usb_endpoint_descriptor *epd) { return epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK; } /** * usb_endpoint_dir_in - check if the endpoint has IN direction * @epd: endpoint to be checked * * Returns true if the endpoint is of type IN, otherwise it returns false. */ static inline int usb_endpoint_dir_in(const struct usb_endpoint_descriptor *epd) { return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN); } /** * usb_endpoint_dir_out - check if the endpoint has OUT direction * @epd: endpoint to be checked * * Returns true if the endpoint is of type OUT, otherwise it returns false. */ static inline int usb_endpoint_dir_out( const struct usb_endpoint_descriptor *epd) { return ((epd->bEndpointAddress & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT); } /** * usb_endpoint_xfer_bulk - check if the endpoint has bulk transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type bulk, otherwise it returns false. */ static inline int usb_endpoint_xfer_bulk( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_BULK); } /** * usb_endpoint_xfer_control - check if the endpoint has control transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type control, otherwise it returns false. */ static inline int usb_endpoint_xfer_control( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_CONTROL); } /** * usb_endpoint_xfer_int - check if the endpoint has interrupt transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type interrupt, otherwise it returns * false. */ static inline int usb_endpoint_xfer_int( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT); } /** * usb_endpoint_xfer_isoc - check if the endpoint has isochronous transfer type * @epd: endpoint to be checked * * Returns true if the endpoint is of type isochronous, otherwise it returns * false. */ static inline int usb_endpoint_xfer_isoc( const struct usb_endpoint_descriptor *epd) { return ((epd->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_ISOC); } /** * usb_endpoint_is_bulk_in - check if the endpoint is bulk IN * @epd: endpoint to be checked * * Returns true if the endpoint has bulk transfer type and IN direction, * otherwise it returns false. */ static inline int usb_endpoint_is_bulk_in( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_in(epd); } /** * usb_endpoint_is_bulk_out - check if the endpoint is bulk OUT * @epd: endpoint to be checked * * Returns true if the endpoint has bulk transfer type and OUT direction, * otherwise it returns false. */ static inline int usb_endpoint_is_bulk_out( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_bulk(epd) && usb_endpoint_dir_out(epd); } /** * usb_endpoint_is_int_in - check if the endpoint is interrupt IN * @epd: endpoint to be checked * * Returns true if the endpoint has interrupt transfer type and IN direction, * otherwise it returns false. */ static inline int usb_endpoint_is_int_in( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_int(epd) && usb_endpoint_dir_in(epd); } /** * usb_endpoint_is_int_out - check if the endpoint is interrupt OUT * @epd: endpoint to be checked * * Returns true if the endpoint has interrupt transfer type and OUT direction, * otherwise it returns false. */ static inline int usb_endpoint_is_int_out( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_int(epd) && usb_endpoint_dir_out(epd); } /** * usb_endpoint_is_isoc_in - check if the endpoint is isochronous IN * @epd: endpoint to be checked * * Returns true if the endpoint has isochronous transfer type and IN direction, * otherwise it returns false. */ static inline int usb_endpoint_is_isoc_in( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_in(epd); } /** * usb_endpoint_is_isoc_out - check if the endpoint is isochronous OUT * @epd: endpoint to be checked * * Returns true if the endpoint has isochronous transfer type and OUT direction, * otherwise it returns false. */ static inline int usb_endpoint_is_isoc_out( const struct usb_endpoint_descriptor *epd) { return usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_out(epd); } /** * usb_endpoint_maxp - get endpoint's max packet size * @epd: endpoint to be checked * * Returns @epd's max packet bits [10:0] */ static inline int usb_endpoint_maxp(const struct usb_endpoint_descriptor *epd) { return __le16_to_cpu(epd->wMaxPacketSize) & USB_ENDPOINT_MAXP_MASK; } /** * usb_endpoint_maxp_mult - get endpoint's transactional opportunities * @epd: endpoint to be checked * * Return @epd's wMaxPacketSize[12:11] + 1 */ static inline int usb_endpoint_maxp_mult(const struct usb_endpoint_descriptor *epd) { int maxp = __le16_to_cpu(epd->wMaxPacketSize); return USB_EP_MAXP_MULT(maxp) + 1; } static inline int usb_endpoint_interrupt_type( const struct usb_endpoint_descriptor *epd) { return epd->bmAttributes & USB_ENDPOINT_INTRTYPE; } /*-------------------------------------------------------------------------*/ /* USB_DT_EUSB2_ISOC_ENDPOINT_COMP: eUSB2 Isoch Endpoint Companion descriptor */ struct usb_eusb2_isoc_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wMaxPacketSize; __le32 dwBytesPerInterval; } __attribute__ ((packed)); #define USB_DT_EUSB2_ISOC_EP_COMP_SIZE 8 /*-------------------------------------------------------------------------*/ /* USB_DT_SSP_ISOC_ENDPOINT_COMP: SuperSpeedPlus Isochronous Endpoint Companion * descriptor */ struct usb_ssp_isoc_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wReseved; __le32 dwBytesPerInterval; } __attribute__ ((packed)); #define USB_DT_SSP_ISOC_EP_COMP_SIZE 8 /*-------------------------------------------------------------------------*/ /* USB_DT_SS_ENDPOINT_COMP: SuperSpeed Endpoint Companion descriptor */ struct usb_ss_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bMaxBurst; __u8 bmAttributes; __le16 wBytesPerInterval; } __attribute__ ((packed)); #define USB_DT_SS_EP_COMP_SIZE 6 /* Bits 4:0 of bmAttributes if this is a bulk endpoint */ static inline int usb_ss_max_streams(const struct usb_ss_ep_comp_descriptor *comp) { int max_streams; if (!comp) return 0; max_streams = comp->bmAttributes & 0x1f; if (!max_streams) return 0; max_streams = 1 << max_streams; return max_streams; } /* Bits 1:0 of bmAttributes if this is an isoc endpoint */ #define USB_SS_MULT(p) (1 + ((p) & 0x3)) /* Bit 7 of bmAttributes if a SSP isoc endpoint companion descriptor exists */ #define USB_SS_SSP_ISOC_COMP(p) ((p) & (1 << 7)) /*-------------------------------------------------------------------------*/ /* USB_DT_DEVICE_QUALIFIER: Device Qualifier descriptor */ struct usb_qualifier_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 bcdUSB; __u8 bDeviceClass; __u8 bDeviceSubClass; __u8 bDeviceProtocol; __u8 bMaxPacketSize0; __u8 bNumConfigurations; __u8 bRESERVED; } __attribute__ ((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_OTG (from OTG 1.0a supplement) */ struct usb_otg_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bmAttributes; /* support for HNP, SRP, etc */ } __attribute__ ((packed)); /* USB_DT_OTG (from OTG 2.0 supplement) */ struct usb_otg20_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bmAttributes; /* support for HNP, SRP and ADP, etc */ __le16 bcdOTG; /* OTG and EH supplement release number * in binary-coded decimal(i.e. 2.0 is 0200H) */ } __attribute__ ((packed)); /* from usb_otg_descriptor.bmAttributes */ #define USB_OTG_SRP (1 << 0) #define USB_OTG_HNP (1 << 1) /* swap host/device roles */ #define USB_OTG_ADP (1 << 2) /* support ADP */ /* OTG 3.0 */ #define USB_OTG_RSP (1 << 3) /* support RSP */ #define OTG_STS_SELECTOR 0xF000 /* OTG status selector */ /*-------------------------------------------------------------------------*/ /* USB_DT_DEBUG: for special highspeed devices, replacing serial console */ struct usb_debug_descriptor { __u8 bLength; __u8 bDescriptorType; /* bulk endpoints with 8 byte maxpacket */ __u8 bDebugInEndpoint; __u8 bDebugOutEndpoint; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_INTERFACE_ASSOCIATION: groups interfaces */ struct usb_interface_assoc_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bFirstInterface; __u8 bInterfaceCount; __u8 bFunctionClass; __u8 bFunctionSubClass; __u8 bFunctionProtocol; __u8 iFunction; } __attribute__ ((packed)); #define USB_DT_INTERFACE_ASSOCIATION_SIZE 8 /*-------------------------------------------------------------------------*/ /* USB_DT_SECURITY: group of wireless security descriptors, including * encryption types available for setting up a CC/association. */ struct usb_security_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wTotalLength; __u8 bNumEncryptionTypes; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_KEY: used with {GET,SET}_SECURITY_DATA; only public keys * may be retrieved. */ struct usb_key_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 tTKID[3]; __u8 bReserved; __u8 bKeyData[]; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_ENCRYPTION_TYPE: bundled in DT_SECURITY groups */ struct usb_encryption_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bEncryptionType; #define USB_ENC_TYPE_UNSECURE 0 #define USB_ENC_TYPE_WIRED 1 /* non-wireless mode */ #define USB_ENC_TYPE_CCM_1 2 /* aes128/cbc session */ #define USB_ENC_TYPE_RSA_1 3 /* rsa3072/sha1 auth */ __u8 bEncryptionValue; /* use in SET_ENCRYPTION */ __u8 bAuthKeyIndex; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_DT_BOS: group of device-level capabilities */ struct usb_bos_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 wTotalLength; __u8 bNumDeviceCaps; } __attribute__((packed)); #define USB_DT_BOS_SIZE 5 /*-------------------------------------------------------------------------*/ /* USB_DT_DEVICE_CAPABILITY: grouped with BOS */ struct usb_dev_cap_header { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; } __attribute__((packed)); #define USB_CAP_TYPE_WIRELESS_USB 1 struct usb_wireless_cap_descriptor { /* Ultra Wide Band */ __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bmAttributes; #define USB_WIRELESS_P2P_DRD (1 << 1) #define USB_WIRELESS_BEACON_MASK (3 << 2) #define USB_WIRELESS_BEACON_SELF (1 << 2) #define USB_WIRELESS_BEACON_DIRECTED (2 << 2) #define USB_WIRELESS_BEACON_NONE (3 << 2) __le16 wPHYRates; /* bit rates, Mbps */ #define USB_WIRELESS_PHY_53 (1 << 0) /* always set */ #define USB_WIRELESS_PHY_80 (1 << 1) #define USB_WIRELESS_PHY_107 (1 << 2) /* always set */ #define USB_WIRELESS_PHY_160 (1 << 3) #define USB_WIRELESS_PHY_200 (1 << 4) /* always set */ #define USB_WIRELESS_PHY_320 (1 << 5) #define USB_WIRELESS_PHY_400 (1 << 6) #define USB_WIRELESS_PHY_480 (1 << 7) __u8 bmTFITXPowerInfo; /* TFI power levels */ __u8 bmFFITXPowerInfo; /* FFI power levels */ __le16 bmBandGroup; __u8 bReserved; } __attribute__((packed)); #define USB_DT_USB_WIRELESS_CAP_SIZE 11 /* USB 2.0 Extension descriptor */ #define USB_CAP_TYPE_EXT 2 struct usb_ext_cap_descriptor { /* Link Power Management */ __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __le32 bmAttributes; #define USB_LPM_SUPPORT (1 << 1) /* supports LPM */ #define USB_BESL_SUPPORT (1 << 2) /* supports BESL */ #define USB_BESL_BASELINE_VALID (1 << 3) /* Baseline BESL valid*/ #define USB_BESL_DEEP_VALID (1 << 4) /* Deep BESL valid */ #define USB_SET_BESL_BASELINE(p) (((p) & 0xf) << 8) #define USB_SET_BESL_DEEP(p) (((p) & 0xf) << 12) #define USB_GET_BESL_BASELINE(p) (((p) & (0xf << 8)) >> 8) #define USB_GET_BESL_DEEP(p) (((p) & (0xf << 12)) >> 12) } __attribute__((packed)); #define USB_DT_USB_EXT_CAP_SIZE 7 /* * SuperSpeed USB Capability descriptor: Defines the set of SuperSpeed USB * specific device level capabilities */ #define USB_SS_CAP_TYPE 3 struct usb_ss_cap_descriptor { /* Link Power Management */ __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bmAttributes; #define USB_LTM_SUPPORT (1 << 1) /* supports LTM */ __le16 wSpeedSupported; #define USB_LOW_SPEED_OPERATION (1) /* Low speed operation */ #define USB_FULL_SPEED_OPERATION (1 << 1) /* Full speed operation */ #define USB_HIGH_SPEED_OPERATION (1 << 2) /* High speed operation */ #define USB_5GBPS_OPERATION (1 << 3) /* Operation at 5Gbps */ __u8 bFunctionalitySupport; __u8 bU1devExitLat; __le16 bU2DevExitLat; } __attribute__((packed)); #define USB_DT_USB_SS_CAP_SIZE 10 /* * Container ID Capability descriptor: Defines the instance unique ID used to * identify the instance across all operating modes */ #define CONTAINER_ID_TYPE 4 struct usb_ss_container_id_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __u8 ContainerID[16]; /* 128-bit number */ } __attribute__((packed)); #define USB_DT_USB_SS_CONTN_ID_SIZE 20 /* * Platform Device Capability descriptor: Defines platform specific device * capabilities */ #define USB_PLAT_DEV_CAP_TYPE 5 struct usb_plat_dev_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __u8 UUID[16]; __u8 CapabilityData[]; } __attribute__((packed)); #define USB_DT_USB_PLAT_DEV_CAP_SIZE(capability_data_size) (20 + capability_data_size) /* * SuperSpeed Plus USB Capability descriptor: Defines the set of * SuperSpeed Plus USB specific device level capabilities */ #define USB_SSP_CAP_TYPE 0xa struct usb_ssp_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __le32 bmAttributes; #define USB_SSP_SUBLINK_SPEED_ATTRIBS (0x1f << 0) /* sublink speed entries */ #define USB_SSP_SUBLINK_SPEED_IDS (0xf << 5) /* speed ID entries */ __le16 wFunctionalitySupport; #define USB_SSP_MIN_SUBLINK_SPEED_ATTRIBUTE_ID (0xf) #define USB_SSP_MIN_RX_LANE_COUNT (0xf << 8) #define USB_SSP_MIN_TX_LANE_COUNT (0xf << 12) __le16 wReserved; union { __le32 legacy_padding; /* list of sublink speed attrib entries */ __DECLARE_FLEX_ARRAY(__le32, bmSublinkSpeedAttr); }; #define USB_SSP_SUBLINK_SPEED_SSID (0xf) /* sublink speed ID */ #define USB_SSP_SUBLINK_SPEED_LSE (0x3 << 4) /* Lanespeed exponent */ #define USB_SSP_SUBLINK_SPEED_LSE_BPS 0 #define USB_SSP_SUBLINK_SPEED_LSE_KBPS 1 #define USB_SSP_SUBLINK_SPEED_LSE_MBPS 2 #define USB_SSP_SUBLINK_SPEED_LSE_GBPS 3 #define USB_SSP_SUBLINK_SPEED_ST (0x3 << 6) /* Sublink type */ #define USB_SSP_SUBLINK_SPEED_ST_SYM_RX 0 #define USB_SSP_SUBLINK_SPEED_ST_ASYM_RX 1 #define USB_SSP_SUBLINK_SPEED_ST_SYM_TX 2 #define USB_SSP_SUBLINK_SPEED_ST_ASYM_TX 3 #define USB_SSP_SUBLINK_SPEED_RSVD (0x3f << 8) /* Reserved */ #define USB_SSP_SUBLINK_SPEED_LP (0x3 << 14) /* Link protocol */ #define USB_SSP_SUBLINK_SPEED_LP_SS 0 #define USB_SSP_SUBLINK_SPEED_LP_SSP 1 #define USB_SSP_SUBLINK_SPEED_LSM (0xff << 16) /* Lanespeed mantissa */ } __attribute__((packed)); /* * USB Power Delivery Capability Descriptor: * Defines capabilities for PD */ /* Defines the various PD Capabilities of this device */ #define USB_PD_POWER_DELIVERY_CAPABILITY 0x06 /* Provides information on each battery supported by the device */ #define USB_PD_BATTERY_INFO_CAPABILITY 0x07 /* The Consumer characteristics of a Port on the device */ #define USB_PD_PD_CONSUMER_PORT_CAPABILITY 0x08 /* The provider characteristics of a Port on the device */ #define USB_PD_PD_PROVIDER_PORT_CAPABILITY 0x09 struct usb_pd_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; /* set to USB_PD_POWER_DELIVERY_CAPABILITY */ __u8 bReserved; __le32 bmAttributes; #define USB_PD_CAP_BATTERY_CHARGING (1 << 1) /* supports Battery Charging specification */ #define USB_PD_CAP_USB_PD (1 << 2) /* supports USB Power Delivery specification */ #define USB_PD_CAP_PROVIDER (1 << 3) /* can provide power */ #define USB_PD_CAP_CONSUMER (1 << 4) /* can consume power */ #define USB_PD_CAP_CHARGING_POLICY (1 << 5) /* supports CHARGING_POLICY feature */ #define USB_PD_CAP_TYPE_C_CURRENT (1 << 6) /* supports power capabilities defined in the USB Type-C Specification */ #define USB_PD_CAP_PWR_AC (1 << 8) #define USB_PD_CAP_PWR_BAT (1 << 9) #define USB_PD_CAP_PWR_USE_V_BUS (1 << 14) __le16 bmProviderPorts; /* Bit zero refers to the UFP of the device */ __le16 bmConsumerPorts; __le16 bcdBCVersion; __le16 bcdPDVersion; __le16 bcdUSBTypeCVersion; } __attribute__((packed)); struct usb_pd_cap_battery_info_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; /* Index of string descriptor shall contain the user friendly name for this battery */ __u8 iBattery; /* Index of string descriptor shall contain the Serial Number String for this battery */ __u8 iSerial; __u8 iManufacturer; __u8 bBatteryId; /* uniquely identifies this battery in status Messages */ __u8 bReserved; /* * Shall contain the Battery Charge value above which this * battery is considered to be fully charged but not necessarily * “topped off.” */ __le32 dwChargedThreshold; /* in mWh */ /* * Shall contain the minimum charge level of this battery such * that above this threshold, a device can be assured of being * able to power up successfully (see Battery Charging 1.2). */ __le32 dwWeakThreshold; /* in mWh */ __le32 dwBatteryDesignCapacity; /* in mWh */ __le32 dwBatteryLastFullchargeCapacity; /* in mWh */ } __attribute__((packed)); struct usb_pd_cap_consumer_port_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved; __u8 bmCapabilities; /* port will oerate under: */ #define USB_PD_CAP_CONSUMER_BC (1 << 0) /* BC */ #define USB_PD_CAP_CONSUMER_PD (1 << 1) /* PD */ #define USB_PD_CAP_CONSUMER_TYPE_C (1 << 2) /* USB Type-C Current */ __le16 wMinVoltage; /* in 50mV units */ __le16 wMaxVoltage; /* in 50mV units */ __u16 wReserved; __le32 dwMaxOperatingPower; /* in 10 mW - operating at steady state */ __le32 dwMaxPeakPower; /* in 10mW units - operating at peak power */ __le32 dwMaxPeakPowerTime; /* in 100ms units - duration of peak */ #define USB_PD_CAP_CONSUMER_UNKNOWN_PEAK_POWER_TIME 0xffff } __attribute__((packed)); struct usb_pd_cap_provider_port_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; __u8 bReserved1; __u8 bmCapabilities; /* port will oerate under: */ #define USB_PD_CAP_PROVIDER_BC (1 << 0) /* BC */ #define USB_PD_CAP_PROVIDER_PD (1 << 1) /* PD */ #define USB_PD_CAP_PROVIDER_TYPE_C (1 << 2) /* USB Type-C Current */ __u8 bNumOfPDObjects; __u8 bReserved2; __le32 wPowerDataObject[]; } __attribute__((packed)); /* * Precision time measurement capability descriptor: advertised by devices and * hubs that support PTM */ #define USB_PTM_CAP_TYPE 0xb struct usb_ptm_cap_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDevCapabilityType; } __attribute__((packed)); #define USB_DT_USB_PTM_ID_SIZE 3 /* * The size of the descriptor for the Sublink Speed Attribute Count * (SSAC) specified in bmAttributes[4:0]. SSAC is zero-based */ #define USB_DT_USB_SSP_CAP_SIZE(ssac) (12 + (ssac + 1) * 4) /*-------------------------------------------------------------------------*/ /* USB_DT_WIRELESS_ENDPOINT_COMP: companion descriptor associated with * each endpoint descriptor for a wireless device */ struct usb_wireless_ep_comp_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bMaxBurst; __u8 bMaxSequence; __le16 wMaxStreamDelay; __le16 wOverTheAirPacketSize; __u8 bOverTheAirInterval; __u8 bmCompAttributes; #define USB_ENDPOINT_SWITCH_MASK 0x03 /* in bmCompAttributes */ #define USB_ENDPOINT_SWITCH_NO 0 #define USB_ENDPOINT_SWITCH_SWITCH 1 #define USB_ENDPOINT_SWITCH_SCALE 2 } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_REQ_SET_HANDSHAKE is a four-way handshake used between a wireless * host and a device for connection set up, mutual authentication, and * exchanging short lived session keys. The handshake depends on a CC. */ struct usb_handshake { __u8 bMessageNumber; __u8 bStatus; __u8 tTKID[3]; __u8 bReserved; __u8 CDID[16]; __u8 nonce[16]; __u8 MIC[8]; } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB_REQ_SET_CONNECTION modifies or revokes a connection context (CC). * A CC may also be set up using non-wireless secure channels (including * wired USB!), and some devices may support CCs with multiple hosts. */ struct usb_connection_context { __u8 CHID[16]; /* persistent host id */ __u8 CDID[16]; /* device id (unique w/in host context) */ __u8 CK[16]; /* connection key */ } __attribute__((packed)); /*-------------------------------------------------------------------------*/ /* USB 2.0 defines three speeds, here's how Linux identifies them */ enum usb_device_speed { USB_SPEED_UNKNOWN = 0, /* enumerating */ USB_SPEED_LOW, USB_SPEED_FULL, /* usb 1.1 */ USB_SPEED_HIGH, /* usb 2.0 */ USB_SPEED_WIRELESS, /* wireless (usb 2.5) */ USB_SPEED_SUPER, /* usb 3.0 */ USB_SPEED_SUPER_PLUS, /* usb 3.1 */ }; enum usb_device_state { /* NOTATTACHED isn't in the USB spec, and this state acts * the same as ATTACHED ... but it's clearer this way. */ USB_STATE_NOTATTACHED = 0, /* chapter 9 and authentication (wireless) device states */ USB_STATE_ATTACHED, USB_STATE_POWERED, /* wired */ USB_STATE_RECONNECTING, /* auth */ USB_STATE_UNAUTHENTICATED, /* auth */ USB_STATE_DEFAULT, /* limited function */ USB_STATE_ADDRESS, USB_STATE_CONFIGURED, /* most functions */ USB_STATE_SUSPENDED /* NOTE: there are actually four different SUSPENDED * states, returning to POWERED, DEFAULT, ADDRESS, or * CONFIGURED respectively when SOF tokens flow again. * At this level there's no difference between L1 and L2 * suspend states. (L2 being original USB 1.1 suspend.) */ }; enum usb3_link_state { USB3_LPM_U0 = 0, USB3_LPM_U1, USB3_LPM_U2, USB3_LPM_U3 }; /* * A U1 timeout of 0x0 means the parent hub will reject any transitions to U1. * 0xff means the parent hub will accept transitions to U1, but will not * initiate a transition. * * A U1 timeout of 0x1 to 0x7F also causes the hub to initiate a transition to * U1 after that many microseconds. Timeouts of 0x80 to 0xFE are reserved * values. * * A U2 timeout of 0x0 means the parent hub will reject any transitions to U2. * 0xff means the parent hub will accept transitions to U2, but will not * initiate a transition. * * A U2 timeout of 0x1 to 0xFE also causes the hub to initiate a transition to * U2 after N*256 microseconds. Therefore a U2 timeout value of 0x1 means a U2 * idle timer of 256 microseconds, 0x2 means 512 microseconds, 0xFE means * 65.024ms. */ #define USB3_LPM_DISABLED 0x0 #define USB3_LPM_U1_MAX_TIMEOUT 0x7F #define USB3_LPM_U2_MAX_TIMEOUT 0xFE #define USB3_LPM_DEVICE_INITIATED 0xFF struct usb_set_sel_req { __u8 u1_sel; __u8 u1_pel; __le16 u2_sel; __le16 u2_pel; } __attribute__ ((packed)); /* * The Set System Exit Latency control transfer provides one byte each for * U1 SEL and U1 PEL, so the max exit latency is 0xFF. U2 SEL and U2 PEL each * are two bytes long. */ #define USB3_LPM_MAX_U1_SEL_PEL 0xFF #define USB3_LPM_MAX_U2_SEL_PEL 0xFFFF /*-------------------------------------------------------------------------*/ /* * As per USB compliance update, a device that is actively drawing * more than 100mA from USB must report itself as bus-powered in * the GetStatus(DEVICE) call. * https://compliance.usb.org/index.asp?UpdateFile=Electrical&Format=Standard#34 */ #define USB_SELF_POWER_VBUS_MAX_DRAW 100 #endif /* _UAPI__LINUX_USB_CH9_H */ |
| 653 653 1021 494 755 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 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 #include "alloc_cache.h" void io_alloc_cache_free(struct io_alloc_cache *cache, void (*free)(const void *)) { void *entry; if (!cache->entries) return; while ((entry = io_alloc_cache_get(cache)) != NULL) free(entry); kvfree(cache->entries); cache->entries = NULL; } /* returns false if the cache was initialized properly */ bool io_alloc_cache_init(struct io_alloc_cache *cache, unsigned max_nr, unsigned int size, unsigned int init_bytes) { cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL); if (!cache->entries) return true; cache->nr_cached = 0; cache->max_cached = max_nr; cache->elem_size = size; cache->init_clear = init_bytes; return false; } void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp) { void *obj; obj = kmalloc(cache->elem_size, gfp); if (obj && cache->init_clear) memset(obj, 0, cache->init_clear); return obj; } |
| 531 392 27 190 505 253 585 472 142 7 68 40 85 20 7 46 3 3 9 2 7 6 6 1 6 6 6 1 6 1 5 6 6 1 5 4 2 1 4 1 36 1 28 7 5 1 29 3 1 1 1 25 21 21 17 4 3 7 5 5 5 5 8 8 11 11 5 4 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * UDPv4 GSO support */ #include <linux/skbuff.h> #include <net/gro.h> #include <net/gso.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> #include <net/udp_tunnel.h> #if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) /* * Dummy GRO tunnel callback, exists mainly to avoid dangling/NULL * values for the udp tunnel static call. */ static struct sk_buff *dummy_gro_rcv(struct sock *sk, struct list_head *head, struct sk_buff *skb) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } typedef struct sk_buff *(*udp_tunnel_gro_rcv_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); struct udp_tunnel_type_entry { udp_tunnel_gro_rcv_t gro_receive; refcount_t count; }; #define UDP_MAX_TUNNEL_TYPES (IS_ENABLED(CONFIG_GENEVE) + \ IS_ENABLED(CONFIG_VXLAN) * 2 + \ IS_ENABLED(CONFIG_NET_FOU) * 2 + \ IS_ENABLED(CONFIG_XFRM) * 2) DEFINE_STATIC_CALL(udp_tunnel_gro_rcv, dummy_gro_rcv); static DEFINE_STATIC_KEY_FALSE(udp_tunnel_static_call); static struct mutex udp_tunnel_gro_type_lock; static struct udp_tunnel_type_entry udp_tunnel_gro_types[UDP_MAX_TUNNEL_TYPES]; static unsigned int udp_tunnel_gro_type_nr; static DEFINE_SPINLOCK(udp_tunnel_gro_lock); void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add) { bool is_ipv6 = sk->sk_family == AF_INET6; struct udp_sock *tup, *up = udp_sk(sk); struct udp_tunnel_gro *udp_tunnel_gro; spin_lock(&udp_tunnel_gro_lock); udp_tunnel_gro = &net->ipv4.udp_tunnel_gro[is_ipv6]; if (add) hlist_add_head(&up->tunnel_list, &udp_tunnel_gro->list); else if (up->tunnel_list.pprev) hlist_del_init(&up->tunnel_list); if (udp_tunnel_gro->list.first && !udp_tunnel_gro->list.first->next) { tup = hlist_entry(udp_tunnel_gro->list.first, struct udp_sock, tunnel_list); rcu_assign_pointer(udp_tunnel_gro->sk, (struct sock *)tup); } else { RCU_INIT_POINTER(udp_tunnel_gro->sk, NULL); } spin_unlock(&udp_tunnel_gro_lock); } EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_lookup); void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) { struct udp_tunnel_type_entry *cur = NULL; struct udp_sock *up = udp_sk(sk); int i, old_gro_type_nr; if (!UDP_MAX_TUNNEL_TYPES || !up->gro_receive) return; mutex_lock(&udp_tunnel_gro_type_lock); /* Check if the static call is permanently disabled. */ if (udp_tunnel_gro_type_nr > UDP_MAX_TUNNEL_TYPES) goto out; for (i = 0; i < udp_tunnel_gro_type_nr; i++) if (udp_tunnel_gro_types[i].gro_receive == up->gro_receive) cur = &udp_tunnel_gro_types[i]; old_gro_type_nr = udp_tunnel_gro_type_nr; if (add) { /* * Update the matching entry, if found, or add a new one * if needed */ if (cur) { refcount_inc(&cur->count); goto out; } if (unlikely(udp_tunnel_gro_type_nr == UDP_MAX_TUNNEL_TYPES)) { pr_err_once("Too many UDP tunnel types, please increase UDP_MAX_TUNNEL_TYPES\n"); /* Ensure static call will never be enabled */ udp_tunnel_gro_type_nr = UDP_MAX_TUNNEL_TYPES + 1; } else { cur = &udp_tunnel_gro_types[udp_tunnel_gro_type_nr++]; refcount_set(&cur->count, 1); cur->gro_receive = up->gro_receive; } } else { /* * The stack cleanups only successfully added tunnel, the * lookup on removal should never fail. */ if (WARN_ON_ONCE(!cur)) goto out; if (!refcount_dec_and_test(&cur->count)) goto out; /* Avoid gaps, so that the enable tunnel has always id 0 */ *cur = udp_tunnel_gro_types[--udp_tunnel_gro_type_nr]; } if (udp_tunnel_gro_type_nr == 1) { static_call_update(udp_tunnel_gro_rcv, udp_tunnel_gro_types[0].gro_receive); static_branch_enable(&udp_tunnel_static_call); } else if (old_gro_type_nr == 1) { static_branch_disable(&udp_tunnel_static_call); static_call_update(udp_tunnel_gro_rcv, dummy_gro_rcv); } out: mutex_unlock(&udp_tunnel_gro_type_lock); } EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_rcv); static void udp_tunnel_gro_init(void) { mutex_init(&udp_tunnel_gro_type_lock); } static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk, struct list_head *head, struct sk_buff *skb) { if (static_branch_likely(&udp_tunnel_static_call)) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; return NULL; } return static_call(udp_tunnel_gro_rcv)(sk, head, skb); } return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); } #else static void udp_tunnel_gro_init(void) {} static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk, struct list_head *head, struct sk_buff *skb) { return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); } #endif static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features), __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the * 16 bit length field due to the header being added outside of an * IP or IPv6 frame that was already limited to 64K - 1. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) partial = (__force __wsum)uh->len; else partial = (__force __wsum)htonl(skb->len); partial = csum_sub(csum_unfold(uh->check), partial); /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb_set_transport_header(skb, skb_inner_transport_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); skb->encap_hdr_csum = need_csum; remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) : (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; if (need_csum) features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and * instead set the flag based on our outer checksum offload value. */ if (remcsum) { features &= ~NETIF_F_CSUM_MASK; if (!need_csum || offload_csum) features |= NETIF_F_HW_CSUM; } /* segment inner packet. */ segs = gso_inner_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; do { unsigned int len; if (remcsum) skb->ip_summed = CHECKSUM_NONE; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); len = skb->len - udp_offset; uh = udp_hdr(skb); /* If we are only performing partial GSO the inner header * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); } else { uh->len = htons(len); } if (!need_csum) continue; uh->check = ~csum_fold(csum_add(partial, (__force __wsum)htonl(len))); if (skb->encapsulation || !offload_csum) { uh->check = gso_make_checksum(skb, ~uh->check); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); } } while ((skb = skb->next)); out: return segs; } struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { const struct net_offload __rcu **offloads; __be16 protocol = skb->protocol; const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features); rcu_read_lock(); switch (skb->inner_protocol_type) { case ENCAP_TYPE_ETHER: protocol = skb->inner_protocol; gso_inner_segment = skb_mac_gso_segment; break; case ENCAP_TYPE_IPPROTO: offloads = is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[skb->inner_ipproto]); if (!ops || !ops->callbacks.gso_segment) goto out_unlock; gso_inner_segment = ops->callbacks.gso_segment; break; default: goto out_unlock; } segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment, protocol, is_ipv6); out_unlock: rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_udp_tunnel_segment); static void __udpv4_gso_segment_csum(struct sk_buff *seg, __be32 *oldip, __be32 *newip, __be16 *oldport, __be16 *newport) { struct udphdr *uh; struct iphdr *iph; if (*oldip == *newip && *oldport == *newport) return; uh = udp_hdr(seg); iph = ip_hdr(seg); if (uh->check) { inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip, true); inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport, false); if (!uh->check) uh->check = CSUM_MANGLED_0; } *oldport = *newport; csum_replace4(&iph->check, *oldip, *newip); *oldip = *newip; } static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) { struct sk_buff *seg; struct udphdr *uh, *uh2; struct iphdr *iph, *iph2; seg = segs; uh = udp_hdr(seg); iph = ip_hdr(seg); if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) && (udp_hdr(seg)->source == udp_hdr(seg->next)->source) && (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) && (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr)) return segs; while ((seg = seg->next)) { uh2 = udp_hdr(seg); iph2 = ip_hdr(seg); __udpv4_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &uh2->source, &uh->source); __udpv4_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &uh2->dest, &uh->dest); } return segs; } static void __udpv6_gso_segment_csum(struct sk_buff *seg, struct in6_addr *oldip, const struct in6_addr *newip, __be16 *oldport, __be16 newport) { struct udphdr *uh = udp_hdr(seg); if (ipv6_addr_equal(oldip, newip) && *oldport == newport) return; if (uh->check) { inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32, newip->s6_addr32, true); inet_proto_csum_replace2(&uh->check, seg, *oldport, newport, false); if (!uh->check) uh->check = CSUM_MANGLED_0; } *oldip = *newip; *oldport = newport; } static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs) { const struct ipv6hdr *iph; const struct udphdr *uh; struct ipv6hdr *iph2; struct sk_buff *seg; struct udphdr *uh2; seg = segs; uh = udp_hdr(seg); iph = ipv6_hdr(seg); uh2 = udp_hdr(seg->next); iph2 = ipv6_hdr(seg->next); if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) && ipv6_addr_equal(&iph->saddr, &iph2->saddr) && ipv6_addr_equal(&iph->daddr, &iph2->daddr)) return segs; while ((seg = seg->next)) { uh2 = udp_hdr(seg); iph2 = ipv6_hdr(seg); __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &uh2->source, uh->source); __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &uh2->dest, uh->dest); } return segs; } static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { unsigned int mss = skb_shinfo(skb)->gso_size; skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); if (IS_ERR(skb)) return skb; udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); if (is_ipv6) return __udpv6_gso_segment_list_csum(skb); else return __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6) { struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; struct sk_buff *segs, *seg; struct udphdr *uh; unsigned int mss; bool copy_dtor; __sum16 check; __be16 newlen; int ret = 0; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); if (unlikely(skb_checksum_start(gso_skb) != skb_transport_header(gso_skb) && !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL); /* We don't know if egress device can segment and checksum the packet * when IPv6 extension headers are present. Fall back to software GSO. */ if (gso_skb->ip_summed != CHECKSUM_PARTIAL) features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), mss); return NULL; } if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { /* Detect modified geometry and pass those to skb_segment. */ if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); ret = __skb_linearize(gso_skb); if (ret) return ERR_PTR(ret); /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); gso_skb->ip_summed = CHECKSUM_PARTIAL; uh = udp_hdr(gso_skb); if (is_ipv6) uh->check = ~udp_v6_check(gso_skb->len, &ipv6_hdr(gso_skb)->saddr, &ipv6_hdr(gso_skb)->daddr, 0); else uh->check = ~udp_v4_check(gso_skb->len, ip_hdr(gso_skb)->saddr, ip_hdr(gso_skb)->daddr, 0); } skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; if (copy_dtor) { gso_skb->destructor = NULL; gso_skb->sk = NULL; } segs = skb_segment(gso_skb, features); if (IS_ERR_OR_NULL(segs)) { if (copy_dtor) { gso_skb->destructor = sock_wfree; gso_skb->sk = sk; } return segs; } /* GSO partial and frag_list segmentation only requires splitting * the frame into an MSS multiple and possibly a remainder, both * cases return a GSO skb. So update the mss now. */ if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; seg = segs; uh = udp_hdr(seg); /* preserve TX timestamp flags and TS key for first segment */ skb_shinfo(seg)->tskey = skb_shinfo(gso_skb)->tskey; skb_shinfo(seg)->tx_flags |= (skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP); /* compute checksum adjustment based on old length versus new */ newlen = htons(sizeof(*uh) + mss); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); for (;;) { if (copy_dtor) { seg->destructor = sock_wfree; seg->sk = sk; sum_truesize += seg->truesize; } if (!seg->next) break; uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; seg = seg->next; uh = udp_hdr(seg); } /* last packet can be partial gso_size, account for that in checksum */ newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + seg->data_len); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; /* On the TX path, CHECKSUM_NONE and CHECKSUM_UNNECESSARY have the same * meaning. However, check for bad offloads in the GSO stack expects the * latter, if the checksum was calculated in software. To vouch for the * segment skbs we actually need to set it on the gso_skb. */ if (gso_skb->ip_summed == CHECKSUM_NONE) gso_skb->ip_summed = CHECKSUM_UNNECESSARY; /* update refcount for the packet */ if (copy_dtor) { int delta = sum_truesize - gso_skb->truesize; /* In some pathological cases, delta can be negative. * We need to either use refcount_add() or refcount_sub_and_test() */ if (likely(delta >= 0)) refcount_add(delta, &sk->sk_wmem_alloc); else WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); } return segs; } EXPORT_SYMBOL_GPL(__udp_gso_segment); static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; __wsum csum; struct udphdr *uh; struct iphdr *iph; if (skb->encapsulation && (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) { segs = skb_udp_tunnel_segment(skb, features, false); goto out; } if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as * HW cannot do checksum of UDP packets sent as multiple * IP fragments. */ uh = udp_hdr(skb); iph = ip_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Fragment the skb. IP headers of the fragments are updated in * inet_gso_segment() */ segs = skb_segment(skb, features); out: return segs; } #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; unsigned int ulen; int ret = 0; int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* Do not deal with padded or malicious packets, sorry ! */ ulen = ntohs(uh->len); if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = udp_hdr(p); /* Match ports only, as csum is always non zero */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { NAPI_GRO_CB(skb)->flush = 1; return p; } flush = gro_receive_network_flush(uh, uh2, p); /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { if (!pskb_may_pull(skb, skb_gro_offset(skb))) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } if ((skb->ip_summed != p->ip_summed) || (skb->csum_level != p->csum_level)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } ret = skb_gro_receive_list(p, skb); } else { skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); ret = skb_gro_receive(p, skb); } } if (ret || ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; return pp; } /* mismatch, but we never need to flush */ return NULL; } struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; /* We can do L4 aggregation only if the packet can't land in a tunnel * otherwise we could corrupt the inner stream. Detecting such packets * cannot be foolproof and the aggregation might still happen in some * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { /* If the packet was locally encapsulated in a UDP tunnel that * wasn't detected above, do not GRO. */ if (skb->encapsulation) goto out; if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist) return call_gro_receive(udp_gro_receive_segment, head, skb); /* no GRO, be sure flush the current packet */ goto out; } if (NAPI_GRO_CB(skb)->encap_mark || (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; flush = 0; list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = (struct udphdr *)(p->data + off); /* Match ports and either checksums are either both zero * or nonzero. */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) || (!uh->check ^ !uh2->check)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = udp_tunnel_gro_rcv(sk, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); struct net *net = dev_net_rcu(skb->dev); struct sock *sk; int iif, sdif; sk = udp_tunnel_sk(net, false); if (sk && dport == htons(sk->sk_num)) return sk; inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, iph->daddr, dport, iif, sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, inet_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; if (static_branch_unlikely(&udp_encap_needed_key)) sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } static int udp_gro_complete_segment(struct sk_buff *skb) { struct udphdr *uh = udp_hdr(skb); skb->csum_start = (unsigned char *)uh - skb->head; skb->csum_offset = offsetof(struct udphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; return 0; } int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup) { __be16 newlen = htons(skb->len - nhoff); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); struct sock *sk; int err; uh->len = newlen; sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; /* clear the encap mark, so that inner frag_list gro_complete * can take place */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Set encapsulation before calling into inner gro_complete() * functions to make them set up the inner offsets. */ skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); } else { err = udp_gro_complete_segment(skb); } if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; return err; } EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } int __init udpv4_offload_init(void) { net_hotdata.udpv4_offload = (struct net_offload) { .callbacks = { .gso_segment = udp4_ufo_fragment, .gro_receive = udp4_gro_receive, .gro_complete = udp4_gro_complete, }, }; udp_tunnel_gro_init(); return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } |
| 509 509 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 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-or-later /* * NET4: Sysctl interface to net af_unix subsystem. * * Authors: Mike Shaver. */ #include <linux/slab.h> #include <linux/string.h> #include <linux/sysctl.h> #include <net/af_unix.h> #include <net/net_namespace.h> #include "af_unix.h" static struct ctl_table unix_table[] = { { .procname = "max_dgram_qlen", .data = &init_net.unx.sysctl_max_dgram_qlen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, }; int __net_init unix_sysctl_register(struct net *net) { struct ctl_table *table; if (net_eq(net, &init_net)) { table = unix_table; } else { table = kmemdup(unix_table, sizeof(unix_table), GFP_KERNEL); if (!table) goto err_alloc; table[0].data = &net->unx.sysctl_max_dgram_qlen; } net->unx.ctl = register_net_sysctl_sz(net, "net/unix", table, ARRAY_SIZE(unix_table)); if (net->unx.ctl == NULL) goto err_reg; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } void unix_sysctl_unregister(struct net *net) { const struct ctl_table *table; table = net->unx.ctl->ctl_table_arg; unregister_net_sysctl_table(net->unx.ctl); if (!net_eq(net, &init_net)) kfree(table); } |
| 2 11 11 11 6 58 4 7 2 5 2 5 2 3 17 1 1 7 8 9 6 12 3 5 1 5 5 2 3 2 3 4 1 5 5 5 8 1 1 8 2 6 2 4 4 2 4 2 6 6 6 6 6 6 29 13 3 3 3 22 22 22 1 1 1 1 1 22 22 14 14 36 1 3 4 1 4 4 4 4 4 4 4 9 9 9 9 13 1 12 1 1 42 18 41 5 44 1 45 45 45 45 30 30 29 29 29 29 24 24 22 22 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2003 Patrick McHardy, <kaber@trash.net> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version 2 * of the License, or (at your option) any later version. * * 2003-10-17 - Ported from altq */ /* * Copyright (c) 1997-1999 Carnegie Mellon University. All Rights Reserved. * * Permission to use, copy, modify, and distribute this software and * its documentation is hereby granted (including for commercial or * for-profit use), provided that both the copyright notice and this * permission notice appear in all copies of the software, derivative * works, or modified versions, and any portions thereof. * * THIS SOFTWARE IS EXPERIMENTAL AND IS KNOWN TO HAVE BUGS, SOME OF * WHICH MAY HAVE SERIOUS CONSEQUENCES. CARNEGIE MELLON PROVIDES THIS * SOFTWARE IN ITS ``AS IS'' CONDITION, AND ANY EXPRESS OR IMPLIED * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE * DISCLAIMED. IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE * USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * * Carnegie Mellon encourages (but does not require) users of this * software to return any improvements or extensions that they make, * and to grant Carnegie Mellon the rights to redistribute these * changes without encumbrance. */ /* * H-FSC is described in Proceedings of SIGCOMM'97, * "A Hierarchical Fair Service Curve Algorithm for Link-Sharing, * Real-Time and Priority Service" * by Ion Stoica, Hui Zhang, and T. S. Eugene Ng. * * Oleg Cherevko <olwi@aq.ml.com.ua> added the upperlimit for link-sharing. * when a class has an upperlimit, the fit-time is computed from the * upperlimit service curve. the link-sharing scheduler does not schedule * a class whose fit-time exceeds the current time. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <asm/div64.h> /* * kernel internal service curve representation: * coordinates are given by 64 bit unsigned integers. * x-axis: unit is clock count. * y-axis: unit is byte. * * The service curve parameters are converted to the internal * representation. The slope values are scaled to avoid overflow. * the inverse slope values as well as the y-projection of the 1st * segment are kept in order to avoid 64-bit divide operations * that are expensive on 32-bit architectures. */ struct internal_sc { u64 sm1; /* scaled slope of the 1st segment */ u64 ism1; /* scaled inverse-slope of the 1st segment */ u64 dx; /* the x-projection of the 1st segment */ u64 dy; /* the y-projection of the 1st segment */ u64 sm2; /* scaled slope of the 2nd segment */ u64 ism2; /* scaled inverse-slope of the 2nd segment */ }; /* runtime service curve */ struct runtime_sc { u64 x; /* current starting position on x-axis */ u64 y; /* current starting position on y-axis */ u64 sm1; /* scaled slope of the 1st segment */ u64 ism1; /* scaled inverse-slope of the 1st segment */ u64 dx; /* the x-projection of the 1st segment */ u64 dy; /* the y-projection of the 1st segment */ u64 sm2; /* scaled slope of the 2nd segment */ u64 ism2; /* scaled inverse-slope of the 2nd segment */ }; enum hfsc_class_flags { HFSC_RSC = 0x1, HFSC_FSC = 0x2, HFSC_USC = 0x4 }; struct hfsc_class { struct Qdisc_class_common cl_common; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ struct tcf_block *block; unsigned int level; /* class level in hierarchy */ struct hfsc_sched *sched; /* scheduler data */ struct hfsc_class *cl_parent; /* parent class */ struct list_head siblings; /* sibling classes */ struct list_head children; /* child classes */ struct Qdisc *qdisc; /* leaf qdisc */ struct rb_node el_node; /* qdisc's eligible tree member */ struct rb_root vt_tree; /* active children sorted by cl_vt */ struct rb_node vt_node; /* parent's vt_tree member */ struct rb_root cf_tree; /* active children sorted by cl_f */ struct rb_node cf_node; /* parent's cf_heap member */ u64 cl_total; /* total work in bytes */ u64 cl_cumul; /* cumulative work in bytes done by real-time criteria */ u64 cl_d; /* deadline*/ u64 cl_e; /* eligible time */ u64 cl_vt; /* virtual time */ u64 cl_f; /* time when this class will fit for link-sharing, max(myf, cfmin) */ u64 cl_myf; /* my fit-time (calculated from this class's own upperlimit curve) */ u64 cl_cfmin; /* earliest children's fit-time (used with cl_myf to obtain cl_f) */ u64 cl_cvtmin; /* minimal virtual time among the children fit for link-sharing (monotonic within a period) */ u64 cl_vtadj; /* intra-period cumulative vt adjustment */ u64 cl_cvtoff; /* largest virtual time seen among the children */ struct internal_sc cl_rsc; /* internal real-time service curve */ struct internal_sc cl_fsc; /* internal fair service curve */ struct internal_sc cl_usc; /* internal upperlimit service curve */ struct runtime_sc cl_deadline; /* deadline curve */ struct runtime_sc cl_eligible; /* eligible curve */ struct runtime_sc cl_virtual; /* virtual curve */ struct runtime_sc cl_ulimit; /* upperlimit curve */ u8 cl_flags; /* which curves are valid */ u32 cl_vtperiod; /* vt period sequence number */ u32 cl_parentperiod;/* parent's vt period sequence number*/ u32 cl_nactive; /* number of active children */ }; struct hfsc_sched { u16 defcls; /* default class id */ struct hfsc_class root; /* root class */ struct Qdisc_class_hash clhash; /* class hash */ struct rb_root eligible; /* eligible tree */ struct qdisc_watchdog watchdog; /* watchdog timer */ }; #define HT_INFINITY 0xffffffffffffffffULL /* infinite time value */ static bool cl_in_el_or_vttree(struct hfsc_class *cl) { return ((cl->cl_flags & HFSC_FSC) && cl->cl_nactive) || ((cl->cl_flags & HFSC_RSC) && !RB_EMPTY_NODE(&cl->el_node)); } /* * eligible tree holds backlogged classes being sorted by their eligible times. * there is one eligible tree per hfsc instance. */ static void eltree_insert(struct hfsc_class *cl) { struct rb_node **p = &cl->sched->eligible.rb_node; struct rb_node *parent = NULL; struct hfsc_class *cl1; while (*p != NULL) { parent = *p; cl1 = rb_entry(parent, struct hfsc_class, el_node); if (cl->cl_e >= cl1->cl_e) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&cl->el_node, parent, p); rb_insert_color(&cl->el_node, &cl->sched->eligible); } static inline void eltree_remove(struct hfsc_class *cl) { if (!RB_EMPTY_NODE(&cl->el_node)) { rb_erase(&cl->el_node, &cl->sched->eligible); RB_CLEAR_NODE(&cl->el_node); } } static inline void eltree_update(struct hfsc_class *cl) { eltree_remove(cl); eltree_insert(cl); } /* find the class with the minimum deadline among the eligible classes */ static inline struct hfsc_class * eltree_get_mindl(struct hfsc_sched *q, u64 cur_time) { struct hfsc_class *p, *cl = NULL; struct rb_node *n; for (n = rb_first(&q->eligible); n != NULL; n = rb_next(n)) { p = rb_entry(n, struct hfsc_class, el_node); if (p->cl_e > cur_time) break; if (cl == NULL || p->cl_d < cl->cl_d) cl = p; } return cl; } /* find the class with minimum eligible time among the eligible classes */ static inline struct hfsc_class * eltree_get_minel(struct hfsc_sched *q) { struct rb_node *n; n = rb_first(&q->eligible); if (n == NULL) return NULL; return rb_entry(n, struct hfsc_class, el_node); } /* * vttree holds holds backlogged child classes being sorted by their virtual * time. each intermediate class has one vttree. */ static void vttree_insert(struct hfsc_class *cl) { struct rb_node **p = &cl->cl_parent->vt_tree.rb_node; struct rb_node *parent = NULL; struct hfsc_class *cl1; while (*p != NULL) { parent = *p; cl1 = rb_entry(parent, struct hfsc_class, vt_node); if (cl->cl_vt >= cl1->cl_vt) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&cl->vt_node, parent, p); rb_insert_color(&cl->vt_node, &cl->cl_parent->vt_tree); } static inline void vttree_remove(struct hfsc_class *cl) { rb_erase(&cl->vt_node, &cl->cl_parent->vt_tree); } static inline void vttree_update(struct hfsc_class *cl) { vttree_remove(cl); vttree_insert(cl); } static inline struct hfsc_class * vttree_firstfit(struct hfsc_class *cl, u64 cur_time) { struct hfsc_class *p; struct rb_node *n; for (n = rb_first(&cl->vt_tree); n != NULL; n = rb_next(n)) { p = rb_entry(n, struct hfsc_class, vt_node); if (p->cl_f <= cur_time) return p; } return NULL; } /* * get the leaf class with the minimum vt in the hierarchy */ static struct hfsc_class * vttree_get_minvt(struct hfsc_class *cl, u64 cur_time) { /* if root-class's cfmin is bigger than cur_time nothing to do */ if (cl->cl_cfmin > cur_time) return NULL; while (cl->level > 0) { cl = vttree_firstfit(cl, cur_time); if (cl == NULL) return NULL; /* * update parent's cl_cvtmin. */ if (cl->cl_parent->cl_cvtmin < cl->cl_vt) cl->cl_parent->cl_cvtmin = cl->cl_vt; } return cl; } static void cftree_insert(struct hfsc_class *cl) { struct rb_node **p = &cl->cl_parent->cf_tree.rb_node; struct rb_node *parent = NULL; struct hfsc_class *cl1; while (*p != NULL) { parent = *p; cl1 = rb_entry(parent, struct hfsc_class, cf_node); if (cl->cl_f >= cl1->cl_f) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&cl->cf_node, parent, p); rb_insert_color(&cl->cf_node, &cl->cl_parent->cf_tree); } static inline void cftree_remove(struct hfsc_class *cl) { rb_erase(&cl->cf_node, &cl->cl_parent->cf_tree); } static inline void cftree_update(struct hfsc_class *cl) { cftree_remove(cl); cftree_insert(cl); } /* * service curve support functions * * external service curve parameters * m: bps * d: us * internal service curve parameters * sm: (bytes/psched_us) << SM_SHIFT * ism: (psched_us/byte) << ISM_SHIFT * dx: psched_us * * The clock source resolution with ktime and PSCHED_SHIFT 10 is 1.024us. * * sm and ism are scaled in order to keep effective digits. * SM_SHIFT and ISM_SHIFT are selected to keep at least 4 effective * digits in decimal using the following table. * * bits/sec 100Kbps 1Mbps 10Mbps 100Mbps 1Gbps * ------------+------------------------------------------------------- * bytes/1.024us 12.8e-3 128e-3 1280e-3 12800e-3 128000e-3 * * 1.024us/byte 78.125 7.8125 0.78125 0.078125 0.0078125 * * So, for PSCHED_SHIFT 10 we need: SM_SHIFT 20, ISM_SHIFT 18. */ #define SM_SHIFT (30 - PSCHED_SHIFT) #define ISM_SHIFT (8 + PSCHED_SHIFT) #define SM_MASK ((1ULL << SM_SHIFT) - 1) #define ISM_MASK ((1ULL << ISM_SHIFT) - 1) static inline u64 seg_x2y(u64 x, u64 sm) { u64 y; /* * compute * y = x * sm >> SM_SHIFT * but divide it for the upper and lower bits to avoid overflow */ y = (x >> SM_SHIFT) * sm + (((x & SM_MASK) * sm) >> SM_SHIFT); return y; } static inline u64 seg_y2x(u64 y, u64 ism) { u64 x; if (y == 0) x = 0; else if (ism == HT_INFINITY) x = HT_INFINITY; else { x = (y >> ISM_SHIFT) * ism + (((y & ISM_MASK) * ism) >> ISM_SHIFT); } return x; } /* Convert m (bps) into sm (bytes/psched us) */ static u64 m2sm(u32 m) { u64 sm; sm = ((u64)m << SM_SHIFT); sm += PSCHED_TICKS_PER_SEC - 1; do_div(sm, PSCHED_TICKS_PER_SEC); return sm; } /* convert m (bps) into ism (psched us/byte) */ static u64 m2ism(u32 m) { u64 ism; if (m == 0) ism = HT_INFINITY; else { ism = ((u64)PSCHED_TICKS_PER_SEC << ISM_SHIFT); ism += m - 1; do_div(ism, m); } return ism; } /* convert d (us) into dx (psched us) */ static u64 d2dx(u32 d) { u64 dx; dx = ((u64)d * PSCHED_TICKS_PER_SEC); dx += USEC_PER_SEC - 1; do_div(dx, USEC_PER_SEC); return dx; } /* convert sm (bytes/psched us) into m (bps) */ static u32 sm2m(u64 sm) { u64 m; m = (sm * PSCHED_TICKS_PER_SEC) >> SM_SHIFT; return (u32)m; } /* convert dx (psched us) into d (us) */ static u32 dx2d(u64 dx) { u64 d; d = dx * USEC_PER_SEC; do_div(d, PSCHED_TICKS_PER_SEC); return (u32)d; } static void sc2isc(struct tc_service_curve *sc, struct internal_sc *isc) { isc->sm1 = m2sm(sc->m1); isc->ism1 = m2ism(sc->m1); isc->dx = d2dx(sc->d); isc->dy = seg_x2y(isc->dx, isc->sm1); isc->sm2 = m2sm(sc->m2); isc->ism2 = m2ism(sc->m2); } /* * initialize the runtime service curve with the given internal * service curve starting at (x, y). */ static void rtsc_init(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y) { rtsc->x = x; rtsc->y = y; rtsc->sm1 = isc->sm1; rtsc->ism1 = isc->ism1; rtsc->dx = isc->dx; rtsc->dy = isc->dy; rtsc->sm2 = isc->sm2; rtsc->ism2 = isc->ism2; } /* * calculate the y-projection of the runtime service curve by the * given x-projection value */ static u64 rtsc_y2x(struct runtime_sc *rtsc, u64 y) { u64 x; if (y < rtsc->y) x = rtsc->x; else if (y <= rtsc->y + rtsc->dy) { /* x belongs to the 1st segment */ if (rtsc->dy == 0) x = rtsc->x + rtsc->dx; else x = rtsc->x + seg_y2x(y - rtsc->y, rtsc->ism1); } else { /* x belongs to the 2nd segment */ x = rtsc->x + rtsc->dx + seg_y2x(y - rtsc->y - rtsc->dy, rtsc->ism2); } return x; } static u64 rtsc_x2y(struct runtime_sc *rtsc, u64 x) { u64 y; if (x <= rtsc->x) y = rtsc->y; else if (x <= rtsc->x + rtsc->dx) /* y belongs to the 1st segment */ y = rtsc->y + seg_x2y(x - rtsc->x, rtsc->sm1); else /* y belongs to the 2nd segment */ y = rtsc->y + rtsc->dy + seg_x2y(x - rtsc->x - rtsc->dx, rtsc->sm2); return y; } /* * update the runtime service curve by taking the minimum of the current * runtime service curve and the service curve starting at (x, y). */ static void rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y) { u64 y1, y2, dx, dy; u32 dsm; if (isc->sm1 <= isc->sm2) { /* service curve is convex */ y1 = rtsc_x2y(rtsc, x); if (y1 < y) /* the current rtsc is smaller */ return; rtsc->x = x; rtsc->y = y; return; } /* * service curve is concave * compute the two y values of the current rtsc * y1: at x * y2: at (x + dx) */ y1 = rtsc_x2y(rtsc, x); if (y1 <= y) { /* rtsc is below isc, no change to rtsc */ return; } y2 = rtsc_x2y(rtsc, x + isc->dx); if (y2 >= y + isc->dy) { /* rtsc is above isc, replace rtsc by isc */ rtsc->x = x; rtsc->y = y; rtsc->dx = isc->dx; rtsc->dy = isc->dy; return; } /* * the two curves intersect * compute the offsets (dx, dy) using the reverse * function of seg_x2y() * seg_x2y(dx, sm1) == seg_x2y(dx, sm2) + (y1 - y) */ dx = (y1 - y) << SM_SHIFT; dsm = isc->sm1 - isc->sm2; do_div(dx, dsm); /* * check if (x, y1) belongs to the 1st segment of rtsc. * if so, add the offset. */ if (rtsc->x + rtsc->dx > x) dx += rtsc->x + rtsc->dx - x; dy = seg_x2y(dx, isc->sm1); rtsc->x = x; rtsc->y = y; rtsc->dx = dx; rtsc->dy = dy; } static void init_ed(struct hfsc_class *cl, unsigned int next_len) { u64 cur_time = psched_get_time(); /* update the deadline curve */ rtsc_min(&cl->cl_deadline, &cl->cl_rsc, cur_time, cl->cl_cumul); /* * update the eligible curve. * for concave, it is equal to the deadline curve. * for convex, it is a linear curve with slope m2. */ cl->cl_eligible = cl->cl_deadline; if (cl->cl_rsc.sm1 <= cl->cl_rsc.sm2) { cl->cl_eligible.dx = 0; cl->cl_eligible.dy = 0; } /* compute e and d */ cl->cl_e = rtsc_y2x(&cl->cl_eligible, cl->cl_cumul); cl->cl_d = rtsc_y2x(&cl->cl_deadline, cl->cl_cumul + next_len); eltree_insert(cl); } static void update_ed(struct hfsc_class *cl, unsigned int next_len) { cl->cl_e = rtsc_y2x(&cl->cl_eligible, cl->cl_cumul); cl->cl_d = rtsc_y2x(&cl->cl_deadline, cl->cl_cumul + next_len); eltree_update(cl); } static inline void update_d(struct hfsc_class *cl, unsigned int next_len) { cl->cl_d = rtsc_y2x(&cl->cl_deadline, cl->cl_cumul + next_len); } static inline void update_cfmin(struct hfsc_class *cl) { struct rb_node *n = rb_first(&cl->cf_tree); struct hfsc_class *p; if (n == NULL) { cl->cl_cfmin = 0; return; } p = rb_entry(n, struct hfsc_class, cf_node); cl->cl_cfmin = p->cl_f; } static void init_vf(struct hfsc_class *cl, unsigned int len) { struct hfsc_class *max_cl; struct rb_node *n; u64 vt, f, cur_time; int go_active; cur_time = 0; go_active = 1; for (; cl->cl_parent != NULL; cl = cl->cl_parent) { if (go_active && cl->cl_nactive++ == 0) go_active = 1; else go_active = 0; if (go_active) { n = rb_last(&cl->cl_parent->vt_tree); if (n != NULL) { max_cl = rb_entry(n, struct hfsc_class, vt_node); /* * set vt to the average of the min and max * classes. if the parent's period didn't * change, don't decrease vt of the class. */ vt = max_cl->cl_vt; if (cl->cl_parent->cl_cvtmin != 0) vt = (cl->cl_parent->cl_cvtmin + vt)/2; if (cl->cl_parent->cl_vtperiod != cl->cl_parentperiod || vt > cl->cl_vt) cl->cl_vt = vt; } else { /* * first child for a new parent backlog period. * initialize cl_vt to the highest value seen * among the siblings. this is analogous to * what cur_time would provide in realtime case. */ cl->cl_vt = cl->cl_parent->cl_cvtoff; cl->cl_parent->cl_cvtmin = 0; } /* update the virtual curve */ rtsc_min(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); cl->cl_vtadj = 0; cl->cl_vtperiod++; /* increment vt period */ cl->cl_parentperiod = cl->cl_parent->cl_vtperiod; if (cl->cl_parent->cl_nactive == 0) cl->cl_parentperiod++; cl->cl_f = 0; vttree_insert(cl); cftree_insert(cl); if (cl->cl_flags & HFSC_USC) { /* class has upper limit curve */ if (cur_time == 0) cur_time = psched_get_time(); /* update the ulimit curve */ rtsc_min(&cl->cl_ulimit, &cl->cl_usc, cur_time, cl->cl_total); /* compute myf */ cl->cl_myf = rtsc_y2x(&cl->cl_ulimit, cl->cl_total); } } f = max(cl->cl_myf, cl->cl_cfmin); if (f != cl->cl_f) { cl->cl_f = f; cftree_update(cl); } update_cfmin(cl->cl_parent); } } static void update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time) { u64 f; /* , myf_bound, delta; */ int go_passive = 0; if (cl->qdisc->q.qlen == 0 && cl->cl_flags & HFSC_FSC) go_passive = 1; for (; cl->cl_parent != NULL; cl = cl->cl_parent) { cl->cl_total += len; if (!(cl->cl_flags & HFSC_FSC) || cl->cl_nactive == 0) continue; if (go_passive && --cl->cl_nactive == 0) go_passive = 1; else go_passive = 0; /* update vt */ cl->cl_vt = rtsc_y2x(&cl->cl_virtual, cl->cl_total) + cl->cl_vtadj; /* * if vt of the class is smaller than cvtmin, * the class was skipped in the past due to non-fit. * if so, we need to adjust vtadj. */ if (cl->cl_vt < cl->cl_parent->cl_cvtmin) { cl->cl_vtadj += cl->cl_parent->cl_cvtmin - cl->cl_vt; cl->cl_vt = cl->cl_parent->cl_cvtmin; } if (go_passive) { /* no more active child, going passive */ /* update cvtoff of the parent class */ if (cl->cl_vt > cl->cl_parent->cl_cvtoff) cl->cl_parent->cl_cvtoff = cl->cl_vt; /* remove this class from the vt tree */ vttree_remove(cl); cftree_remove(cl); update_cfmin(cl->cl_parent); continue; } /* update the vt tree */ vttree_update(cl); /* update f */ if (cl->cl_flags & HFSC_USC) { cl->cl_myf = rtsc_y2x(&cl->cl_ulimit, cl->cl_total); #if 0 cl->cl_myf = cl->cl_myfadj + rtsc_y2x(&cl->cl_ulimit, cl->cl_total); /* * This code causes classes to stay way under their * limit when multiple classes are used at gigabit * speed. needs investigation. -kaber */ /* * if myf lags behind by more than one clock tick * from the current time, adjust myfadj to prevent * a rate-limited class from going greedy. * in a steady state under rate-limiting, myf * fluctuates within one clock tick. */ myf_bound = cur_time - PSCHED_JIFFIE2US(1); if (cl->cl_myf < myf_bound) { delta = cur_time - cl->cl_myf; cl->cl_myfadj += delta; cl->cl_myf += delta; } #endif } f = max(cl->cl_myf, cl->cl_cfmin); if (f != cl->cl_f) { cl->cl_f = f; cftree_update(cl); update_cfmin(cl->cl_parent); } } } static unsigned int qdisc_peek_len(struct Qdisc *sch) { struct sk_buff *skb; unsigned int len; skb = sch->ops->peek(sch); if (unlikely(skb == NULL)) { qdisc_warn_nonwc("qdisc_peek_len", sch); return 0; } len = qdisc_pkt_len(skb); return len; } static void hfsc_adjust_levels(struct hfsc_class *cl) { struct hfsc_class *p; unsigned int level; do { level = 0; list_for_each_entry(p, &cl->children, siblings) { if (p->level >= level) level = p->level + 1; } cl->level = level; } while ((cl = cl->cl_parent) != NULL); } static inline struct hfsc_class * hfsc_find_class(u32 classid, struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct Qdisc_class_common *clc; clc = qdisc_class_find(&q->clhash, classid); if (clc == NULL) return NULL; return container_of(clc, struct hfsc_class, cl_common); } static void hfsc_change_rsc(struct hfsc_class *cl, struct tc_service_curve *rsc, u64 cur_time) { sc2isc(rsc, &cl->cl_rsc); rtsc_init(&cl->cl_deadline, &cl->cl_rsc, cur_time, cl->cl_cumul); cl->cl_eligible = cl->cl_deadline; if (cl->cl_rsc.sm1 <= cl->cl_rsc.sm2) { cl->cl_eligible.dx = 0; cl->cl_eligible.dy = 0; } cl->cl_flags |= HFSC_RSC; } static void hfsc_change_fsc(struct hfsc_class *cl, struct tc_service_curve *fsc) { sc2isc(fsc, &cl->cl_fsc); rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); cl->cl_flags |= HFSC_FSC; } static void hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc, u64 cur_time) { sc2isc(usc, &cl->cl_usc); rtsc_init(&cl->cl_ulimit, &cl->cl_usc, cur_time, cl->cl_total); cl->cl_flags |= HFSC_USC; } static void hfsc_upgrade_rt(struct hfsc_class *cl) { cl->cl_fsc = cl->cl_rsc; rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); cl->cl_flags |= HFSC_FSC; } static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { [TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_USC] = { .len = sizeof(struct tc_service_curve) }, }; static int hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)*arg; struct hfsc_class *parent = NULL; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HFSC_MAX + 1]; struct tc_service_curve *rsc = NULL, *fsc = NULL, *usc = NULL; u64 cur_time; int err; if (opt == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_HFSC_MAX, opt, hfsc_policy, NULL); if (err < 0) return err; if (tb[TCA_HFSC_RSC]) { rsc = nla_data(tb[TCA_HFSC_RSC]); if (rsc->m1 == 0 && rsc->m2 == 0) rsc = NULL; } if (tb[TCA_HFSC_FSC]) { fsc = nla_data(tb[TCA_HFSC_FSC]); if (fsc->m1 == 0 && fsc->m2 == 0) fsc = NULL; } if (tb[TCA_HFSC_USC]) { usc = nla_data(tb[TCA_HFSC_USC]); if (usc->m1 == 0 && usc->m2 == 0) usc = NULL; } if (cl != NULL) { int old_flags; int len = 0; if (parentid) { if (cl->cl_parent && cl->cl_parent->cl_common.classid != parentid) return -EINVAL; if (cl->cl_parent == NULL && parentid != TC_H_ROOT) return -EINVAL; } cur_time = psched_get_time(); if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, true, tca[TCA_RATE]); if (err) return err; } sch_tree_lock(sch); old_flags = cl->cl_flags; if (rsc != NULL) hfsc_change_rsc(cl, rsc, cur_time); if (fsc != NULL) hfsc_change_fsc(cl, fsc); if (usc != NULL) hfsc_change_usc(cl, usc, cur_time); if (cl->qdisc->q.qlen != 0) len = qdisc_peek_len(cl->qdisc); /* Check queue length again since some qdisc implementations * (e.g., netem/codel) might empty the queue during the peek * operation. */ if (cl->qdisc->q.qlen != 0) { if (cl->cl_flags & HFSC_RSC) { if (old_flags & HFSC_RSC) update_ed(cl, len); else init_ed(cl, len); } if (cl->cl_flags & HFSC_FSC) { if (old_flags & HFSC_FSC) update_vf(cl, 0, cur_time); else init_vf(cl, len); } } sch_tree_unlock(sch); return 0; } if (parentid == TC_H_ROOT) return -EEXIST; parent = &q->root; if (parentid) { parent = hfsc_find_class(parentid, sch); if (parent == NULL) return -ENOENT; } if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0) return -EINVAL; if (hfsc_find_class(classid, sch)) return -EEXIST; if (rsc == NULL && fsc == NULL) return -EINVAL; cl = kzalloc(sizeof(struct hfsc_class), GFP_KERNEL); if (cl == NULL) return -ENOBUFS; RB_CLEAR_NODE(&cl->el_node); err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); return err; } if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, true, tca[TCA_RATE]); if (err) { tcf_block_put(cl->block); kfree(cl); return err; } } if (rsc != NULL) hfsc_change_rsc(cl, rsc, 0); if (fsc != NULL) hfsc_change_fsc(cl, fsc); if (usc != NULL) hfsc_change_usc(cl, usc, 0); cl->cl_common.classid = classid; cl->sched = q; cl->cl_parent = parent; cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; else qdisc_hash_add(cl->qdisc, true); INIT_LIST_HEAD(&cl->children); cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; sch_tree_lock(sch); /* Check if the inner class is a misconfigured 'rt' */ if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { NL_SET_ERR_MSG(extack, "Forced curve change on parent 'rt' to 'sc'"); hfsc_upgrade_rt(parent); } qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) qdisc_purge_queue(parent->qdisc); hfsc_adjust_levels(parent); sch_tree_unlock(sch); qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; } static void hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) { struct hfsc_sched *q = qdisc_priv(sch); tcf_block_put(cl->block); qdisc_put(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) kfree(cl); } static int hfsc_delete_class(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl->level > 0 || qdisc_class_in_use(&cl->cl_common) || cl == &q->root) { NL_SET_ERR_MSG(extack, "HFSC class in use"); return -EBUSY; } sch_tree_lock(sch); list_del(&cl->siblings); hfsc_adjust_levels(cl->cl_parent); qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->cl_common); sch_tree_unlock(sch); hfsc_destroy_class(sch, cl); return 0; } static struct hfsc_class * hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *head, *cl; struct tcf_result res; struct tcf_proto *tcf; int result; if (TC_H_MAJ(skb->priority ^ sch->handle) == 0 && (cl = hfsc_find_class(skb->priority, sch)) != NULL) if (cl->level == 0) return cl; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return NULL; } #endif cl = (struct hfsc_class *)res.class; if (!cl) { cl = hfsc_find_class(res.classid, sch); if (!cl) break; /* filter selected invalid classid */ if (cl->level >= head->level) break; /* filter may only point downwards */ } if (cl->level == 0) return cl; /* hit leaf class */ /* apply inner filter chain */ tcf = rcu_dereference_bh(cl->filter_list); head = cl; } /* classification failed, try default class */ cl = hfsc_find_class(TC_H_MAKE(TC_H_MAJ(sch->handle), READ_ONCE(q->defcls)), sch); if (cl == NULL || cl->level > 0) return NULL; return cl; } static int hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl->level > 0) return -EINVAL; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->cl_common.classid, NULL); if (new == NULL) new = &noop_qdisc; } *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } static struct Qdisc * hfsc_class_leaf(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl->level == 0) return cl->qdisc; return NULL; } static void hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; /* vttree is now handled in update_vf() so that update_vf(cl, 0, 0) * needs to be called explicitly to remove a class from vttree. */ if (cl->cl_nactive) update_vf(cl, 0, 0); if (cl->cl_flags & HFSC_RSC) eltree_remove(cl); } static unsigned long hfsc_search_class(struct Qdisc *sch, u32 classid) { return (unsigned long)hfsc_find_class(classid, sch); } static unsigned long hfsc_bind_tcf(struct Qdisc *sch, unsigned long parent, u32 classid) { struct hfsc_class *p = (struct hfsc_class *)parent; struct hfsc_class *cl = hfsc_find_class(classid, sch); if (cl != NULL) { if (p != NULL && p->level <= cl->level) return 0; qdisc_class_get(&cl->cl_common); } return (unsigned long)cl; } static void hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; qdisc_class_put(&cl->cl_common); } static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; if (cl == NULL) cl = &q->root; return cl->block; } static int hfsc_dump_sc(struct sk_buff *skb, int attr, struct internal_sc *sc) { struct tc_service_curve tsc; tsc.m1 = sm2m(sc->sm1); tsc.d = dx2d(sc->dx); tsc.m2 = sm2m(sc->sm2); if (nla_put(skb, attr, sizeof(tsc), &tsc)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int hfsc_dump_curves(struct sk_buff *skb, struct hfsc_class *cl) { if ((cl->cl_flags & HFSC_RSC) && (hfsc_dump_sc(skb, TCA_HFSC_RSC, &cl->cl_rsc) < 0)) goto nla_put_failure; if ((cl->cl_flags & HFSC_FSC) && (hfsc_dump_sc(skb, TCA_HFSC_FSC, &cl->cl_fsc) < 0)) goto nla_put_failure; if ((cl->cl_flags & HFSC_USC) && (hfsc_dump_sc(skb, TCA_HFSC_USC, &cl->cl_usc) < 0)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct hfsc_class *cl = (struct hfsc_class *)arg; struct nlattr *nest; tcm->tcm_parent = cl->cl_parent ? cl->cl_parent->cl_common.classid : TC_H_ROOT; tcm->tcm_handle = cl->cl_common.classid; if (cl->level == 0) tcm->tcm_info = cl->qdisc->handle; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; if (hfsc_dump_curves(skb, cl) < 0) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct hfsc_class *cl = (struct hfsc_class *)arg; struct tc_hfsc_stats xstats; __u32 qlen; qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &cl->qstats.backlog); xstats.level = cl->level; xstats.period = cl->cl_vtperiod; xstats.work = cl->cl_total; xstats.rtwork = cl->cl_cumul; if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); } static void hfsc_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) return; } } } static void hfsc_schedule_watchdog(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; u64 next_time = 0; cl = eltree_get_minel(q); if (cl) next_time = cl->cl_e; if (q->root.cl_cfmin != 0) { if (next_time == 0 || next_time > q->root.cl_cfmin) next_time = q->root.cl_cfmin; } if (next_time) qdisc_watchdog_schedule(&q->watchdog, next_time); } static int hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; int err; qdisc_watchdog_init(&q->watchdog, sch); if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); q->defcls = qopt->defcls; err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; q->eligible = RB_ROOT; err = tcf_block_get(&q->root.block, &q->root.filter_list, sch, extack); if (err) return err; gnet_stats_basic_sync_init(&q->root.bstats); q->root.cl_common.classid = sch->handle; q->root.sched = q; q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, NULL); if (q->root.qdisc == NULL) q->root.qdisc = &noop_qdisc; else qdisc_hash_add(q->root.qdisc, true); INIT_LIST_HEAD(&q->root.children); q->root.vt_tree = RB_ROOT; q->root.cf_tree = RB_ROOT; qdisc_class_hash_insert(&q->clhash, &q->root.cl_common); qdisc_class_hash_grow(sch, &q->clhash); return 0; } static int hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct tc_hfsc_qopt *qopt; if (nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); WRITE_ONCE(q->defcls, qopt->defcls); return 0; } static void hfsc_reset_class(struct hfsc_class *cl) { cl->cl_total = 0; cl->cl_cumul = 0; cl->cl_d = 0; cl->cl_e = 0; cl->cl_vt = 0; cl->cl_vtadj = 0; cl->cl_cvtmin = 0; cl->cl_cvtoff = 0; cl->cl_vtperiod = 0; cl->cl_parentperiod = 0; cl->cl_f = 0; cl->cl_myf = 0; cl->cl_cfmin = 0; cl->cl_nactive = 0; cl->vt_tree = RB_ROOT; cl->cf_tree = RB_ROOT; qdisc_reset(cl->qdisc); if (cl->cl_flags & HFSC_RSC) rtsc_init(&cl->cl_deadline, &cl->cl_rsc, 0, 0); if (cl->cl_flags & HFSC_FSC) rtsc_init(&cl->cl_virtual, &cl->cl_fsc, 0, 0); if (cl->cl_flags & HFSC_USC) rtsc_init(&cl->cl_ulimit, &cl->cl_usc, 0, 0); } static void hfsc_reset_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) hfsc_reset_class(cl); } q->eligible = RB_ROOT; qdisc_watchdog_cancel(&q->watchdog); } static void hfsc_destroy_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hlist_node *next; struct hfsc_class *cl; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { tcf_block_put(cl->block); cl->block = NULL; } } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], cl_common.hnode) hfsc_destroy_class(sch, cl); } qdisc_class_hash_destroy(&q->clhash); qdisc_watchdog_cancel(&q->watchdog); } static int hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) { struct hfsc_sched *q = qdisc_priv(sch); unsigned char *b = skb_tail_pointer(skb); struct tc_hfsc_qopt qopt; qopt.defcls = READ_ONCE(q->defcls); if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; return skb->len; nla_put_failure: nlmsg_trim(skb, b); return -1; } static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb); struct hfsc_class *cl; int err; bool first; cl = hfsc_classify(skb, sch, &err); if (cl == NULL) { if (err & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return err; } first = !cl->qdisc->q.qlen; err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { cl->qstats.drops++; qdisc_qstats_drop(sch); } return err; } sch->qstats.backlog += len; sch->q.qlen++; if (first && !cl_in_el_or_vttree(cl)) { if (cl->cl_flags & HFSC_RSC) init_ed(cl, len); if (cl->cl_flags & HFSC_FSC) init_vf(cl, len); /* * If this is the first packet, isolate the head so an eventual * head drop before the first dequeue operation has no chance * to invalidate the deadline. */ if (cl->cl_flags & HFSC_RSC) cl->qdisc->ops->peek(cl->qdisc); } return NET_XMIT_SUCCESS; } static struct sk_buff * hfsc_dequeue(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; struct sk_buff *skb; u64 cur_time; unsigned int next_len; int realtime = 0; if (sch->q.qlen == 0) return NULL; cur_time = psched_get_time(); /* * if there are eligible classes, use real-time criteria. * find the class with the minimum deadline among * the eligible classes. */ cl = eltree_get_mindl(q, cur_time); if (cl) { realtime = 1; } else { /* * use link-sharing criteria * get the class with the minimum vt in the hierarchy */ cl = vttree_get_minvt(&q->root, cur_time); if (cl == NULL) { qdisc_qstats_overlimit(sch); hfsc_schedule_watchdog(sch); return NULL; } } skb = qdisc_dequeue_peeked(cl->qdisc); if (skb == NULL) { qdisc_warn_nonwc("HFSC", cl->qdisc); return NULL; } bstats_update(&cl->bstats, skb); update_vf(cl, qdisc_pkt_len(skb), cur_time); if (realtime) cl->cl_cumul += qdisc_pkt_len(skb); if (cl->cl_flags & HFSC_RSC) { if (cl->qdisc->q.qlen != 0) { /* update ed */ next_len = qdisc_peek_len(cl->qdisc); /* Check queue length again since some qdisc implementations * (e.g., netem/codel) might empty the queue during the peek * operation. */ if (cl->qdisc->q.qlen != 0) { if (realtime) update_ed(cl, next_len); else update_d(cl, next_len); } } else { /* the class becomes passive */ eltree_remove(cl); } } qdisc_bstats_update(sch, skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; return skb; } static const struct Qdisc_class_ops hfsc_class_ops = { .change = hfsc_change_class, .delete = hfsc_delete_class, .graft = hfsc_graft_class, .leaf = hfsc_class_leaf, .qlen_notify = hfsc_qlen_notify, .find = hfsc_search_class, .bind_tcf = hfsc_bind_tcf, .unbind_tcf = hfsc_unbind_tcf, .tcf_block = hfsc_tcf_block, .dump = hfsc_dump_class, .dump_stats = hfsc_dump_class_stats, .walk = hfsc_walk }; static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = { .id = "hfsc", .init = hfsc_init_qdisc, .change = hfsc_change_qdisc, .reset = hfsc_reset_qdisc, .destroy = hfsc_destroy_qdisc, .dump = hfsc_dump_qdisc, .enqueue = hfsc_enqueue, .dequeue = hfsc_dequeue, .peek = qdisc_peek_dequeued, .cl_ops = &hfsc_class_ops, .priv_size = sizeof(struct hfsc_sched), .owner = THIS_MODULE }; MODULE_ALIAS_NET_SCH("hfsc"); static int __init hfsc_init(void) { return register_qdisc(&hfsc_qdisc_ops); } static void __exit hfsc_cleanup(void) { unregister_qdisc(&hfsc_qdisc_ops); } MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Hierarchical Fair Service Curve scheduler"); module_init(hfsc_init); module_exit(hfsc_cleanup); |
| 11555 11555 623 623 18117 18113 9269 9264 12939 12938 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old; \ CODE \ if (likely(try_cmpxchg64_relaxed(&lockref->lock_count, \ &old.lock_count, \ new.lock_count))) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ bool lockref_get_not_zero(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count > 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return false; lockref->count--; spin_unlock(&lockref->lock); return true; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ bool lockref_get_not_dead(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count >= 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 68 69 16 56 56 23 47 1 47 25 141 141 104 104 61 67 2 25 25 25 25 68 69 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "timers.h" #include "device.h" #include "peer.h" #include "socket.h" #include "messages.h" #include "cookie.h" #include <linux/uio.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <net/ip_tunnels.h> #include <net/udp.h> #include <net/sock.h> static void wg_packet_send_handshake_initiation(struct wg_peer *peer) { struct message_handshake_initiation packet; if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT)) return; /* This function is rate limited. */ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); wg_timers_handshake_initiated(peer); } } void wg_packet_handshake_send_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_handshake_work); wg_packet_send_handshake_initiation(peer); wg_peer_put(peer); } void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry) { if (!is_retry) peer->timer_handshake_attempts = 0; rcu_read_lock_bh(); /* We check last_sent_handshake here in addition to the actual function * we're queueing up, so that we don't queue things if not strictly * necessary: */ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT) || unlikely(READ_ONCE(peer->is_dead))) goto out; wg_peer_get(peer); /* Queues up calling packet_send_queued_handshakes(peer), where we do a * peer_put(peer) after: */ if (!queue_work(peer->device->handshake_send_wq, &peer->transmit_handshake_work)) /* If the work was already queued, we want to drop the * extra reference: */ wg_peer_put(peer); out: rcu_read_unlock_bh(); } void wg_packet_send_handshake_response(struct wg_peer *peer) { struct message_handshake_response packet; atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_response(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); if (wg_noise_handshake_begin_session(&peer->handshake, &peer->keypairs)) { wg_timers_session_derived(peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); } } } void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index) { struct message_handshake_cookie packet; net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n", wg->dev->name, initiating_skb); wg_cookie_message_create(&packet, initiating_skb, sender_index, &wg->cookie_checker); wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet, sizeof(packet)); } static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); send = keypair && READ_ONCE(keypair->sending.is_valid) && (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES || (keypair->i_am_the_initiator && wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } static unsigned int calculate_skb_padding(struct sk_buff *skb) { unsigned int padded_size, last_unit = skb->len; if (unlikely(!PACKET_CB(skb)->mtu)) return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the * padded_size being clamped. Fortunately, that's very rarely the case, * so we optimize for that not happening. */ if (unlikely(last_unit > PACKET_CB(skb)->mtu)) last_unit %= PACKET_CB(skb)->mtu; padded_size = min(PACKET_CB(skb)->mtu, ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) { unsigned int padding_len, plaintext_len, trailer_len; struct scatterlist sg[MAX_SKB_FRAGS + 8]; struct message_data *header; struct sk_buff *trailer; int num_frags; /* Force hash calculation before encryption so that flow analysis is * consistent over the inner packet. */ skb_get_hash(skb); /* Calculate lengths. */ padding_len = calculate_skb_padding(skb); trailer_len = padding_len + noise_encrypted_len(0); plaintext_len = skb->len + padding_len; /* Expand data section to have room for padding and auth tag. */ num_frags = skb_cow_data(skb, trailer_len, &trailer); if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) return false; /* Set the padding to zeros, and make sure it and the auth tag are part * of the skb. */ memset(skb_tail_pointer(trailer), 0, padding_len); /* Expand head section to have room for our header and the network * stack's headers. */ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0)) return false; /* Finalize checksum calculation for the inner packet, if required. */ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))) return false; /* Only after checksumming can we safely add on the padding at the end * and the header. */ skb_set_inner_network_header(skb, 0); header = (struct message_data *)skb_push(skb, sizeof(*header)); header->header.type = cpu_to_le32(MESSAGE_DATA); header->key_idx = keypair->remote_index; header->counter = cpu_to_le64(PACKET_CB(skb)->nonce); pskb_put(skb, trailer, trailer_len); /* Now we can encrypt the scattergather segments */ sg_init_table(sg, num_frags); if (skb_to_sgvec(skb, sg, sizeof(struct message_data), noise_encrypted_len(plaintext_len)) <= 0) return false; return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0, PACKET_CB(skb)->nonce, keypair->sending.key); } void wg_packet_send_keepalive(struct wg_peer *peer) { struct sk_buff *skb; if (skb_queue_empty_lockless(&peer->staged_packet_queue)) { skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH, GFP_ATOMIC); if (unlikely(!skb)) return; skb_reserve(skb, DATA_PACKET_HEAD_ROOM); skb->dev = peer->device->dev; PACKET_CB(skb)->mtu = skb->dev->mtu; skb_queue_tail(&peer->staged_packet_queue, skb); net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); } wg_packet_send_staged_packets(peer); } static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) { struct sk_buff *skb, *next; bool is_keepalive, data_sent = false; wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); skb_list_walk_safe(first, skb, next) { is_keepalive = skb->len == message_data_len(0); if (likely(!wg_socket_send_skb_to_peer(peer, skb, PACKET_CB(skb)->ds) && !is_keepalive)) data_sent = true; } if (likely(data_sent)) wg_timers_data_sent(peer); keep_key_fresh(peer); } void wg_packet_tx_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); struct noise_keypair *keypair; enum packet_state state; struct sk_buff *first; while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(first)->state)) != PACKET_STATE_UNCRYPTED) { wg_prev_queue_drop_peeked(&peer->tx_queue); keypair = PACKET_CB(first)->keypair; if (likely(state == PACKET_STATE_CRYPTED)) wg_packet_create_data_done(peer, first); else kfree_skb_list(first); wg_noise_keypair_put(keypair, false); wg_peer_put(peer); if (need_resched()) cond_resched(); } } void wg_packet_encrypt_worker(struct work_struct *work) { struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; struct sk_buff *first, *skb, *next; while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) { enum packet_state state = PACKET_STATE_CRYPTED; skb_list_walk_safe(first, skb, next) { if (likely(encrypt_packet(skb, PACKET_CB(first)->keypair))) { wg_reset_packet(skb, true); } else { state = PACKET_STATE_DEAD; break; } } wg_queue_enqueue_per_peer_tx(first, state); if (need_resched()) cond_resched(); } } static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) { struct wg_device *wg = peer->device; int ret = -EINVAL; rcu_read_lock_bh(); if (unlikely(READ_ONCE(peer->is_dead))) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: rcu_read_unlock_bh(); if (likely(!ret || ret == -EPIPE)) return; wg_noise_keypair_put(PACKET_CB(first)->keypair, false); wg_peer_put(peer); kfree_skb_list(first); } void wg_packet_purge_staged_packets(struct wg_peer *peer) { spin_lock_bh(&peer->staged_packet_queue.lock); DEV_STATS_ADD(peer->device->dev, tx_dropped, peer->staged_packet_queue.qlen); __skb_queue_purge(&peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); } void wg_packet_send_staged_packets(struct wg_peer *peer) { struct noise_keypair *keypair; struct sk_buff_head packets; struct sk_buff *skb; /* Steal the current queue into our local one. */ __skb_queue_head_init(&packets); spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice_init(&peer->staged_packet_queue, &packets); spin_unlock_bh(&peer->staged_packet_queue.lock); if (unlikely(skb_queue_empty(&packets))) return; /* First we make sure we have a valid reference to a valid key. */ rcu_read_lock_bh(); keypair = wg_noise_keypair_get( rcu_dereference_bh(peer->keypairs.current_keypair)); rcu_read_unlock_bh(); if (unlikely(!keypair)) goto out_nokey; if (unlikely(!READ_ONCE(keypair->sending.is_valid))) goto out_nokey; if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, REJECT_AFTER_TIME))) goto out_invalid; /* After we know we have a somewhat valid key, we now try to assign * nonces to all of the packets in the queue. If we can't assign nonces * for all of them, we just consider it a failure and wait for the next * handshake. */ skb_queue_walk(&packets, skb) { /* 0 for no outer TOS: no leak. TODO: at some later point, we * might consider using flowi->tos as outer instead. */ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb); PACKET_CB(skb)->nonce = atomic64_inc_return(&keypair->sending_counter) - 1; if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES)) goto out_invalid; } packets.prev->next = NULL; wg_peer_get(keypair->entry.peer); PACKET_CB(packets.next)->keypair = keypair; wg_packet_create_data(peer, packets.next); return; out_invalid: WRITE_ONCE(keypair->sending.is_valid, false); out_nokey: wg_noise_keypair_put(keypair, false); /* We orphan the packets if we're waiting on a handshake, so that they * don't block a socket's pool. */ skb_queue_walk(&packets, skb) skb_orphan(skb); /* Then we put them back on the top of the queue. We're not too * concerned about accidentally getting things a little out of order if * packets are being added really fast, because this queue is for before * packets can even be sent and it's small anyway. */ spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); /* If we're exiting because there's something wrong with the key, it * means we should initiate a new handshake. */ wg_packet_send_queued_handshake_initiation(peer, false); } |
| 16 216 217 76 9 45 43 216 13 7 115 102 216 140 5 57 57 216 153 44 3 27 191 195 43 43 22 584 539 507 32 539 42 7 49 152 152 130 37 16 22 47 2 473 2 471 426 471 446 20 533 489 46 35 27 15 31 520 20 534 22 21 21 52 20 32 7 45 45 45 42 7 1 6 21 15 13 23 4 12 57 43 15 132 132 132 91 92 41 115 17 83 16 17 16 16 16 5 11 105 43 1 1 284 285 144 33 122 7 45 72 72 72 148 22 3 2 174 176 176 18 8 168 12 17 100 32 11 122 122 73 27 3 19 121 122 120 72 13 13 1 12 13 13 1 6 72 56 1 8 3 26 25 6 18 26 3 41 3 38 1 3 8 3 1 3 3 2 141 2 137 139 50 50 136 1 136 68 61 1 122 122 122 36 26 2 24 974 978 436 436 426 436 426 117 34 82 6 40 43 81 1 1 83 32 22 3 540 509 30 36 36 36 598 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/rculist.h> #include <linux/err.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <net/rtnetlink.h> #include <net/udp.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #endif static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) { return hash_32((__force u32)key ^ (__force u32)remote, IP_TNL_HASH_BITS); } static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, const unsigned long *flags, __be32 key) { if (!test_bit(IP_TUNNEL_KEY_BIT, flags)) return !test_bit(IP_TUNNEL_KEY_BIT, p->i_flags); return test_bit(IP_TUNNEL_KEY_BIT, p->i_flags) && p->i_key == key; } /* Fallback tunnel: no source, no destination, no key, no options Tunnel hash table: We require exact key match i.e. if a key is present in packet it will match only tunnel with the same key; if it is not present, it will match only keyless tunnel. All keysless packets, if not matched configured keyless tunnels will match fallback tunnel. Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key) { struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; struct net_device *ndev; unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if (remote != t->parms.iph.daddr || t->parms.iph.saddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } hash = ip_tunnel_hash(key, 0); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) continue; if (!(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if ((!test_bit(IP_TUNNEL_NO_KEY_BIT, flags) && t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } if (cand) return cand; t = rcu_dereference(itn->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; ndev = READ_ONCE(itn->fb_tunnel_dev); if (ndev && ndev->flags & IFF_UP) return netdev_priv(ndev); return NULL; } EXPORT_SYMBOL_GPL(ip_tunnel_lookup); static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms) { unsigned int h; __be32 remote; __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; if (!test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags) && test_bit(IP_TUNNEL_VTI_BIT, parms->i_flags)) i_key = 0; h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t) { struct hlist_head *head = ip_bucket(itn, &t->parms); if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, t); hlist_add_head_rcu(&t->hash_node, head); } static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) { if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, NULL); hlist_del_init_rcu(&t->hash_node); } static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms, int type) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; IP_TUNNEL_DECLARE_FLAGS(flags); __be32 key = parms->i_key; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); ip_tunnel_flags_copy(flags, parms->i_flags); hlist_for_each_entry_rcu(t, head, hash_node, lockdep_rtnl_is_held()) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == READ_ONCE(t->parms.link) && type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } return t; } static struct net_device *__ip_tunnel_create(struct net *net, const struct rtnl_link_ops *ops, struct ip_tunnel_parm_kern *parms) { int err; struct ip_tunnel *tunnel; struct net_device *dev; char name[IFNAMSIZ]; err = -E2BIG; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strscpy(name, parms->name); } else { if (strlen(ops->kind) > (IFNAMSIZ - 3)) goto failed; strscpy(name, ops->kind); strcat(name, "%d"); } ASSERT_RTNL(); dev = alloc_netdev(ops->priv_size, name, NET_NAME_UNKNOWN, ops->setup); if (!dev) { err = -ENOMEM; goto failed; } dev_net_set(dev, net); dev->rtnl_link_ops = ops; tunnel = netdev_priv(dev); tunnel->parms = *parms; tunnel->net = net; err = register_netdevice(dev); if (err) goto failed_free; return dev; failed_free: free_netdev(dev); failed: return ERR_PTR(err); } static int ip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *iph; int hlen = LL_MAX_HEADER; int mtu = ETH_DATA_LEN; int t_hlen = tunnel->hlen + sizeof(struct iphdr); iph = &tunnel->parms.iph; /* Guess output device to choose reasonable mtu and needed_headroom */ if (iph->daddr) { struct flowi4 fl4; struct rtable *rt; ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, iph->tos & INET_DSCP_MASK, tunnel->net, tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) dev->flags |= IFF_POINTOPOINT; dst_cache_reset(&tunnel->dst_cache); } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev) { hlen = tdev->hard_header_len + tdev->needed_headroom; mtu = min(tdev->mtu, IP_MAX_MTU); } dev->needed_headroom = t_hlen + hlen; mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; return mtu; } static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms) { struct ip_tunnel *nt; struct net_device *dev; int t_hlen; int mtu; int err; dev = __ip_tunnel_create(net, itn->rtnl_link_ops, parms); if (IS_ERR(dev)) return ERR_CAST(dev); mtu = ip_tunnel_bind_dev(dev); err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) dev->max_mtu -= dev->hard_header_len; ip_tunnel_add(itn, nt); return nt; err_dev_set_mtu: unregister_netdevice(dev); return ERR_PTR(err); } void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info) { const struct iphdr *iph = ip_hdr(skb); const struct udphdr *udph; if (iph->protocol != IPPROTO_UDP) return; udph = (struct udphdr *)((__u8 *)iph + (iph->ihl << 2)); info->encap.sport = udph->source; info->encap.dport = udph->dest; } EXPORT_SYMBOL(ip_tunnel_md_udp_encap); int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { DEV_STATS_INC(tunnel->dev, multicast); skb->pkt_type = PACKET_BROADCAST; } #endif if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } iph = (struct iphdr *)(skb->head + nh); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tunnel->dev->type == ARPHRD_ETHER) { skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; } if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: if (tun_dst) dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_rcv); int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; return !cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL(ip_tunnel_encap_add_ops); int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { int ret; if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; ret = (cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL(ip_tunnel_encap_del_ops); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap) { int hlen; memset(&t->encap, 0, sizeof(t->encap)); hlen = ip_encap_hlen(ipencap); if (hlen < 0) return hlen; t->encap.type = ipencap->type; t->encap.sport = ipencap->sport; t->encap.dport = ipencap->dport; t->encap.flags = ipencap->flags; t->encap_hlen = hlen; t->hlen = t->encap_hlen + t->tun_hlen; return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup); static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df, const struct iphdr *inner_iph, int tunnel_hlen, __be32 dst, bool md) { struct ip_tunnel *tunnel = netdev_priv(dev); int pkt_size; int mtu; tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; pkt_size = skb->len - tunnel_hlen; pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; if (df) { mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; } else { mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; } if (skb_valid_dst(skb)) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && (inner_iph->frag_off & htons(IP_DF)) && mtu < pkt_size) { icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; } } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6; __be32 daddr; rt6 = skb_valid_dst(skb) ? dst_rt6_info(skb_dst(skb)) : NULL; daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { if ((daddr && !ipv4_is_multicast(daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); } } if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && mtu < pkt_size) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -E2BIG; } } #endif return 0; } static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) { /* we must cap headroom to some upperlimit, else pskb_expand_head * will overflow header offsets in skb_headers_offset_update(). */ static const unsigned int max_allowed = 512; if (headroom > max_allowed) headroom = max_allowed; if (headroom > READ_ONCE(dev->needed_headroom)) WRITE_ONCE(dev->needed_headroom, headroom); } void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; const struct iphdr *inner_iph; struct rtable *rt = NULL; struct flowi4 fl4; __be16 df = 0; u8 tos, ttl; bool use_cache; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto tx_error; key = &tun_info->key; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); inner_iph = (const struct iphdr *)skb_inner_network_header(skb); tos = key->tos; if (tos == 1) { if (skb->protocol == htons(ETH_P_IP)) tos = inner_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark, skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) tunnel_hlen = ip_encap_hlen(&tun_info->encap); if (ip_tunnel_encap(skb, &tun_info->encap, &proto, &fl4) < 0) goto tx_error; use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { ip_rt_put(rt); goto tx_error; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; else ttl = ip4_dst_hoplimit(&rt->dst); } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } ip_tunnel_adj_headroom(dev, headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; tx_error: DEV_STATS_INC(dev, tx_errors); goto kfree; tx_dropped: DEV_STATS_INC(dev, tx_dropped); kfree: kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_md_tunnel_xmit); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info = NULL; const struct iphdr *inner_iph; unsigned int max_headroom; /* The extra header space needed */ struct rtable *rt = NULL; /* Route to the other host */ __be16 payload_protocol; bool use_cache = false; struct flowi4 fl4; bool md = false; bool connected; u8 tos, ttl; __be32 dst; __be16 df; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); payload_protocol = skb_protocol(skb, true); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ if (!skb_dst(skb)) { DEV_STATS_INC(dev, tx_fifo_errors); goto tx_error; } tun_info = skb_tunnel_info(skb); if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) && ip_tunnel_info_af(tun_info) == AF_INET && tun_info->key.u.ipv4.dst) { dst = tun_info->key.u.ipv4.dst; md = true; connected = true; } else if (payload_protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (payload_protocol == htons(ETH_P_IPV6)) { const struct in6_addr *addr6; struct neighbour *neigh; bool do_tx_error_icmp; int addr_type; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) do_tx_error_icmp = true; else { do_tx_error_icmp = false; dst = addr6->s6_addr32[3]; } neigh_release(neigh); if (do_tx_error_icmp) goto tx_error_icmp; } #endif else goto tx_error; if (!md) connected = false; } tos = tnl_params->tos; if (tos & 0x1) { tos &= ~0x1; if (payload_protocol == htons(ETH_P_IP)) { tos = inner_iph->tos; connected = false; } else if (payload_protocol == htons(ETH_P_IPV6)) { tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); connected = false; } } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, tos & INET_DSCP_MASK, tunnel->net, READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) goto tx_error; if (connected && md) { use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); } else { rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) : NULL; } if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); else if (!md && connected) dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } df = tnl_params->frag_off; if (payload_protocol == htons(ETH_P_IP) && !tunnel->ignore_df) df |= (inner_iph->frag_off & htons(IP_DF)); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) { ip_rt_put(rt); goto tx_error; } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (payload_protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) else if (payload_protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; #endif else ttl = ip4_dst_hoplimit(&rt->dst); } max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return; } ip_tunnel_adj_headroom(dev, max_headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; #if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); #endif tx_error: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_tunnel_xmit); static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel *t, struct net_device *dev, struct ip_tunnel_parm_kern *p, bool set_mtu, __u32 fwmark) { ip_tunnel_del(itn, t); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; if (dev->type != ARPHRD_ETHER) { __dev_addr_set(dev, &p->iph.saddr, 4); memcpy(dev->broadcast, &p->iph.daddr, 4); } ip_tunnel_add(itn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { int mtu; WRITE_ONCE(t->parms.link, p->link); t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) WRITE_ONCE(dev->mtu, mtu); } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); } int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); struct net *net = t->net; struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id); switch (cmd) { case SIOCGETTUNNEL: if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) t = netdev_priv(dev); } memcpy(p, &t->parms, sizeof(*p)); break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); if (!test_bit(IP_TUNNEL_VTI_BIT, p->i_flags)) { if (!test_bit(IP_TUNNEL_KEY_BIT, p->i_flags)) p->i_key = 0; if (!test_bit(IP_TUNNEL_KEY_BIT, p->o_flags)) p->o_key = 0; } t = ip_tunnel_find(itn, p, itn->type); if (cmd == SIOCADDTUNNEL) { if (!t) { t = ip_tunnel_create(net, itn, p); err = PTR_ERR_OR_ZERO(t); break; } err = -EEXIST; break; } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) { err = -EINVAL; break; } t = netdev_priv(dev); } } if (t) { err = 0; ip_tunnel_update(itn, t, dev, p, true, 0); } else { err = -ENOENT; } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == itn->fb_tunnel_dev) { err = -ENOENT; t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) goto done; err = -EPERM; if (t == netdev_priv(itn->fb_tunnel_dev)) goto done; dev = t->dev; } unregister_netdevice(dev); err = 0; break; default: err = -EINVAL; } done: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, const void __user *data) { struct ip_tunnel_parm p; if (copy_from_user(&p, data, sizeof(p))) return false; strscpy(kp->name, p.name); kp->link = p.link; ip_tunnel_flags_from_be16(kp->i_flags, p.i_flags); ip_tunnel_flags_from_be16(kp->o_flags, p.o_flags); kp->i_key = p.i_key; kp->o_key = p.o_key; memcpy(&kp->iph, &p.iph, min(sizeof(kp->iph), sizeof(p.iph))); return true; } EXPORT_SYMBOL_GPL(ip_tunnel_parm_from_user); bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp) { struct ip_tunnel_parm p; if (!ip_tunnel_flags_is_be16_compat(kp->i_flags) || !ip_tunnel_flags_is_be16_compat(kp->o_flags)) return false; memset(&p, 0, sizeof(p)); strscpy(p.name, kp->name); p.link = kp->link; p.i_flags = ip_tunnel_flags_to_be16(kp->i_flags); p.o_flags = ip_tunnel_flags_to_be16(kp->o_flags); p.i_key = kp->i_key; p.o_key = kp->o_key; memcpy(&p.iph, &kp->iph, min(sizeof(p.iph), sizeof(kp->iph))); return !copy_to_user(data, &p, sizeof(p)); } EXPORT_SYMBOL_GPL(ip_tunnel_parm_to_user); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct ip_tunnel_parm_kern p; int err; if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); if (!err && !ip_tunnel_parm_to_user(data, &p)) return -EFAULT; return err; } EXPORT_SYMBOL_GPL(ip_tunnel_siocdevprivate); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); int max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) max_mtu -= dev->hard_header_len; if (new_mtu < ETH_MIN_MTU) return -EINVAL; if (new_mtu > max_mtu) { if (strict) return -EINVAL; new_mtu = max_mtu; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) { return __ip_tunnel_change_mtu(dev, new_mtu, true); } EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); gro_cells_destroy(&tunnel->gro_cells); dst_cache_destroy(&tunnel->dst_cache); } void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_net *itn; itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id); if (itn->fb_tunnel_dev != dev) { ip_tunnel_del(itn, netdev_priv(dev)); unregister_netdevice_queue(dev, head); } } EXPORT_SYMBOL_GPL(ip_tunnel_dellink); struct net *ip_tunnel_get_link_net(const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip_tunnel_get_link_net); int ip_tunnel_get_iflink(const struct net_device *dev) { const struct ip_tunnel *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->parms.link); } EXPORT_SYMBOL(ip_tunnel_get_iflink); int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id); struct ip_tunnel_parm_kern parms; unsigned int i; itn->rtnl_link_ops = ops; for (i = 0; i < IP_TNL_HASH_SIZE; i++) INIT_HLIST_HEAD(&itn->tunnels[i]); if (!ops || !net_has_fallback_tunnels(net)) { struct ip_tunnel_net *it_init_net; it_init_net = net_generic(&init_net, ip_tnl_net_id); itn->type = it_init_net->type; itn->fb_tunnel_dev = NULL; return 0; } memset(&parms, 0, sizeof(parms)); if (devname) strscpy(parms.name, devname, IFNAMSIZ); rtnl_lock(); itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->netns_immutable = true; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); itn->type = itn->fb_tunnel_dev->type; } rtnl_unlock(); return PTR_ERR_OR_ZERO(itn->fb_tunnel_dev); } EXPORT_SYMBOL_GPL(ip_tunnel_init_net); void ip_tunnel_delete_net(struct net *net, unsigned int id, struct rtnl_link_ops *ops, struct list_head *head) { struct ip_tunnel_net *itn = net_generic(net, id); struct net_device *dev, *aux; int h; ASSERT_RTNL_NET(net); for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == ops) unregister_netdevice_queue(dev, head); for (h = 0; h < IP_TNL_HASH_SIZE; h++) { struct ip_tunnel *t; struct hlist_node *n; struct hlist_head *thead = &itn->tunnels[h]; hlist_for_each_entry_safe(t, n, thead, hash_node) /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); } } EXPORT_SYMBOL_GPL(ip_tunnel_delete_net); int ip_tunnel_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *nt; struct ip_tunnel_net *itn; int mtu; int err; nt = netdev_priv(dev); itn = net_generic(net, nt->ip_tnl_net_id); if (nt->collect_md) { if (rtnl_dereference(itn->collect_md_tun)) return -EEXIST; } else { if (ip_tunnel_find(itn, p, dev->type)) return -EEXIST; } nt->net = net; nt->parms = *p; nt->fwmark = fwmark; err = register_netdevice(dev); if (err) goto err_register_netdevice; if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); if (dev->type == ARPHRD_ETHER) max -= dev->hard_header_len; mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; ip_tunnel_add(itn, nt); return 0; err_dev_set_mtu: unregister_netdevice(dev); err_register_netdevice: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_newlink); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *t; struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id); if (dev == itn->fb_tunnel_dev) return -EINVAL; t = ip_tunnel_find(itn, p, dev->type); if (t) { if (t->dev != dev) return -EEXIST; } else { t = tunnel; if (dev->type != ARPHRD_ETHER) { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags ^ nflags) & (IFF_POINTOPOINT | IFF_BROADCAST)) return -EINVAL; } } ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU], fwmark); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_changelink); int ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; int err; dev->needs_free_netdev = true; dev->priv_destructor = ip_tunnel_dev_free; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) return err; err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { dst_cache_destroy(&tunnel->dst_cache); return err; } tunnel->dev = dev; strscpy(tunnel->parms.name, dev->name); iph->version = 4; iph->ihl = 5; if (tunnel->collect_md) netif_keep_dst(dev); netdev_lockdep_set_classes(dev); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); void ip_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn; itn = net_generic(net, tunnel->ip_tnl_net_id); ip_tunnel_del(itn, netdev_priv(dev)); if (itn->fb_tunnel_dev == dev) WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); /* Do least required initialization, rest of init is done in tunnel_init call */ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id) { struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->ip_tnl_net_id = net_id; } EXPORT_SYMBOL_GPL(ip_tunnel_setup); MODULE_DESCRIPTION("IPv4 tunnel implementation library"); MODULE_LICENSE("GPL"); |
| 6 261 5 5 180 11 109 38 5 119 47 72 30 37 66 102 117 43 76 119 338 34 187 63 28 168 107 107 1 107 2 31 31 76 105 2 23 14 4 89 18 1 74 59 4 25 67 82 22 5 77 15 8 29 29 7 7 50 29 7 27 27 10 15 1 1 24 14 7 15 11 5 5 5 86 86 63 85 47 1 34 26 33 8 7 44 76 112 36 76 76 10 23 31 76 76 23 27 3 11 4 2 2 2 45 86 21 17 48 2 5 10 5 81 28 1 85 110 4 13 95 95 95 95 95 6 19 71 2 9 97 97 97 97 95 97 13 2 10 10 97 1 10 3 10 9 3 2 104 103 1 103 23 62 3 1 12 45 45 103 43 3 43 3 183 183 183 182 103 254 253 1 130 124 158 35 19 152 101 89 80 16 119 1 102 16 223 1 70 152 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * inet_diag.c Module for monitoring INET transport protocols sockets. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/time.h> #include <net/icmp.h> #include <net/tcp.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/inet6_hashtables.h> #include <net/bpf_sk_storage.h> #include <net/netlink.h> #include <linux/inet.h> #include <linux/stddef.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> static const struct inet_diag_handler __rcu **inet_diag_table; struct inet_diag_entry { const __be32 *saddr; const __be32 *daddr; u16 sport; u16 dport; u16 family; u16 userlocks; u32 ifindex; u32 mark; #ifdef CONFIG_SOCK_CGROUP_DATA u64 cgroup_id; #endif }; static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { const struct inet_diag_handler *handler; if (proto < 0 || proto >= IPPROTO_MAX) return NULL; if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); rcu_read_lock(); handler = rcu_dereference(inet_diag_table[proto]); if (handler && !try_module_get(handler->owner)) handler = NULL; rcu_read_unlock(); return handler; } static void inet_diag_unlock_handler(const struct inet_diag_handler *handler) { module_put(handler->owner); } void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk) { r->idiag_family = sk->sk_family; r->id.idiag_sport = htons(sk->sk_num); r->id.idiag_dport = sk->sk_dport; r->id.idiag_if = sk->sk_bound_dev_if; sock_diag_save_cookie(sk, r->id.idiag_cookie); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) { *(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr; *(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr; } else #endif { memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); r->id.idiag_src[0] = sk->sk_rcv_saddr; r->id.idiag_dst[0] = sk->sk_daddr; } } EXPORT_SYMBOL_GPL(inet_diag_msg_common_fill); static size_t inet_sk_attr_size(struct sock *sk, const struct inet_diag_req_v2 *req, bool net_admin) { const struct inet_diag_handler *handler; size_t aux = 0; rcu_read_lock(); handler = rcu_dereference(inet_diag_table[req->sdiag_protocol]); DEBUG_NET_WARN_ON_ONCE(!handler); if (handler && handler->idiag_get_aux_size) aux = handler->idiag_get_aux_size(sk, net_admin); rcu_read_unlock(); return nla_total_size(sizeof(struct tcp_info)) + nla_total_size(sizeof(struct inet_diag_msg)) + inet_diag_msg_attrs_size() + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + nla_total_size(TCP_CA_NAME_MAX) + nla_total_size(sizeof(struct tcpvegas_info)) + aux + 64; } int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_msg *r, int ext, struct user_namespace *user_ns, bool net_admin) { const struct inet_sock *inet = inet_sk(sk); struct inet_diag_sockopt inet_sockopt; if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) goto errout; /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, * hence this needs to be included regardless of socket family. */ if (ext & (1 << (INET_DIAG_TOS - 1))) if (nla_put_u8(skb, INET_DIAG_TOS, READ_ONCE(inet->tos)) < 0) goto errout; #if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { if (ext & (1 << (INET_DIAG_TCLASS - 1))) if (nla_put_u8(skb, INET_DIAG_TCLASS, inet6_sk(sk)->tclass) < 0) goto errout; if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk))) goto errout; } #endif if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark))) goto errout; if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || ext & (1 << (INET_DIAG_TCLASS - 1))) { u32 classid = 0; #ifdef CONFIG_CGROUP_NET_CLASSID classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif /* Fallback to socket priority if class id isn't set. * Classful qdiscs use it as direct reference to class. * For cgroup2 classid is always zero. */ if (!classid) classid = READ_ONCE(sk->sk_priority); if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; } #ifdef CONFIG_SOCK_CGROUP_DATA if (nla_put_u64_64bit(skb, INET_DIAG_CGROUP_ID, cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)), INET_DIAG_PAD)) goto errout; #endif r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); memset(&inet_sockopt, 0, sizeof(inet_sockopt)); inet_sockopt.recverr = inet_test_bit(RECVERR, sk); inet_sockopt.is_icsk = inet_test_bit(IS_ICSK, sk); inet_sockopt.freebind = inet_test_bit(FREEBIND, sk); inet_sockopt.hdrincl = inet_test_bit(HDRINCL, sk); inet_sockopt.mc_loop = inet_test_bit(MC_LOOP, sk); inet_sockopt.transparent = inet_test_bit(TRANSPARENT, sk); inet_sockopt.mc_all = inet_test_bit(MC_ALL, sk); inet_sockopt.nodefrag = inet_test_bit(NODEFRAG, sk); inet_sockopt.bind_address_no_port = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); inet_sockopt.recverr_rfc4884 = inet_test_bit(RECVERR_RFC4884, sk); inet_sockopt.defer_connect = inet_test_bit(DEFER_CONNECT, sk); if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt), &inet_sockopt)) goto errout; return 0; errout: return 1; } EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill); static int inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, struct nlattr **req_nlas) { struct nlattr *nla; int remaining; nlmsg_for_each_attr(nla, nlh, hdrlen, remaining) { int type = nla_type(nla); if (type == INET_DIAG_REQ_PROTOCOL && nla_len(nla) != sizeof(u32)) return -EINVAL; if (type < __INET_DIAG_REQ_MAX) req_nlas[type] = nla; } return 0; } static int inet_diag_get_protocol(const struct inet_diag_req_v2 *req, const struct inet_diag_dump_data *data) { if (data->req_nlas[INET_DIAG_REQ_PROTOCOL]) return nla_get_u32(data->req_nlas[INET_DIAG_REQ_PROTOCOL]); return req->sdiag_protocol; } #define MAX_DUMP_ALLOC_SIZE (KMALLOC_MAX_SIZE - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, u16 nlmsg_flags, bool net_admin) { const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; struct inet_diag_dump_data *cb_data; int ext = req->idiag_ext; struct inet_diag_msg *r; struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; u8 icsk_pending; int protocol; cb_data = cb->data; protocol = inet_diag_get_protocol(req, cb_data); /* inet_diag_lock_handler() made sure inet_diag_table[] is stable. */ handler = rcu_dereference_protected(inet_diag_table[protocol], 1); DEBUG_NET_WARN_ON_ONCE(!handler); if (!handler) return -ENXIO; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); BUG_ON(!sk_fullsock(sk)); inet_diag_msg_common_fill(r, sk); r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; r->idiag_expires = 0; if (inet_diag_msg_attrs_fill(sk, skb, r, ext, sk_user_ns(NETLINK_CB(cb->skb).sk), net_admin)) goto errout; if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), .idiag_fmem = READ_ONCE(sk->sk_forward_alloc), .idiag_tmem = sk_wmem_alloc_get(sk), }; if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0) goto errout; } if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO)) goto errout; /* * RAW sockets might have user-defined protocols assigned, * so report the one supplied on socket creation. */ if (sk->sk_type == SOCK_RAW) { if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol)) goto errout; } if (!icsk) { handler->idiag_get_info(sk, r, NULL); goto out; } icsk_pending = smp_load_acquire(&icsk->icsk_pending); if (icsk_pending == ICSK_TIME_RETRANS || icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { r->idiag_timer = 1; r->idiag_retrans = icsk->icsk_retransmits; r->idiag_expires = jiffies_delta_to_msecs(icsk_timeout(icsk) - jiffies); } else if (icsk_pending == ICSK_TIME_PROBE0) { r->idiag_timer = 4; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = jiffies_delta_to_msecs(icsk_timeout(icsk) - jiffies); } else if (timer_pending(&sk->sk_timer)) { r->idiag_timer = 2; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies); } if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) { attr = nla_reserve_64bit(skb, INET_DIAG_INFO, handler->idiag_info_size, INET_DIAG_PAD); if (!attr) goto errout; info = nla_data(attr); } if (ext & (1 << (INET_DIAG_CONG - 1))) { int err = 0; rcu_read_lock(); ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops) err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name); rcu_read_unlock(); if (err < 0) goto errout; } handler->idiag_get_info(sk, r, info); if (ext & (1 << (INET_DIAG_INFO - 1)) && handler->idiag_get_aux) if (handler->idiag_get_aux(sk, net_admin, skb) < 0) goto errout; if (sk->sk_state < TCP_TIME_WAIT) { union tcp_cc_info info; size_t sz = 0; int attr; rcu_read_lock(); ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ext, &attr, &info); rcu_read_unlock(); if (sz && nla_put(skb, attr, sz, &info) < 0) goto errout; } /* Keep it at the end for potential retry with a larger skb, * or else do best-effort fitting, which is only done for the * first_nlmsg. */ if (cb_data->bpf_stg_diag) { bool first_nlmsg = ((unsigned char *)nlh == skb->data); unsigned int prev_min_dump_alloc; unsigned int total_nla_size = 0; unsigned int msg_len; int err; msg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; err = bpf_sk_storage_diag_put(cb_data->bpf_stg_diag, sk, skb, INET_DIAG_SK_BPF_STORAGES, &total_nla_size); if (!err) goto out; total_nla_size += msg_len; prev_min_dump_alloc = cb->min_dump_alloc; if (total_nla_size > prev_min_dump_alloc) cb->min_dump_alloc = min_t(u32, total_nla_size, MAX_DUMP_ALLOC_SIZE); if (!first_nlmsg) goto errout; if (cb->min_dump_alloc > prev_min_dump_alloc) /* Retry with pskb_expand_head() with * __GFP_DIRECT_RECLAIM */ goto errout; WARN_ON_ONCE(total_nla_size <= prev_min_dump_alloc); /* Send what we have for this sk * and move on to the next sk in the following * dump() */ } out: nlmsg_end(skb, nlh); return 0; errout: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, u16 nlmsg_flags, bool net_admin) { struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); BUG_ON(tw->tw_state != TCP_TIME_WAIT); inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; r->idiag_state = READ_ONCE(tw->tw_substate); r->idiag_timer = 3; tmo = tw->tw_timer.expires - jiffies; r->idiag_expires = jiffies_delta_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, tw->tw_mark)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, u16 nlmsg_flags, bool net_admin) { struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); inet_diag_msg_common_fill(r, sk); r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; r->idiag_retrans = reqsk->num_retrans; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies; r->idiag_expires = jiffies_delta_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, inet_rsk(reqsk)->ir_mark)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, u16 nlmsg_flags, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, nlmsg_flags, net_admin); } struct sock *inet_diag_find_one_icsk(struct net *net, struct inet_hashinfo *hashinfo, const struct inet_diag_req_v2 *req) { struct sock *sk; rcu_read_lock(); if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if); else sk = inet6_lookup(net, hashinfo, NULL, 0, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if); } #endif else { rcu_read_unlock(); return ERR_PTR(-EINVAL); } rcu_read_unlock(); if (!sk) return ERR_PTR(-ENOENT); if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { sock_gen_put(sk); return ERR_PTR(-ENOENT); } return sk; } EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { struct sk_buff *in_skb = cb->skb; bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN); struct net *net = sock_net(in_skb->sk); struct sk_buff *rep; struct sock *sk; int err; sk = inet_diag_find_one_icsk(net, hashinfo, req); if (IS_ERR(sk)) return PTR_ERR(sk); rep = nlmsg_new(inet_sk_attr_size(sk, req, net_admin), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; } err = sk_diag_fill(sk, rep, cb, req, 0, net_admin); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); goto out; } err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) sock_gen_put(sk); return err; } EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, const struct nlmsghdr *nlh, int hdrlen, const struct inet_diag_req_v2 *req) { const struct inet_diag_handler *handler; struct inet_diag_dump_data dump_data; int err, protocol; memset(&dump_data, 0, sizeof(dump_data)); err = inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas); if (err) return err; protocol = inet_diag_get_protocol(req, &dump_data); handler = inet_diag_lock_handler(protocol); if (!handler) return -ENOENT; if (cmd == SOCK_DIAG_BY_FAMILY) { struct netlink_callback cb = { .nlh = nlh, .skb = in_skb, .data = &dump_data, }; err = handler->dump_one(&cb, req); } else if (cmd == SOCK_DESTROY && handler->destroy) { err = handler->destroy(in_skb, req); } else { err = -EOPNOTSUPP; } inet_diag_unlock_handler(handler); return err; } static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits) { int words = bits >> 5; bits &= 0x1f; if (words) { if (memcmp(a1, a2, words << 2)) return 0; } if (bits) { __be32 w1, w2; __be32 mask; w1 = a1[words]; w2 = a2[words]; mask = htonl((0xffffffff) << (32 - bits)); if ((w1 ^ w2) & mask) return 0; } return 1; } static int inet_diag_bc_run(const struct nlattr *_bc, const struct inet_diag_entry *entry) { const void *bc = nla_data(_bc); int len = nla_len(_bc); while (len > 0) { int yes = 1; const struct inet_diag_bc_op *op = bc; switch (op->code) { case INET_DIAG_BC_NOP: break; case INET_DIAG_BC_JMP: yes = 0; break; case INET_DIAG_BC_S_EQ: yes = entry->sport == op[1].no; break; case INET_DIAG_BC_S_GE: yes = entry->sport >= op[1].no; break; case INET_DIAG_BC_S_LE: yes = entry->sport <= op[1].no; break; case INET_DIAG_BC_D_EQ: yes = entry->dport == op[1].no; break; case INET_DIAG_BC_D_GE: yes = entry->dport >= op[1].no; break; case INET_DIAG_BC_D_LE: yes = entry->dport <= op[1].no; break; case INET_DIAG_BC_AUTO: yes = !(entry->userlocks & SOCK_BINDPORT_LOCK); break; case INET_DIAG_BC_S_COND: case INET_DIAG_BC_D_COND: { const struct inet_diag_hostcond *cond; const __be32 *addr; cond = (const struct inet_diag_hostcond *)(op + 1); if (cond->port != -1 && cond->port != (op->code == INET_DIAG_BC_S_COND ? entry->sport : entry->dport)) { yes = 0; break; } if (op->code == INET_DIAG_BC_S_COND) addr = entry->saddr; else addr = entry->daddr; if (cond->family != AF_UNSPEC && cond->family != entry->family) { if (entry->family == AF_INET6 && cond->family == AF_INET) { if (addr[0] == 0 && addr[1] == 0 && addr[2] == htonl(0xffff) && bitstring_match(addr + 3, cond->addr, cond->prefix_len)) break; } yes = 0; break; } if (cond->prefix_len == 0) break; if (bitstring_match(addr, cond->addr, cond->prefix_len)) break; yes = 0; break; } case INET_DIAG_BC_DEV_COND: { u32 ifindex; ifindex = *((const u32 *)(op + 1)); if (ifindex != entry->ifindex) yes = 0; break; } case INET_DIAG_BC_MARK_COND: { struct inet_diag_markcond *cond; cond = (struct inet_diag_markcond *)(op + 1); if ((entry->mark & cond->mask) != cond->mark) yes = 0; break; } #ifdef CONFIG_SOCK_CGROUP_DATA case INET_DIAG_BC_CGROUP_COND: { u64 cgroup_id; cgroup_id = get_unaligned((const u64 *)(op + 1)); if (cgroup_id != entry->cgroup_id) yes = 0; break; } #endif } if (yes) { len -= op->yes; bc += op->yes; } else { len -= op->no; bc += op->no; } } return len == 0; } /* This helper is available for all sockets (ESTABLISH, TIMEWAIT, SYN_RECV) */ static void entry_fill_addrs(struct inet_diag_entry *entry, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) { entry->saddr = sk->sk_v6_rcv_saddr.s6_addr32; entry->daddr = sk->sk_v6_daddr.s6_addr32; } else #endif { entry->saddr = &sk->sk_rcv_saddr; entry->daddr = &sk->sk_daddr; } } int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct inet_diag_entry entry; if (!bc) return 1; entry.family = sk->sk_family; entry_fill_addrs(&entry, sk); entry.sport = inet->inet_num; entry.dport = ntohs(inet->inet_dport); entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; if (sk_fullsock(sk)) entry.mark = READ_ONCE(sk->sk_mark); else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; else if (sk->sk_state == TCP_TIME_WAIT) entry.mark = inet_twsk(sk)->tw_mark; else entry.mark = 0; #ifdef CONFIG_SOCK_CGROUP_DATA entry.cgroup_id = sk_fullsock(sk) ? cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)) : 0; #endif return inet_diag_bc_run(bc, &entry); } EXPORT_SYMBOL_GPL(inet_diag_bc_sk); static int valid_cc(const void *bc, int len, int cc) { while (len >= 0) { const struct inet_diag_bc_op *op = bc; if (cc > len) return 0; if (cc == len) return 1; if (op->yes < 4 || op->yes & 3) return 0; len -= op->yes; bc += op->yes; } return 0; } /* data is u32 ifindex */ static bool valid_devcond(const struct inet_diag_bc_op *op, int len, int *min_len) { /* Check ifindex space. */ *min_len += sizeof(u32); if (len < *min_len) return false; return true; } /* Validate an inet_diag_hostcond. */ static bool valid_hostcond(const struct inet_diag_bc_op *op, int len, int *min_len) { struct inet_diag_hostcond *cond; int addr_len; /* Check hostcond space. */ *min_len += sizeof(struct inet_diag_hostcond); if (len < *min_len) return false; cond = (struct inet_diag_hostcond *)(op + 1); /* Check address family and address length. */ switch (cond->family) { case AF_UNSPEC: addr_len = 0; break; case AF_INET: addr_len = sizeof(struct in_addr); break; case AF_INET6: addr_len = sizeof(struct in6_addr); break; default: return false; } *min_len += addr_len; if (len < *min_len) return false; /* Check prefix length (in bits) vs address length (in bytes). */ if (cond->prefix_len > 8 * addr_len) return false; return true; } /* Validate a port comparison operator. */ static bool valid_port_comparison(const struct inet_diag_bc_op *op, int len, int *min_len) { /* Port comparisons put the port in a follow-on inet_diag_bc_op. */ *min_len += sizeof(struct inet_diag_bc_op); if (len < *min_len) return false; return true; } static bool valid_markcond(const struct inet_diag_bc_op *op, int len, int *min_len) { *min_len += sizeof(struct inet_diag_markcond); return len >= *min_len; } #ifdef CONFIG_SOCK_CGROUP_DATA static bool valid_cgroupcond(const struct inet_diag_bc_op *op, int len, int *min_len) { *min_len += sizeof(u64); return len >= *min_len; } #endif static int inet_diag_bc_audit(const struct nlattr *attr, const struct sk_buff *skb) { bool net_admin = netlink_net_capable(skb, CAP_NET_ADMIN); const void *bytecode, *bc; int bytecode_len, len; if (!attr || nla_len(attr) < sizeof(struct inet_diag_bc_op)) return -EINVAL; bytecode = bc = nla_data(attr); len = bytecode_len = nla_len(attr); while (len > 0) { int min_len = sizeof(struct inet_diag_bc_op); const struct inet_diag_bc_op *op = bc; switch (op->code) { case INET_DIAG_BC_S_COND: case INET_DIAG_BC_D_COND: if (!valid_hostcond(bc, len, &min_len)) return -EINVAL; break; case INET_DIAG_BC_DEV_COND: if (!valid_devcond(bc, len, &min_len)) return -EINVAL; break; case INET_DIAG_BC_S_EQ: case INET_DIAG_BC_S_GE: case INET_DIAG_BC_S_LE: case INET_DIAG_BC_D_EQ: case INET_DIAG_BC_D_GE: case INET_DIAG_BC_D_LE: if (!valid_port_comparison(bc, len, &min_len)) return -EINVAL; break; case INET_DIAG_BC_MARK_COND: if (!net_admin) return -EPERM; if (!valid_markcond(bc, len, &min_len)) return -EINVAL; break; #ifdef CONFIG_SOCK_CGROUP_DATA case INET_DIAG_BC_CGROUP_COND: if (!valid_cgroupcond(bc, len, &min_len)) return -EINVAL; break; #endif case INET_DIAG_BC_AUTO: case INET_DIAG_BC_JMP: case INET_DIAG_BC_NOP: break; default: return -EINVAL; } if (op->code != INET_DIAG_BC_NOP) { if (op->no < min_len || op->no > len + 4 || op->no & 3) return -EINVAL; if (op->no < len && !valid_cc(bytecode, bytecode_len, len - op->no)) return -EINVAL; } if (op->yes < min_len || op->yes > len + 4 || op->yes & 3) return -EINVAL; bc += op->yes; len -= op->yes; } return len == 0 ? 0 : -EINVAL; } static void twsk_build_assert(void) { BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) != offsetof(struct sock, sk_family)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_num) != offsetof(struct inet_sock, inet_num)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_dport) != offsetof(struct inet_sock, inet_dport)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_rcv_saddr) != offsetof(struct inet_sock, inet_rcv_saddr)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_daddr) != offsetof(struct inet_sock, inet_daddr)); #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_rcv_saddr) != offsetof(struct sock, sk_v6_rcv_saddr)); BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_daddr) != offsetof(struct sock, sk_v6_daddr)); #endif } void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct inet_diag_dump_data *cb_data = cb->data; struct net *net = sock_net(skb->sk); u32 idiag_states = r->idiag_states; int i, num, s_i, s_num; struct nlattr *bc; struct sock *sk; bc = cb_data->inet_diag_nla_bc; if (idiag_states & TCPF_SYN_RECV) idiag_states |= TCPF_NEW_SYN_RECV; s_i = cb->args[1]; s_num = num = cb->args[2]; if (cb->args[0] == 0) { if (!(idiag_states & TCPF_LISTEN) || r->id.idiag_dport) goto skip_listen_ht; for (i = s_i; i <= hashinfo->lhash2_mask; i++) { struct inet_listen_hashbucket *ilb; struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->lhash2[i]; if (hlist_nulls_empty(&ilb->nulls_head)) { s_num = 0; continue; } spin_lock(&ilb->lock); sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) { num++; continue; } if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_listen; if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_listen; if (!inet_diag_bc_sk(bc, sk)) goto next_listen; if (inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, NLM_F_MULTI, net_admin) < 0) { spin_unlock(&ilb->lock); goto done; } next_listen: ++num; } spin_unlock(&ilb->lock); s_num = 0; } skip_listen_ht: cb->args[0] = 1; s_i = num = s_num = 0; } /* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets * with bh disabled. */ #define SKARR_SZ 16 /* Dump bound but inactive (not listening, connecting, etc.) sockets */ if (cb->args[0] == 1) { if (!(idiag_states & TCPF_BOUND_INACTIVE)) goto skip_bind_ht; for (i = s_i; i < hashinfo->bhash_size; i++) { struct inet_bind_hashbucket *ibb; struct inet_bind2_bucket *tb2; struct sock *sk_arr[SKARR_SZ]; int num_arr[SKARR_SZ]; int idx, accum, res; resume_bind_walk: num = 0; accum = 0; ibb = &hashinfo->bhash2[i]; if (hlist_empty(&ibb->chain)) { s_num = 0; continue; } spin_lock_bh(&ibb->lock); inet_bind_bucket_for_each(tb2, &ibb->chain) { if (!net_eq(ib2_net(tb2), net)) continue; sk_for_each_bound(sk, &tb2->owners) { struct inet_sock *inet = inet_sk(sk); if (num < s_num) goto next_bind; if (sk->sk_state != TCP_CLOSE || !inet->inet_num) goto next_bind; if (r->sdiag_family != AF_UNSPEC && r->sdiag_family != sk->sk_family) goto next_bind; if (!inet_diag_bc_sk(bc, sk)) goto next_bind; sock_hold(sk); num_arr[accum] = num; sk_arr[accum] = sk; if (++accum == SKARR_SZ) goto pause_bind_walk; next_bind: num++; } } pause_bind_walk: spin_unlock_bh(&ibb->lock); res = 0; for (idx = 0; idx < accum; idx++) { if (res >= 0) { res = inet_sk_diag_fill(sk_arr[idx], NULL, skb, cb, r, NLM_F_MULTI, net_admin); if (res < 0) num = num_arr[idx]; } sock_put(sk_arr[idx]); } if (res < 0) goto done; cond_resched(); if (accum == SKARR_SZ) { s_num = num + 1; goto resume_bind_walk; } s_num = 0; } skip_bind_ht: cb->args[0] = 2; s_i = num = s_num = 0; } if (!(idiag_states & ~TCPF_LISTEN)) goto out; for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); struct hlist_nulls_node *node; struct sock *sk_arr[SKARR_SZ]; int num_arr[SKARR_SZ]; int idx, accum, res; if (hlist_nulls_empty(&head->chain)) continue; if (i > s_i) s_num = 0; next_chunk: num = 0; accum = 0; spin_lock_bh(lock); sk_nulls_for_each(sk, node, &head->chain) { int state; if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) goto next_normal; state = (sk->sk_state == TCP_TIME_WAIT) ? READ_ONCE(inet_twsk(sk)->tw_substate) : sk->sk_state; if (!(idiag_states & (1 << state))) goto next_normal; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_normal; if (r->id.idiag_sport != htons(sk->sk_num) && r->id.idiag_sport) goto next_normal; if (r->id.idiag_dport != sk->sk_dport && r->id.idiag_dport) goto next_normal; twsk_build_assert(); if (!inet_diag_bc_sk(bc, sk)) goto next_normal; if (!refcount_inc_not_zero(&sk->sk_refcnt)) goto next_normal; num_arr[accum] = num; sk_arr[accum] = sk; if (++accum == SKARR_SZ) break; next_normal: ++num; } spin_unlock_bh(lock); res = 0; for (idx = 0; idx < accum; idx++) { if (res >= 0) { res = sk_diag_fill(sk_arr[idx], skb, cb, r, NLM_F_MULTI, net_admin); if (res < 0) num = num_arr[idx]; } sock_gen_put(sk_arr[idx]); } if (res < 0) break; cond_resched(); if (accum == SKARR_SZ) { s_num = num + 1; goto next_chunk; } } done: cb->args[1] = i; cb->args[2] = num; out: ; } EXPORT_SYMBOL_GPL(inet_diag_dump_icsk); static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { struct inet_diag_dump_data *cb_data = cb->data; const struct inet_diag_handler *handler; u32 prev_min_dump_alloc; int protocol, err = 0; protocol = inet_diag_get_protocol(r, cb_data); again: prev_min_dump_alloc = cb->min_dump_alloc; handler = inet_diag_lock_handler(protocol); if (handler) { handler->dump(skb, cb, r); inet_diag_unlock_handler(handler); } else { err = -ENOENT; } /* The skb is not large enough to fit one sk info and * inet_sk_diag_fill() has requested for a larger skb. */ if (!skb->len && cb->min_dump_alloc > prev_min_dump_alloc) { err = pskb_expand_head(skb, 0, cb->min_dump_alloc, GFP_KERNEL); if (!err) goto again; } return err ? : skb->len; } static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh)); } static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen) { const struct nlmsghdr *nlh = cb->nlh; struct inet_diag_dump_data *cb_data; struct sk_buff *skb = cb->skb; struct nlattr *nla; int err; cb_data = kzalloc(sizeof(*cb_data), GFP_KERNEL); if (!cb_data) return -ENOMEM; err = inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas); if (err) { kfree(cb_data); return err; } nla = cb_data->inet_diag_nla_bc; if (nla) { err = inet_diag_bc_audit(nla, skb); if (err) { kfree(cb_data); return err; } } nla = cb_data->inet_diag_nla_bpf_stgs; if (nla) { struct bpf_sk_storage_diag *bpf_stg_diag; bpf_stg_diag = bpf_sk_storage_diag_alloc(nla); if (IS_ERR(bpf_stg_diag)) { kfree(cb_data); return PTR_ERR(bpf_stg_diag); } cb_data->bpf_stg_diag = bpf_stg_diag; } cb->data = cb_data; return 0; } static int inet_diag_dump_start(struct netlink_callback *cb) { return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req_v2)); } static int inet_diag_dump_start_compat(struct netlink_callback *cb) { return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req)); } static int inet_diag_dump_done(struct netlink_callback *cb) { struct inet_diag_dump_data *cb_data = cb->data; bpf_sk_storage_diag_free(cb_data->bpf_stg_diag); kfree(cb->data); return 0; } static int inet_diag_type2proto(int type) { switch (type) { case TCPDIAG_GETSOCK: return IPPROTO_TCP; default: return 0; } } static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb) { struct inet_diag_req *rc = nlmsg_data(cb->nlh); struct inet_diag_req_v2 req; req.sdiag_family = AF_UNSPEC; /* compatibility */ req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type); req.idiag_ext = rc->idiag_ext; req.pad = 0; req.idiag_states = rc->idiag_states; req.id = rc->id; return __inet_diag_dump(skb, cb, &req); } static int inet_diag_get_exact_compat(struct sk_buff *in_skb, const struct nlmsghdr *nlh) { struct inet_diag_req *rc = nlmsg_data(nlh); struct inet_diag_req_v2 req; req.sdiag_family = rc->idiag_family; req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type); req.idiag_ext = rc->idiag_ext; req.pad = 0; req.idiag_states = rc->idiag_states; req.id = rc->id; return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, sizeof(struct inet_diag_req), &req); } static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) { int hdrlen = sizeof(struct inet_diag_req); struct net *net = sock_net(skb->sk); if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX || nlmsg_len(nlh) < hdrlen) return -EINVAL; if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = inet_diag_dump_start_compat, .done = inet_diag_dump_done, .dump = inet_diag_dump_compat, }; return netlink_dump_start(net->diag_nlsk, skb, nlh, &c); } return inet_diag_get_exact_compat(skb, nlh); } static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct inet_diag_req_v2); struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY && h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = inet_diag_dump_start, .done = inet_diag_dump_done, .dump = inet_diag_dump, }; return netlink_dump_start(net->diag_nlsk, skb, h, &c); } return inet_diag_cmd_exact(h->nlmsg_type, skb, h, hdrlen, nlmsg_data(h)); } static int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) { const struct inet_diag_handler *handler; struct nlmsghdr *nlh; struct nlattr *attr; struct inet_diag_msg *r; void *info = NULL; int err = 0; nlh = nlmsg_put(skb, 0, 0, SOCK_DIAG_BY_FAMILY, sizeof(*r), 0); if (!nlh) return -ENOMEM; r = nlmsg_data(nlh); memset(r, 0, sizeof(*r)); inet_diag_msg_common_fill(r, sk); if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_STREAM) r->id.idiag_sport = inet_sk(sk)->inet_sport; r->idiag_state = sk->sk_state; if ((err = nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))) { nlmsg_cancel(skb, nlh); return err; } handler = inet_diag_lock_handler(sk->sk_protocol); if (!handler) { nlmsg_cancel(skb, nlh); return -ENOENT; } attr = handler->idiag_info_size ? nla_reserve_64bit(skb, INET_DIAG_INFO, handler->idiag_info_size, INET_DIAG_PAD) : NULL; if (attr) info = nla_data(attr); handler->idiag_get_info(sk, r, info); inet_diag_unlock_handler(handler); nlmsg_end(skb, nlh); return 0; } static const struct sock_diag_handler inet_diag_handler = { .owner = THIS_MODULE, .family = AF_INET, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, .destroy = inet_diag_handler_cmd, }; static const struct sock_diag_handler inet6_diag_handler = { .owner = THIS_MODULE, .family = AF_INET6, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, .destroy = inet_diag_handler_cmd, }; int inet_diag_register(const struct inet_diag_handler *h) { const __u16 type = h->idiag_type; if (type >= IPPROTO_MAX) return -EINVAL; return !cmpxchg((const struct inet_diag_handler **)&inet_diag_table[type], NULL, h) ? 0 : -EEXIST; } EXPORT_SYMBOL_GPL(inet_diag_register); void inet_diag_unregister(const struct inet_diag_handler *h) { const __u16 type = h->idiag_type; if (type >= IPPROTO_MAX) return; xchg((const struct inet_diag_handler **)&inet_diag_table[type], NULL); } EXPORT_SYMBOL_GPL(inet_diag_unregister); static const struct sock_diag_inet_compat inet_diag_compat = { .owner = THIS_MODULE, .fn = inet_diag_rcv_msg_compat, }; static int __init inet_diag_init(void) { const int inet_diag_table_size = (IPPROTO_MAX * sizeof(struct inet_diag_handler *)); int err = -ENOMEM; inet_diag_table = kzalloc(inet_diag_table_size, GFP_KERNEL); if (!inet_diag_table) goto out; err = sock_diag_register(&inet_diag_handler); if (err) goto out_free_nl; err = sock_diag_register(&inet6_diag_handler); if (err) goto out_free_inet; sock_diag_register_inet_compat(&inet_diag_compat); out: return err; out_free_inet: sock_diag_unregister(&inet_diag_handler); out_free_nl: kfree(inet_diag_table); goto out; } static void __exit inet_diag_exit(void) { sock_diag_unregister(&inet6_diag_handler); sock_diag_unregister(&inet_diag_handler); sock_diag_unregister_inet_compat(&inet_diag_compat); kfree(inet_diag_table); } module_init(inet_diag_init); module_exit(inet_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("INET/INET6: socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */); |
| 509 509 124 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright(c) 2004-2005 Intel Corporation. All rights reserved. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/types.h> #include <linux/string.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/in.h> #include <linux/sysfs.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/rtnetlink.h> #include <linux/etherdevice.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/nsproxy.h> #include <net/bonding.h> #define to_bond(cd) ((struct bonding *)(netdev_priv(to_net_dev(cd)))) /* "show" function for the bond_masters attribute. * The class parameter is ignored. */ static ssize_t bonding_show_bonds(const struct class *cls, const struct class_attribute *attr, char *buf) { const struct bond_net *bn = container_of_const(attr, struct bond_net, class_attr_bonding_masters); struct bonding *bond; int res = 0; rcu_read_lock(); list_for_each_entry_rcu(bond, &bn->dev_list, bond_list) { if (res > (PAGE_SIZE - IFNAMSIZ)) { /* not enough space for another interface name */ if ((PAGE_SIZE - res) > 10) res = PAGE_SIZE - 10; res += sysfs_emit_at(buf, res, "++more++ "); break; } res += sysfs_emit_at(buf, res, "%s ", bond->dev->name); } if (res) buf[res-1] = '\n'; /* eat the leftover space */ rcu_read_unlock(); return res; } static struct net_device *bond_get_by_name(const struct bond_net *bn, const char *ifname) { struct bonding *bond; list_for_each_entry(bond, &bn->dev_list, bond_list) { if (strncmp(bond->dev->name, ifname, IFNAMSIZ) == 0) return bond->dev; } return NULL; } /* "store" function for the bond_masters attribute. This is what * creates and deletes entire bonds. * * The class parameter is ignored. */ static ssize_t bonding_store_bonds(const struct class *cls, const struct class_attribute *attr, const char *buffer, size_t count) { const struct bond_net *bn = container_of_const(attr, struct bond_net, class_attr_bonding_masters); char command[IFNAMSIZ + 1] = {0, }; char *ifname; int rv, res = count; sscanf(buffer, "%16s", command); /* IFNAMSIZ*/ ifname = command + 1; if ((strlen(command) <= 1) || !dev_valid_name(ifname)) goto err_no_cmd; if (command[0] == '+') { pr_info("%s is being created...\n", ifname); rv = bond_create(bn->net, ifname); if (rv) { if (rv == -EEXIST) pr_info("%s already exists\n", ifname); else pr_info("%s creation failed\n", ifname); res = rv; } } else if (command[0] == '-') { struct net_device *bond_dev; rtnl_lock(); bond_dev = bond_get_by_name(bn, ifname); if (bond_dev) { pr_info("%s is being deleted...\n", ifname); unregister_netdevice(bond_dev); } else { pr_err("unable to delete non-existent %s\n", ifname); res = -ENODEV; } rtnl_unlock(); } else goto err_no_cmd; /* Always return either count or an error. If you return 0, you'll * get called forever, which is bad. */ return res; err_no_cmd: pr_err("no command found in bonding_masters - use +ifname or -ifname\n"); return -EPERM; } /* class attribute for bond_masters file. This ends up in /sys/class/net */ static const struct class_attribute class_attr_bonding_masters = { .attr = { .name = "bonding_masters", .mode = 0644, }, .show = bonding_show_bonds, .store = bonding_store_bonds, }; /* Generic "store" method for bonding sysfs option setting */ static ssize_t bonding_sysfs_store_option(struct device *d, struct device_attribute *attr, const char *buffer, size_t count) { struct bonding *bond = to_bond(d); const struct bond_option *opt; char *buffer_clone; int ret; opt = bond_opt_get_by_name(attr->attr.name); if (WARN_ON(!opt)) return -ENOENT; buffer_clone = kstrndup(buffer, count, GFP_KERNEL); if (!buffer_clone) return -ENOMEM; ret = bond_opt_tryset_rtnl(bond, opt->id, buffer_clone); if (!ret) ret = count; kfree(buffer_clone); return ret; } /* Show the slaves in the current bond. */ static ssize_t bonding_show_slaves(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); struct list_head *iter; struct slave *slave; int res = 0; rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) { if (res > (PAGE_SIZE - IFNAMSIZ)) { /* not enough space for another interface name */ if ((PAGE_SIZE - res) > 10) res = PAGE_SIZE - 10; res += sysfs_emit_at(buf, res, "++more++ "); break; } res += sysfs_emit_at(buf, res, "%s ", slave->dev->name); } rcu_read_unlock(); if (res) buf[res-1] = '\n'; /* eat the leftover space */ return res; } static DEVICE_ATTR(slaves, 0644, bonding_show_slaves, bonding_sysfs_store_option); /* Show the bonding mode. */ static ssize_t bonding_show_mode(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_MODE, BOND_MODE(bond)); return sysfs_emit(buf, "%s %d\n", val->string, BOND_MODE(bond)); } static DEVICE_ATTR(mode, 0644, bonding_show_mode, bonding_sysfs_store_option); /* Show the bonding transmit hash method. */ static ssize_t bonding_show_xmit_hash(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_XMIT_HASH, bond->params.xmit_policy); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.xmit_policy); } static DEVICE_ATTR(xmit_hash_policy, 0644, bonding_show_xmit_hash, bonding_sysfs_store_option); /* Show arp_validate. */ static ssize_t bonding_show_arp_validate(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, bond->params.arp_validate); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.arp_validate); } static DEVICE_ATTR(arp_validate, 0644, bonding_show_arp_validate, bonding_sysfs_store_option); /* Show arp_all_targets. */ static ssize_t bonding_show_arp_all_targets(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_ARP_ALL_TARGETS, bond->params.arp_all_targets); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.arp_all_targets); } static DEVICE_ATTR(arp_all_targets, 0644, bonding_show_arp_all_targets, bonding_sysfs_store_option); /* Show fail_over_mac. */ static ssize_t bonding_show_fail_over_mac(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_FAIL_OVER_MAC, bond->params.fail_over_mac); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.fail_over_mac); } static DEVICE_ATTR(fail_over_mac, 0644, bonding_show_fail_over_mac, bonding_sysfs_store_option); /* Show the arp timer interval. */ static ssize_t bonding_show_arp_interval(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.arp_interval); } static DEVICE_ATTR(arp_interval, 0644, bonding_show_arp_interval, bonding_sysfs_store_option); /* Show the arp targets. */ static ssize_t bonding_show_arp_targets(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); int i, res = 0; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) { if (bond->params.arp_targets[i]) res += sysfs_emit_at(buf, res, "%pI4 ", &bond->params.arp_targets[i]); } if (res) buf[res-1] = '\n'; /* eat the leftover space */ return res; } static DEVICE_ATTR(arp_ip_target, 0644, bonding_show_arp_targets, bonding_sysfs_store_option); /* Show the arp missed max. */ static ssize_t bonding_show_missed_max(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%u\n", bond->params.missed_max); } static DEVICE_ATTR(arp_missed_max, 0644, bonding_show_missed_max, bonding_sysfs_store_option); /* Show the up and down delays. */ static ssize_t bonding_show_downdelay(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.downdelay * bond->params.miimon); } static DEVICE_ATTR(downdelay, 0644, bonding_show_downdelay, bonding_sysfs_store_option); static ssize_t bonding_show_updelay(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.updelay * bond->params.miimon); } static DEVICE_ATTR(updelay, 0644, bonding_show_updelay, bonding_sysfs_store_option); static ssize_t bonding_show_peer_notif_delay(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.peer_notif_delay * bond->params.miimon); } static DEVICE_ATTR(peer_notif_delay, 0644, bonding_show_peer_notif_delay, bonding_sysfs_store_option); /* Show the LACP activity and interval. */ static ssize_t bonding_show_lacp_active(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_LACP_ACTIVE, bond->params.lacp_active); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.lacp_active); } static DEVICE_ATTR(lacp_active, 0644, bonding_show_lacp_active, bonding_sysfs_store_option); static ssize_t bonding_show_lacp_rate(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_LACP_RATE, bond->params.lacp_fast); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.lacp_fast); } static DEVICE_ATTR(lacp_rate, 0644, bonding_show_lacp_rate, bonding_sysfs_store_option); static ssize_t bonding_show_min_links(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%u\n", bond->params.min_links); } static DEVICE_ATTR(min_links, 0644, bonding_show_min_links, bonding_sysfs_store_option); static ssize_t bonding_show_ad_select(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_AD_SELECT, bond->params.ad_select); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.ad_select); } static DEVICE_ATTR(ad_select, 0644, bonding_show_ad_select, bonding_sysfs_store_option); /* Show the number of peer notifications to send after a failover event. */ static ssize_t bonding_show_num_peer_notif(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.num_peer_notif); } static DEVICE_ATTR(num_grat_arp, 0644, bonding_show_num_peer_notif, bonding_sysfs_store_option); static DEVICE_ATTR(num_unsol_na, 0644, bonding_show_num_peer_notif, bonding_sysfs_store_option); /* Show the MII monitor interval. */ static ssize_t bonding_show_miimon(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.miimon); } static DEVICE_ATTR(miimon, 0644, bonding_show_miimon, bonding_sysfs_store_option); /* Show the primary slave. */ static ssize_t bonding_show_primary(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); struct slave *primary; int count = 0; rcu_read_lock(); primary = rcu_dereference(bond->primary_slave); if (primary) count = sysfs_emit(buf, "%s\n", primary->dev->name); rcu_read_unlock(); return count; } static DEVICE_ATTR(primary, 0644, bonding_show_primary, bonding_sysfs_store_option); /* Show the primary_reselect flag. */ static ssize_t bonding_show_primary_reselect(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_PRIMARY_RESELECT, bond->params.primary_reselect); return sysfs_emit(buf, "%s %d\n", val->string, bond->params.primary_reselect); } static DEVICE_ATTR(primary_reselect, 0644, bonding_show_primary_reselect, bonding_sysfs_store_option); /* Show the use_carrier flag. */ static ssize_t bonding_show_carrier(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.use_carrier); } static DEVICE_ATTR(use_carrier, 0644, bonding_show_carrier, bonding_sysfs_store_option); /* Show currently active_slave. */ static ssize_t bonding_show_active_slave(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); struct net_device *slave_dev; int count = 0; rcu_read_lock(); slave_dev = bond_option_active_slave_get_rcu(bond); if (slave_dev) count = sysfs_emit(buf, "%s\n", slave_dev->name); rcu_read_unlock(); return count; } static DEVICE_ATTR(active_slave, 0644, bonding_show_active_slave, bonding_sysfs_store_option); /* Show link status of the bond interface. */ static ssize_t bonding_show_mii_status(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); bool active = netif_carrier_ok(bond->dev); return sysfs_emit(buf, "%s\n", active ? "up" : "down"); } static DEVICE_ATTR(mii_status, 0444, bonding_show_mii_status, NULL); /* Show current 802.3ad aggregator ID. */ static ssize_t bonding_show_ad_aggregator(struct device *d, struct device_attribute *attr, char *buf) { int count = 0; struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info ad_info; count = sysfs_emit(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.aggregator_id); } return count; } static DEVICE_ATTR(ad_aggregator, 0444, bonding_show_ad_aggregator, NULL); /* Show number of active 802.3ad ports. */ static ssize_t bonding_show_ad_num_ports(struct device *d, struct device_attribute *attr, char *buf) { int count = 0; struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info ad_info; count = sysfs_emit(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.ports); } return count; } static DEVICE_ATTR(ad_num_ports, 0444, bonding_show_ad_num_ports, NULL); /* Show current 802.3ad actor key. */ static ssize_t bonding_show_ad_actor_key(struct device *d, struct device_attribute *attr, char *buf) { int count = 0; struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) { struct ad_info ad_info; count = sysfs_emit(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.actor_key); } return count; } static DEVICE_ATTR(ad_actor_key, 0444, bonding_show_ad_actor_key, NULL); /* Show current 802.3ad partner key. */ static ssize_t bonding_show_ad_partner_key(struct device *d, struct device_attribute *attr, char *buf) { int count = 0; struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) { struct ad_info ad_info; count = sysfs_emit(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.partner_key); } return count; } static DEVICE_ATTR(ad_partner_key, 0444, bonding_show_ad_partner_key, NULL); /* Show current 802.3ad partner mac. */ static ssize_t bonding_show_ad_partner_mac(struct device *d, struct device_attribute *attr, char *buf) { int count = 0; struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) { struct ad_info ad_info; if (!bond_3ad_get_active_agg_info(bond, &ad_info)) count = sysfs_emit(buf, "%pM\n", ad_info.partner_system); } return count; } static DEVICE_ATTR(ad_partner_mac, 0444, bonding_show_ad_partner_mac, NULL); /* Show the queue_ids of the slaves in the current bond. */ static ssize_t bonding_show_queue_id(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); struct list_head *iter; struct slave *slave; int res = 0; rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) { if (res > (PAGE_SIZE - IFNAMSIZ - 6)) { /* not enough space for another interface_name:queue_id pair */ if ((PAGE_SIZE - res) > 10) res = PAGE_SIZE - 10; res += sysfs_emit_at(buf, res, "++more++ "); break; } res += sysfs_emit_at(buf, res, "%s:%d ", slave->dev->name, READ_ONCE(slave->queue_id)); } if (res) buf[res-1] = '\n'; /* eat the leftover space */ rcu_read_unlock(); return res; } static DEVICE_ATTR(queue_id, 0644, bonding_show_queue_id, bonding_sysfs_store_option); /* Show the all_slaves_active flag. */ static ssize_t bonding_show_slaves_active(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.all_slaves_active); } static DEVICE_ATTR(all_slaves_active, 0644, bonding_show_slaves_active, bonding_sysfs_store_option); /* Show the number of IGMP membership reports to send on link failure */ static ssize_t bonding_show_resend_igmp(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.resend_igmp); } static DEVICE_ATTR(resend_igmp, 0644, bonding_show_resend_igmp, bonding_sysfs_store_option); static ssize_t bonding_show_lp_interval(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.lp_interval); } static DEVICE_ATTR(lp_interval, 0644, bonding_show_lp_interval, bonding_sysfs_store_option); static ssize_t bonding_show_tlb_dynamic_lb(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); return sysfs_emit(buf, "%d\n", bond->params.tlb_dynamic_lb); } static DEVICE_ATTR(tlb_dynamic_lb, 0644, bonding_show_tlb_dynamic_lb, bonding_sysfs_store_option); static ssize_t bonding_show_packets_per_slave(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); unsigned int packets_per_slave = bond->params.packets_per_slave; return sysfs_emit(buf, "%u\n", packets_per_slave); } static DEVICE_ATTR(packets_per_slave, 0644, bonding_show_packets_per_slave, bonding_sysfs_store_option); static ssize_t bonding_show_ad_actor_sys_prio(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) return sysfs_emit(buf, "%hu\n", bond->params.ad_actor_sys_prio); return 0; } static DEVICE_ATTR(ad_actor_sys_prio, 0644, bonding_show_ad_actor_sys_prio, bonding_sysfs_store_option); static ssize_t bonding_show_ad_actor_system(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) return sysfs_emit(buf, "%pM\n", bond->params.ad_actor_system); return 0; } static DEVICE_ATTR(ad_actor_system, 0644, bonding_show_ad_actor_system, bonding_sysfs_store_option); static ssize_t bonding_show_ad_user_port_key(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) return sysfs_emit(buf, "%hu\n", bond->params.ad_user_port_key); return 0; } static DEVICE_ATTR(ad_user_port_key, 0644, bonding_show_ad_user_port_key, bonding_sysfs_store_option); static struct attribute *per_bond_attrs[] = { &dev_attr_slaves.attr, &dev_attr_mode.attr, &dev_attr_fail_over_mac.attr, &dev_attr_arp_validate.attr, &dev_attr_arp_all_targets.attr, &dev_attr_arp_interval.attr, &dev_attr_arp_ip_target.attr, &dev_attr_downdelay.attr, &dev_attr_updelay.attr, &dev_attr_peer_notif_delay.attr, &dev_attr_lacp_active.attr, &dev_attr_lacp_rate.attr, &dev_attr_ad_select.attr, &dev_attr_xmit_hash_policy.attr, &dev_attr_num_grat_arp.attr, &dev_attr_num_unsol_na.attr, &dev_attr_miimon.attr, &dev_attr_primary.attr, &dev_attr_primary_reselect.attr, &dev_attr_use_carrier.attr, &dev_attr_active_slave.attr, &dev_attr_mii_status.attr, &dev_attr_ad_aggregator.attr, &dev_attr_ad_num_ports.attr, &dev_attr_ad_actor_key.attr, &dev_attr_ad_partner_key.attr, &dev_attr_ad_partner_mac.attr, &dev_attr_queue_id.attr, &dev_attr_all_slaves_active.attr, &dev_attr_resend_igmp.attr, &dev_attr_min_links.attr, &dev_attr_lp_interval.attr, &dev_attr_packets_per_slave.attr, &dev_attr_tlb_dynamic_lb.attr, &dev_attr_ad_actor_sys_prio.attr, &dev_attr_ad_actor_system.attr, &dev_attr_ad_user_port_key.attr, &dev_attr_arp_missed_max.attr, NULL, }; static const struct attribute_group bonding_group = { .name = "bonding", .attrs = per_bond_attrs, }; /* Initialize sysfs. This sets up the bonding_masters file in * /sys/class/net. */ int __net_init bond_create_sysfs(struct bond_net *bn) { int ret; bn->class_attr_bonding_masters = class_attr_bonding_masters; sysfs_attr_init(&bn->class_attr_bonding_masters.attr); ret = netdev_class_create_file_ns(&bn->class_attr_bonding_masters, bn->net); /* Permit multiple loads of the module by ignoring failures to * create the bonding_masters sysfs file. Bonding devices * created by second or subsequent loads of the module will * not be listed in, or controllable by, bonding_masters, but * will have the usual "bonding" sysfs directory. * * This is done to preserve backwards compatibility for * initscripts/sysconfig, which load bonding multiple times to * configure multiple bonding devices. */ if (ret == -EEXIST) { /* Is someone being kinky and naming a device bonding_master? */ if (netdev_name_in_use(bn->net, class_attr_bonding_masters.attr.name)) pr_err("network device named %s already exists in sysfs\n", class_attr_bonding_masters.attr.name); ret = 0; } return ret; } /* Remove /sys/class/net/bonding_masters. */ void __net_exit bond_destroy_sysfs(struct bond_net *bn) { netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net); } /* Initialize sysfs for each bond. This sets up and registers * the 'bondctl' directory for each individual bond under /sys/class/net. */ void bond_prepare_sysfs_group(struct bonding *bond) { bond->dev->sysfs_groups[0] = &bonding_group; } |
| 72 72 351 351 351 343 4 14 351 351 4 348 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Support for INET6 connection oriented protocols. * * Authors: See the TCPv6 sources */ #include <linux/module.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/jhash.h> #include <linux/slab.h> #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_ecn.h> #include <net/inet_hashtables.h> #include <net/ip6_route.h> #include <net/sock.h> #include <net/inet6_connection_sock.h> #include <net/sock_reuseport.h> struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req, u8 proto) { struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = proto; fl6->daddr = ireq->ir_v6_rmt_addr; rcu_read_lock(); final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); fl6->saddr = ireq->ir_v6_loc_addr; fl6->flowi6_oif = ireq->ir_iif; fl6->flowi6_mark = ireq->ir_mark; fl6->fl6_dport = ireq->ir_rmt_port; fl6->fl6_sport = htons(ireq->ir_num); fl6->flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi_common(fl6)); dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(dst)) return NULL; return dst; } static inline struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) { return __sk_dst_check(sk, cookie); } static struct dst_entry *inet6_csk_route_socket(struct sock *sk, struct flowi6 *fl6) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = sk->sk_protocol; fl6->daddr = sk->sk_v6_daddr; fl6->saddr = np->saddr; fl6->flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl6->flowlabel); fl6->flowi6_oif = sk->sk_bound_dev_if; fl6->flowi6_mark = sk->sk_mark; fl6->fl6_sport = inet->inet_sport; fl6->fl6_dport = inet->inet_dport; fl6->flowi6_uid = sk->sk_uid; security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); rcu_read_lock(); final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!IS_ERR(dst)) ip6_dst_store(sk, dst, NULL, NULL); } return dst; } int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused) { struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 fl6; struct dst_entry *dst; int res; dst = inet6_csk_route_socket(sk, &fl6); if (IS_ERR(dst)) { WRITE_ONCE(sk->sk_err_soft, -PTR_ERR(dst)); sk->sk_route_caps = 0; kfree_skb(skb); return PTR_ERR(dst); } rcu_read_lock(); skb_dst_set_noref(skb, dst); /* Restore final destination back after routing done */ fl6.daddr = sk->sk_v6_daddr; res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt), np->tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(inet6_csk_xmit); struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) { struct flowi6 fl6; struct dst_entry *dst = inet6_csk_route_socket(sk, &fl6); if (IS_ERR(dst)) return NULL; dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = inet6_csk_route_socket(sk, &fl6); return IS_ERR(dst) ? NULL : dst; } |
| 9 9 64 301 28 1 1 11 147 13 763 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET Generic infrastructure for INET connection oriented protocols. * * Definitions for inet_connection_sock * * Authors: Many people, see the TCP sources * * From code originally in TCP */ #ifndef _INET_CONNECTION_SOCK_H #define _INET_CONNECTION_SOCK_H #include <linux/compiler.h> #include <linux/string.h> #include <linux/timer.h> #include <linux/poll.h> #include <linux/kernel.h> #include <linux/sockptr.h> #include <net/inet_sock.h> #include <net/request_sock.h> /* Cancel timers, when they are not required. */ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; struct inet_bind2_bucket; struct tcp_congestion_ops; /* * Pointers to address related TCP functions * (i.e. things that depend on the address family) */ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl); void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req); u16 net_header_len; int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); void (*mtu_reduced)(struct sock *sk); }; /** inet_connection_sock - INET connection oriented sock * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout * @icsk_pmtu_cookie Last pmtu seen by socket * @icsk_ca_ops Pluggable congestion control hook * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event * @icsk_backoff: Backoff * @icsk_syn_retries: Number of allowed SYN (or equivalent) retries * @icsk_probes_out: unanswered 0 window probes * @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options) * @icsk_ack: Delayed ACK control data * @icsk_mtup; MTU probing control data * @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack) * @icsk_user_timeout: TCP_USER_TIMEOUT value */ struct inet_connection_sock { /* inet_sock has to be the first member! */ struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; struct inet_bind2_bucket *icsk_bind2_hash; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; __u32 icsk_rto_min; u32 icsk_rto_max; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; __u8 icsk_pending; __u8 icsk_backoff; __u8 icsk_syn_retries; __u8 icsk_probes_out; __u16 icsk_ext_hdr_len; struct { __u8 pending; /* ACK is pending */ __u8 quick; /* Scheduled number of quick acks */ __u8 pingpong; /* The session is interactive */ __u8 retry; /* Number of attempts */ #define ATO_BITS 8 __u32 ato:ATO_BITS, /* Predicted tick of soft clock */ lrcv_flowlabel:20, /* last received ipv6 flowlabel */ dst_quick_ack:1, /* cache dst RTAX_QUICKACK */ unused:3; __u32 lrcvtime; /* timestamp of last received data packet */ __u16 last_seg_size; /* Size of last incoming segment */ __u16 rcv_mss; /* MSS used for delayed ACK decisions */ } icsk_ack; struct { /* Range of MTUs to search */ int search_high; int search_low; /* Information on the current probe. */ u32 probe_size:31, /* Is the MTUP feature enabled for this connection? */ enabled:1; u32 probe_timestamp; } icsk_mtup; u32 icsk_probes_tstamp; u32 icsk_user_timeout; u64 icsk_ca_priv[104 / sizeof(u64)]; #define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ #define ICSK_TIME_DACK 2 /* Delayed ack timer */ #define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ #define inet_csk(ptr) container_of_const(ptr, struct inet_connection_sock, icsk_inet.sk) static inline void *inet_csk_ca(const struct sock *sk) { return (void *)inet_csk(sk)->icsk_ca_priv; } struct sock *inet_csk_clone_lock(const struct sock *sk, const struct request_sock *req, const gfp_t priority); enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, ICSK_ACK_PUSHED2 = 8, ICSK_ACK_NOW = 16, /* Send the next ACK immediately (once) */ ICSK_ACK_NOMEM = 32, }; void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *), void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED; } static inline int inet_csk_ack_scheduled(const struct sock *sk) { return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED; } static inline void inet_csk_delack_init(struct sock *sk) { memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack)); } static inline unsigned long icsk_timeout(const struct inet_connection_sock *icsk) { return READ_ONCE(icsk->icsk_retransmit_timer.expires); } static inline unsigned long icsk_delack_timeout(const struct inet_connection_sock *icsk) { return READ_ONCE(icsk->icsk_delack_timer.expires); } static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) { struct inet_connection_sock *icsk = inet_csk(sk); if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { smp_store_release(&icsk->icsk_pending, 0); #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, 0); icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } /* * Reset the retransmission timer */ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { struct inet_connection_sock *icsk = inet_csk(sk); if (when > max_when) { pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, (void *)_THIS_IP_); when = max_when; } when += jiffies; if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { smp_store_release(&icsk->icsk_pending, what); sk_reset_timer(sk, &icsk->icsk_retransmit_timer, when); } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_TIMER); sk_reset_timer(sk, &icsk->icsk_delack_timer, when); } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } static inline unsigned long inet_csk_rto_backoff(const struct inet_connection_sock *icsk, unsigned long max_when) { u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff; return (unsigned long)min_t(u64, when, max_when); } struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg); int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req); static inline void inet_csk_reqsk_queue_added(struct sock *sk) { reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_len(const struct sock *sk) { return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); static inline unsigned long reqsk_timeout(struct request_sock *req, unsigned long max_timeout) { u64 timeout = (u64)req->timeout << req->num_timeout; return (unsigned long)min_t(u64, timeout, max_timeout); } static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ sock_set_flag(sk, SOCK_DEAD); this_cpu_inc(*sk->sk_prot->orphan_count); } void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); /* * LISTEN is a special case for poll.. */ static inline __poll_t inet_csk_listen_poll(const struct sock *sk) { return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ? (EPOLLIN | EPOLLRDNORM) : 0; } int inet_csk_listen_start(struct sock *sk); void inet_csk_listen_stop(struct sock *sk); /* update the fast reuse flag when adding a socket */ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk); struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); static inline void inet_csk_enter_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh); } static inline void inet_csk_exit_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = 0; } static inline bool inet_csk_in_pingpong_mode(struct sock *sk) { return inet_csk(sk)->icsk_ack.pingpong >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh); } static inline void inet_csk_inc_pingpong_cnt(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.pingpong < U8_MAX) icsk->icsk_ack.pingpong++; } static inline bool inet_csk_has_ulp(const struct sock *sk) { return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops; } static inline void inet_init_csk_locks(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); } #endif /* _INET_CONNECTION_SOCK_H */ |
| 4 3 18 1 39 7 61 109 58 4 7 4 1 3 71 7 18 6 18 6 6 26 5 23 106 31 2 188 1 189 188 188 8 8 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _NET_GRO_H #define _NET_GRO_H #include <linux/indirect_call_wrapper.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h> #include <linux/skbuff.h> #include <net/udp.h> #include <net/hotdata.h> /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) struct napi_gro_cb { union { struct { /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ void *frag0; /* Length of frag0. */ unsigned int frag0_len; }; struct { /* used in skb_gro_receive() slow path */ struct sk_buff *last; /* jiffies when first packet was created/queued */ unsigned long age; }; }; /* This indicates where we are processing relative to skb->data. */ int data_offset; /* This is non-zero if the packet cannot be merged with the new skb. */ u16 flush; /* Number of segments aggregated. */ u16 count; /* Used in ipv6_gro_receive() and foo-over-udp and esp-in-udp */ u16 proto; u16 pad; /* Used in napi_gro_cb::free */ #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 /* portion of the cb set to zero at every gro iteration */ struct_group(zeroed, /* Start offset for remote checksum offload */ u16 gro_remcsum_start; /* This is non-zero if the packet may be of the same flow. */ u8 same_flow:1; /* Used in tunnel GRO receive */ u8 encap_mark:1; /* GRO checksum is valid */ u8 csum_valid:1; /* Number of checksums via CHECKSUM_UNNECESSARY */ u8 csum_cnt:3; /* Free the skb? */ u8 free:2; /* Used in foo-over-udp, set in udp[46]_gro_receive */ u8 is_ipv6:1; /* Used in GRE, set in fou/gue_gro_receive */ u8 is_fou:1; /* Used to determine if ipid_offset can be ignored */ u8 ip_fixedid:1; /* Number of gro_receive callbacks this packet already went through */ u8 recursion_counter:4; /* GRO is done by frag_list pointer chaining. */ u8 is_flist:1; ); /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; /* L3 offsets */ union { struct { u16 network_offset; u16 inner_network_offset; }; u16 network_offsets[2]; }; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) #define GRO_RECURSION_LIMIT 15 static inline int gro_recursion_inc_test(struct sk_buff *skb) { return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; } typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); static inline struct sk_buff *call_gro_receive(gro_receive_t cb, struct list_head *head, struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; return NULL; } return cb(head, skb); } typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, struct sk_buff *); static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, struct sock *sk, struct list_head *head, struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; return NULL; } return cb(sk, head, skb); } static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { return NAPI_GRO_CB(skb)->data_offset; } static inline unsigned int skb_gro_len(const struct sk_buff *skb) { return skb->len - NAPI_GRO_CB(skb)->data_offset; } static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) { NAPI_GRO_CB(skb)->data_offset += len; } static inline void *skb_gro_header_fast(const struct sk_buff *skb, unsigned int offset) { return NAPI_GRO_CB(skb)->frag0 + offset; } static inline bool skb_gro_may_pull(const struct sk_buff *skb, unsigned int hlen) { return likely(hlen <= NAPI_GRO_CB(skb)->frag0_len); } static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { if (!pskb_may_pull(skb, hlen)) return NULL; return skb->data + offset; } static inline void *skb_gro_header(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { void *ptr; ptr = skb_gro_header_fast(skb, offset); if (!skb_gro_may_pull(skb, hlen)) ptr = skb_gro_header_slow(skb, hlen, offset); return ptr; } static inline int skb_gro_receive_network_offset(const struct sk_buff *skb) { return NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark]; } static inline void *skb_gro_network_header(const struct sk_buff *skb) { if (skb_gro_may_pull(skb, skb_gro_offset(skb))) return skb_gro_header_fast(skb, skb_gro_receive_network_offset(skb)); return skb->data + skb_gro_receive_network_offset(skb); } static inline __wsum inet_gro_compute_pseudo(const struct sk_buff *skb, int proto) { const struct iphdr *iph = skb_gro_network_header(skb); return csum_tcpudp_nofold(iph->saddr, iph->daddr, skb_gro_len(skb), proto, 0); } static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (NAPI_GRO_CB(skb)->csum_valid) NAPI_GRO_CB(skb)->csum = wsum_negate(csum_partial(start, len, wsum_negate(NAPI_GRO_CB(skb)->csum))); } /* GRO checksum functions. These are logical equivalents of the normal * checksum functions (in skbuff.h) except that they operate on the GRO * offsets and fields in sk_buff. */ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb); static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); } static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { return ((skb->ip_summed != CHECKSUM_PARTIAL || skb_checksum_start_offset(skb) < skb_gro_offset(skb)) && !skb_at_gro_remcsum_start(skb) && NAPI_GRO_CB(skb)->csum_cnt == 0 && (!zero_okay || check)); } static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, __wsum psum) { if (NAPI_GRO_CB(skb)->csum_valid && !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) return 0; NAPI_GRO_CB(skb)->csum = psum; return __skb_gro_checksum_complete(skb); } static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->csum_cnt > 0) { /* Consume a checksum from CHECKSUM_UNNECESSARY */ NAPI_GRO_CB(skb)->csum_cnt--; } else { /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we * verified a new top level checksum or an encapsulated one * during GRO. This saves work if we fallback to normal path. */ __skb_incr_checksum_unnecessary(skb); } } #define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ compute_pseudo) \ ({ \ __sum16 __ret = 0; \ if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_gro_checksum_validate_complete(skb, \ compute_pseudo(skb, proto)); \ if (!__ret) \ skb_gro_incr_csum_unnecessary(skb); \ __ret; \ }) #define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) #define skb_gro_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) #define skb_gro_checksum_simple_validate(skb) \ __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid); } static inline void __skb_gro_checksum_convert(struct sk_buff *skb, __wsum pseudo) { NAPI_GRO_CB(skb)->csum = ~pseudo; NAPI_GRO_CB(skb)->csum_valid = 1; } #define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_gro_checksum_convert_check(skb)) \ __skb_gro_checksum_convert(skb, \ compute_pseudo(skb, proto)); \ } while (0) struct gro_remcsum { int offset; __wsum delta; }; static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) { grc->offset = 0; grc->delta = 0; } static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, unsigned int off, size_t hdrlen, int start, int offset, struct gro_remcsum *grc, bool nopartial) { __wsum delta; size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); if (!nopartial) { NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; return ptr; } ptr = skb_gro_header(skb, off + plen, off); if (!ptr) return NULL; delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, start, offset); /* Adjust skb->csum since we changed the packet */ NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); grc->offset = off + hdrlen + offset; grc->delta = delta; return ptr; } static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, struct gro_remcsum *grc) { void *ptr; size_t plen = grc->offset + sizeof(u16); if (!grc->delta) return; ptr = skb_gro_header(skb, plen, grc->offset); if (!ptr) return; remcsum_unadjust((__sum16 *)ptr, grc->delta); } #ifdef CONFIG_XFRM_OFFLOAD static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, struct sk_buff *pp, int flush, struct gro_remcsum *grc) { if (PTR_ERR(pp) != -EINPROGRESS) { NAPI_GRO_CB(skb)->flush |= flush; skb_gro_remcsum_cleanup(skb, grc); skb->remcsum_offload = 0; } } #else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, struct sk_buff *pp, int flush, struct gro_remcsum *grc) { NAPI_GRO_CB(skb)->flush |= flush; skb_gro_remcsum_cleanup(skb, grc); skb->remcsum_offload = 0; } #endif INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); #define indirect_call_gro_receive_inet(cb, f2, f1, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ NAPI_GRO_CB(skb)->flush |= 1, NULL : \ INDIRECT_CALL_INET(cb, f2, f1, head, skb); \ }) struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) { struct udphdr *uh; unsigned int hlen, off; off = skb_gro_offset(skb); hlen = off + sizeof(*uh); uh = skb_gro_header(skb, hlen, off); return uh; } static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb, int proto) { const struct ipv6hdr *iph = skb_gro_network_header(skb); return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, skb_gro_len(skb), proto, 0)); } static inline int inet_gro_flush(const struct iphdr *iph, const struct iphdr *iph2, struct sk_buff *p, bool outer) { const u32 id = ntohl(*(__be32 *)&iph->id); const u32 id2 = ntohl(*(__be32 *)&iph2->id); const u16 ipid_offset = (id >> 16) - (id2 >> 16); const u16 count = NAPI_GRO_CB(p)->count; const u32 df = id & IP_DF; int flush; /* All fields must match except length and checksum. */ flush = (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | (df ^ (id2 & IP_DF)); if (flush | (outer && df)) return flush; /* When we receive our second frame we can make a decision on if we * continue this flow as an atomic flow with a fixed ID or if we use * an incrementing ID. */ if (count == 1 && df && !ipid_offset) NAPI_GRO_CB(p)->ip_fixedid = true; return ipid_offset ^ (count * !NAPI_GRO_CB(p)->ip_fixedid); } static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr *iph2) { /* <Version:4><Traffic_Class:8><Flow_Label:20> */ __be32 first_word = *(__be32 *)iph ^ *(__be32 *)iph2; /* Flush if Traffic Class fields are different. */ return !!((first_word & htonl(0x0FF00000)) | (__force __be32)(iph->hop_limit ^ iph2->hop_limit)); } static inline int __gro_receive_network_flush(const void *th, const void *th2, struct sk_buff *p, const u16 diff, bool outer) { const void *nh = th - diff; const void *nh2 = th2 - diff; if (((struct iphdr *)nh)->version == 6) return ipv6_gro_flush(nh, nh2); else return inet_gro_flush(nh, nh2, p, outer); } static inline int gro_receive_network_flush(const void *th, const void *th2, struct sk_buff *p) { const bool encap_mark = NAPI_GRO_CB(p)->encap_mark; int off = skb_transport_offset(p); int flush; flush = __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->network_offset, encap_mark); if (encap_mark) flush |= __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->inner_network_offset, false); return flush; } int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); void __gro_flush(struct gro_node *gro, bool flush_old); static inline void gro_flush(struct gro_node *gro, bool flush_old) { if (!gro->bitmask) return; __gro_flush(gro, flush_old); } static inline void napi_gro_flush(struct napi_struct *napi, bool flush_old) { gro_flush(&napi->gro, flush_old); } /* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ static inline void gro_normal_list(struct gro_node *gro) { if (!gro->rx_count) return; netif_receive_skb_list_internal(&gro->rx_list); INIT_LIST_HEAD(&gro->rx_list); gro->rx_count = 0; } /* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, * pass the whole batch up to the stack. */ static inline void gro_normal_one(struct gro_node *gro, struct sk_buff *skb, int segs) { list_add_tail(&skb->list, &gro->rx_list); gro->rx_count += segs; if (gro->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch)) gro_normal_list(gro); } void gro_init(struct gro_node *gro); void gro_cleanup(struct gro_node *gro); /* This function is the alternative of 'inet_iif' and 'inet_sdif' * functions in case we can not rely on fields of IPCB. * * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized. * The caller must hold the RCU read lock. */ static inline void inet_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif) { *iif = inet_iif(skb) ?: skb->dev->ifindex; *sdif = 0; #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (netif_is_l3_slave(skb->dev)) { struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev); *sdif = *iif; *iif = master ? master->ifindex : 0; } #endif } /* This function is the alternative of 'inet6_iif' and 'inet6_sdif' * functions in case we can not rely on fields of IP6CB. * * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized. * The caller must hold the RCU read lock. */ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif) { /* using skb->dev->ifindex because skb_dst(skb) is not initialized */ *iif = skb->dev->ifindex; *sdif = 0; #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (netif_is_l3_slave(skb->dev)) { struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev); *sdif = *iif; *iif = master ? master->ifindex : 0; } #endif } struct packet_offload *gro_find_receive_by_type(__be16 type); struct packet_offload *gro_find_complete_by_type(__be16 type); #endif /* _NET_GRO_H */ |
| 358 264 361 203 595 205 94 94 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * pm_runtime.h - Device run-time power management helper functions. * * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl> */ #ifndef _LINUX_PM_RUNTIME_H #define _LINUX_PM_RUNTIME_H #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm.h> #include <linux/jiffies.h> /* Runtime PM flag argument bits */ #define RPM_ASYNC 0x01 /* Request is asynchronous */ #define RPM_NOWAIT 0x02 /* Don't wait for concurrent state change */ #define RPM_GET_PUT 0x04 /* Increment/decrement the usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ /* * Use this for defining a set of PM operations to be used in all situations * (system suspend, hibernation or runtime PM). * * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() * macro, which uses the provided callbacks for both runtime PM and system * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() * and pm_runtime_force_resume() for its system sleep callbacks. * * If the underlying dev_pm_ops struct symbol has to be exported, use * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. */ #define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ pm_runtime_force_resume, suspend_fn, \ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_GPL_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; static inline bool queue_pm_work(struct work_struct *work) { return queue_work(pm_wq, work); } extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); extern bool pm_runtime_need_not_resume(struct device *dev); extern int pm_runtime_force_suspend(struct device *dev); extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); extern int pm_runtime_get_if_active(struct device *dev); extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); extern bool pm_runtime_block_if_disabled(struct device *dev); extern void pm_runtime_unblock(struct device *dev); extern void pm_runtime_enable(struct device *dev); extern void __pm_runtime_disable(struct device *dev, bool check_resume); extern void pm_runtime_allow(struct device *dev); extern void pm_runtime_forbid(struct device *dev); extern void pm_runtime_no_callbacks(struct device *dev); extern void pm_runtime_irq_safe(struct device *dev); extern void __pm_runtime_use_autosuspend(struct device *dev, bool use); extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); extern void pm_runtime_release_supplier(struct device_link *link); int devm_pm_runtime_set_active_enabled(struct device *dev); extern int devm_pm_runtime_enable(struct device *dev); int devm_pm_runtime_get_noresume(struct device *dev); /** * pm_suspend_ignore_children - Set runtime PM behavior regarding children. * @dev: Target device. * @enable: Whether or not to ignore possible dependencies on children. * * The dependencies of @dev on its children will not be taken into account by * the runtime PM framework going forward if @enable is %true, or they will * be taken into account otherwise. */ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { dev->power.ignore_children = enable; } /** * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device. * @dev: Target device. */ static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); } /** * pm_runtime_put_noidle - Drop runtime PM usage counter of a device. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev unless it is 0 already. */ static inline void pm_runtime_put_noidle(struct device *dev) { atomic_add_unless(&dev->power.usage_count, -1, 0); } /** * pm_runtime_suspended - Check whether or not a device is runtime-suspended. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev and its runtime PM status is * %RPM_SUSPENDED, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED && !dev->power.disable_depth; } /** * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_active(struct device *dev) { return dev->power.runtime_status == RPM_ACTIVE || dev->power.disable_depth; } /** * pm_runtime_status_suspended - Check if runtime PM status is "suspended". * @dev: Target device. * * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false * otherwise, regardless of whether or not runtime PM has been enabled for @dev. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which the * runtime PM status of @dev cannot change. */ static inline bool pm_runtime_status_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED; } /** * pm_runtime_enabled - Check if runtime PM is enabled. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev. */ static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; } /** * pm_runtime_blocked - Check if runtime PM enabling is blocked. * @dev: Target device. * * Do not call this function outside system suspend/resume code paths. */ static inline bool pm_runtime_blocked(struct device *dev) { return dev->power.last_status == RPM_BLOCKED; } /** * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. * @dev: Target device. * * Return %true if @dev is a special device without runtime PM callbacks or * %false otherwise. */ static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return dev->power.no_callbacks; } /** * pm_runtime_mark_last_busy - Update the last access time of a device. * @dev: Target device. * * Update the last access time of @dev used by the runtime PM autosuspend * mechanism to the current time as returned by ktime_get_mono_fast_ns(). */ static inline void pm_runtime_mark_last_busy(struct device *dev) { WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } /** * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context. * @dev: Target device. * * Return %true if @dev has been marked as an "IRQ-safe" device (with respect * to runtime PM), in which case its runtime PM callabcks can be expected to * work correctly when invoked from interrupt handlers. */ static inline bool pm_runtime_is_irq_safe(struct device *dev) { return dev->power.irq_safe; } extern u64 pm_runtime_suspended_time(struct device *dev); #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } static inline bool pm_runtime_need_not_resume(struct device *dev) {return true; } static inline int pm_runtime_force_suspend(struct device *dev) { return 0; } static inline int pm_runtime_force_resume(struct device *dev) { return 0; } static inline int __pm_runtime_idle(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_suspend(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_resume(struct device *dev, int rpmflags) { return 1; } static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) { return -ENOSYS; } static inline int pm_runtime_get_if_in_use(struct device *dev) { return -EINVAL; } static inline int pm_runtime_get_if_active(struct device *dev) { return -EINVAL; } static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } static inline bool pm_runtime_block_if_disabled(struct device *dev) { return true; } static inline void pm_runtime_unblock(struct device *dev) {} static inline void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline bool pm_runtime_blocked(struct device *dev) { return true; } static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline int devm_pm_runtime_set_active_enabled(struct device *dev) { return 0; } static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } static inline int devm_pm_runtime_get_noresume(struct device *dev) { return 0; } static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} static inline void pm_runtime_irq_safe(struct device *dev) {} static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; } static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return false; } static inline void pm_runtime_mark_last_busy(struct device *dev) {} static inline void __pm_runtime_use_autosuspend(struct device *dev, bool use) {} static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ /** * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it. * @dev: Target device. * * Invoke the "idle check" callback of @dev and, depending on its return value, * set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend has been enabled for it). */ static inline int pm_runtime_idle(struct device *dev) { return __pm_runtime_idle(dev, 0); } /** * pm_runtime_suspend - Suspend a device synchronously. * @dev: Target device. */ static inline int pm_runtime_suspend(struct device *dev) { return __pm_runtime_suspend(dev, 0); } /** * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it. * @dev: Target device. * * Set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend is enabled for it) without engaging its "idle check" callback. */ static inline int pm_runtime_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_AUTO); } /** * pm_runtime_resume - Resume a device synchronously. * @dev: Target device. */ static inline int pm_runtime_resume(struct device *dev) { return __pm_runtime_resume(dev, 0); } /** * pm_request_idle - Queue up "idle check" execution for a device. * @dev: Target device. * * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev * asynchronously. */ static inline int pm_request_idle(struct device *dev) { return __pm_runtime_idle(dev, RPM_ASYNC); } /** * pm_request_resume - Queue up runtime-resume of a device. * @dev: Target device. */ static inline int pm_request_resume(struct device *dev) { return __pm_runtime_resume(dev, RPM_ASYNC); } /** * pm_request_autosuspend - Queue up autosuspend of a device. * @dev: Target device. * * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev * asynchronously. */ static inline int pm_request_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_get - Bump up usage counter and queue up resume of a device. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and queue up a work item to * carry out runtime-resume of it. */ static inline int pm_runtime_get(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC); } /** * pm_runtime_get_sync - Bump up usage counter of a device and resume it. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of * it synchronously. * * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. * Consider using pm_runtime_resume_and_get() instead of it, especially * if its return value is checked by the caller, as this is likely to result * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT); } /** * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. * @dev: Target device. * * Resume @dev synchronously and if that is successful, increment its runtime * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been * incremented or a negative error code otherwise. */ static inline int pm_runtime_resume_and_get(struct device *dev) { int ret; ret = __pm_runtime_resume(dev, RPM_GET_PUT); if (ret < 0) { pm_runtime_put_noidle(dev); return ret; } return 0; } /** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). */ static inline int pm_runtime_put(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } DEFINE_FREE(pm_runtime_put, struct device *, if (_T) pm_runtime_put(_T)) /** * __pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int __pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, invoke the "idle check" callback of @dev and, depending on its * return value, set up autosuspend of @dev or suspend it (depending on whether * or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_idle() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, carry out runtime-suspend of @dev synchronously. * * The possible return values of this function are the same as for * pm_runtime_suspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_suspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending * on whether or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); } /** * pm_runtime_set_active - Set runtime PM status to "active". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies * of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_active(struct device *dev) { return __pm_runtime_set_status(dev, RPM_ACTIVE); } /** * pm_runtime_set_suspended - Set runtime PM status to "suspended". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that * dependencies of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_suspended(struct device *dev) { return __pm_runtime_set_status(dev, RPM_SUSPENDED); } /** * pm_runtime_disable - Disable runtime PM for a device. * @dev: Target device. * * Prevent the runtime PM framework from working with @dev by incrementing its * "disable" counter. * * If the counter is zero when this function runs and there is a pending runtime * resume request for @dev, it will be resumed. If the counter is still zero at * that point, all of the pending runtime PM requests for @dev will be canceled * and all runtime PM operations in progress involving it will be waited for to * complete. * * For each invocation of this function for @dev, there must be a matching * pm_runtime_enable() call, so that runtime PM is eventually enabled for it * again. */ static inline void pm_runtime_disable(struct device *dev) { __pm_runtime_disable(dev, true); } /** * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device. * @dev: Target device. * * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). * * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() * at driver exit time unless your driver initially enabled pm_runtime * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, true); } /** * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used. * @dev: Target device. * * Prevent the runtime PM autosuspend mechanism from being used for @dev which * means that "autosuspend" will be handled as direct runtime-suspend for it * going forward. */ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, false); } #endif |
| 4358 3352 1016 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __LICENSE_H #define __LICENSE_H static inline int license_is_gpl_compatible(const char *license) { return (strcmp(license, "GPL") == 0 || strcmp(license, "GPL v2") == 0 || strcmp(license, "GPL and additional rights") == 0 || strcmp(license, "Dual BSD/GPL") == 0 || strcmp(license, "Dual MIT/GPL") == 0 || strcmp(license, "Dual MPL/GPL") == 0); } #endif |
| 63 3 25 4171 6 3 3 25 25 25 25 4171 4169 4171 26 25 25 1 1 1 3 3 3 509 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 | // SPDX-License-Identifier: GPL-2.0-only /* * CAIF Interface registration. * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland * * Borrowed heavily from file: pn_dev.c. Thanks to Remi Denis-Courmont * and Sakari Ailus <sakari.ailus@nokia.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/kernel.h> #include <linux/if_arp.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/spinlock.h> #include <net/netns/generic.h> #include <net/net_namespace.h> #include <net/pkt_sched.h> #include <net/caif/caif_device.h> #include <net/caif/caif_layer.h> #include <net/caif/caif_dev.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> #include <net/caif/cfserl.h> MODULE_DESCRIPTION("ST-Ericsson CAIF modem protocol support"); MODULE_LICENSE("GPL"); /* Used for local tracking of the CAIF net devices */ struct caif_device_entry { struct cflayer layer; struct list_head list; struct net_device *netdev; int __percpu *pcpu_refcnt; spinlock_t flow_lock; struct sk_buff *xoff_skb; void (*xoff_skb_dtor)(struct sk_buff *skb); bool xoff; }; struct caif_device_entry_list { struct list_head list; /* Protects simulanous deletes in list */ struct mutex lock; }; struct caif_net { struct cfcnfg *cfg; struct caif_device_entry_list caifdevs; }; static unsigned int caif_net_id; static int q_high = 50; /* Percent */ struct cfcnfg *get_cfcnfg(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); return caifn->cfg; } EXPORT_SYMBOL(get_cfcnfg); static struct caif_device_entry_list *caif_device_list(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); return &caifn->caifdevs; } static void caifd_put(struct caif_device_entry *e) { this_cpu_dec(*e->pcpu_refcnt); } static void caifd_hold(struct caif_device_entry *e) { this_cpu_inc(*e->pcpu_refcnt); } static int caifd_refcnt_read(struct caif_device_entry *e) { int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(e->pcpu_refcnt, i); return refcnt; } /* Allocate new CAIF device. */ static struct caif_device_entry *caif_device_alloc(struct net_device *dev) { struct caif_device_entry *caifd; caifd = kzalloc(sizeof(*caifd), GFP_KERNEL); if (!caifd) return NULL; caifd->pcpu_refcnt = alloc_percpu(int); if (!caifd->pcpu_refcnt) { kfree(caifd); return NULL; } caifd->netdev = dev; dev_hold(dev); return caifd; } static struct caif_device_entry *caif_get(struct net_device *dev) { struct caif_device_entry_list *caifdevs = caif_device_list(dev_net(dev)); struct caif_device_entry *caifd; list_for_each_entry_rcu(caifd, &caifdevs->list, list, lockdep_rtnl_is_held()) { if (caifd->netdev == dev) return caifd; } return NULL; } static void caif_flow_cb(struct sk_buff *skb) { struct caif_device_entry *caifd; void (*dtor)(struct sk_buff *skb) = NULL; bool send_xoff; WARN_ON(skb->dev == NULL); rcu_read_lock(); caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); if (!caifd) { rcu_read_unlock(); return; } caifd_hold(caifd); rcu_read_unlock(); spin_lock_bh(&caifd->flow_lock); send_xoff = caifd->xoff; caifd->xoff = false; dtor = caifd->xoff_skb_dtor; if (WARN_ON(caifd->xoff_skb != skb)) skb = NULL; caifd->xoff_skb = NULL; caifd->xoff_skb_dtor = NULL; spin_unlock_bh(&caifd->flow_lock); if (dtor && skb) dtor(skb); if (send_xoff) caifd->layer.up-> ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND, caifd->layer.id); caifd_put(caifd); } static int transmit(struct cflayer *layer, struct cfpkt *pkt) { int err, high = 0, qlen = 0; struct caif_device_entry *caifd = container_of(layer, struct caif_device_entry, layer); struct sk_buff *skb; struct netdev_queue *txq; rcu_read_lock_bh(); skb = cfpkt_tonative(pkt); skb->dev = caifd->netdev; skb_reset_network_header(skb); skb->protocol = htons(ETH_P_CAIF); /* Check if we need to handle xoff */ if (likely(caifd->netdev->priv_flags & IFF_NO_QUEUE)) goto noxoff; if (unlikely(caifd->xoff)) goto noxoff; if (likely(!netif_queue_stopped(caifd->netdev))) { struct Qdisc *sch; /* If we run with a TX queue, check if the queue is too long*/ txq = netdev_get_tx_queue(skb->dev, 0); sch = rcu_dereference_bh(txq->qdisc); if (likely(qdisc_is_empty(sch))) goto noxoff; /* can check for explicit qdisc len value only !NOLOCK, * always set flow off otherwise */ high = (caifd->netdev->tx_queue_len * q_high) / 100; if (!(sch->flags & TCQ_F_NOLOCK) && likely(sch->q.qlen < high)) goto noxoff; } /* Hold lock while accessing xoff */ spin_lock_bh(&caifd->flow_lock); if (caifd->xoff) { spin_unlock_bh(&caifd->flow_lock); goto noxoff; } /* * Handle flow off, we do this by temporary hi-jacking this * skb's destructor function, and replace it with our own * flow-on callback. The callback will set flow-on and call * the original destructor. */ pr_debug("queue has stopped(%d) or is full (%d > %d)\n", netif_queue_stopped(caifd->netdev), qlen, high); caifd->xoff = true; caifd->xoff_skb = skb; caifd->xoff_skb_dtor = skb->destructor; skb->destructor = caif_flow_cb; spin_unlock_bh(&caifd->flow_lock); caifd->layer.up->ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, caifd->layer.id); noxoff: rcu_read_unlock_bh(); err = dev_queue_xmit(skb); if (err > 0) err = -EIO; return err; } /* * Stuff received packets into the CAIF stack. * On error, returns non-zero and releases the skb. */ static int receive(struct sk_buff *skb, struct net_device *dev, struct packet_type *pkttype, struct net_device *orig_dev) { struct cfpkt *pkt; struct caif_device_entry *caifd; int err; pkt = cfpkt_fromnative(CAIF_DIR_IN, skb); rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->receive || !netif_oper_up(caifd->netdev)) { rcu_read_unlock(); kfree_skb(skb); return NET_RX_DROP; } /* Hold reference to netdevice while using CAIF stack */ caifd_hold(caifd); rcu_read_unlock(); err = caifd->layer.up->receive(caifd->layer.up, pkt); /* For -EILSEQ the packet is not freed so free it now */ if (err == -EILSEQ) cfpkt_destroy(pkt); /* Release reference to stack upwards */ caifd_put(caifd); if (err != 0) err = NET_RX_DROP; return err; } static struct packet_type caif_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_CAIF), .func = receive, }; static void dev_flowctrl(struct net_device *dev, int on) { struct caif_device_entry *caifd; rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { rcu_read_unlock(); return; } caifd_hold(caifd); rcu_read_unlock(); caifd->layer.up->ctrlcmd(caifd->layer.up, on ? _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND : _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, caifd->layer.id); caifd_put(caifd); } int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *)) { struct caif_device_entry *caifd; enum cfcnfg_phy_preference pref; struct cfcnfg *cfg = get_cfcnfg(dev_net(dev)); struct caif_device_entry_list *caifdevs; int res; caifdevs = caif_device_list(dev_net(dev)); caifd = caif_device_alloc(dev); if (!caifd) return -ENOMEM; *layer = &caifd->layer; spin_lock_init(&caifd->flow_lock); switch (caifdev->link_select) { case CAIF_LINK_HIGH_BANDW: pref = CFPHYPREF_HIGH_BW; break; case CAIF_LINK_LOW_LATENCY: pref = CFPHYPREF_LOW_LAT; break; default: pref = CFPHYPREF_HIGH_BW; break; } mutex_lock(&caifdevs->lock); list_add_rcu(&caifd->list, &caifdevs->list); strscpy(caifd->layer.name, dev->name, sizeof(caifd->layer.name)); caifd->layer.transmit = transmit; res = cfcnfg_add_phy_layer(cfg, dev, &caifd->layer, pref, link_support, caifdev->use_fcs, head_room); mutex_unlock(&caifdevs->lock); if (rcv_func) *rcv_func = receive; return res; } EXPORT_SYMBOL(caif_enroll_dev); /* notify Caif of device events */ static int caif_device_notify(struct notifier_block *me, unsigned long what, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct caif_device_entry *caifd = NULL; struct caif_dev_common *caifdev; struct cfcnfg *cfg; struct cflayer *layer, *link_support; int head_room = 0; struct caif_device_entry_list *caifdevs; int res; cfg = get_cfcnfg(dev_net(dev)); caifdevs = caif_device_list(dev_net(dev)); caifd = caif_get(dev); if (caifd == NULL && dev->type != ARPHRD_CAIF) return 0; switch (what) { case NETDEV_REGISTER: if (caifd != NULL) break; caifdev = netdev_priv(dev); link_support = NULL; if (caifdev->use_frag) { head_room = 1; link_support = cfserl_create(dev->ifindex, caifdev->use_stx); if (!link_support) { pr_warn("Out of memory\n"); break; } } res = caif_enroll_dev(dev, caifdev, link_support, head_room, &layer, NULL); if (res) cfserl_release(link_support); caifdev->flowctrl = dev_flowctrl; break; case NETDEV_UP: rcu_read_lock(); caifd = caif_get(dev); if (caifd == NULL) { rcu_read_unlock(); break; } caifd->xoff = false; cfcnfg_set_phy_state(cfg, &caifd->layer, true); rcu_read_unlock(); break; case NETDEV_DOWN: rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { rcu_read_unlock(); return -EINVAL; } cfcnfg_set_phy_state(cfg, &caifd->layer, false); caifd_hold(caifd); rcu_read_unlock(); caifd->layer.up->ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_DOWN_IND, caifd->layer.id); spin_lock_bh(&caifd->flow_lock); /* * Replace our xoff-destructor with original destructor. * We trust that skb->destructor *always* is called before * the skb reference is invalid. The hijacked SKB destructor * takes the flow_lock so manipulating the skb->destructor here * should be safe. */ if (caifd->xoff_skb_dtor != NULL && caifd->xoff_skb != NULL) caifd->xoff_skb->destructor = caifd->xoff_skb_dtor; caifd->xoff = false; caifd->xoff_skb_dtor = NULL; caifd->xoff_skb = NULL; spin_unlock_bh(&caifd->flow_lock); caifd_put(caifd); break; case NETDEV_UNREGISTER: mutex_lock(&caifdevs->lock); caifd = caif_get(dev); if (caifd == NULL) { mutex_unlock(&caifdevs->lock); break; } list_del_rcu(&caifd->list); /* * NETDEV_UNREGISTER is called repeatedly until all reference * counts for the net-device are released. If references to * caifd is taken, simply ignore NETDEV_UNREGISTER and wait for * the next call to NETDEV_UNREGISTER. * * If any packets are in flight down the CAIF Stack, * cfcnfg_del_phy_layer will return nonzero. * If no packets are in flight, the CAIF Stack associated * with the net-device un-registering is freed. */ if (caifd_refcnt_read(caifd) != 0 || cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0) { pr_info("Wait for device inuse\n"); /* Enrole device if CAIF Stack is still in use */ list_add_rcu(&caifd->list, &caifdevs->list); mutex_unlock(&caifdevs->lock); break; } synchronize_rcu(); dev_put(caifd->netdev); free_percpu(caifd->pcpu_refcnt); kfree(caifd); mutex_unlock(&caifdevs->lock); break; } return 0; } static struct notifier_block caif_device_notifier = { .notifier_call = caif_device_notify, .priority = 0, }; /* Per-namespace Caif devices handling */ static int caif_init_net(struct net *net) { struct caif_net *caifn = net_generic(net, caif_net_id); INIT_LIST_HEAD(&caifn->caifdevs.list); mutex_init(&caifn->caifdevs.lock); caifn->cfg = cfcnfg_create(); if (!caifn->cfg) return -ENOMEM; return 0; } static void caif_exit_net(struct net *net) { struct caif_device_entry *caifd, *tmp; struct caif_device_entry_list *caifdevs = caif_device_list(net); struct cfcnfg *cfg = get_cfcnfg(net); rtnl_lock(); mutex_lock(&caifdevs->lock); list_for_each_entry_safe(caifd, tmp, &caifdevs->list, list) { int i = 0; list_del_rcu(&caifd->list); cfcnfg_set_phy_state(cfg, &caifd->layer, false); while (i < 10 && (caifd_refcnt_read(caifd) != 0 || cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0)) { pr_info("Wait for device inuse\n"); msleep(250); i++; } synchronize_rcu(); dev_put(caifd->netdev); free_percpu(caifd->pcpu_refcnt); kfree(caifd); } cfcnfg_remove(cfg); mutex_unlock(&caifdevs->lock); rtnl_unlock(); } static struct pernet_operations caif_net_ops = { .init = caif_init_net, .exit = caif_exit_net, .id = &caif_net_id, .size = sizeof(struct caif_net), }; /* Initialize Caif devices list */ static int __init caif_device_init(void) { int result; result = register_pernet_subsys(&caif_net_ops); if (result) return result; register_netdevice_notifier(&caif_device_notifier); dev_add_pack(&caif_packet_type); return result; } static void __exit caif_device_exit(void) { unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); unregister_pernet_subsys(&caif_net_ops); } module_init(caif_device_init); module_exit(caif_device_exit); |
| 28 122 66 142 17 4 97 32 32 32 39 53 52 4 16 17 2 2 2 95 95 95 36 36 36 95 95 94 16 17 17 17 17 2 2 2 32 32 2 32 32 17 17 2 2 4 4 4 5 4 132 4 34 34 2 2 32 4 2 4 4 4 36 36 1 4 4 3 1 13 5 96 2 36 1 1 119 120 119 3 1 1 1 1 36 36 95 95 24 37 1 36 36 36 36 36 36 95 71 70 71 95 95 95 95 95 95 121 78 58 118 41 104 63 63 122 121 62 121 1 2 6 69 69 1 2 63 63 2 62 62 14 26 36 36 36 4 22 34 36 26 28 28 94 24 95 93 16 94 5 95 63 59 95 95 95 95 95 18 5 5 15 1 15 1 15 1 29 15 121 1 1 120 121 1 1 1 122 2 1 1 122 3 1 1 1 13 13 13 13 13 32 32 31 48 107 107 5 5 5 7 7 105 105 81 35 81 28 169 171 4 4 3 3 2 1 2 401 401 56 56 45 124 124 78 78 30 60 67 154 154 3 2 1 2 54 45 23 38 45 10 50 65 4 13 13 13 13 13 13 13 1 1 12 30 2 51 3 3 157 158 2 154 18 3 122 122 158 1 157 3 196 3 158 157 158 158 3 158 4 3 1 1 1 63 37 1 7 2 5 24 7 3 3 3 35 25 9 32 1 32 34 26 32 29 20 1 5 2 2 3 27 5 48 156 1 155 87 95 130 44 156 156 157 155 1 1 157 6 4 2 193 193 134 134 121 134 128 12 155 155 130 10 34 149 12 3 98 144 113 44 61 94 36 36 95 94 4173 4162 188 6 6 56 40 6 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/team/team.c - Network team device driver * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com> */ #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/errno.h> #include <linux/ctype.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netpoll.h> #include <linux/if_vlan.h> #include <linux/if_arp.h> #include <linux/socket.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <net/genetlink.h> #include <net/netdev_lock.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <linux/if_team.h> #include "team_nl.h" #define DRV_NAME "team" /********** * Helpers **********/ static struct team_port *team_port_get_rtnl(const struct net_device *dev) { struct team_port *port = rtnl_dereference(dev->rx_handler_data); return netif_is_team_port(dev) ? port : NULL; } /* * Since the ability to change device address for open port device is tested in * team_port_add, this function can be called without control of return value */ static int __set_port_dev_addr(struct net_device *port_dev, const unsigned char *dev_addr) { struct sockaddr_storage addr; memcpy(addr.__data, dev_addr, port_dev->addr_len); addr.ss_family = port_dev->type; return dev_set_mac_address(port_dev, &addr, NULL); } static int team_port_set_orig_dev_addr(struct team_port *port) { return __set_port_dev_addr(port->dev, port->orig.dev_addr); } static int team_port_set_team_dev_addr(struct team *team, struct team_port *port) { return __set_port_dev_addr(port->dev, team->dev->dev_addr); } int team_modeop_port_enter(struct team *team, struct team_port *port) { return team_port_set_team_dev_addr(team, port); } EXPORT_SYMBOL(team_modeop_port_enter); void team_modeop_port_change_dev_addr(struct team *team, struct team_port *port) { team_port_set_team_dev_addr(team, port); } EXPORT_SYMBOL(team_modeop_port_change_dev_addr); static void team_lower_state_changed(struct team_port *port) { struct netdev_lag_lower_state_info info; info.link_up = port->linkup; info.tx_enabled = team_port_enabled(port); netdev_lower_state_changed(port->dev, &info); } static void team_refresh_port_linkup(struct team_port *port) { bool new_linkup = port->user.linkup_enabled ? port->user.linkup : port->state.linkup; if (port->linkup != new_linkup) { port->linkup = new_linkup; team_lower_state_changed(port); } } /******************* * Options handling *******************/ struct team_option_inst { /* One for each option instance */ struct list_head list; struct list_head tmp_list; struct team_option *option; struct team_option_inst_info info; bool changed; bool removed; }; static struct team_option *__team_find_option(struct team *team, const char *opt_name) { struct team_option *option; list_for_each_entry(option, &team->option_list, list) { if (strcmp(option->name, opt_name) == 0) return option; } return NULL; } static void __team_option_inst_del(struct team_option_inst *opt_inst) { list_del(&opt_inst->list); kfree(opt_inst); } static void __team_option_inst_del_option(struct team *team, struct team_option *option) { struct team_option_inst *opt_inst, *tmp; list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option == option) __team_option_inst_del(opt_inst); } } static int __team_option_inst_add(struct team *team, struct team_option *option, struct team_port *port) { struct team_option_inst *opt_inst; unsigned int array_size; unsigned int i; array_size = option->array_size; if (!array_size) array_size = 1; /* No array but still need one instance */ for (i = 0; i < array_size; i++) { opt_inst = kmalloc(sizeof(*opt_inst), GFP_KERNEL); if (!opt_inst) return -ENOMEM; opt_inst->option = option; opt_inst->info.port = port; opt_inst->info.array_index = i; opt_inst->changed = true; opt_inst->removed = false; list_add_tail(&opt_inst->list, &team->option_inst_list); if (option->init) option->init(team, &opt_inst->info); } return 0; } static int __team_option_inst_add_option(struct team *team, struct team_option *option) { int err; if (!option->per_port) { err = __team_option_inst_add(team, option, NULL); if (err) goto inst_del_option; } return 0; inst_del_option: __team_option_inst_del_option(team, option); return err; } static void __team_option_inst_mark_removed_option(struct team *team, struct team_option *option) { struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->option == option) { opt_inst->changed = true; opt_inst->removed = true; } } } static void __team_option_inst_del_port(struct team *team, struct team_port *port) { struct team_option_inst *opt_inst, *tmp; list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option->per_port && opt_inst->info.port == port) __team_option_inst_del(opt_inst); } } static int __team_option_inst_add_port(struct team *team, struct team_port *port) { struct team_option *option; int err; list_for_each_entry(option, &team->option_list, list) { if (!option->per_port) continue; err = __team_option_inst_add(team, option, port); if (err) goto inst_del_port; } return 0; inst_del_port: __team_option_inst_del_port(team, port); return err; } static void __team_option_inst_mark_removed_port(struct team *team, struct team_port *port) { struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->info.port == port) { opt_inst->changed = true; opt_inst->removed = true; } } } static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) { int i; struct team_option **dst_opts; int err; dst_opts = kcalloc(option_count, sizeof(struct team_option *), GFP_KERNEL); if (!dst_opts) return -ENOMEM; for (i = 0; i < option_count; i++, option++) { if (__team_find_option(team, option->name)) { err = -EEXIST; goto alloc_rollback; } dst_opts[i] = kmemdup(option, sizeof(*option), GFP_KERNEL); if (!dst_opts[i]) { err = -ENOMEM; goto alloc_rollback; } } for (i = 0; i < option_count; i++) { err = __team_option_inst_add_option(team, dst_opts[i]); if (err) goto inst_rollback; list_add_tail(&dst_opts[i]->list, &team->option_list); } kfree(dst_opts); return 0; inst_rollback: for (i--; i >= 0; i--) { __team_option_inst_del_option(team, dst_opts[i]); list_del(&dst_opts[i]->list); } i = option_count; alloc_rollback: for (i--; i >= 0; i--) kfree(dst_opts[i]); kfree(dst_opts); return err; } static void __team_options_mark_removed(struct team *team, const struct team_option *option, size_t option_count) { int i; for (i = 0; i < option_count; i++, option++) { struct team_option *del_opt; del_opt = __team_find_option(team, option->name); if (del_opt) __team_option_inst_mark_removed_option(team, del_opt); } } static void __team_options_unregister(struct team *team, const struct team_option *option, size_t option_count) { int i; for (i = 0; i < option_count; i++, option++) { struct team_option *del_opt; del_opt = __team_find_option(team, option->name); if (del_opt) { __team_option_inst_del_option(team, del_opt); list_del(&del_opt->list); kfree(del_opt); } } } static void __team_options_change_check(struct team *team); int team_options_register(struct team *team, const struct team_option *option, size_t option_count) { int err; err = __team_options_register(team, option, option_count); if (err) return err; __team_options_change_check(team); return 0; } EXPORT_SYMBOL(team_options_register); void team_options_unregister(struct team *team, const struct team_option *option, size_t option_count) { __team_options_mark_removed(team, option, option_count); __team_options_change_check(team); __team_options_unregister(team, option, option_count); } EXPORT_SYMBOL(team_options_unregister); static int team_option_get(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { if (!opt_inst->option->getter) return -EOPNOTSUPP; opt_inst->option->getter(team, ctx); return 0; } static int team_option_set(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { if (!opt_inst->option->setter) return -EOPNOTSUPP; return opt_inst->option->setter(team, ctx); } void team_option_inst_set_change(struct team_option_inst_info *opt_inst_info) { struct team_option_inst *opt_inst; opt_inst = container_of(opt_inst_info, struct team_option_inst, info); opt_inst->changed = true; } EXPORT_SYMBOL(team_option_inst_set_change); void team_options_change_check(struct team *team) { __team_options_change_check(team); } EXPORT_SYMBOL(team_options_change_check); /**************** * Mode handling ****************/ static LIST_HEAD(mode_list); static DEFINE_SPINLOCK(mode_list_lock); struct team_mode_item { struct list_head list; const struct team_mode *mode; }; static struct team_mode_item *__find_mode(const char *kind) { struct team_mode_item *mitem; list_for_each_entry(mitem, &mode_list, list) { if (strcmp(mitem->mode->kind, kind) == 0) return mitem; } return NULL; } static bool is_good_mode_name(const char *name) { while (*name != '\0') { if (!isalpha(*name) && !isdigit(*name) && *name != '_') return false; name++; } return true; } int team_mode_register(const struct team_mode *mode) { int err = 0; struct team_mode_item *mitem; if (!is_good_mode_name(mode->kind) || mode->priv_size > TEAM_MODE_PRIV_SIZE) return -EINVAL; mitem = kmalloc(sizeof(*mitem), GFP_KERNEL); if (!mitem) return -ENOMEM; spin_lock(&mode_list_lock); if (__find_mode(mode->kind)) { err = -EEXIST; kfree(mitem); goto unlock; } mitem->mode = mode; list_add_tail(&mitem->list, &mode_list); unlock: spin_unlock(&mode_list_lock); return err; } EXPORT_SYMBOL(team_mode_register); void team_mode_unregister(const struct team_mode *mode) { struct team_mode_item *mitem; spin_lock(&mode_list_lock); mitem = __find_mode(mode->kind); if (mitem) { list_del_init(&mitem->list); kfree(mitem); } spin_unlock(&mode_list_lock); } EXPORT_SYMBOL(team_mode_unregister); static const struct team_mode *team_mode_get(const char *kind) { struct team_mode_item *mitem; const struct team_mode *mode = NULL; if (!try_module_get(THIS_MODULE)) return NULL; spin_lock(&mode_list_lock); mitem = __find_mode(kind); if (!mitem) { spin_unlock(&mode_list_lock); request_module("team-mode-%s", kind); spin_lock(&mode_list_lock); mitem = __find_mode(kind); } if (mitem) { mode = mitem->mode; if (!try_module_get(mode->owner)) mode = NULL; } spin_unlock(&mode_list_lock); module_put(THIS_MODULE); return mode; } static void team_mode_put(const struct team_mode *mode) { module_put(mode->owner); } static bool team_dummy_transmit(struct team *team, struct sk_buff *skb) { dev_kfree_skb_any(skb); return false; } static rx_handler_result_t team_dummy_receive(struct team *team, struct team_port *port, struct sk_buff *skb) { return RX_HANDLER_ANOTHER; } static const struct team_mode __team_no_mode = { .kind = "*NOMODE*", }; static bool team_is_mode_set(struct team *team) { return team->mode != &__team_no_mode; } static void team_set_no_mode(struct team *team) { team->user_carrier_enabled = false; team->mode = &__team_no_mode; } static void team_adjust_ops(struct team *team) { /* * To avoid checks in rx/tx skb paths, ensure here that non-null and * correct ops are always set. */ if (!team->en_port_count || !team_is_mode_set(team) || !team->mode->ops->transmit) team->ops.transmit = team_dummy_transmit; else team->ops.transmit = team->mode->ops->transmit; if (!team->en_port_count || !team_is_mode_set(team) || !team->mode->ops->receive) team->ops.receive = team_dummy_receive; else team->ops.receive = team->mode->ops->receive; } /* * We can benefit from the fact that it's ensured no port is present * at the time of mode change. Therefore no packets are in fly so there's no * need to set mode operations in any special way. */ static int __team_change_mode(struct team *team, const struct team_mode *new_mode) { /* Check if mode was previously set and do cleanup if so */ if (team_is_mode_set(team)) { void (*exit_op)(struct team *team) = team->ops.exit; /* Clear ops area so no callback is called any longer */ memset(&team->ops, 0, sizeof(struct team_mode_ops)); team_adjust_ops(team); if (exit_op) exit_op(team); team_mode_put(team->mode); team_set_no_mode(team); /* zero private data area */ memset(&team->mode_priv, 0, sizeof(struct team) - offsetof(struct team, mode_priv)); } if (!new_mode) return 0; if (new_mode->ops->init) { int err; err = new_mode->ops->init(team); if (err) return err; } team->mode = new_mode; memcpy(&team->ops, new_mode->ops, sizeof(struct team_mode_ops)); team_adjust_ops(team); return 0; } static int team_change_mode(struct team *team, const char *kind) { const struct team_mode *new_mode; struct net_device *dev = team->dev; int err; if (!list_empty(&team->port_list)) { netdev_err(dev, "No ports can be present during mode change\n"); return -EBUSY; } if (team_is_mode_set(team) && strcmp(team->mode->kind, kind) == 0) { netdev_err(dev, "Unable to change to the same mode the team is in\n"); return -EINVAL; } new_mode = team_mode_get(kind); if (!new_mode) { netdev_err(dev, "Mode \"%s\" not found\n", kind); return -EINVAL; } err = __team_change_mode(team, new_mode); if (err) { netdev_err(dev, "Failed to change to mode \"%s\"\n", kind); team_mode_put(new_mode); return err; } netdev_info(dev, "Mode changed to \"%s\"\n", kind); return 0; } /********************* * Peers notification *********************/ static void team_notify_peers_work(struct work_struct *work) { struct team *team; int val; team = container_of(work, struct team, notify_peers.dw.work); if (!rtnl_trylock()) { schedule_delayed_work(&team->notify_peers.dw, 0); return; } val = atomic_dec_if_positive(&team->notify_peers.count_pending); if (val < 0) { rtnl_unlock(); return; } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev); rtnl_unlock(); if (val) schedule_delayed_work(&team->notify_peers.dw, msecs_to_jiffies(team->notify_peers.interval)); } static void team_notify_peers(struct team *team) { if (!team->notify_peers.count || !netif_running(team->dev)) return; atomic_add(team->notify_peers.count, &team->notify_peers.count_pending); schedule_delayed_work(&team->notify_peers.dw, 0); } static void team_notify_peers_init(struct team *team) { INIT_DELAYED_WORK(&team->notify_peers.dw, team_notify_peers_work); } static void team_notify_peers_fini(struct team *team) { cancel_delayed_work_sync(&team->notify_peers.dw); } /******************************* * Send multicast group rejoins *******************************/ static void team_mcast_rejoin_work(struct work_struct *work) { struct team *team; int val; team = container_of(work, struct team, mcast_rejoin.dw.work); if (!rtnl_trylock()) { schedule_delayed_work(&team->mcast_rejoin.dw, 0); return; } val = atomic_dec_if_positive(&team->mcast_rejoin.count_pending); if (val < 0) { rtnl_unlock(); return; } call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev); rtnl_unlock(); if (val) schedule_delayed_work(&team->mcast_rejoin.dw, msecs_to_jiffies(team->mcast_rejoin.interval)); } static void team_mcast_rejoin(struct team *team) { if (!team->mcast_rejoin.count || !netif_running(team->dev)) return; atomic_add(team->mcast_rejoin.count, &team->mcast_rejoin.count_pending); schedule_delayed_work(&team->mcast_rejoin.dw, 0); } static void team_mcast_rejoin_init(struct team *team) { INIT_DELAYED_WORK(&team->mcast_rejoin.dw, team_mcast_rejoin_work); } static void team_mcast_rejoin_fini(struct team *team) { cancel_delayed_work_sync(&team->mcast_rejoin.dw); } /************************ * Rx path frame handler ************************/ /* note: already called with rcu_read_lock */ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct team_port *port; struct team *team; rx_handler_result_t res; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return RX_HANDLER_CONSUMED; *pskb = skb; port = team_port_get_rcu(skb->dev); team = port->team; if (!team_port_enabled(port)) { if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) /* link-local packets are mostly useful when stack receives them * with the link they arrive on. */ return RX_HANDLER_PASS; /* allow exact match delivery for disabled ports */ res = RX_HANDLER_EXACT; } else { res = team->ops.receive(team, port, skb); } if (res == RX_HANDLER_ANOTHER) { struct team_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->rx_packets); u64_stats_add(&pcpu_stats->rx_bytes, skb->len); if (skb->pkt_type == PACKET_MULTICAST) u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); skb->dev = team->dev; } else if (res == RX_HANDLER_EXACT) { this_cpu_inc(team->pcpu_stats->rx_nohandler); } else { this_cpu_inc(team->pcpu_stats->rx_dropped); } return res; } /************************************* * Multiqueue Tx port select override *************************************/ static int team_queue_override_init(struct team *team) { struct list_head *listarr; unsigned int queue_cnt = team->dev->num_tx_queues - 1; unsigned int i; if (!queue_cnt) return 0; listarr = kmalloc_array(queue_cnt, sizeof(struct list_head), GFP_KERNEL); if (!listarr) return -ENOMEM; team->qom_lists = listarr; for (i = 0; i < queue_cnt; i++) INIT_LIST_HEAD(listarr++); return 0; } static void team_queue_override_fini(struct team *team) { kfree(team->qom_lists); } static struct list_head *__team_get_qom_list(struct team *team, u16 queue_id) { return &team->qom_lists[queue_id - 1]; } /* * note: already called with rcu_read_lock */ static bool team_queue_override_transmit(struct team *team, struct sk_buff *skb) { struct list_head *qom_list; struct team_port *port; if (!team->queue_override_enabled || !skb->queue_mapping) return false; qom_list = __team_get_qom_list(team, skb->queue_mapping); list_for_each_entry_rcu(port, qom_list, qom_list) { if (!team_dev_queue_xmit(team, port, skb)) return true; } return false; } static void __team_queue_override_port_del(struct team *team, struct team_port *port) { if (!port->queue_id) return; list_del_rcu(&port->qom_list); } static bool team_queue_override_port_has_gt_prio_than(struct team_port *port, struct team_port *cur) { if (port->priority < cur->priority) return true; if (port->priority > cur->priority) return false; if (port->index < cur->index) return true; return false; } static void __team_queue_override_port_add(struct team *team, struct team_port *port) { struct team_port *cur; struct list_head *qom_list; struct list_head *node; if (!port->queue_id) return; qom_list = __team_get_qom_list(team, port->queue_id); node = qom_list; list_for_each_entry(cur, qom_list, qom_list) { if (team_queue_override_port_has_gt_prio_than(port, cur)) break; node = &cur->qom_list; } list_add_tail_rcu(&port->qom_list, node); } static void __team_queue_override_enabled_check(struct team *team) { struct team_port *port; bool enabled = false; list_for_each_entry(port, &team->port_list, list) { if (port->queue_id) { enabled = true; break; } } if (enabled == team->queue_override_enabled) return; netdev_dbg(team->dev, "%s queue override\n", enabled ? "Enabling" : "Disabling"); team->queue_override_enabled = enabled; } static void team_queue_override_port_prio_changed(struct team *team, struct team_port *port) { if (!port->queue_id || team_port_enabled(port)) return; __team_queue_override_port_del(team, port); __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } static void team_queue_override_port_change_queue_id(struct team *team, struct team_port *port, u16 new_queue_id) { if (team_port_enabled(port)) { __team_queue_override_port_del(team, port); port->queue_id = new_queue_id; __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } else { port->queue_id = new_queue_id; } } static void team_queue_override_port_add(struct team *team, struct team_port *port) { __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } static void team_queue_override_port_del(struct team *team, struct team_port *port) { __team_queue_override_port_del(team, port); __team_queue_override_enabled_check(team); } /**************** * Port handling ****************/ static bool team_port_find(const struct team *team, const struct team_port *port) { struct team_port *cur; list_for_each_entry(cur, &team->port_list, list) if (cur == port) return true; return false; } /* * Enable/disable port by adding to enabled port hashlist and setting * port->index (Might be racy so reader could see incorrect ifindex when * processing a flying packet, but that is not a problem). Write guarded * by team->lock. */ static void team_port_enable(struct team *team, struct team_port *port) { if (team_port_enabled(port)) return; port->index = team->en_port_count++; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); team_adjust_ops(team); team_queue_override_port_add(team, port); if (team->ops.port_enabled) team->ops.port_enabled(team, port); team_notify_peers(team); team_mcast_rejoin(team); team_lower_state_changed(port); } static void __reconstruct_port_hlist(struct team *team, int rm_index) { int i; struct team_port *port; for (i = rm_index + 1; i < team->en_port_count; i++) { port = team_get_port_by_index(team, i); hlist_del_rcu(&port->hlist); port->index--; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); } } static void team_port_disable(struct team *team, struct team_port *port) { if (!team_port_enabled(port)) return; if (team->ops.port_disabled) team->ops.port_disabled(team, port); hlist_del_rcu(&port->hlist); __reconstruct_port_hlist(team, port->index); port->index = -1; team->en_port_count--; team_queue_override_port_del(team, port); team_adjust_ops(team); team_lower_state_changed(port); } #define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_HIGHDMA | NETIF_F_LRO | \ NETIF_F_GSO_ENCAP_ALL) #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) static void __team_compute_features(struct team *team) { struct team_port *port; netdev_features_t vlan_features = TEAM_VLAN_FEATURES; netdev_features_t enc_features = TEAM_ENC_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; rcu_read_lock(); if (list_empty(&team->port_list)) goto done; vlan_features = netdev_base_features(vlan_features); enc_features = netdev_base_features(enc_features); list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, TEAM_VLAN_FEATURES); enc_features = netdev_increment_features(enc_features, port->dev->hw_enc_features, TEAM_ENC_FEATURES); dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } done: rcu_read_unlock(); team->dev->vlan_features = vlan_features; team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; team->dev->hard_header_len = max_hard_header_len; team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) team->dev->priv_flags |= IFF_XMIT_DST_RELEASE; } static void team_compute_features(struct team *team) { __team_compute_features(team); netdev_change_features(team->dev); } static int team_port_enter(struct team *team, struct team_port *port) { int err = 0; dev_hold(team->dev); if (team->ops.port_enter) { err = team->ops.port_enter(team, port); if (err) { netdev_err(team->dev, "Device %s failed to enter team mode\n", port->dev->name); goto err_port_enter; } } return 0; err_port_enter: dev_put(team->dev); return err; } static void team_port_leave(struct team *team, struct team_port *port) { if (team->ops.port_leave) team->ops.port_leave(team, port); dev_put(team->dev); } #ifdef CONFIG_NET_POLL_CONTROLLER static int __team_port_enable_netpoll(struct team_port *port) { struct netpoll *np; int err; np = kzalloc(sizeof(*np), GFP_KERNEL); if (!np) return -ENOMEM; err = __netpoll_setup(np, port->dev); if (err) { kfree(np); return err; } port->np = np; return err; } static int team_port_enable_netpoll(struct team_port *port) { if (!port->team->dev->npinfo) return 0; return __team_port_enable_netpoll(port); } static void team_port_disable_netpoll(struct team_port *port) { struct netpoll *np = port->np; if (!np) return; port->np = NULL; __netpoll_free(np); } #else static int team_port_enable_netpoll(struct team_port *port) { return 0; } static void team_port_disable_netpoll(struct team_port *port) { } #endif static int team_upper_dev_link(struct team *team, struct team_port *port, struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; int err; lag_upper_info.tx_type = team->mode->lag_tx_type; lag_upper_info.hash_type = NETDEV_LAG_HASH_UNKNOWN; err = netdev_master_upper_dev_link(port->dev, team->dev, NULL, &lag_upper_info, extack); if (err) return err; port->dev->priv_flags |= IFF_TEAM_PORT; return 0; } static void team_upper_dev_unlink(struct team *team, struct team_port *port) { netdev_upper_dev_unlink(port->dev, team->dev); port->dev->priv_flags &= ~IFF_TEAM_PORT; } static void __team_port_change_port_added(struct team_port *port, bool linkup); static int team_dev_type_check_change(struct net_device *dev, struct net_device *port_dev); static int team_port_add(struct team *team, struct net_device *port_dev, struct netlink_ext_ack *extack) { struct net_device *dev = team->dev; struct team_port *port; char *portname = port_dev->name; int err; if (port_dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Loopback device can't be added as a team port"); netdev_err(dev, "Device %s is loopback device. Loopback devices can't be added as a team port\n", portname); return -EINVAL; } if (netif_is_team_port(port_dev)) { NL_SET_ERR_MSG(extack, "Device is already a port of a team device"); netdev_err(dev, "Device %s is already a port " "of a team device\n", portname); return -EBUSY; } if (dev == port_dev) { NL_SET_ERR_MSG(extack, "Cannot enslave team device to itself"); netdev_err(dev, "Cannot enslave team device to itself\n"); return -EINVAL; } if (netdev_has_upper_dev(dev, port_dev)) { NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface"); netdev_err(dev, "Device %s is already an upper device of the team interface\n", portname); return -EBUSY; } if (netdev_has_upper_dev(port_dev, dev)) { NL_SET_ERR_MSG(extack, "Device is already a lower device of the team interface"); netdev_err(dev, "Device %s is already a lower device of the team interface\n", portname); return -EBUSY; } if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); netdev_err(dev, "Device %s is VLAN challenged and team device has VLAN set up\n", portname); return -EPERM; } err = team_dev_type_check_change(dev, port_dev); if (err) return err; if (port_dev->flags & IFF_UP) { NL_SET_ERR_MSG(extack, "Device is up. Set it down before adding it as a team port"); netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n", portname); return -EBUSY; } port = kzalloc(sizeof(struct team_port) + team->mode->port_priv_size, GFP_KERNEL); if (!port) return -ENOMEM; port->dev = port_dev; port->team = team; INIT_LIST_HEAD(&port->qom_list); port->orig.mtu = port_dev->mtu; err = dev_set_mtu(port_dev, dev->mtu); if (err) { netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err); goto err_set_mtu; } memcpy(port->orig.dev_addr, port_dev->dev_addr, port_dev->addr_len); err = team_port_enter(team, port); if (err) { netdev_err(dev, "Device %s failed to enter team mode\n", portname); goto err_port_enter; } err = dev_open(port_dev, extack); if (err) { netdev_dbg(dev, "Device %s opening failed\n", portname); goto err_dev_open; } err = vlan_vids_add_by_dev(port_dev, dev); if (err) { netdev_err(dev, "Failed to add vlan ids to device %s\n", portname); goto err_vids_add; } err = team_port_enable_netpoll(port); if (err) { netdev_err(dev, "Failed to enable netpoll on device %s\n", portname); goto err_enable_netpoll; } if (!(dev->features & NETIF_F_LRO)) dev_disable_lro(port_dev); err = netdev_rx_handler_register(port_dev, team_handle_frame, port); if (err) { netdev_err(dev, "Device %s failed to register rx_handler\n", portname); goto err_handler_register; } err = team_upper_dev_link(team, port, extack); if (err) { netdev_err(dev, "Device %s failed to set upper link\n", portname); goto err_set_upper_link; } err = __team_option_inst_add_port(team, port); if (err) { netdev_err(dev, "Device %s failed to add per-port options\n", portname); goto err_option_port_add; } /* set promiscuity level to new slave */ if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(port_dev, 1); if (err) goto err_set_slave_promisc; } /* set allmulti level to new slave */ if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(port_dev, 1); if (err) { if (dev->flags & IFF_PROMISC) dev_set_promiscuity(port_dev, -1); goto err_set_slave_promisc; } } if (dev->flags & IFF_UP) { netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); dev_mc_sync_multiple(port_dev, dev); netif_addr_unlock_bh(dev); } port->index = -1; list_add_tail_rcu(&port->list, &team->port_list); team_port_enable(team, port); __team_compute_features(team); __team_port_change_port_added(port, !!netif_oper_up(port_dev)); __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); return 0; err_set_slave_promisc: __team_option_inst_del_port(team, port); err_option_port_add: team_upper_dev_unlink(team, port); err_set_upper_link: netdev_rx_handler_unregister(port_dev); err_handler_register: team_port_disable_netpoll(port); err_enable_netpoll: vlan_vids_del_by_dev(port_dev, dev); err_vids_add: dev_close(port_dev); err_dev_open: team_port_leave(team, port); team_port_set_orig_dev_addr(port); err_port_enter: dev_set_mtu(port_dev, port->orig.mtu); err_set_mtu: kfree(port); return err; } static void __team_port_change_port_removed(struct team_port *port); static int team_port_del(struct team *team, struct net_device *port_dev) { struct net_device *dev = team->dev; struct team_port *port; char *portname = port_dev->name; port = team_port_get_rtnl(port_dev); if (!port || !team_port_find(team, port)) { netdev_err(dev, "Device %s does not act as a port of this team\n", portname); return -ENOENT; } team_port_disable(team, port); list_del_rcu(&port->list); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(port_dev, -1); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(port_dev, -1); team_upper_dev_unlink(team, port); netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); if (dev->flags & IFF_UP) { dev_uc_unsync(port_dev, dev); dev_mc_unsync(port_dev, dev); } dev_close(port_dev); team_port_leave(team, port); __team_option_inst_mark_removed_port(team, port); __team_options_change_check(team); __team_option_inst_del_port(team, port); __team_port_change_port_removed(port); team_port_set_orig_dev_addr(port); dev_set_mtu(port_dev, port->orig.mtu); kfree_rcu(port, rcu); netdev_info(dev, "Port device %s removed\n", portname); __team_compute_features(team); return 0; } /***************** * Net device ops *****************/ static void team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.str_val = team->mode->kind; } static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) { return team_change_mode(team, ctx->data.str_val); } static void team_notify_peers_count_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.count; } static int team_notify_peers_count_set(struct team *team, struct team_gsetter_ctx *ctx) { team->notify_peers.count = ctx->data.u32_val; return 0; } static void team_notify_peers_interval_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.interval; } static int team_notify_peers_interval_set(struct team *team, struct team_gsetter_ctx *ctx) { team->notify_peers.interval = ctx->data.u32_val; return 0; } static void team_mcast_rejoin_count_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.count; } static int team_mcast_rejoin_count_set(struct team *team, struct team_gsetter_ctx *ctx) { team->mcast_rejoin.count = ctx->data.u32_val; return 0; } static void team_mcast_rejoin_interval_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.interval; } static int team_mcast_rejoin_interval_set(struct team *team, struct team_gsetter_ctx *ctx) { team->mcast_rejoin.interval = ctx->data.u32_val; return 0; } static void team_port_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = team_port_enabled(port); } static int team_port_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; if (ctx->data.bool_val) team_port_enable(team, port); else team_port_disable(team, port); return 0; } static void team_user_linkup_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup; } static void __team_carrier_check(struct team *team); static int team_user_linkup_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; port->user.linkup = ctx->data.bool_val; team_refresh_port_linkup(port); __team_carrier_check(port->team); return 0; } static void team_user_linkup_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup_enabled; } static int team_user_linkup_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; port->user.linkup_enabled = ctx->data.bool_val; team_refresh_port_linkup(port); __team_carrier_check(port->team); return 0; } static void team_priority_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.s32_val = port->priority; } static int team_priority_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; s32 priority = ctx->data.s32_val; if (port->priority == priority) return 0; port->priority = priority; team_queue_override_port_prio_changed(team, port); return 0; } static void team_queue_id_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.u32_val = port->queue_id; } static int team_queue_id_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; u16 new_queue_id = ctx->data.u32_val; if (port->queue_id == new_queue_id) return 0; if (new_queue_id >= team->dev->real_num_tx_queues) return -EINVAL; team_queue_override_port_change_queue_id(team, port, new_queue_id); return 0; } static const struct team_option team_options[] = { { .name = "mode", .type = TEAM_OPTION_TYPE_STRING, .getter = team_mode_option_get, .setter = team_mode_option_set, }, { .name = "notify_peers_count", .type = TEAM_OPTION_TYPE_U32, .getter = team_notify_peers_count_get, .setter = team_notify_peers_count_set, }, { .name = "notify_peers_interval", .type = TEAM_OPTION_TYPE_U32, .getter = team_notify_peers_interval_get, .setter = team_notify_peers_interval_set, }, { .name = "mcast_rejoin_count", .type = TEAM_OPTION_TYPE_U32, .getter = team_mcast_rejoin_count_get, .setter = team_mcast_rejoin_count_set, }, { .name = "mcast_rejoin_interval", .type = TEAM_OPTION_TYPE_U32, .getter = team_mcast_rejoin_interval_get, .setter = team_mcast_rejoin_interval_set, }, { .name = "enabled", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_port_en_option_get, .setter = team_port_en_option_set, }, { .name = "user_linkup", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_user_linkup_option_get, .setter = team_user_linkup_option_set, }, { .name = "user_linkup_enabled", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_user_linkup_en_option_get, .setter = team_user_linkup_en_option_set, }, { .name = "priority", .type = TEAM_OPTION_TYPE_S32, .per_port = true, .getter = team_priority_option_get, .setter = team_priority_option_set, }, { .name = "queue_id", .type = TEAM_OPTION_TYPE_U32, .per_port = true, .getter = team_queue_id_option_get, .setter = team_queue_id_option_set, }, }; static int team_init(struct net_device *dev) { struct team *team = netdev_priv(dev); int i; int err; team->dev = dev; team_set_no_mode(team); team->notifier_ctx = false; team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) return -ENOMEM; for (i = 0; i < TEAM_PORT_HASHENTRIES; i++) INIT_HLIST_HEAD(&team->en_port_hlist[i]); INIT_LIST_HEAD(&team->port_list); err = team_queue_override_init(team); if (err) goto err_team_queue_override_init; team_adjust_ops(team); INIT_LIST_HEAD(&team->option_list); INIT_LIST_HEAD(&team->option_inst_list); team_notify_peers_init(team); team_mcast_rejoin_init(team); err = team_options_register(team, team_options, ARRAY_SIZE(team_options)); if (err) goto err_options_register; netif_carrier_off(dev); lockdep_register_key(&team->team_lock_key); __mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key); netdev_lockdep_set_classes(dev); return 0; err_options_register: team_mcast_rejoin_fini(team); team_notify_peers_fini(team); team_queue_override_fini(team); err_team_queue_override_init: free_percpu(team->pcpu_stats); return err; } static void team_uninit(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; struct team_port *tmp; mutex_lock(&team->lock); list_for_each_entry_safe(port, tmp, &team->port_list, list) team_port_del(team, port->dev); __team_change_mode(team, NULL); /* cleanup */ __team_options_unregister(team, team_options, ARRAY_SIZE(team_options)); team_mcast_rejoin_fini(team); team_notify_peers_fini(team); team_queue_override_fini(team); mutex_unlock(&team->lock); netdev_change_features(dev); lockdep_unregister_key(&team->team_lock_key); } static void team_destructor(struct net_device *dev) { struct team *team = netdev_priv(dev); free_percpu(team->pcpu_stats); } static int team_open(struct net_device *dev) { return 0; } static int team_close(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; list_for_each_entry(port, &team->port_list, list) { dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); } return 0; } /* * note: already called with rcu_read_lock */ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) { struct team *team = netdev_priv(dev); bool tx_success; unsigned int len = skb->len; tx_success = team_queue_override_transmit(team, skb); if (!tx_success) tx_success = team->ops.transmit(team, skb); if (tx_success) { struct team_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->tx_packets); u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(team->pcpu_stats->tx_dropped); } return NETDEV_TX_OK; } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* * This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to * skb_tx_hash and will put the skbs in the queue we expect on their * way down to the team driver. */ u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; /* * Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; if (unlikely(txq >= dev->real_num_tx_queues)) { do { txq -= dev->real_num_tx_queues; } while (txq >= dev->real_num_tx_queues); } return txq; } static void team_change_rx_flags(struct net_device *dev, int change) { struct team *team = netdev_priv(dev); struct team_port *port; int inc; mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { if (change & IFF_PROMISC) { inc = dev->flags & IFF_PROMISC ? 1 : -1; dev_set_promiscuity(port->dev, inc); } if (change & IFF_ALLMULTI) { inc = dev->flags & IFF_ALLMULTI ? 1 : -1; dev_set_allmulti(port->dev, inc); } } mutex_unlock(&team->lock); } static void team_set_rx_mode(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { dev_uc_sync_multiple(port->dev, dev); dev_mc_sync_multiple(port->dev, dev); } rcu_read_unlock(); } static int team_set_mac_address(struct net_device *dev, void *p) { struct sockaddr *addr = p; struct team *team = netdev_priv(dev); struct team_port *port; if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; dev_addr_set(dev, addr->sa_data); mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) if (team->ops.port_change_dev_addr) team->ops.port_change_dev_addr(team, port); mutex_unlock(&team->lock); return 0; } static int team_change_mtu(struct net_device *dev, int new_mtu) { struct team *team = netdev_priv(dev); struct team_port *port; int err; /* * Alhough this is reader, it's guarded by team lock. It's not possible * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); team->port_mtu_change_allowed = true; list_for_each_entry(port, &team->port_list, list) { err = dev_set_mtu(port->dev, new_mtu); if (err) { netdev_err(dev, "Device %s failed to change mtu", port->dev->name); goto unwind; } } team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); WRITE_ONCE(dev->mtu, new_mtu); return 0; unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) dev_set_mtu(port->dev, dev->mtu); team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); return err; } static void team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct team *team = netdev_priv(dev); struct team_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_dropped = 0, tx_dropped = 0, rx_nohandler = 0; unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(team->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); rx_multicast = u64_stats_read(&p->rx_multicast); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; stats->multicast += rx_multicast; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* * rx_dropped, tx_dropped & rx_nohandler are u32, * updated without syncp protection. */ rx_dropped += READ_ONCE(p->rx_dropped); tx_dropped += READ_ONCE(p->tx_dropped); rx_nohandler += READ_ONCE(p->rx_nohandler); } stats->rx_dropped = rx_dropped; stats->tx_dropped = tx_dropped; stats->rx_nohandler = rx_nohandler; } static int team_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct team *team = netdev_priv(dev); struct team_port *port; int err; /* * Alhough this is reader, it's guarded by team lock. It's not possible * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { err = vlan_vid_add(port->dev, proto, vid); if (err) goto unwind; } mutex_unlock(&team->lock); return 0; unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); mutex_unlock(&team->lock); return err; } static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct team *team = netdev_priv(dev); struct team_port *port; mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); mutex_unlock(&team->lock); return 0; } #ifdef CONFIG_NET_POLL_CONTROLLER static void team_poll_controller(struct net_device *dev) { } static void __team_netpoll_cleanup(struct team *team) { struct team_port *port; list_for_each_entry(port, &team->port_list, list) team_port_disable_netpoll(port); } static void team_netpoll_cleanup(struct net_device *dev) { struct team *team = netdev_priv(dev); mutex_lock(&team->lock); __team_netpoll_cleanup(team); mutex_unlock(&team->lock); } static int team_netpoll_setup(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; int err = 0; mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { err = __team_port_enable_netpoll(port); if (err) { __team_netpoll_cleanup(team); break; } } mutex_unlock(&team->lock); return err; } #endif static int team_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { struct team *team = netdev_priv(dev); int err; mutex_lock(&team->lock); err = team_port_add(team, port_dev, extack); mutex_unlock(&team->lock); if (!err) netdev_change_features(dev); return err; } static int team_del_slave(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); int err; mutex_lock(&team->lock); err = team_port_del(team, port_dev); mutex_unlock(&team->lock); if (err) return err; if (netif_is_team_master(port_dev)) { lockdep_unregister_key(&team->team_lock_key); lockdep_register_key(&team->team_lock_key); lockdep_set_class(&team->lock, &team->team_lock_key); } netdev_change_features(dev); return err; } static netdev_features_t team_fix_features(struct net_device *dev, netdev_features_t features) { struct team_port *port; struct team *team = netdev_priv(dev); netdev_features_t mask; mask = features; features = netdev_base_features(features); rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { features = netdev_increment_features(features, port->dev->features, mask); } rcu_read_unlock(); features = netdev_add_tso_features(features, mask); return features; } static int team_change_carrier(struct net_device *dev, bool new_carrier) { struct team *team = netdev_priv(dev); team->user_carrier_enabled = true; if (new_carrier) netif_carrier_on(dev); else netif_carrier_off(dev); return 0; } static const struct net_device_ops team_netdev_ops = { .ndo_init = team_init, .ndo_uninit = team_uninit, .ndo_open = team_open, .ndo_stop = team_close, .ndo_start_xmit = team_xmit, .ndo_select_queue = team_select_queue, .ndo_change_rx_flags = team_change_rx_flags, .ndo_set_rx_mode = team_set_rx_mode, .ndo_set_mac_address = team_set_mac_address, .ndo_change_mtu = team_change_mtu, .ndo_get_stats64 = team_get_stats64, .ndo_vlan_rx_add_vid = team_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = team_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = team_poll_controller, .ndo_netpoll_setup = team_netpoll_setup, .ndo_netpoll_cleanup = team_netpoll_cleanup, #endif .ndo_add_slave = team_add_slave, .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, .ndo_features_check = passthru_features_check, }; /*********************** * ethtool interface ***********************/ static void team_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); } static int team_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct team *team= netdev_priv(dev); unsigned long speed = 0; struct team_port *port; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { if (team_port_txable(port)) { if (port->state.speed != SPEED_UNKNOWN) speed += port->state.speed; if (cmd->base.duplex == DUPLEX_UNKNOWN && port->state.duplex != DUPLEX_UNKNOWN) cmd->base.duplex = port->state.duplex; } } rcu_read_unlock(); cmd->base.speed = speed ? : SPEED_UNKNOWN; return 0; } static const struct ethtool_ops team_ethtool_ops = { .get_drvinfo = team_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = team_ethtool_get_link_ksettings, }; /*********************** * rt netlink interface ***********************/ static void team_setup_by_port(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); if (port_dev->type == ARPHRD_ETHER) dev->header_ops = team->header_ops_cache; else dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; dev->needed_headroom = port_dev->needed_headroom; dev->addr_len = port_dev->addr_len; dev->mtu = port_dev->mtu; memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len); eth_hw_addr_inherit(dev, port_dev); if (port_dev->flags & IFF_POINTOPOINT) { dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } else if ((port_dev->flags & (IFF_BROADCAST | IFF_MULTICAST)) == (IFF_BROADCAST | IFF_MULTICAST)) { dev->flags |= (IFF_BROADCAST | IFF_MULTICAST); dev->flags &= ~(IFF_POINTOPOINT | IFF_NOARP); } } static int team_dev_type_check_change(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); char *portname = port_dev->name; int err; if (dev->type == port_dev->type) return 0; if (!list_empty(&team->port_list)) { netdev_err(dev, "Device %s is of different type\n", portname); return -EBUSY; } err = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, dev); err = notifier_to_errno(err); if (err) { netdev_err(dev, "Refused to change device type\n"); return err; } dev_uc_flush(dev); dev_mc_flush(dev); team_setup_by_port(dev, port_dev); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); return 0; } static void team_setup(struct net_device *dev) { struct team *team = netdev_priv(dev); ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; team->header_ops_cache = dev->header_ops; dev->netdev_ops = &team_netdev_ops; dev->ethtool_ops = &team_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = team_destructor; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_TEAM; /* * Indicate we support unicast address filtering. That way core won't * bring us to promisc mode in case a unicast addr is added. * Let this up to underlay drivers. */ dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; dev->lltx = true; /* Don't allow team devices to change network namespaces. */ dev->netns_immutable = true; dev->features |= NETIF_F_GRO; dev->hw_features = TEAM_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_FILTER; dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } static int team_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **tb = params->tb; if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); return register_netdevice(dev); } static int team_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static unsigned int team_get_num_tx_queues(void) { return TEAM_DEFAULT_NUM_TX_QUEUES; } static unsigned int team_get_num_rx_queues(void) { return TEAM_DEFAULT_NUM_RX_QUEUES; } static struct rtnl_link_ops team_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct team), .setup = team_setup, .newlink = team_newlink, .validate = team_validate, .get_num_tx_queues = team_get_num_tx_queues, .get_num_rx_queues = team_get_num_rx_queues, }; /*********************************** * Generic netlink custom interface ***********************************/ static struct genl_family team_nl_family; int team_nl_noop_doit(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; void *hdr; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &team_nl_family, 0, TEAM_CMD_NOOP); if (!hdr) { err = -EMSGSIZE; goto err_msg_put; } genlmsg_end(msg, hdr); return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); err_msg_put: nlmsg_free(msg); return err; } /* * Netlink cmd functions should be locked by following two functions. * Since dev gets held here, that ensures dev won't disappear in between. */ static struct team *team_nl_team_get(struct genl_info *info) { struct net *net = genl_info_net(info); int ifindex; struct net_device *dev; struct team *team; if (!info->attrs[TEAM_ATTR_TEAM_IFINDEX]) return NULL; ifindex = nla_get_u32(info->attrs[TEAM_ATTR_TEAM_IFINDEX]); dev = dev_get_by_index(net, ifindex); if (!dev || dev->netdev_ops != &team_netdev_ops) { dev_put(dev); return NULL; } team = netdev_priv(dev); mutex_lock(&team->lock); return team; } static void team_nl_team_put(struct team *team) { mutex_unlock(&team->lock); dev_put(team->dev); } typedef int team_nl_send_func_t(struct sk_buff *skb, struct team *team, u32 portid); static int team_nl_send_unicast(struct sk_buff *skb, struct team *team, u32 portid) { return genlmsg_unicast(dev_net(team->dev), skb, portid); } static int team_nl_fill_one_option_get(struct sk_buff *skb, struct team *team, struct team_option_inst *opt_inst) { struct nlattr *option_item; struct team_option *option = opt_inst->option; struct team_option_inst_info *opt_inst_info = &opt_inst->info; struct team_gsetter_ctx ctx; int err; ctx.info = opt_inst_info; err = team_option_get(team, opt_inst, &ctx); if (err) return err; option_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_OPTION); if (!option_item) return -EMSGSIZE; if (nla_put_string(skb, TEAM_ATTR_OPTION_NAME, option->name)) goto nest_cancel; if (opt_inst_info->port && nla_put_u32(skb, TEAM_ATTR_OPTION_PORT_IFINDEX, opt_inst_info->port->dev->ifindex)) goto nest_cancel; if (opt_inst->option->array_size && nla_put_u32(skb, TEAM_ATTR_OPTION_ARRAY_INDEX, opt_inst_info->array_index)) goto nest_cancel; switch (option->type) { case TEAM_OPTION_TYPE_U32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32)) goto nest_cancel; if (nla_put_u32(skb, TEAM_ATTR_OPTION_DATA, ctx.data.u32_val)) goto nest_cancel; break; case TEAM_OPTION_TYPE_STRING: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_STRING)) goto nest_cancel; if (nla_put_string(skb, TEAM_ATTR_OPTION_DATA, ctx.data.str_val)) goto nest_cancel; break; case TEAM_OPTION_TYPE_BINARY: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_BINARY)) goto nest_cancel; if (nla_put(skb, TEAM_ATTR_OPTION_DATA, ctx.data.bin_val.len, ctx.data.bin_val.ptr)) goto nest_cancel; break; case TEAM_OPTION_TYPE_BOOL: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_FLAG)) goto nest_cancel; if (ctx.data.bool_val && nla_put_flag(skb, TEAM_ATTR_OPTION_DATA)) goto nest_cancel; break; case TEAM_OPTION_TYPE_S32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_S32)) goto nest_cancel; if (nla_put_s32(skb, TEAM_ATTR_OPTION_DATA, ctx.data.s32_val)) goto nest_cancel; break; default: BUG(); } if (opt_inst->removed && nla_put_flag(skb, TEAM_ATTR_OPTION_REMOVED)) goto nest_cancel; if (opt_inst->changed) { if (nla_put_flag(skb, TEAM_ATTR_OPTION_CHANGED)) goto nest_cancel; opt_inst->changed = false; } nla_nest_end(skb, option_item); return 0; nest_cancel: nla_nest_cancel(skb, option_item); return -EMSGSIZE; } static int __send_and_alloc_skb(struct sk_buff **pskb, struct team *team, u32 portid, team_nl_send_func_t *send_func) { int err; if (*pskb) { err = send_func(*pskb, team, portid); if (err) return err; } *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!*pskb) return -ENOMEM; return 0; } static int team_nl_send_options_get(struct team *team, u32 portid, u32 seq, int flags, team_nl_send_func_t *send_func, struct list_head *sel_opt_inst_list) { struct nlattr *option_list; struct nlmsghdr *nlh; void *hdr; struct team_option_inst *opt_inst; int err; struct sk_buff *skb = NULL; bool incomplete; int i; opt_inst = list_first_entry(sel_opt_inst_list, struct team_option_inst, tmp_list); start_again: err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_OPTIONS_GET); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; option_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_OPTION); if (!option_list) goto nla_put_failure; i = 0; incomplete = false; list_for_each_entry_from(opt_inst, sel_opt_inst_list, tmp_list) { err = team_nl_fill_one_option_get(skb, team, opt_inst); if (err) { if (err == -EMSGSIZE) { if (!i) goto errout; incomplete = true; break; } goto errout; } i++; } nla_nest_end(skb, option_list); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, portid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; goto send_done; } return send_func(skb, team, portid); nla_put_failure: err = -EMSGSIZE; errout: nlmsg_free(skb); return err; } int team_nl_options_get_doit(struct sk_buff *skb, struct genl_info *info) { struct team *team; struct team_option_inst *opt_inst; int err; LIST_HEAD(sel_opt_inst_list); team = team_nl_team_get(info); if (!team) return -EINVAL; list_for_each_entry(opt_inst, &team->option_inst_list, list) list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); err = team_nl_send_options_get(team, info->snd_portid, info->snd_seq, NLM_F_ACK, team_nl_send_unicast, &sel_opt_inst_list); team_nl_team_put(team); return err; } static int team_nl_send_event_options_get(struct team *team, struct list_head *sel_opt_inst_list); int team_nl_options_set_doit(struct sk_buff *skb, struct genl_info *info) { struct team *team; int err = 0; int i; struct nlattr *nl_option; rtnl_lock(); team = team_nl_team_get(info); if (!team) { err = -EINVAL; goto rtnl_unlock; } err = -EINVAL; if (!info->attrs[TEAM_ATTR_LIST_OPTION]) { err = -EINVAL; goto team_put; } nla_for_each_nested(nl_option, info->attrs[TEAM_ATTR_LIST_OPTION], i) { struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; struct nlattr *attr; struct nlattr *attr_data; LIST_HEAD(opt_inst_list); enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ u32 opt_array_index = 0; bool opt_is_array = false; struct team_option_inst *opt_inst; char *opt_name; bool opt_found = false; if (nla_type(nl_option) != TEAM_ATTR_ITEM_OPTION) { err = -EINVAL; goto team_put; } err = nla_parse_nested_deprecated(opt_attrs, TEAM_ATTR_OPTION_MAX, nl_option, team_attr_option_nl_policy, info->extack); if (err) goto team_put; if (!opt_attrs[TEAM_ATTR_OPTION_NAME] || !opt_attrs[TEAM_ATTR_OPTION_TYPE]) { err = -EINVAL; goto team_put; } switch (nla_get_u8(opt_attrs[TEAM_ATTR_OPTION_TYPE])) { case NLA_U32: opt_type = TEAM_OPTION_TYPE_U32; break; case NLA_STRING: opt_type = TEAM_OPTION_TYPE_STRING; break; case NLA_BINARY: opt_type = TEAM_OPTION_TYPE_BINARY; break; case NLA_FLAG: opt_type = TEAM_OPTION_TYPE_BOOL; break; case NLA_S32: opt_type = TEAM_OPTION_TYPE_S32; break; default: goto team_put; } attr_data = opt_attrs[TEAM_ATTR_OPTION_DATA]; if (opt_type != TEAM_OPTION_TYPE_BOOL && !attr_data) { err = -EINVAL; goto team_put; } opt_name = nla_data(opt_attrs[TEAM_ATTR_OPTION_NAME]); attr = opt_attrs[TEAM_ATTR_OPTION_PORT_IFINDEX]; if (attr) opt_port_ifindex = nla_get_u32(attr); attr = opt_attrs[TEAM_ATTR_OPTION_ARRAY_INDEX]; if (attr) { opt_is_array = true; opt_array_index = nla_get_u32(attr); } list_for_each_entry(opt_inst, &team->option_inst_list, list) { struct team_option *option = opt_inst->option; struct team_gsetter_ctx ctx; struct team_option_inst_info *opt_inst_info; int tmp_ifindex; opt_inst_info = &opt_inst->info; tmp_ifindex = opt_inst_info->port ? opt_inst_info->port->dev->ifindex : 0; if (option->type != opt_type || strcmp(option->name, opt_name) || tmp_ifindex != opt_port_ifindex || (option->array_size && !opt_is_array) || opt_inst_info->array_index != opt_array_index) continue; opt_found = true; ctx.info = opt_inst_info; switch (opt_type) { case TEAM_OPTION_TYPE_U32: ctx.data.u32_val = nla_get_u32(attr_data); break; case TEAM_OPTION_TYPE_STRING: if (nla_len(attr_data) > TEAM_STRING_MAX_LEN || !memchr(nla_data(attr_data), '\0', nla_len(attr_data))) { err = -EINVAL; goto team_put; } ctx.data.str_val = nla_data(attr_data); break; case TEAM_OPTION_TYPE_BINARY: ctx.data.bin_val.len = nla_len(attr_data); ctx.data.bin_val.ptr = nla_data(attr_data); break; case TEAM_OPTION_TYPE_BOOL: ctx.data.bool_val = attr_data ? true : false; break; case TEAM_OPTION_TYPE_S32: ctx.data.s32_val = nla_get_s32(attr_data); break; default: BUG(); } err = team_option_set(team, opt_inst, &ctx); if (err) goto team_put; opt_inst->changed = true; list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; goto team_put; } err = team_nl_send_event_options_get(team, &opt_inst_list); if (err) break; } team_put: team_nl_team_put(team); rtnl_unlock: rtnl_unlock(); return err; } static int team_nl_fill_one_port_get(struct sk_buff *skb, struct team_port *port) { struct nlattr *port_item; port_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_PORT); if (!port_item) goto nest_cancel; if (nla_put_u32(skb, TEAM_ATTR_PORT_IFINDEX, port->dev->ifindex)) goto nest_cancel; if (port->changed) { if (nla_put_flag(skb, TEAM_ATTR_PORT_CHANGED)) goto nest_cancel; port->changed = false; } if ((port->removed && nla_put_flag(skb, TEAM_ATTR_PORT_REMOVED)) || (port->state.linkup && nla_put_flag(skb, TEAM_ATTR_PORT_LINKUP)) || nla_put_u32(skb, TEAM_ATTR_PORT_SPEED, port->state.speed) || nla_put_u8(skb, TEAM_ATTR_PORT_DUPLEX, port->state.duplex)) goto nest_cancel; nla_nest_end(skb, port_item); return 0; nest_cancel: nla_nest_cancel(skb, port_item); return -EMSGSIZE; } static int team_nl_send_port_list_get(struct team *team, u32 portid, u32 seq, int flags, team_nl_send_func_t *send_func, struct team_port *one_port) { struct nlattr *port_list; struct nlmsghdr *nlh; void *hdr; struct team_port *port; int err; struct sk_buff *skb = NULL; bool incomplete; int i; port = list_first_entry_or_null(&team->port_list, struct team_port, list); start_again: err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_PORT_LIST_GET); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; port_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_PORT); if (!port_list) goto nla_put_failure; i = 0; incomplete = false; /* If one port is selected, called wants to send port list containing * only this port. Otherwise go through all listed ports and send all */ if (one_port) { err = team_nl_fill_one_port_get(skb, one_port); if (err) goto errout; } else if (port) { list_for_each_entry_from(port, &team->port_list, list) { err = team_nl_fill_one_port_get(skb, port); if (err) { if (err == -EMSGSIZE) { if (!i) goto errout; incomplete = true; break; } goto errout; } i++; } } nla_nest_end(skb, port_list); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, portid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; goto send_done; } return send_func(skb, team, portid); nla_put_failure: err = -EMSGSIZE; errout: nlmsg_free(skb); return err; } int team_nl_port_list_get_doit(struct sk_buff *skb, struct genl_info *info) { struct team *team; int err; team = team_nl_team_get(info); if (!team) return -EINVAL; err = team_nl_send_port_list_get(team, info->snd_portid, info->snd_seq, NLM_F_ACK, team_nl_send_unicast, NULL); team_nl_team_put(team); return err; } static const struct genl_multicast_group team_nl_mcgrps[] = { { .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME, }, }; static struct genl_family team_nl_family __ro_after_init = { .name = TEAM_GENL_NAME, .version = TEAM_GENL_VERSION, .maxattr = ARRAY_SIZE(team_nl_policy) - 1, .policy = team_nl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = team_nl_ops, .n_small_ops = ARRAY_SIZE(team_nl_ops), .resv_start_op = TEAM_CMD_PORT_LIST_GET + 1, .mcgrps = team_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(team_nl_mcgrps), }; static int team_nl_send_multicast(struct sk_buff *skb, struct team *team, u32 portid) { return genlmsg_multicast_netns(&team_nl_family, dev_net(team->dev), skb, 0, 0, GFP_KERNEL); } static int team_nl_send_event_options_get(struct team *team, struct list_head *sel_opt_inst_list) { return team_nl_send_options_get(team, 0, 0, 0, team_nl_send_multicast, sel_opt_inst_list); } static int team_nl_send_event_port_get(struct team *team, struct team_port *port) { return team_nl_send_port_list_get(team, 0, 0, 0, team_nl_send_multicast, port); } static int __init team_nl_init(void) { return genl_register_family(&team_nl_family); } static void __exit team_nl_fini(void) { genl_unregister_family(&team_nl_family); } /****************** * Change checkers ******************/ static void __team_options_change_check(struct team *team) { int err; struct team_option_inst *opt_inst; LIST_HEAD(sel_opt_inst_list); list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->changed) list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); } err = team_nl_send_event_options_get(team, &sel_opt_inst_list); if (err && err != -ESRCH) netdev_warn(team->dev, "Failed to send options change via netlink (err %d)\n", err); } /* rtnl lock is held */ static void __team_port_change_send(struct team_port *port, bool linkup) { int err; port->changed = true; port->state.linkup = linkup; team_refresh_port_linkup(port); if (linkup) { struct ethtool_link_ksettings ecmd; err = __ethtool_get_link_ksettings(port->dev, &ecmd); if (!err) { port->state.speed = ecmd.base.speed; port->state.duplex = ecmd.base.duplex; goto send_event; } } port->state.speed = 0; port->state.duplex = 0; send_event: err = team_nl_send_event_port_get(port->team, port); if (err && err != -ESRCH) netdev_warn(port->team->dev, "Failed to send port change of device %s via netlink (err %d)\n", port->dev->name, err); } static void __team_carrier_check(struct team *team) { struct team_port *port; bool team_linkup; if (team->user_carrier_enabled) return; team_linkup = false; list_for_each_entry(port, &team->port_list, list) { if (port->linkup) { team_linkup = true; break; } } if (team_linkup) netif_carrier_on(team->dev); else netif_carrier_off(team->dev); } static void __team_port_change_check(struct team_port *port, bool linkup) { if (port->state.linkup != linkup) __team_port_change_send(port, linkup); __team_carrier_check(port->team); } static void __team_port_change_port_added(struct team_port *port, bool linkup) { __team_port_change_send(port, linkup); __team_carrier_check(port->team); } static void __team_port_change_port_removed(struct team_port *port) { port->removed = true; __team_port_change_send(port, false); __team_carrier_check(port->team); } static void team_port_change_check(struct team_port *port, bool linkup) { struct team *team = port->team; mutex_lock(&team->lock); __team_port_change_check(port, linkup); mutex_unlock(&team->lock); } /************************************ * Net device notifier event handler ************************************/ static int team_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct team_port *port; port = team_port_get_rtnl(dev); if (!port) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (netif_oper_up(dev)) team_port_change_check(port, true); break; case NETDEV_DOWN: team_port_change_check(port, false); break; case NETDEV_CHANGE: if (netif_running(port->dev)) team_port_change_check(port, !!netif_oper_up(port->dev)); break; case NETDEV_UNREGISTER: team_del_slave(port->team->dev, dev); break; case NETDEV_FEAT_CHANGE: if (!port->team->notifier_ctx) { port->team->notifier_ctx = true; team_compute_features(port->team); port->team->notifier_ctx = false; } break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ if (!port->team->port_mtu_change_allowed) return NOTIFY_BAD; break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid to change type of underlaying device */ return NOTIFY_BAD; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, port->team->dev); break; } return NOTIFY_DONE; } static struct notifier_block team_notifier_block __read_mostly = { .notifier_call = team_device_event, }; /*********************** * Module init and exit ***********************/ static int __init team_module_init(void) { int err; register_netdevice_notifier(&team_notifier_block); err = rtnl_link_register(&team_link_ops); if (err) goto err_rtnl_reg; err = team_nl_init(); if (err) goto err_nl_init; return 0; err_nl_init: rtnl_link_unregister(&team_link_ops); err_rtnl_reg: unregister_netdevice_notifier(&team_notifier_block); return err; } static void __exit team_module_exit(void) { team_nl_fini(); rtnl_link_unregister(&team_link_ops); unregister_netdevice_notifier(&team_notifier_block); } module_init(team_module_init); module_exit(team_module_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>"); MODULE_DESCRIPTION("Ethernet team device driver"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 193 194 50 50 50 50 50 83 194 193 111 83 83 83 83 111 111 111 111 111 50 50 50 50 50 50 50 50 50 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/resource.c * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 1999 Martin Mares <mj@ucw.cz> * * Arbitrary resource management. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/export.h> #include <linux/errno.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/pseudo_fs.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/device.h> #include <linux/pfn.h> #include <linux/mm.h> #include <linux/mount.h> #include <linux/resource_ext.h> #include <uapi/linux/magic.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <asm/io.h> struct resource ioport_resource = { .name = "PCI IO", .start = 0, .end = IO_SPACE_LIMIT, .flags = IORESOURCE_IO, }; EXPORT_SYMBOL(ioport_resource); struct resource iomem_resource = { .name = "PCI mem", .start = 0, .end = -1, .flags = IORESOURCE_MEM, }; EXPORT_SYMBOL(iomem_resource); static DEFINE_RWLOCK(resource_lock); /* * Return the next node of @p in pre-order tree traversal. If * @skip_children is true, skip the descendant nodes of @p in * traversal. If @p is a descendant of @subtree_root, only traverse * the subtree under @subtree_root. */ static struct resource *next_resource(struct resource *p, bool skip_children, struct resource *subtree_root) { if (!skip_children && p->child) return p->child; while (!p->sibling && p->parent) { p = p->parent; if (p == subtree_root) return NULL; } return p->sibling; } /* * Traverse the resource subtree under @_root in pre-order, excluding * @_root itself. * * NOTE: '__p' is introduced to avoid shadowing '_p' outside of loop. * And it is referenced to avoid unused variable warning. */ #define for_each_resource(_root, _p, _skip_children) \ for (typeof(_root) __root = (_root), __p = _p = __root->child; \ __p && _p; _p = next_resource(_p, _skip_children, __root)) #ifdef CONFIG_PROC_FS enum { MAX_IORES_LEVEL = 5 }; static void *r_start(struct seq_file *m, loff_t *pos) __acquires(resource_lock) { struct resource *root = pde_data(file_inode(m->file)); struct resource *p; loff_t l = *pos; read_lock(&resource_lock); for_each_resource(root, p, false) { if (l-- == 0) break; } return p; } static void *r_next(struct seq_file *m, void *v, loff_t *pos) { struct resource *p = v; (*pos)++; return (void *)next_resource(p, false, NULL); } static void r_stop(struct seq_file *m, void *v) __releases(resource_lock) { read_unlock(&resource_lock); } static int r_show(struct seq_file *m, void *v) { struct resource *root = pde_data(file_inode(m->file)); struct resource *r = v, *p; unsigned long long start, end; int width = root->end < 0x10000 ? 4 : 8; int depth; for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent) if (p->parent == root) break; if (file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) { start = r->start; end = r->end; } else { start = end = 0; } seq_printf(m, "%*s%0*llx-%0*llx : %s\n", depth * 2, "", width, start, width, end, r->name ? r->name : "<BAD>"); return 0; } static const struct seq_operations resource_op = { .start = r_start, .next = r_next, .stop = r_stop, .show = r_show, }; static int __init ioresources_init(void) { proc_create_seq_data("ioports", 0, NULL, &resource_op, &ioport_resource); proc_create_seq_data("iomem", 0, NULL, &resource_op, &iomem_resource); return 0; } __initcall(ioresources_init); #endif /* CONFIG_PROC_FS */ static void free_resource(struct resource *res) { /** * If the resource was allocated using memblock early during boot * we'll leak it here: we can only return full pages back to the * buddy and trying to be smart and reusing them eventually in * alloc_resource() overcomplicates resource handling. */ if (res && PageSlab(virt_to_head_page(res))) kfree(res); } static struct resource *alloc_resource(gfp_t flags) { return kzalloc(sizeof(struct resource), flags); } /* Return the conflict entry if you can't request it */ static struct resource * __request_resource(struct resource *root, struct resource *new) { resource_size_t start = new->start; resource_size_t end = new->end; struct resource *tmp, **p; if (end < start) return root; if (start < root->start) return root; if (end > root->end) return root; p = &root->child; for (;;) { tmp = *p; if (!tmp || tmp->start > end) { new->sibling = tmp; *p = new; new->parent = root; return NULL; } p = &tmp->sibling; if (tmp->end < start) continue; return tmp; } } static int __release_resource(struct resource *old, bool release_child) { struct resource *tmp, **p, *chd; p = &old->parent->child; for (;;) { tmp = *p; if (!tmp) break; if (tmp == old) { if (release_child || !(tmp->child)) { *p = tmp->sibling; } else { for (chd = tmp->child;; chd = chd->sibling) { chd->parent = tmp->parent; if (!(chd->sibling)) break; } *p = tmp->child; chd->sibling = tmp->sibling; } old->parent = NULL; return 0; } p = &tmp->sibling; } return -EINVAL; } static void __release_child_resources(struct resource *r) { struct resource *tmp, *p; resource_size_t size; p = r->child; r->child = NULL; while (p) { tmp = p; p = p->sibling; tmp->parent = NULL; tmp->sibling = NULL; __release_child_resources(tmp); printk(KERN_DEBUG "release child resource %pR\n", tmp); /* need to restore size, and keep flags */ size = resource_size(tmp); tmp->start = 0; tmp->end = size - 1; } } void release_child_resources(struct resource *r) { write_lock(&resource_lock); __release_child_resources(r); write_unlock(&resource_lock); } /** * request_resource_conflict - request and reserve an I/O or memory resource * @root: root resource descriptor * @new: resource descriptor desired by caller * * Returns 0 for success, conflict resource on error. */ struct resource *request_resource_conflict(struct resource *root, struct resource *new) { struct resource *conflict; write_lock(&resource_lock); conflict = __request_resource(root, new); write_unlock(&resource_lock); return conflict; } /** * request_resource - request and reserve an I/O or memory resource * @root: root resource descriptor * @new: resource descriptor desired by caller * * Returns 0 for success, negative error code on error. */ int request_resource(struct resource *root, struct resource *new) { struct resource *conflict; conflict = request_resource_conflict(root, new); return conflict ? -EBUSY : 0; } EXPORT_SYMBOL(request_resource); /** * release_resource - release a previously reserved resource * @old: resource pointer */ int release_resource(struct resource *old) { int retval; write_lock(&resource_lock); retval = __release_resource(old, true); write_unlock(&resource_lock); return retval; } EXPORT_SYMBOL(release_resource); static bool is_type_match(struct resource *p, unsigned long flags, unsigned long desc) { return (p->flags & flags) == flags && (desc == IORES_DESC_NONE || desc == p->desc); } /** * find_next_iomem_res - Finds the lowest iomem resource that covers part of * [@start..@end]. * * If a resource is found, returns 0 and @*res is overwritten with the part * of the resource that's within [@start..@end]; if none is found, returns * -ENODEV. Returns -EINVAL for invalid parameters. * * @start: start address of the resource searched for * @end: end address of same resource * @flags: flags which the resource must have * @desc: descriptor the resource must have * @res: return ptr, if resource found * * The caller must specify @start, @end, @flags, and @desc * (which may be IORES_DESC_NONE). */ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, struct resource *res) { struct resource *p; if (!res) return -EINVAL; if (start >= end) return -EINVAL; read_lock(&resource_lock); for_each_resource(&iomem_resource, p, false) { /* If we passed the resource we are looking for, stop */ if (p->start > end) { p = NULL; break; } /* Skip until we find a range that matches what we look for */ if (p->end < start) continue; /* Found a match, break */ if (is_type_match(p, flags, desc)) break; } if (p) { /* copy data */ *res = (struct resource) { .start = max(start, p->start), .end = min(end, p->end), .flags = p->flags, .desc = p->desc, .parent = p->parent, }; } read_unlock(&resource_lock); return p ? 0 : -ENODEV; } static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, void *arg, int (*func)(struct resource *, void *)) { struct resource res; int ret = -EINVAL; while (start < end && !find_next_iomem_res(start, end, flags, desc, &res)) { ret = (*func)(&res, arg); if (ret) break; start = res.end + 1; } return ret; } /** * walk_iomem_res_desc - Walks through iomem resources and calls func() * with matching resource ranges. * * * @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check. * @flags: I/O resource flags * @start: start addr * @end: end addr * @arg: function argument for the callback @func * @func: callback function that is called for each qualifying resource area * * All the memory ranges which overlap start,end and also match flags and * desc are valid candidates. * * NOTE: For a new descriptor search, define a new IORES_DESC in * <linux/ioport.h> and set it in 'desc' of a target resource entry. */ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)) { return __walk_iomem_res_desc(start, end, flags, desc, arg, func); } EXPORT_SYMBOL_GPL(walk_iomem_res_desc); /* * This function calls the @func callback against all memory ranges of type * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. * Now, this function is only for System RAM, it deals with full ranges and * not PFNs. If resources are not PFN-aligned, dealing with PFNs can truncate * ranges. */ int walk_system_ram_res(u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)) { unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, arg, func); } /* * This function, being a variant of walk_system_ram_res(), calls the @func * callback against all memory ranges of type System RAM which are marked as * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from * higher to lower. */ int walk_system_ram_res_rev(u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)) { struct resource res, *rams; int rams_size = 16, i; unsigned long flags; int ret = -1; /* create a list */ rams = kvcalloc(rams_size, sizeof(struct resource), GFP_KERNEL); if (!rams) return ret; flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; i = 0; while ((start < end) && (!find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res))) { if (i >= rams_size) { /* re-alloc */ struct resource *rams_new; rams_new = kvrealloc(rams, (rams_size + 16) * sizeof(struct resource), GFP_KERNEL); if (!rams_new) goto out; rams = rams_new; rams_size += 16; } rams[i++] = res; start = res.end + 1; } /* go reverse */ for (i--; i >= 0; i--) { ret = (*func)(&rams[i], arg); if (ret) break; } out: kvfree(rams); return ret; } /* * This function calls the @func callback against all memory ranges, which * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY. */ int walk_mem_res(u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)) { unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY; return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, arg, func); } /* * This function calls the @func callback against all memory ranges of type * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. * It is to be used only for System RAM. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) { resource_size_t start, end; unsigned long flags; struct resource res; unsigned long pfn, end_pfn; int ret = -EINVAL; start = (u64) start_pfn << PAGE_SHIFT; end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; while (start < end && !find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res)) { pfn = PFN_UP(res.start); end_pfn = PFN_DOWN(res.end + 1); if (end_pfn > pfn) ret = (*func)(pfn, end_pfn - pfn, arg); if (ret) break; start = res.end + 1; } return ret; } static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) { return 1; } /* * This generic page_is_ram() returns true if specified address is * registered as System RAM in iomem_resource list. */ int __weak page_is_ram(unsigned long pfn) { return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1; } EXPORT_SYMBOL_GPL(page_is_ram); static int __region_intersects(struct resource *parent, resource_size_t start, size_t size, unsigned long flags, unsigned long desc) { int type = 0; int other = 0; struct resource *p, *dp; struct resource res, o; bool covered; res = DEFINE_RES(start, size, 0); for (p = parent->child; p ; p = p->sibling) { if (!resource_intersection(p, &res, &o)) continue; if (is_type_match(p, flags, desc)) { type++; continue; } /* * Continue to search in descendant resources as if the * matched descendant resources cover some ranges of 'p'. * * |------------- "CXL Window 0" ------------| * |-- "System RAM" --| * * will behave similar as the following fake resource * tree when searching "System RAM". * * |-- "System RAM" --||-- "CXL Window 0a" --| */ covered = false; for_each_resource(p, dp, false) { if (!resource_overlaps(dp, &res)) continue; if (is_type_match(dp, flags, desc)) { type++; /* * Range from 'o.start' to 'dp->start' * isn't covered by matched resource. */ if (dp->start > o.start) break; if (dp->end >= o.end) { covered = true; break; } /* Remove covered range */ o.start = max(o.start, dp->end + 1); } } if (!covered) other++; } if (type == 0) return REGION_DISJOINT; if (other == 0) return REGION_INTERSECTS; return REGION_MIXED; } /** * region_intersects() - determine intersection of region with known resources * @start: region start address * @size: size of region * @flags: flags of resource (in iomem_resource) * @desc: descriptor of resource (in iomem_resource) or IORES_DESC_NONE * * Check if the specified region partially overlaps or fully eclipses a * resource identified by @flags and @desc (optional with IORES_DESC_NONE). * Return REGION_DISJOINT if the region does not overlap @flags/@desc, * return REGION_MIXED if the region overlaps @flags/@desc and another * resource, and return REGION_INTERSECTS if the region overlaps @flags/@desc * and no other defined resource. Note that REGION_INTERSECTS is also * returned in the case when the specified region overlaps RAM and undefined * memory holes. * * region_intersect() is used by memory remapping functions to ensure * the user is not remapping RAM and is a vast speed up over walking * through the resource table page by page. */ int region_intersects(resource_size_t start, size_t size, unsigned long flags, unsigned long desc) { int ret; read_lock(&resource_lock); ret = __region_intersects(&iomem_resource, start, size, flags, desc); read_unlock(&resource_lock); return ret; } EXPORT_SYMBOL_GPL(region_intersects); void __weak arch_remove_reservations(struct resource *avail) { } static void resource_clip(struct resource *res, resource_size_t min, resource_size_t max) { if (res->start < min) res->start = min; if (res->end > max) res->end = max; } /* * Find empty space in the resource tree with the given range and * alignment constraints */ static int __find_resource_space(struct resource *root, struct resource *old, struct resource *new, resource_size_t size, struct resource_constraint *constraint) { struct resource *this = root->child; struct resource tmp = *new, avail, alloc; resource_alignf alignf = constraint->alignf; tmp.start = root->start; /* * Skip past an allocated resource that starts at 0, since the assignment * of this->start - 1 to tmp->end below would cause an underflow. */ if (this && this->start == root->start) { tmp.start = (this == old) ? old->start : this->end + 1; this = this->sibling; } for(;;) { if (this) tmp.end = (this == old) ? this->end : this->start - 1; else tmp.end = root->end; if (tmp.end < tmp.start) goto next; resource_clip(&tmp, constraint->min, constraint->max); arch_remove_reservations(&tmp); /* Check for overflow after ALIGN() */ avail.start = ALIGN(tmp.start, constraint->align); avail.end = tmp.end; avail.flags = new->flags & ~IORESOURCE_UNSET; if (avail.start >= tmp.start) { alloc.flags = avail.flags; if (alignf) { alloc.start = alignf(constraint->alignf_data, &avail, size, constraint->align); } else { alloc.start = avail.start; } alloc.end = alloc.start + size - 1; if (alloc.start <= alloc.end && resource_contains(&avail, &alloc)) { new->start = alloc.start; new->end = alloc.end; return 0; } } next: if (!this || this->end == root->end) break; if (this != old) tmp.start = this->end + 1; this = this->sibling; } return -EBUSY; } /** * find_resource_space - Find empty space in the resource tree * @root: Root resource descriptor * @new: Resource descriptor awaiting an empty resource space * @size: The minimum size of the empty space * @constraint: The range and alignment constraints to be met * * Finds an empty space under @root in the resource tree satisfying range and * alignment @constraints. * * Return: * * %0 - if successful, @new members start, end, and flags are altered. * * %-EBUSY - if no empty space was found. */ int find_resource_space(struct resource *root, struct resource *new, resource_size_t size, struct resource_constraint *constraint) { return __find_resource_space(root, NULL, new, size, constraint); } EXPORT_SYMBOL_GPL(find_resource_space); /** * reallocate_resource - allocate a slot in the resource tree given range & alignment. * The resource will be relocated if the new size cannot be reallocated in the * current location. * * @root: root resource descriptor * @old: resource descriptor desired by caller * @newsize: new size of the resource descriptor * @constraint: the memory range and alignment constraints to be met. */ static int reallocate_resource(struct resource *root, struct resource *old, resource_size_t newsize, struct resource_constraint *constraint) { int err=0; struct resource new = *old; struct resource *conflict; write_lock(&resource_lock); if ((err = __find_resource_space(root, old, &new, newsize, constraint))) goto out; if (resource_contains(&new, old)) { old->start = new.start; old->end = new.end; goto out; } if (old->child) { err = -EBUSY; goto out; } if (resource_contains(old, &new)) { old->start = new.start; old->end = new.end; } else { __release_resource(old, true); *old = new; conflict = __request_resource(root, old); BUG_ON(conflict); } out: write_unlock(&resource_lock); return err; } /** * allocate_resource - allocate empty slot in the resource tree given range & alignment. * The resource will be reallocated with a new size if it was already allocated * @root: root resource descriptor * @new: resource descriptor desired by caller * @size: requested resource region size * @min: minimum boundary to allocate * @max: maximum boundary to allocate * @align: alignment requested, in bytes * @alignf: alignment function, optional, called if not NULL * @alignf_data: arbitrary data to pass to the @alignf function */ int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, resource_size_t max, resource_size_t align, resource_alignf alignf, void *alignf_data) { int err; struct resource_constraint constraint; constraint.min = min; constraint.max = max; constraint.align = align; constraint.alignf = alignf; constraint.alignf_data = alignf_data; if ( new->parent ) { /* resource is already allocated, try reallocating with the new constraints */ return reallocate_resource(root, new, size, &constraint); } write_lock(&resource_lock); err = find_resource_space(root, new, size, &constraint); if (err >= 0 && __request_resource(root, new)) err = -EBUSY; write_unlock(&resource_lock); return err; } EXPORT_SYMBOL(allocate_resource); /** * lookup_resource - find an existing resource by a resource start address * @root: root resource descriptor * @start: resource start address * * Returns a pointer to the resource if found, NULL otherwise */ struct resource *lookup_resource(struct resource *root, resource_size_t start) { struct resource *res; read_lock(&resource_lock); for (res = root->child; res; res = res->sibling) { if (res->start == start) break; } read_unlock(&resource_lock); return res; } /* * Insert a resource into the resource tree. If successful, return NULL, * otherwise return the conflicting resource (compare to __request_resource()) */ static struct resource * __insert_resource(struct resource *parent, struct resource *new) { struct resource *first, *next; for (;; parent = first) { first = __request_resource(parent, new); if (!first) return first; if (first == parent) return first; if (WARN_ON(first == new)) /* duplicated insertion */ return first; if ((first->start > new->start) || (first->end < new->end)) break; if ((first->start == new->start) && (first->end == new->end)) break; } for (next = first; ; next = next->sibling) { /* Partial overlap? Bad, and unfixable */ if (next->start < new->start || next->end > new->end) return next; if (!next->sibling) break; if (next->sibling->start > new->end) break; } new->parent = parent; new->sibling = next->sibling; new->child = first; next->sibling = NULL; for (next = first; next; next = next->sibling) next->parent = new; if (parent->child == first) { parent->child = new; } else { next = parent->child; while (next->sibling != first) next = next->sibling; next->sibling = new; } return NULL; } /** * insert_resource_conflict - Inserts resource in the resource tree * @parent: parent of the new resource * @new: new resource to insert * * Returns 0 on success, conflict resource if the resource can't be inserted. * * This function is equivalent to request_resource_conflict when no conflict * happens. If a conflict happens, and the conflicting resources * entirely fit within the range of the new resource, then the new * resource is inserted and the conflicting resources become children of * the new resource. * * This function is intended for producers of resources, such as FW modules * and bus drivers. */ struct resource *insert_resource_conflict(struct resource *parent, struct resource *new) { struct resource *conflict; write_lock(&resource_lock); conflict = __insert_resource(parent, new); write_unlock(&resource_lock); return conflict; } /** * insert_resource - Inserts a resource in the resource tree * @parent: parent of the new resource * @new: new resource to insert * * Returns 0 on success, -EBUSY if the resource can't be inserted. * * This function is intended for producers of resources, such as FW modules * and bus drivers. */ int insert_resource(struct resource *parent, struct resource *new) { struct resource *conflict; conflict = insert_resource_conflict(parent, new); return conflict ? -EBUSY : 0; } EXPORT_SYMBOL_GPL(insert_resource); /** * insert_resource_expand_to_fit - Insert a resource into the resource tree * @root: root resource descriptor * @new: new resource to insert * * Insert a resource into the resource tree, possibly expanding it in order * to make it encompass any conflicting resources. */ void insert_resource_expand_to_fit(struct resource *root, struct resource *new) { if (new->parent) return; write_lock(&resource_lock); for (;;) { struct resource *conflict; conflict = __insert_resource(root, new); if (!conflict) break; if (conflict == root) break; /* Ok, expand resource to cover the conflict, then try again .. */ if (conflict->start < new->start) new->start = conflict->start; if (conflict->end > new->end) new->end = conflict->end; pr_info("Expanded resource %s due to conflict with %s\n", new->name, conflict->name); } write_unlock(&resource_lock); } /* * Not for general consumption, only early boot memory map parsing, PCI * resource discovery, and late discovery of CXL resources are expected * to use this interface. The former are built-in and only the latter, * CXL, is a module. */ EXPORT_SYMBOL_NS_GPL(insert_resource_expand_to_fit, "CXL"); /** * remove_resource - Remove a resource in the resource tree * @old: resource to remove * * Returns 0 on success, -EINVAL if the resource is not valid. * * This function removes a resource previously inserted by insert_resource() * or insert_resource_conflict(), and moves the children (if any) up to * where they were before. insert_resource() and insert_resource_conflict() * insert a new resource, and move any conflicting resources down to the * children of the new resource. * * insert_resource(), insert_resource_conflict() and remove_resource() are * intended for producers of resources, such as FW modules and bus drivers. */ int remove_resource(struct resource *old) { int retval; write_lock(&resource_lock); retval = __release_resource(old, false); write_unlock(&resource_lock); return retval; } EXPORT_SYMBOL_GPL(remove_resource); static int __adjust_resource(struct resource *res, resource_size_t start, resource_size_t size) { struct resource *tmp, *parent = res->parent; resource_size_t end = start + size - 1; int result = -EBUSY; if (!parent) goto skip; if ((start < parent->start) || (end > parent->end)) goto out; if (res->sibling && (res->sibling->start <= end)) goto out; tmp = parent->child; if (tmp != res) { while (tmp->sibling != res) tmp = tmp->sibling; if (start <= tmp->end) goto out; } skip: for (tmp = res->child; tmp; tmp = tmp->sibling) if ((tmp->start < start) || (tmp->end > end)) goto out; res->start = start; res->end = end; result = 0; out: return result; } /** * adjust_resource - modify a resource's start and size * @res: resource to modify * @start: new start value * @size: new size * * Given an existing resource, change its start and size to match the * arguments. Returns 0 on success, -EBUSY if it can't fit. * Existing children of the resource are assumed to be immutable. */ int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size) { int result; write_lock(&resource_lock); result = __adjust_resource(res, start, size); write_unlock(&resource_lock); return result; } EXPORT_SYMBOL(adjust_resource); static void __init __reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name) { struct resource *parent = root; struct resource *conflict; struct resource *res = alloc_resource(GFP_ATOMIC); struct resource *next_res = NULL; int type = resource_type(root); if (!res) return; res->name = name; res->start = start; res->end = end; res->flags = type | IORESOURCE_BUSY; res->desc = IORES_DESC_NONE; while (1) { conflict = __request_resource(parent, res); if (!conflict) { if (!next_res) break; res = next_res; next_res = NULL; continue; } /* conflict covered whole area */ if (conflict->start <= res->start && conflict->end >= res->end) { free_resource(res); WARN_ON(next_res); break; } /* failed, split and try again */ if (conflict->start > res->start) { end = res->end; res->end = conflict->start - 1; if (conflict->end < end) { next_res = alloc_resource(GFP_ATOMIC); if (!next_res) { free_resource(res); break; } next_res->name = name; next_res->start = conflict->end + 1; next_res->end = end; next_res->flags = type | IORESOURCE_BUSY; next_res->desc = IORES_DESC_NONE; } } else { res->start = conflict->end + 1; } } } void __init reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name) { int abort = 0; write_lock(&resource_lock); if (root->start > start || root->end < end) { pr_err("requested range [0x%llx-0x%llx] not in root %pr\n", (unsigned long long)start, (unsigned long long)end, root); if (start > root->end || end < root->start) abort = 1; else { if (end > root->end) end = root->end; if (start < root->start) start = root->start; pr_err("fixing request to [0x%llx-0x%llx]\n", (unsigned long long)start, (unsigned long long)end); } dump_stack(); } if (!abort) __reserve_region_with_split(root, start, end, name); write_unlock(&resource_lock); } /** * resource_alignment - calculate resource's alignment * @res: resource pointer * * Returns alignment on success, 0 (invalid alignment) on failure. */ resource_size_t resource_alignment(struct resource *res) { switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) { case IORESOURCE_SIZEALIGN: return resource_size(res); case IORESOURCE_STARTALIGN: return res->start; default: return 0; } } /* * This is compatibility stuff for IO resources. * * Note how this, unlike the above, knows about * the IO flag meanings (busy etc). * * request_region creates a new busy region. * * release_region releases a matching busy region. */ static DECLARE_WAIT_QUEUE_HEAD(muxed_resource_wait); static struct inode *iomem_inode; #ifdef CONFIG_IO_STRICT_DEVMEM static void revoke_iomem(struct resource *res) { /* pairs with smp_store_release() in iomem_init_inode() */ struct inode *inode = smp_load_acquire(&iomem_inode); /* * Check that the initialization has completed. Losing the race * is ok because it means drivers are claiming resources before * the fs_initcall level of init and prevent iomem_get_mapping users * from establishing mappings. */ if (!inode) return; /* * The expectation is that the driver has successfully marked * the resource busy by this point, so devmem_is_allowed() * should start returning false, however for performance this * does not iterate the entire resource range. */ if (devmem_is_allowed(PHYS_PFN(res->start)) && devmem_is_allowed(PHYS_PFN(res->end))) { /* * *cringe* iomem=relaxed says "go ahead, what's the * worst that can happen?" */ return; } unmap_mapping_range(inode->i_mapping, res->start, resource_size(res), 1); } #else static void revoke_iomem(struct resource *res) {} #endif struct address_space *iomem_get_mapping(void) { /* * This function is only called from file open paths, hence guaranteed * that fs_initcalls have completed and no need to check for NULL. But * since revoke_iomem can be called before the initcall we still need * the barrier to appease checkers. */ return smp_load_acquire(&iomem_inode)->i_mapping; } static int __request_region_locked(struct resource *res, struct resource *parent, resource_size_t start, resource_size_t n, const char *name, int flags) { DECLARE_WAITQUEUE(wait, current); res->name = name; res->start = start; res->end = start + n - 1; for (;;) { struct resource *conflict; res->flags = resource_type(parent) | resource_ext_type(parent); res->flags |= IORESOURCE_BUSY | flags; res->desc = parent->desc; conflict = __request_resource(parent, res); if (!conflict) break; /* * mm/hmm.c reserves physical addresses which then * become unavailable to other users. Conflicts are * not expected. Warn to aid debugging if encountered. */ if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) { pr_warn("Unaddressable device %s %pR conflicts with %pR", conflict->name, conflict, res); } if (conflict != parent) { if (!(conflict->flags & IORESOURCE_BUSY)) { parent = conflict; continue; } } if (conflict->flags & flags & IORESOURCE_MUXED) { add_wait_queue(&muxed_resource_wait, &wait); write_unlock(&resource_lock); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); remove_wait_queue(&muxed_resource_wait, &wait); write_lock(&resource_lock); continue; } /* Uhhuh, that didn't work out.. */ return -EBUSY; } return 0; } /** * __request_region - create a new busy resource region * @parent: parent resource descriptor * @start: resource start address * @n: resource region size * @name: reserving caller's ID string * @flags: IO resource flags */ struct resource *__request_region(struct resource *parent, resource_size_t start, resource_size_t n, const char *name, int flags) { struct resource *res = alloc_resource(GFP_KERNEL); int ret; if (!res) return NULL; write_lock(&resource_lock); ret = __request_region_locked(res, parent, start, n, name, flags); write_unlock(&resource_lock); if (ret) { free_resource(res); return NULL; } if (parent == &iomem_resource) revoke_iomem(res); return res; } EXPORT_SYMBOL(__request_region); /** * __release_region - release a previously reserved resource region * @parent: parent resource descriptor * @start: resource start address * @n: resource region size * * The described resource region must match a currently busy region. */ void __release_region(struct resource *parent, resource_size_t start, resource_size_t n) { struct resource **p; resource_size_t end; p = &parent->child; end = start + n - 1; write_lock(&resource_lock); for (;;) { struct resource *res = *p; if (!res) break; if (res->start <= start && res->end >= end) { if (!(res->flags & IORESOURCE_BUSY)) { p = &res->child; continue; } if (res->start != start || res->end != end) break; *p = res->sibling; write_unlock(&resource_lock); if (res->flags & IORESOURCE_MUXED) wake_up(&muxed_resource_wait); free_resource(res); return; } p = &res->sibling; } write_unlock(&resource_lock); pr_warn("Trying to free nonexistent resource <%pa-%pa>\n", &start, &end); } EXPORT_SYMBOL(__release_region); #ifdef CONFIG_MEMORY_HOTREMOVE /** * release_mem_region_adjustable - release a previously reserved memory region * @start: resource start address * @size: resource region size * * This interface is intended for memory hot-delete. The requested region * is released from a currently busy memory resource. The requested region * must either match exactly or fit into a single busy resource entry. In * the latter case, the remaining resource is adjusted accordingly. * Existing children of the busy memory resource must be immutable in the * request. * * Note: * - Additional release conditions, such as overlapping region, can be * supported after they are confirmed as valid cases. * - When a busy memory resource gets split into two entries, the code * assumes that all children remain in the lower address entry for * simplicity. Enhance this logic when necessary. */ void release_mem_region_adjustable(resource_size_t start, resource_size_t size) { struct resource *parent = &iomem_resource; struct resource *new_res = NULL; bool alloc_nofail = false; struct resource **p; struct resource *res; resource_size_t end; end = start + size - 1; if (WARN_ON_ONCE((start < parent->start) || (end > parent->end))) return; /* * We free up quite a lot of memory on memory hotunplug (esp., memap), * just before releasing the region. This is highly unlikely to * fail - let's play save and make it never fail as the caller cannot * perform any error handling (e.g., trying to re-add memory will fail * similarly). */ retry: new_res = alloc_resource(GFP_KERNEL | (alloc_nofail ? __GFP_NOFAIL : 0)); p = &parent->child; write_lock(&resource_lock); while ((res = *p)) { if (res->start >= end) break; /* look for the next resource if it does not fit into */ if (res->start > start || res->end < end) { p = &res->sibling; continue; } if (!(res->flags & IORESOURCE_MEM)) break; if (!(res->flags & IORESOURCE_BUSY)) { p = &res->child; continue; } /* found the target resource; let's adjust accordingly */ if (res->start == start && res->end == end) { /* free the whole entry */ *p = res->sibling; free_resource(res); } else if (res->start == start && res->end != end) { /* adjust the start */ WARN_ON_ONCE(__adjust_resource(res, end + 1, res->end - end)); } else if (res->start != start && res->end == end) { /* adjust the end */ WARN_ON_ONCE(__adjust_resource(res, res->start, start - res->start)); } else { /* split into two entries - we need a new resource */ if (!new_res) { new_res = alloc_resource(GFP_ATOMIC); if (!new_res) { alloc_nofail = true; write_unlock(&resource_lock); goto retry; } } new_res->name = res->name; new_res->start = end + 1; new_res->end = res->end; new_res->flags = res->flags; new_res->desc = res->desc; new_res->parent = res->parent; new_res->sibling = res->sibling; new_res->child = NULL; if (WARN_ON_ONCE(__adjust_resource(res, res->start, start - res->start))) break; res->sibling = new_res; new_res = NULL; } break; } write_unlock(&resource_lock); free_resource(new_res); } #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_MEMORY_HOTPLUG static bool system_ram_resources_mergeable(struct resource *r1, struct resource *r2) { /* We assume either r1 or r2 is IORESOURCE_SYSRAM_MERGEABLE. */ return r1->flags == r2->flags && r1->end + 1 == r2->start && r1->name == r2->name && r1->desc == r2->desc && !r1->child && !r2->child; } /** * merge_system_ram_resource - mark the System RAM resource mergeable and try to * merge it with adjacent, mergeable resources * @res: resource descriptor * * This interface is intended for memory hotplug, whereby lots of contiguous * system ram resources are added (e.g., via add_memory*()) by a driver, and * the actual resource boundaries are not of interest (e.g., it might be * relevant for DIMMs). Only resources that are marked mergeable, that have the * same parent, and that don't have any children are considered. All mergeable * resources must be immutable during the request. * * Note: * - The caller has to make sure that no pointers to resources that are * marked mergeable are used anymore after this call - the resource might * be freed and the pointer might be stale! * - release_mem_region_adjustable() will split on demand on memory hotunplug */ void merge_system_ram_resource(struct resource *res) { const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; struct resource *cur; if (WARN_ON_ONCE((res->flags & flags) != flags)) return; write_lock(&resource_lock); res->flags |= IORESOURCE_SYSRAM_MERGEABLE; /* Try to merge with next item in the list. */ cur = res->sibling; if (cur && system_ram_resources_mergeable(res, cur)) { res->end = cur->end; res->sibling = cur->sibling; free_resource(cur); } /* Try to merge with previous item in the list. */ cur = res->parent->child; while (cur && cur->sibling != res) cur = cur->sibling; if (cur && system_ram_resources_mergeable(cur, res)) { cur->end = res->end; cur->sibling = res->sibling; free_resource(res); } write_unlock(&resource_lock); } #endif /* CONFIG_MEMORY_HOTPLUG */ /* * Managed region resource */ static void devm_resource_release(struct device *dev, void *ptr) { struct resource **r = ptr; release_resource(*r); } /** * devm_request_resource() - request and reserve an I/O or memory resource * @dev: device for which to request the resource * @root: root of the resource tree from which to request the resource * @new: descriptor of the resource to request * * This is a device-managed version of request_resource(). There is usually * no need to release resources requested by this function explicitly since * that will be taken care of when the device is unbound from its driver. * If for some reason the resource needs to be released explicitly, because * of ordering issues for example, drivers must call devm_release_resource() * rather than the regular release_resource(). * * When a conflict is detected between any existing resources and the newly * requested resource, an error message will be printed. * * Returns 0 on success or a negative error code on failure. */ int devm_request_resource(struct device *dev, struct resource *root, struct resource *new) { struct resource *conflict, **ptr; ptr = devres_alloc(devm_resource_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return -ENOMEM; *ptr = new; conflict = request_resource_conflict(root, new); if (conflict) { dev_err(dev, "resource collision: %pR conflicts with %s %pR\n", new, conflict->name, conflict); devres_free(ptr); return -EBUSY; } devres_add(dev, ptr); return 0; } EXPORT_SYMBOL(devm_request_resource); static int devm_resource_match(struct device *dev, void *res, void *data) { struct resource **ptr = res; return *ptr == data; } /** * devm_release_resource() - release a previously requested resource * @dev: device for which to release the resource * @new: descriptor of the resource to release * * Releases a resource previously requested using devm_request_resource(). */ void devm_release_resource(struct device *dev, struct resource *new) { WARN_ON(devres_release(dev, devm_resource_release, devm_resource_match, new)); } EXPORT_SYMBOL(devm_release_resource); struct region_devres { struct resource *parent; resource_size_t start; resource_size_t n; }; static void devm_region_release(struct device *dev, void *res) { struct region_devres *this = res; __release_region(this->parent, this->start, this->n); } static int devm_region_match(struct device *dev, void *res, void *match_data) { struct region_devres *this = res, *match = match_data; return this->parent == match->parent && this->start == match->start && this->n == match->n; } struct resource * __devm_request_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n, const char *name) { struct region_devres *dr = NULL; struct resource *res; dr = devres_alloc(devm_region_release, sizeof(struct region_devres), GFP_KERNEL); if (!dr) return NULL; dr->parent = parent; dr->start = start; dr->n = n; res = __request_region(parent, start, n, name, 0); if (res) devres_add(dev, dr); else devres_free(dr); return res; } EXPORT_SYMBOL(__devm_request_region); void __devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n) { struct region_devres match_data = { parent, start, n }; WARN_ON(devres_release(dev, devm_region_release, devm_region_match, &match_data)); } EXPORT_SYMBOL(__devm_release_region); /* * Reserve I/O ports or memory based on "reserve=" kernel parameter. */ #define MAXRESERVE 4 static int __init reserve_setup(char *str) { static int reserved; static struct resource reserve[MAXRESERVE]; for (;;) { unsigned int io_start, io_num; int x = reserved; struct resource *parent; if (get_option(&str, &io_start) != 2) break; if (get_option(&str, &io_num) == 0) break; if (x < MAXRESERVE) { struct resource *res = reserve + x; /* * If the region starts below 0x10000, we assume it's * I/O port space; otherwise assume it's memory. */ if (io_start < 0x10000) { *res = DEFINE_RES_IO_NAMED(io_start, io_num, "reserved"); parent = &ioport_resource; } else { *res = DEFINE_RES_MEM_NAMED(io_start, io_num, "reserved"); parent = &iomem_resource; } res->flags |= IORESOURCE_BUSY; if (request_resource(parent, res) == 0) reserved = x+1; } } return 1; } __setup("reserve=", reserve_setup); /* * Check if the requested addr and size spans more than any slot in the * iomem resource tree. */ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) { resource_size_t end = addr + size - 1; struct resource *p; int err = 0; read_lock(&resource_lock); for_each_resource(&iomem_resource, p, false) { /* * We can probably skip the resources without * IORESOURCE_IO attribute? */ if (p->start > end) continue; if (p->end < addr) continue; if (PFN_DOWN(p->start) <= PFN_DOWN(addr) && PFN_DOWN(p->end) >= PFN_DOWN(end)) continue; /* * if a resource is "BUSY", it's not a hardware resource * but a driver mapping of such a resource; we don't want * to warn for those; some drivers legitimately map only * partial hardware resources. (example: vesafb) */ if (p->flags & IORESOURCE_BUSY) continue; pr_warn("resource sanity check: requesting [mem %pa-%pa], which spans more than %s %pR\n", &addr, &end, p->name, p); err = -1; break; } read_unlock(&resource_lock); return err; } #ifdef CONFIG_STRICT_DEVMEM static int strict_iomem_checks = 1; #else static int strict_iomem_checks; #endif /* * Check if an address is exclusive to the kernel and must not be mapped to * user space, for example, via /dev/mem. * * Returns true if exclusive to the kernel, otherwise returns false. */ bool resource_is_exclusive(struct resource *root, u64 addr, resource_size_t size) { const unsigned int exclusive_system_ram = IORESOURCE_SYSTEM_RAM | IORESOURCE_EXCLUSIVE; bool skip_children = false, err = false; struct resource *p; read_lock(&resource_lock); for_each_resource(root, p, skip_children) { if (p->start >= addr + size) break; if (p->end < addr) { skip_children = true; continue; } skip_children = false; /* * IORESOURCE_SYSTEM_RAM resources are exclusive if * IORESOURCE_EXCLUSIVE is set, even if they * are not busy and even if "iomem=relaxed" is set. The * responsible driver dynamically adds/removes system RAM within * such an area and uncontrolled access is dangerous. */ if ((p->flags & exclusive_system_ram) == exclusive_system_ram) { err = true; break; } /* * A resource is exclusive if IORESOURCE_EXCLUSIVE is set * or CONFIG_IO_STRICT_DEVMEM is enabled and the * resource is busy. */ if (!strict_iomem_checks || !(p->flags & IORESOURCE_BUSY)) continue; if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM) || p->flags & IORESOURCE_EXCLUSIVE) { err = true; break; } } read_unlock(&resource_lock); return err; } bool iomem_is_exclusive(u64 addr) { return resource_is_exclusive(&iomem_resource, addr & PAGE_MASK, PAGE_SIZE); } struct resource_entry *resource_list_create_entry(struct resource *res, size_t extra_size) { struct resource_entry *entry; entry = kzalloc(sizeof(*entry) + extra_size, GFP_KERNEL); if (entry) { INIT_LIST_HEAD(&entry->node); entry->res = res ? res : &entry->__res; } return entry; } EXPORT_SYMBOL(resource_list_create_entry); void resource_list_free(struct list_head *head) { struct resource_entry *entry, *tmp; list_for_each_entry_safe(entry, tmp, head, node) resource_list_destroy_entry(entry); } EXPORT_SYMBOL(resource_list_free); #ifdef CONFIG_GET_FREE_REGION #define GFR_DESCENDING (1UL << 0) #define GFR_REQUEST_REGION (1UL << 1) #ifdef PA_SECTION_SHIFT #define GFR_DEFAULT_ALIGN (1UL << PA_SECTION_SHIFT) #else #define GFR_DEFAULT_ALIGN PAGE_SIZE #endif static resource_size_t gfr_start(struct resource *base, resource_size_t size, resource_size_t align, unsigned long flags) { if (flags & GFR_DESCENDING) { resource_size_t end; end = min_t(resource_size_t, base->end, DIRECT_MAP_PHYSMEM_END); return end - size + 1; } return ALIGN(max(base->start, align), align); } static bool gfr_continue(struct resource *base, resource_size_t addr, resource_size_t size, unsigned long flags) { if (flags & GFR_DESCENDING) return addr > size && addr >= base->start; /* * In the ascend case be careful that the last increment by * @size did not wrap 0. */ return addr > addr - size && addr <= min_t(resource_size_t, base->end, DIRECT_MAP_PHYSMEM_END); } static resource_size_t gfr_next(resource_size_t addr, resource_size_t size, unsigned long flags) { if (flags & GFR_DESCENDING) return addr - size; return addr + size; } static void remove_free_mem_region(void *_res) { struct resource *res = _res; if (res->parent) remove_resource(res); free_resource(res); } static struct resource * get_free_mem_region(struct device *dev, struct resource *base, resource_size_t size, const unsigned long align, const char *name, const unsigned long desc, const unsigned long flags) { resource_size_t addr; struct resource *res; struct region_devres *dr = NULL; size = ALIGN(size, align); res = alloc_resource(GFP_KERNEL); if (!res) return ERR_PTR(-ENOMEM); if (dev && (flags & GFR_REQUEST_REGION)) { dr = devres_alloc(devm_region_release, sizeof(struct region_devres), GFP_KERNEL); if (!dr) { free_resource(res); return ERR_PTR(-ENOMEM); } } else if (dev) { if (devm_add_action_or_reset(dev, remove_free_mem_region, res)) return ERR_PTR(-ENOMEM); } write_lock(&resource_lock); for (addr = gfr_start(base, size, align, flags); gfr_continue(base, addr, align, flags); addr = gfr_next(addr, align, flags)) { if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) != REGION_DISJOINT) continue; if (flags & GFR_REQUEST_REGION) { if (__request_region_locked(res, &iomem_resource, addr, size, name, 0)) break; if (dev) { dr->parent = &iomem_resource; dr->start = addr; dr->n = size; devres_add(dev, dr); } res->desc = desc; write_unlock(&resource_lock); /* * A driver is claiming this region so revoke any * mappings. */ revoke_iomem(res); } else { *res = DEFINE_RES_NAMED_DESC(addr, size, name, IORESOURCE_MEM, desc); /* * Only succeed if the resource hosts an exclusive * range after the insert */ if (__insert_resource(base, res) || res->child) break; write_unlock(&resource_lock); } return res; } write_unlock(&resource_lock); if (flags & GFR_REQUEST_REGION) { free_resource(res); devres_free(dr); } else if (dev) devm_release_action(dev, remove_free_mem_region, res); return ERR_PTR(-ERANGE); } /** * devm_request_free_mem_region - find free region for device private memory * * @dev: device struct to bind the resource to * @size: size in bytes of the device memory to add * @base: resource tree to look in * * This function tries to find an empty range of physical address big enough to * contain the new resource, so that it can later be hotplugged as ZONE_DEVICE * memory, which in turn allocates struct pages. */ struct resource *devm_request_free_mem_region(struct device *dev, struct resource *base, unsigned long size) { unsigned long flags = GFR_DESCENDING | GFR_REQUEST_REGION; return get_free_mem_region(dev, base, size, GFR_DEFAULT_ALIGN, dev_name(dev), IORES_DESC_DEVICE_PRIVATE_MEMORY, flags); } EXPORT_SYMBOL_GPL(devm_request_free_mem_region); struct resource *request_free_mem_region(struct resource *base, unsigned long size, const char *name) { unsigned long flags = GFR_DESCENDING | GFR_REQUEST_REGION; return get_free_mem_region(NULL, base, size, GFR_DEFAULT_ALIGN, name, IORES_DESC_DEVICE_PRIVATE_MEMORY, flags); } EXPORT_SYMBOL_GPL(request_free_mem_region); /** * alloc_free_mem_region - find a free region relative to @base * @base: resource that will parent the new resource * @size: size in bytes of memory to allocate from @base * @align: alignment requirements for the allocation * @name: resource name * * Buses like CXL, that can dynamically instantiate new memory regions, * need a method to allocate physical address space for those regions. * Allocate and insert a new resource to cover a free, unclaimed by a * descendant of @base, range in the span of @base. */ struct resource *alloc_free_mem_region(struct resource *base, unsigned long size, unsigned long align, const char *name) { /* Default of ascending direction and insert resource */ unsigned long flags = 0; return get_free_mem_region(NULL, base, size, align, name, IORES_DESC_NONE, flags); } EXPORT_SYMBOL_GPL(alloc_free_mem_region); #endif /* CONFIG_GET_FREE_REGION */ static int __init strict_iomem(char *str) { if (strstr(str, "relaxed")) strict_iomem_checks = 0; if (strstr(str, "strict")) strict_iomem_checks = 1; return 1; } static int iomem_fs_init_fs_context(struct fs_context *fc) { return init_pseudo(fc, DEVMEM_MAGIC) ? 0 : -ENOMEM; } static struct file_system_type iomem_fs_type = { .name = "iomem", .owner = THIS_MODULE, .init_fs_context = iomem_fs_init_fs_context, .kill_sb = kill_anon_super, }; static int __init iomem_init_inode(void) { static struct vfsmount *iomem_vfs_mount; static int iomem_fs_cnt; struct inode *inode; int rc; rc = simple_pin_fs(&iomem_fs_type, &iomem_vfs_mount, &iomem_fs_cnt); if (rc < 0) { pr_err("Cannot mount iomem pseudo filesystem: %d\n", rc); return rc; } inode = alloc_anon_inode(iomem_vfs_mount->mnt_sb); if (IS_ERR(inode)) { rc = PTR_ERR(inode); pr_err("Cannot allocate inode for iomem: %d\n", rc); simple_release_fs(&iomem_vfs_mount, &iomem_fs_cnt); return rc; } /* * Publish iomem revocation inode initialized. * Pairs with smp_load_acquire() in revoke_iomem(). */ smp_store_release(&iomem_inode, inode); return 0; } fs_initcall(iomem_init_inode); __setup("iomem=", strict_iomem); |
| 9 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel module to match connection tracking information. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2005 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_state.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); MODULE_DESCRIPTION("ip[6]_tables connection tracking state match module"); MODULE_ALIAS("ipt_state"); MODULE_ALIAS("ip6t_state"); static bool state_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_state_info *sinfo = par->matchinfo; enum ip_conntrack_info ctinfo; unsigned int statebit; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct) statebit = XT_STATE_BIT(ctinfo); else if (ctinfo == IP_CT_UNTRACKED) statebit = XT_STATE_UNTRACKED; else statebit = XT_STATE_INVALID; return (sinfo->statemask & statebit); } static int state_mt_check(const struct xt_mtchk_param *par) { int ret; ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) pr_info_ratelimited("cannot load conntrack support for proto=%u\n", par->family); return ret; } static void state_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_netns_put(par->net, par->family); } static struct xt_match state_mt_reg __read_mostly = { .name = "state", .family = NFPROTO_UNSPEC, .checkentry = state_mt_check, .match = state_mt, .destroy = state_mt_destroy, .matchsize = sizeof(struct xt_state_info), .me = THIS_MODULE, }; static int __init state_mt_init(void) { return xt_register_match(&state_mt_reg); } static void __exit state_mt_exit(void) { xt_unregister_match(&state_mt_reg); } module_init(state_mt_init); module_exit(state_mt_exit); |
| 644 311 4 9 298 237 255 237 72 277 3 1 274 986 10 464 3 666 986 373 29 35 308 38 12 38 30 20 48 1 47 48 67 27 1 1 50 52 105 52 29 35 55 269 74 195 268 209 209 206 209 71 2 69 55 55 179 39 48 92 139 140 2 2 1 1 2 138 138 138 138 140 82 1 51 51 24 14 30 51 202 178 29 30 30 3 28 28 28 30 29 2 29 2 16 35 35 51 52 43 17 2 18 36 1 2 36 5 10 18 18 18 18 18 111 111 77 34 15 69 18 87 15 15 52 11 5 39 2 38 52 52 52 21 21 21 21 21 21 21 3 20 28 5 26 4 3 19 22 18 4 2 9 9 29 14 14 14 14 4 4 25 1 24 25 94 49 2 60 6 63 11 10 1 11 11 11 11 11 14 14 1 15 1 9 14 1 4 15 28 28 3 3 3 341 339 2 337 2 319 20 1 338 341 341 74 277 302 39 213 151 77 2 2 2 77 77 77 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: LGPL-2.1 /* * Copyright (c) 2012 Taobao. * Written by Tao Ma <boyu.mt@taobao.com> */ #include <linux/iomap.h> #include <linux/fiemap.h> #include <linux/namei.h> #include <linux/iversion.h> #include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "truncate.h" #define EXT4_XATTR_SYSTEM_DATA "data" #define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) #define EXT4_INLINE_DOTDOT_OFFSET 2 #define EXT4_INLINE_DOTDOT_SIZE 4 static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, void **fsdata); static int ext4_get_inline_size(struct inode *inode) { if (EXT4_I(inode)->i_inline_off) return EXT4_I(inode)->i_inline_size; return 0; } static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_iloc *iloc) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; void *end; int free, min_offs; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; min_offs = EXT4_SB(inode->i_sb)->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - EXT4_I(inode)->i_extra_isize - sizeof(struct ext4_xattr_ibody_header); /* * We need to subtract another sizeof(__u32) since an in-inode xattr * needs an empty 4 bytes to indicate the gap between the xattr entry * and the name/value pair. */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return EXT4_XATTR_SIZE(min_offs - EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)) - EXT4_XATTR_ROUND - sizeof(__u32)); raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; /* Compute min_offs. */ while (!IS_LAST_ENTRY(entry)) { void *next = EXT4_XATTR_NEXT(entry); if (next >= end) { EXT4_ERROR_INODE(inode, "corrupt xattr in inline inode"); return 0; } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); if (EXT4_I(inode)->i_inline_off) { entry = (struct ext4_xattr_entry *) ((void *)raw_inode + EXT4_I(inode)->i_inline_off); free += EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)); goto out; } free -= EXT4_XATTR_LEN(strlen(EXT4_XATTR_SYSTEM_DATA)); if (free > EXT4_XATTR_ROUND) free = EXT4_XATTR_SIZE(free - EXT4_XATTR_ROUND); else free = 0; out: return free; } /* * Get the maximum size we now can store in an inode. * If we can't find the space for a xattr entry, don't use the space * of the extents since we have no space to indicate the inline data. */ int ext4_get_max_inline_size(struct inode *inode) { int error, max_inline_size; struct ext4_iloc iloc; if (EXT4_I(inode)->i_extra_isize == 0) return 0; error = ext4_get_inode_loc(inode, &iloc); if (error) { ext4_error_inode_err(inode, __func__, __LINE__, 0, -error, "can't get inode location %lu", inode->i_ino); return 0; } down_read(&EXT4_I(inode)->xattr_sem); max_inline_size = get_max_inline_xattr_value_size(inode, &iloc); up_read(&EXT4_I(inode)->xattr_sem); brelse(iloc.bh); if (!max_inline_size) return 0; return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE; } /* * this function does not take xattr_sem, which is OK because it is * currently only used in a code path coming form ext4_iget, before * the new inode has been unlocked */ int ext4_find_inline_data_nolock(struct inode *inode) { struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; int error; if (EXT4_I(inode)->i_extra_isize == 0) return 0; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; if (!is.s.not_found) { if (is.s.here->e_value_inum) { EXT4_ERROR_INODE(inode, "inline data xattr refers " "to an external xattr inode"); error = -EFSCORRUPTED; goto out; } EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); } out: brelse(is.iloc.bh); return error; } static int ext4_read_inline_data(struct inode *inode, void *buffer, unsigned int len, struct ext4_iloc *iloc) { struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; int cp_len = 0; struct ext4_inode *raw_inode; if (!len) return 0; BUG_ON(len > EXT4_I(inode)->i_inline_size); cp_len = min_t(unsigned int, len, EXT4_MIN_INLINE_DATA_SIZE); raw_inode = ext4_raw_inode(iloc); memcpy(buffer, (void *)(raw_inode->i_block), cp_len); len -= cp_len; buffer += cp_len; if (!len) goto out; header = IHDR(inode, raw_inode); entry = (struct ext4_xattr_entry *)((void *)raw_inode + EXT4_I(inode)->i_inline_off); len = min_t(unsigned int, len, (unsigned int)le32_to_cpu(entry->e_value_size)); memcpy(buffer, (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs), len); cp_len += len; out: return cp_len; } /* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, void *buffer, loff_t pos, unsigned int len) { struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; int cp_len = 0; if (unlikely(ext4_emergency_state(inode->i_sb))) return; BUG_ON(!EXT4_I(inode)->i_inline_off); BUG_ON(pos + len > EXT4_I(inode)->i_inline_size); raw_inode = ext4_raw_inode(iloc); buffer += pos; if (pos < EXT4_MIN_INLINE_DATA_SIZE) { cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ? EXT4_MIN_INLINE_DATA_SIZE - pos : len; memcpy((void *)raw_inode->i_block + pos, buffer, cp_len); len -= cp_len; buffer += cp_len; pos += cp_len; } if (!len) return; pos -= EXT4_MIN_INLINE_DATA_SIZE; header = IHDR(inode, raw_inode); entry = (struct ext4_xattr_entry *)((void *)raw_inode + EXT4_I(inode)->i_inline_off); memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos, buffer, len); } static int ext4_create_inline_data(handle_t *handle, struct inode *inode, unsigned len) { int error; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, is.iloc.bh, EXT4_JTR_NONE); if (error) goto out; if (len > EXT4_MIN_INLINE_DATA_SIZE) { value = EXT4_ZERO_XATTR_VALUE; len -= EXT4_MIN_INLINE_DATA_SIZE; } else { value = ""; len = 0; } /* Insert the xttr entry. */ i.value = value; i.value_len = len; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; BUG_ON(!is.s.not_found); error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); goto out; } memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE; ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); out: brelse(is.iloc.bh); return error; } static int ext4_update_inline_data(handle_t *handle, struct inode *inode, unsigned int len) { int error; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; /* If the old space is ok, write the data directly. */ if (len <= EXT4_I(inode)->i_inline_size) return 0; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; BUG_ON(is.s.not_found); len -= EXT4_MIN_INLINE_DATA_SIZE; value = kzalloc(len, GFP_NOFS); if (!value) { error = -ENOMEM; goto out; } error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); if (error < 0) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, is.iloc.bh, EXT4_JTR_NONE); if (error) goto out; /* Update the xattr entry. */ i.value = value; i.value_len = len; error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here - (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); out: kfree(value); brelse(is.iloc.bh); return error; } static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, loff_t len) { int ret, size, no_expand; struct ext4_inode_info *ei = EXT4_I(inode); if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) return -ENOSPC; size = ext4_get_max_inline_size(inode); if (size < len) return -ENOSPC; ext4_write_lock_xattr(inode, &no_expand); if (ei->i_inline_off) ret = ext4_update_inline_data(handle, inode, len); else ret = ext4_create_inline_data(handle, inode, len); ext4_write_unlock_xattr(inode, &no_expand); return ret; } static int ext4_destroy_inline_data_nolock(handle_t *handle, struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_xattr_ibody_find is = { .s = { .not_found = 0, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, .value = NULL, .value_len = 0, }; int error; if (!ei->i_inline_off) return 0; error = ext4_get_inode_loc(inode, &is.iloc); if (error) return error; error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, is.iloc.bh, EXT4_JTR_NONE); if (error) goto out; error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE); if (ext4_has_feature_extents(inode->i_sb)) { if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode); } } ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA); get_bh(is.iloc.bh); error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); EXT4_I(inode)->i_inline_off = 0; EXT4_I(inode)->i_inline_size = 0; ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); out: brelse(is.iloc.bh); if (error == -ENODATA) error = 0; return error; } static int ext4_read_inline_folio(struct inode *inode, struct folio *folio) { void *kaddr; int ret = 0; size_t len; struct ext4_iloc iloc; BUG_ON(!folio_test_locked(folio)); BUG_ON(!ext4_has_inline_data(inode)); BUG_ON(folio->index); if (!EXT4_I(inode)->i_inline_off) { ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.", inode->i_ino); goto out; } ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out; len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode)); BUG_ON(len > PAGE_SIZE); kaddr = kmap_local_folio(folio, 0); ret = ext4_read_inline_data(inode, kaddr, len, &iloc); kaddr = folio_zero_tail(folio, len, kaddr + len); kunmap_local(kaddr); folio_mark_uptodate(folio); brelse(iloc.bh); out: return ret; } int ext4_readpage_inline(struct inode *inode, struct folio *folio) { int ret = 0; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); return -EAGAIN; } /* * Current inline data can only exist in the 1st page, * So for all the other pages, just set them uptodate. */ if (!folio->index) ret = ext4_read_inline_folio(inode, folio); else if (!folio_test_uptodate(folio)) { folio_zero_segment(folio, 0, folio_size(folio)); folio_mark_uptodate(folio); } up_read(&EXT4_I(inode)->xattr_sem); folio_unlock(folio); return ret >= 0 ? 0 : ret; } static int ext4_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode) { int ret, needed_blocks, no_expand; handle_t *handle = NULL; int retries = 0, sem_held = 0; struct folio *folio = NULL; unsigned from, to; struct ext4_iloc iloc; if (!ext4_has_inline_data(inode)) { /* * clear the flag so that no new write * will trap here again. */ ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; } needed_blocks = ext4_writepage_trans_blocks(inode); ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; retry: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { ret = PTR_ERR(handle); handle = NULL; goto out; } /* We cannot recurse into the filesystem as the transaction is already * started */ folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN | FGP_NOFS, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto out_nofolio; } ext4_write_lock_xattr(inode, &no_expand); sem_held = 1; /* If some one has already done this for us, just exit. */ if (!ext4_has_inline_data(inode)) { ret = 0; goto out; } from = 0; to = ext4_get_inline_size(inode); if (!folio_test_uptodate(folio)) { ret = ext4_read_inline_folio(inode, folio); if (ret < 0) goto out; } ext4_fc_track_inode(handle, inode); ret = ext4_destroy_inline_data_nolock(handle, inode); if (ret) goto out; if (ext4_should_dioread_nolock(inode)) { ret = ext4_block_write_begin(handle, folio, from, to, ext4_get_block_unwritten); } else ret = ext4_block_write_begin(handle, folio, from, to, ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, inode, folio_buffers(folio), from, to, NULL, do_journal_get_write_access); } if (ret) { folio_unlock(folio); folio_put(folio); folio = NULL; ext4_orphan_add(handle, inode); ext4_write_unlock_xattr(inode, &no_expand); sem_held = 0; ext4_journal_stop(handle); handle = NULL; ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; if (folio) block_commit_write(folio, from, to); out: if (folio) { folio_unlock(folio); folio_put(folio); } out_nofolio: if (sem_held) ext4_write_unlock_xattr(inode, &no_expand); if (handle) ext4_journal_stop(handle); brelse(iloc.bh); return ret; } /* * Prepare the write for the inline data. * If the data can be written into the inode, we just read * the page and make it uptodate, and start the journal. * Otherwise read the page, makes it dirty so that it can be * handle in writepages(the i_disksize update is left to the * normal ext4_da_write_end). */ int ext4_generic_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct folio **foliop, void **fsdata, bool da) { int ret; handle_t *handle; struct folio *folio; struct ext4_iloc iloc; int retries = 0; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; retry_journal: handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_release_bh; } ret = ext4_prepare_inline_data(handle, inode, pos + len); if (ret && ret != -ENOSPC) goto out_stop_journal; if (ret == -ENOSPC) { ext4_journal_stop(handle); if (!da) { brelse(iloc.bh); /* Retry inside */ return ext4_convert_inline_data_to_extent(mapping, inode); } ret = ext4_da_convert_inline_data_to_extent(mapping, inode, fsdata); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; goto out_release_bh; } folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN | FGP_NOFS, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto out_stop_journal; } down_read(&EXT4_I(inode)->xattr_sem); /* Someone else had converted it to extent */ if (!ext4_has_inline_data(inode)) { ret = 0; goto out_release_folio; } if (!folio_test_uptodate(folio)) { ret = ext4_read_inline_folio(inode, folio); if (ret < 0) goto out_release_folio; } ret = ext4_journal_get_write_access(handle, inode->i_sb, iloc.bh, EXT4_JTR_NONE); if (ret) goto out_release_folio; *foliop = folio; up_read(&EXT4_I(inode)->xattr_sem); brelse(iloc.bh); return 1; out_release_folio: up_read(&EXT4_I(inode)->xattr_sem); folio_unlock(folio); folio_put(folio); out_stop_journal: ext4_journal_stop(handle); out_release_bh: brelse(iloc.bh); return ret; } /* * Try to write data in the inode. * If the inode has inline data, check whether the new write can be * in the inode also. If not, create the page the handle, move the data * to the page make it update and let the later codes create extent for it. */ int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, struct folio **foliop) { if (pos + len > ext4_get_max_inline_size(inode)) return ext4_convert_inline_data_to_extent(mapping, inode); return ext4_generic_write_inline_data(mapping, inode, pos, len, foliop, NULL, false); } int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct folio *folio) { handle_t *handle = ext4_journal_current_handle(); int no_expand; void *kaddr; struct ext4_iloc iloc; int ret = 0, ret2; if (unlikely(copied < len) && !folio_test_uptodate(folio)) copied = 0; if (likely(copied)) { ret = ext4_get_inode_loc(inode, &iloc); if (ret) { folio_unlock(folio); folio_put(folio); ext4_std_error(inode->i_sb, ret); goto out; } ext4_write_lock_xattr(inode, &no_expand); BUG_ON(!ext4_has_inline_data(inode)); /* * ei->i_inline_off may have changed since * ext4_write_begin() called * ext4_try_to_write_inline_data() */ (void) ext4_find_inline_data_nolock(inode); kaddr = kmap_local_folio(folio, 0); ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); kunmap_local(kaddr); folio_mark_uptodate(folio); /* clear dirty flag so that writepages wouldn't work for us. */ folio_clear_dirty(folio); ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); /* * It's important to update i_size while still holding folio * lock: page writeout could otherwise come in and zero * beyond i_size. */ ext4_update_inode_size(inode, pos + copied); } folio_unlock(folio); folio_put(folio); /* * Don't mark the inode dirty under folio lock. First, it unnecessarily * makes the holding time of folio lock longer. Second, it forces lock * ordering of folio lock and transaction start for journaling * filesystems. */ if (likely(copied)) mark_inode_dirty(inode); out: /* * If we didn't copy as much data as expected, we need to trim back * size of xattr containing inline data. */ if (pos + len > inode->i_size && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied; } /* * Try to make the page cache and handle ready for the inline data case. * We can call this function in 2 cases: * 1. The inode is created and the first write exceeds inline size. We can * clear the inode state safely. * 2. The inode has inline data, then we need to read the data, make it * update and dirty so that ext4_da_writepages can handle it. We don't * need to start the journal since the file's metadata isn't changed now. */ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, void **fsdata) { int ret = 0, inline_size; struct folio *folio; folio = __filemap_get_folio(mapping, 0, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); goto out; } inline_size = ext4_get_inline_size(inode); if (!folio_test_uptodate(folio)) { ret = ext4_read_inline_folio(inode, folio); if (ret < 0) goto out; } ret = ext4_block_write_begin(NULL, folio, 0, inline_size, ext4_da_get_block_prep); if (ret) { up_read(&EXT4_I(inode)->xattr_sem); folio_unlock(folio); folio_put(folio); ext4_truncate_failed_write(inode); return ret; } folio_mark_dirty(folio); folio_mark_uptodate(folio); ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); *fsdata = (void *)CONVERT_INLINE_DATA; out: up_read(&EXT4_I(inode)->xattr_sem); if (folio) { folio_unlock(folio); folio_put(folio); } return ret; } #ifdef INLINE_DIR_DEBUG void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, void *inline_start, int inline_size) { int offset; unsigned short de_len; struct ext4_dir_entry_2 *de = inline_start; void *dlimit = inline_start + inline_size; trace_printk("inode %lu\n", dir->i_ino); offset = 0; while ((void *)de < dlimit) { de_len = ext4_rec_len_from_disk(de->rec_len, inline_size); trace_printk("de: off %u rlen %u name %.*s nlen %u ino %u\n", offset, de_len, de->name_len, de->name, de->name_len, le32_to_cpu(de->inode)); if (ext4_check_dir_entry(dir, NULL, de, bh, inline_start, inline_size, offset)) BUG(); offset += de_len; de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); } } #else #define ext4_show_inline_dir(dir, bh, inline_start, inline_size) #endif /* * Add a new entry into a inline dir. * It will return -ENOSPC if no space is available, and -EIO * and -EEXIST if directory entry already exists. */ static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode, struct ext4_iloc *iloc, void *inline_start, int inline_size) { int err; struct ext4_dir_entry_2 *de; err = ext4_find_dest_de(dir, iloc->bh, inline_start, inline_size, fname, &de); if (err) return err; BUFFER_TRACE(iloc->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, dir->i_sb, iloc->bh, EXT4_JTR_NONE); if (err) return err; ext4_insert_dentry(dir, inode, de, inline_size, fname); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); /* * XXX shouldn't update any times until successful * completion of syscall, but too many callers depend * on this. * * XXX similarly, too many callers depend on * ext4_new_inode() setting the times, but error * recovery deletes the inode, so the worst that can * happen is that the times are slightly out of date * and/or different from the directory change time. */ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); inode_inc_iversion(dir); return 1; } static void *ext4_get_inline_xattr_pos(struct inode *inode, struct ext4_iloc *iloc) { struct ext4_xattr_entry *entry; struct ext4_xattr_ibody_header *header; BUG_ON(!EXT4_I(inode)->i_inline_off); header = IHDR(inode, ext4_raw_inode(iloc)); entry = (struct ext4_xattr_entry *)((void *)ext4_raw_inode(iloc) + EXT4_I(inode)->i_inline_off); return (void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs); } /* Set the final de to cover the whole block. */ static void ext4_update_final_de(void *de_buf, int old_size, int new_size) { struct ext4_dir_entry_2 *de, *prev_de; void *limit; int de_len; de = de_buf; if (old_size) { limit = de_buf + old_size; do { prev_de = de; de_len = ext4_rec_len_from_disk(de->rec_len, old_size); de_buf += de_len; de = de_buf; } while (de_buf < limit); prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size - old_size, new_size); } else { /* this is just created, so create an empty entry. */ de->inode = 0; de->rec_len = ext4_rec_len_to_disk(new_size, new_size); } } static int ext4_update_inline_dir(handle_t *handle, struct inode *dir, struct ext4_iloc *iloc) { int ret; int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; int new_size = get_max_inline_xattr_value_size(dir, iloc); if (new_size - old_size <= ext4_dir_rec_len(1, NULL)) return -ENOSPC; ret = ext4_update_inline_data(handle, dir, new_size + EXT4_MIN_INLINE_DATA_SIZE); if (ret) return ret; ext4_update_final_de(ext4_get_inline_xattr_pos(dir, iloc), old_size, EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE); dir->i_size = EXT4_I(dir)->i_disksize = EXT4_I(dir)->i_inline_size; return 0; } static void ext4_restore_inline_data(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc, void *buf, int inline_size) { int ret; ret = ext4_create_inline_data(handle, inode, inline_size); if (ret) { ext4_msg(inode->i_sb, KERN_EMERG, "error restoring inline_data for inode -- potential data loss! (inode %lu, error %d)", inode->i_ino, ret); return; } ext4_write_inline_data(inode, iloc, buf, 0, inline_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } static int ext4_finish_convert_inline_dir(handle_t *handle, struct inode *inode, struct buffer_head *dir_block, void *buf, int inline_size) { int err, csum_size = 0, header_size = 0; struct ext4_dir_entry_2 *de; void *target = dir_block->b_data; /* * First create "." and ".." and then copy the dir information * back to the block. */ de = target; de = ext4_init_dot_dotdot(inode, de, inode->i_sb->s_blocksize, csum_size, le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1); header_size = (void *)de - target; memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); if (ext4_has_feature_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); inode->i_size = inode->i_sb->s_blocksize; i_size_write(inode, inode->i_sb->s_blocksize); EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; ext4_update_final_de(dir_block->b_data, inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size, inode->i_sb->s_blocksize - csum_size); if (csum_size) ext4_initialize_dirent_tail(dir_block, inode->i_sb->s_blocksize); set_buffer_uptodate(dir_block); unlock_buffer(dir_block); err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) return err; set_buffer_verified(dir_block); return ext4_mark_inode_dirty(handle, inode); } static int ext4_convert_inline_data_nolock(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { int error; void *buf = NULL; struct buffer_head *data_bh = NULL; struct ext4_map_blocks map; int inline_size; inline_size = ext4_get_inline_size(inode); buf = kmalloc(inline_size, GFP_NOFS); if (!buf) { error = -ENOMEM; goto out; } error = ext4_read_inline_data(inode, buf, inline_size, iloc); if (error < 0) goto out; /* * Make sure the inline directory entries pass checks before we try to * convert them, so that we avoid touching stuff that needs fsck. */ if (S_ISDIR(inode->i_mode)) { error = ext4_check_all_de(inode, iloc->bh, buf + EXT4_INLINE_DOTDOT_SIZE, inline_size - EXT4_INLINE_DOTDOT_SIZE); if (error) goto out; } error = ext4_destroy_inline_data_nolock(handle, inode); if (error) goto out; map.m_lblk = 0; map.m_len = 1; map.m_flags = 0; error = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE); if (error < 0) goto out_restore; if (!(map.m_flags & EXT4_MAP_MAPPED)) { error = -EIO; goto out_restore; } data_bh = sb_getblk(inode->i_sb, map.m_pblk); if (!data_bh) { error = -ENOMEM; goto out_restore; } lock_buffer(data_bh); error = ext4_journal_get_create_access(handle, inode->i_sb, data_bh, EXT4_JTR_NONE); if (error) { unlock_buffer(data_bh); error = -EIO; goto out_restore; } memset(data_bh->b_data, 0, inode->i_sb->s_blocksize); if (!S_ISDIR(inode->i_mode)) { memcpy(data_bh->b_data, buf, inline_size); set_buffer_uptodate(data_bh); unlock_buffer(data_bh); error = ext4_handle_dirty_metadata(handle, inode, data_bh); } else { error = ext4_finish_convert_inline_dir(handle, inode, data_bh, buf, inline_size); } out_restore: if (error) ext4_restore_inline_data(handle, inode, iloc, buf, inline_size); out: brelse(data_bh); kfree(buf); return error; } /* * Try to add the new entry to the inline data. * If succeeds, return 0. If not, extended the inline dir and copied data to * the new created block. */ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode) { int ret, ret2, inline_size, no_expand; void *inline_start; struct ext4_iloc iloc; ret = ext4_get_inode_loc(dir, &iloc); if (ret) return ret; ext4_write_lock_xattr(dir, &no_expand); if (!ext4_has_inline_data(dir)) goto out; inline_start = (void *)ext4_raw_inode(&iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); if (ret != -ENOSPC) goto out; /* check whether it can be inserted to inline xattr space. */ inline_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; if (!inline_size) { /* Try to use the xattr space.*/ ret = ext4_update_inline_dir(handle, dir, &iloc); if (ret && ret != -ENOSPC) goto out; inline_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; } if (inline_size) { inline_start = ext4_get_inline_xattr_pos(dir, &iloc); ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); if (ret != -ENOSPC) goto out; } /* * The inline space is filled up, so create a new block for it. * As the extent tree will be created, we have to save the inline * dir first. */ ret = ext4_convert_inline_data_nolock(handle, dir, &iloc); out: ext4_write_unlock_xattr(dir, &no_expand); ret2 = ext4_mark_inode_dirty(handle, dir); if (unlikely(ret2 && !ret)) ret = ret2; brelse(iloc.bh); return ret; } /* * This function fills a red-black tree with information from an * inlined dir. It returns the number directory entries loaded * into the tree. If there is an error it is returned in err. */ int ext4_inlinedir_to_tree(struct file *dir_file, struct inode *dir, ext4_lblk_t block, struct dx_hash_info *hinfo, __u32 start_hash, __u32 start_minor_hash, int *has_inline_data) { int err = 0, count = 0; unsigned int parent_ino; int pos; struct ext4_dir_entry_2 *de; struct inode *inode = file_inode(dir_file); int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; struct ext4_dir_entry_2 fake; struct fscrypt_str tmp_str; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); *has_inline_data = 0; goto out; } inline_size = ext4_get_inline_size(inode); dir_buf = kmalloc(inline_size, GFP_NOFS); if (!dir_buf) { ret = -ENOMEM; up_read(&EXT4_I(inode)->xattr_sem); goto out; } ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); up_read(&EXT4_I(inode)->xattr_sem); if (ret < 0) goto out; pos = 0; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); while (pos < inline_size) { /* * As inlined dir doesn't store any information about '.' and * only the inode number of '..' is stored, we have to handle * them differently. */ if (pos == 0) { fake.inode = cpu_to_le32(inode->i_ino); fake.name_len = 1; strcpy(fake.name, "."); fake.rec_len = ext4_rec_len_to_disk( ext4_dir_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_OFFSET; } else if (pos == EXT4_INLINE_DOTDOT_OFFSET) { fake.inode = cpu_to_le32(parent_ino); fake.name_len = 2; strcpy(fake.name, ".."); fake.rec_len = ext4_rec_len_to_disk( ext4_dir_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_SIZE; } else { de = (struct ext4_dir_entry_2 *)(dir_buf + pos); pos += ext4_rec_len_from_disk(de->rec_len, inline_size); if (ext4_check_dir_entry(inode, dir_file, de, iloc.bh, dir_buf, inline_size, pos)) { ret = count; goto out; } } if (ext4_hash_in_dirent(dir)) { hinfo->hash = EXT4_DIRENT_HASH(de); hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); } else { err = ext4fs_dirhash(dir, de->name, de->name_len, hinfo); if (err) { ret = err; goto out; } } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) continue; if (de->inode == 0) continue; tmp_str.name = de->name; tmp_str.len = de->name_len; err = ext4_htree_store_dirent(dir_file, hinfo->hash, hinfo->minor_hash, de, &tmp_str); if (err) { ret = err; goto out; } count++; } ret = count; out: kfree(dir_buf); brelse(iloc.bh); return ret; } /* * So this function is called when the volume is mkfsed with * dir_index disabled. In order to keep f_pos persistent * after we convert from an inlined dir to a blocked based, * we just pretend that we are a normal dir and return the * offset as if '.' and '..' really take place. * */ int ext4_read_inline_dir(struct file *file, struct dir_context *ctx, int *has_inline_data) { unsigned int offset, parent_ino; int i; struct ext4_dir_entry_2 *de; struct super_block *sb; struct inode *inode = file_inode(file); int ret, inline_size = 0; struct ext4_iloc iloc; void *dir_buf = NULL; int dotdot_offset, dotdot_size, extra_offset, extra_size; struct dir_private_info *info = file->private_data; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) { up_read(&EXT4_I(inode)->xattr_sem); *has_inline_data = 0; goto out; } inline_size = ext4_get_inline_size(inode); dir_buf = kmalloc(inline_size, GFP_NOFS); if (!dir_buf) { ret = -ENOMEM; up_read(&EXT4_I(inode)->xattr_sem); goto out; } ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc); up_read(&EXT4_I(inode)->xattr_sem); if (ret < 0) goto out; ret = 0; sb = inode->i_sb; parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode); offset = ctx->pos; /* * dotdot_offset and dotdot_size is the real offset and * size for ".." and "." if the dir is block based while * the real size for them are only EXT4_INLINE_DOTDOT_SIZE. * So we will use extra_offset and extra_size to indicate them * during the inline dir iteration. */ dotdot_offset = ext4_dir_rec_len(1, NULL); dotdot_size = dotdot_offset + ext4_dir_rec_len(2, NULL); extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; extra_size = extra_offset + inline_size; /* * If the cookie has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the inline * dir to make sure. */ if (!inode_eq_iversion(inode, info->cookie)) { for (i = 0; i < extra_size && i < offset;) { /* * "." is with offset 0 and * ".." is dotdot_offset. */ if (!i) { i = dotdot_offset; continue; } else if (i == dotdot_offset) { i = dotdot_size; continue; } /* for other entry, the real offset in * the buf has to be tuned accordingly. */ de = (struct ext4_dir_entry_2 *) (dir_buf + i - extra_offset); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, extra_size) < ext4_dir_rec_len(1, NULL)) break; i += ext4_rec_len_from_disk(de->rec_len, extra_size); } offset = i; ctx->pos = offset; info->cookie = inode_query_iversion(inode); } while (ctx->pos < extra_size) { if (ctx->pos == 0) { if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR)) goto out; ctx->pos = dotdot_offset; continue; } if (ctx->pos == dotdot_offset) { if (!dir_emit(ctx, "..", 2, parent_ino, DT_DIR)) goto out; ctx->pos = dotdot_size; continue; } de = (struct ext4_dir_entry_2 *) (dir_buf + ctx->pos - extra_offset); if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf, extra_size, ctx->pos)) goto out; if (le32_to_cpu(de->inode)) { if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto out; } ctx->pos += ext4_rec_len_from_disk(de->rec_len, extra_size); } out: kfree(dir_buf); brelse(iloc.bh); return ret; } void *ext4_read_inline_link(struct inode *inode) { struct ext4_iloc iloc; int ret, inline_size; void *link; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ERR_PTR(ret); ret = -ENOMEM; inline_size = ext4_get_inline_size(inode); link = kmalloc(inline_size + 1, GFP_NOFS); if (!link) goto out; ret = ext4_read_inline_data(inode, link, inline_size, &iloc); if (ret < 0) { kfree(link); goto out; } nd_terminate_link(link, inode->i_size, ret); out: if (ret < 0) link = ERR_PTR(ret); brelse(iloc.bh); return link; } struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval) { struct ext4_iloc iloc; *retval = ext4_get_inode_loc(inode, &iloc); if (*retval) return NULL; *parent_de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; return iloc.bh; } /* * Try to create the inline data for the new dir. * If it succeeds, return 0, otherwise return the error. * In case of ENOSPC, the caller should create the normal disk layout dir. */ int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, struct inode *inode) { int ret, inline_size = EXT4_MIN_INLINE_DATA_SIZE; struct ext4_iloc iloc; struct ext4_dir_entry_2 *de; ret = ext4_get_inode_loc(inode, &iloc); if (ret) return ret; ret = ext4_prepare_inline_data(handle, inode, inline_size); if (ret) goto out; /* * For inline dir, we only save the inode information for the ".." * and create a fake dentry to cover the left space. */ de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; de->inode = cpu_to_le32(parent->i_ino); de = (struct ext4_dir_entry_2 *)((void *)de + EXT4_INLINE_DOTDOT_SIZE); de->inode = 0; de->rec_len = ext4_rec_len_to_disk( inline_size - EXT4_INLINE_DOTDOT_SIZE, inline_size); set_nlink(inode, 2); inode->i_size = EXT4_I(inode)->i_disksize = inline_size; out: brelse(iloc.bh); return ret; } struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, int *has_inline_data) { struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; int ret; void *inline_start; int inline_size; ret = ext4_get_inode_loc(dir, &is.iloc); if (ret) return ERR_PTR(ret); down_read(&EXT4_I(dir)->xattr_sem); ret = ext4_xattr_ibody_find(dir, &i, &is); if (ret) goto out; if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; goto out; } inline_start = (void *)ext4_raw_inode(&is.iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size, dir, fname, 0, res_dir); if (ret == 1) goto out_find; if (ret < 0) goto out; if (ext4_get_inline_size(dir) == EXT4_MIN_INLINE_DATA_SIZE) goto out; inline_start = ext4_get_inline_xattr_pos(dir, &is.iloc); inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size, dir, fname, 0, res_dir); if (ret == 1) goto out_find; out: brelse(is.iloc.bh); if (ret < 0) is.iloc.bh = ERR_PTR(ret); else is.iloc.bh = NULL; out_find: up_read(&EXT4_I(dir)->xattr_sem); return is.iloc.bh; } int ext4_delete_inline_entry(handle_t *handle, struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, int *has_inline_data) { int err, inline_size, no_expand; struct ext4_iloc iloc; void *inline_start; err = ext4_get_inode_loc(dir, &iloc); if (err) return err; ext4_write_lock_xattr(dir, &no_expand); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; goto out; } if ((void *)de_del - ((void *)ext4_raw_inode(&iloc)->i_block) < EXT4_MIN_INLINE_DATA_SIZE) { inline_start = (void *)ext4_raw_inode(&iloc)->i_block + EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; } else { inline_start = ext4_get_inline_xattr_pos(dir, &iloc); inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; } BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, dir->i_sb, bh, EXT4_JTR_NONE); if (err) goto out; err = ext4_generic_delete_entry(dir, de_del, bh, inline_start, inline_size, 0); if (err) goto out; ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size); out: ext4_write_unlock_xattr(dir, &no_expand); if (likely(err == 0)) err = ext4_mark_inode_dirty(handle, dir); brelse(iloc.bh); if (err != -ENOENT) ext4_std_error(dir->i_sb, err); return err; } /* * Get the inline dentry at offset. */ static inline struct ext4_dir_entry_2 * ext4_get_inline_entry(struct inode *inode, struct ext4_iloc *iloc, unsigned int offset, void **inline_start, int *inline_size) { void *inline_pos; BUG_ON(offset > ext4_get_inline_size(inode)); if (offset < EXT4_MIN_INLINE_DATA_SIZE) { inline_pos = (void *)ext4_raw_inode(iloc)->i_block; *inline_size = EXT4_MIN_INLINE_DATA_SIZE; } else { inline_pos = ext4_get_inline_xattr_pos(inode, iloc); offset -= EXT4_MIN_INLINE_DATA_SIZE; *inline_size = ext4_get_inline_size(inode) - EXT4_MIN_INLINE_DATA_SIZE; } if (inline_start) *inline_start = inline_pos; return (struct ext4_dir_entry_2 *)(inline_pos + offset); } bool empty_inline_dir(struct inode *dir, int *has_inline_data) { int err, inline_size; struct ext4_iloc iloc; size_t inline_len; void *inline_pos; unsigned int offset; struct ext4_dir_entry_2 *de; bool ret = false; err = ext4_get_inode_loc(dir, &iloc); if (err) { EXT4_ERROR_INODE_ERR(dir, -err, "error %d getting inode %lu block", err, dir->i_ino); return false; } down_read(&EXT4_I(dir)->xattr_sem); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; ret = true; goto out; } de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block; if (!le32_to_cpu(de->inode)) { ext4_warning(dir->i_sb, "bad inline directory (dir #%lu) - no `..'", dir->i_ino); goto out; } inline_len = ext4_get_inline_size(dir); offset = EXT4_INLINE_DOTDOT_SIZE; while (offset < inline_len) { de = ext4_get_inline_entry(dir, &iloc, offset, &inline_pos, &inline_size); if (ext4_check_dir_entry(dir, NULL, de, iloc.bh, inline_pos, inline_size, offset)) { ext4_warning(dir->i_sb, "bad inline directory (dir #%lu) - " "inode %u, rec_len %u, name_len %d" "inline size %d", dir->i_ino, le32_to_cpu(de->inode), le16_to_cpu(de->rec_len), de->name_len, inline_size); goto out; } if (le32_to_cpu(de->inode)) { goto out; } offset += ext4_rec_len_from_disk(de->rec_len, inline_size); } ret = true; out: up_read(&EXT4_I(dir)->xattr_sem); brelse(iloc.bh); return ret; } int ext4_destroy_inline_data(handle_t *handle, struct inode *inode) { int ret, no_expand; ext4_write_lock_xattr(inode, &no_expand); ret = ext4_destroy_inline_data_nolock(handle, inode); ext4_write_unlock_xattr(inode, &no_expand); return ret; } int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap) { __u64 addr; int error = -EAGAIN; struct ext4_iloc iloc; down_read(&EXT4_I(inode)->xattr_sem); if (!ext4_has_inline_data(inode)) goto out; error = ext4_get_inode_loc(inode, &iloc); if (error) goto out; addr = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits; addr += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; addr += offsetof(struct ext4_inode, i_block); brelse(iloc.bh); iomap->addr = addr; iomap->offset = 0; iomap->length = min_t(loff_t, ext4_get_inline_size(inode), i_size_read(inode)); iomap->type = IOMAP_INLINE; iomap->flags = 0; out: up_read(&EXT4_I(inode)->xattr_sem); return error; } int ext4_inline_data_truncate(struct inode *inode, int *has_inline) { handle_t *handle; int inline_size, value_len, needed_blocks, no_expand, err = 0; size_t i_size; void *value = NULL; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_info i = { .name_index = EXT4_XATTR_INDEX_SYSTEM, .name = EXT4_XATTR_SYSTEM_DATA, }; needed_blocks = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_write_lock_xattr(inode, &no_expand); if (!ext4_has_inline_data(inode)) { ext4_write_unlock_xattr(inode, &no_expand); *has_inline = 0; ext4_journal_stop(handle); return 0; } if ((err = ext4_orphan_add(handle, inode)) != 0) goto out; if ((err = ext4_get_inode_loc(inode, &is.iloc)) != 0) goto out; down_write(&EXT4_I(inode)->i_data_sem); i_size = inode->i_size; inline_size = ext4_get_inline_size(inode); EXT4_I(inode)->i_disksize = i_size; if (i_size < inline_size) { /* * if there's inline data to truncate and this file was * converted to extents after that inline data was written, * the extent status cache must be cleared to avoid leaving * behind stale delayed allocated extent entries */ if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); /* Clear the content in the xattr space. */ if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) { if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0) goto out_error; BUG_ON(is.s.not_found); value_len = le32_to_cpu(is.s.here->e_value_size); value = kmalloc(value_len, GFP_NOFS); if (!value) { err = -ENOMEM; goto out_error; } err = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, value_len); if (err <= 0) goto out_error; i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; } /* Clear the content within i_blocks. */ if (i_size < EXT4_MIN_INLINE_DATA_SIZE) { void *p = (void *) ext4_raw_inode(&is.iloc)->i_block; memset(p + i_size, 0, EXT4_MIN_INLINE_DATA_SIZE - i_size); } EXT4_I(inode)->i_inline_size = i_size < EXT4_MIN_INLINE_DATA_SIZE ? EXT4_MIN_INLINE_DATA_SIZE : i_size; } out_error: up_write(&EXT4_I(inode)->i_data_sem); out: brelse(is.iloc.bh); ext4_write_unlock_xattr(inode, &no_expand); kfree(value); if (inode->i_nlink) ext4_orphan_del(handle, inode); if (err == 0) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); if (IS_SYNC(inode)) ext4_handle_sync(handle); } ext4_journal_stop(handle); return err; } int ext4_convert_inline_data(struct inode *inode) { int error, needed_blocks, no_expand; handle_t *handle; struct ext4_iloc iloc; if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; } else if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { /* * Inode has inline data but EXT4_STATE_MAY_INLINE_DATA is * cleared. This means we are in the middle of moving of * inline data to delay allocated block. Just force writeout * here to finish conversion. */ error = filemap_flush(inode->i_mapping); if (error) return error; if (!ext4_has_inline_data(inode)) return 0; } needed_blocks = ext4_writepage_trans_blocks(inode); iloc.bh = NULL; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto out_free; } ext4_write_lock_xattr(inode, &no_expand); if (ext4_has_inline_data(inode)) error = ext4_convert_inline_data_nolock(handle, inode, &iloc); ext4_write_unlock_xattr(inode, &no_expand); ext4_journal_stop(handle); out_free: brelse(iloc.bh); return error; } |
| 6 2 3 1 2 6 1 1 3 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Xtables module for matching the value of the IPv4/IPv6 and TCP ECN bits * * (C) 2002 by Harald Welte <laforge@gnumonks.org> * (C) 2011 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/ip.h> #include <net/ip.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/tcp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_ecn.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: Explicit Congestion Notification (ECN) flag match"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_ecn"); MODULE_ALIAS("ip6t_ecn"); static bool match_tcp(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_ecn_info *einfo = par->matchinfo; struct tcphdr _tcph; const struct tcphdr *th; /* In practice, TCP match does this, so can't fail. But let's * be good citizens. */ th = skb_header_pointer(skb, par->thoff, sizeof(_tcph), &_tcph); if (th == NULL) return false; if (einfo->operation & XT_ECN_OP_MATCH_ECE) { if (einfo->invert & XT_ECN_OP_MATCH_ECE) { if (th->ece == 1) return false; } else { if (th->ece == 0) return false; } } if (einfo->operation & XT_ECN_OP_MATCH_CWR) { if (einfo->invert & XT_ECN_OP_MATCH_CWR) { if (th->cwr == 1) return false; } else { if (th->cwr == 0) return false; } } return true; } static inline bool match_ip(const struct sk_buff *skb, const struct xt_ecn_info *einfo) { return ((ip_hdr(skb)->tos & XT_ECN_IP_MASK) == einfo->ip_ect) ^ !!(einfo->invert & XT_ECN_OP_MATCH_IP); } static bool ecn_mt4(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_ecn_info *info = par->matchinfo; if (info->operation & XT_ECN_OP_MATCH_IP && !match_ip(skb, info)) return false; if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) && !match_tcp(skb, par)) return false; return true; } static int ecn_mt_check4(const struct xt_mtchk_param *par) { const struct xt_ecn_info *info = par->matchinfo; const struct ipt_ip *ip = par->entryinfo; if (info->operation & XT_ECN_OP_MATCH_MASK) return -EINVAL; if (info->invert & XT_ECN_OP_MATCH_MASK) return -EINVAL; if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) && (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) { pr_info_ratelimited("cannot match TCP bits for non-tcp packets\n"); return -EINVAL; } return 0; } static inline bool match_ipv6(const struct sk_buff *skb, const struct xt_ecn_info *einfo) { return (((ipv6_hdr(skb)->flow_lbl[0] >> 4) & XT_ECN_IP_MASK) == einfo->ip_ect) ^ !!(einfo->invert & XT_ECN_OP_MATCH_IP); } static bool ecn_mt6(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_ecn_info *info = par->matchinfo; if (info->operation & XT_ECN_OP_MATCH_IP && !match_ipv6(skb, info)) return false; if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) && !match_tcp(skb, par)) return false; return true; } static int ecn_mt_check6(const struct xt_mtchk_param *par) { const struct xt_ecn_info *info = par->matchinfo; const struct ip6t_ip6 *ip = par->entryinfo; if (info->operation & XT_ECN_OP_MATCH_MASK) return -EINVAL; if (info->invert & XT_ECN_OP_MATCH_MASK) return -EINVAL; if (info->operation & (XT_ECN_OP_MATCH_ECE | XT_ECN_OP_MATCH_CWR) && (ip->proto != IPPROTO_TCP || ip->invflags & IP6T_INV_PROTO)) { pr_info_ratelimited("cannot match TCP bits for non-tcp packets\n"); return -EINVAL; } return 0; } static struct xt_match ecn_mt_reg[] __read_mostly = { { .name = "ecn", .family = NFPROTO_IPV4, .match = ecn_mt4, .matchsize = sizeof(struct xt_ecn_info), .checkentry = ecn_mt_check4, .me = THIS_MODULE, }, { .name = "ecn", .family = NFPROTO_IPV6, .match = ecn_mt6, .matchsize = sizeof(struct xt_ecn_info), .checkentry = ecn_mt_check6, .me = THIS_MODULE, }, }; static int __init ecn_mt_init(void) { return xt_register_matches(ecn_mt_reg, ARRAY_SIZE(ecn_mt_reg)); } static void __exit ecn_mt_exit(void) { xt_unregister_matches(ecn_mt_reg, ARRAY_SIZE(ecn_mt_reg)); } module_init(ecn_mt_init); module_exit(ecn_mt_exit); |
| 17 1 1 2 12 4 1 8 4 1 3 2 5 6 1 4 3 6 2 2 5 7 1 7 4 3 3 4 3 3 4 4 4 509 509 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_skbmod.c skb data modifier * * Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com> */ #include <linux/module.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/inet_ecn.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/tc_act/tc_skbmod.h> #include <net/tc_act/tc_skbmod.h> static struct tc_action_ops act_skbmod_ops; TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_skbmod *d = to_skbmod(a); int action, max_edit_len, err; struct tcf_skbmod_params *p; u64 flags; tcf_lastuse_update(&d->tcf_tm); bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); action = READ_ONCE(d->tcf_action); if (unlikely(action == TC_ACT_SHOT)) goto drop; max_edit_len = skb_mac_header_len(skb); p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; /* tcf_skbmod_init() guarantees "flags" to be one of the following: * 1. a combination of SKBMOD_F_{DMAC,SMAC,ETYPE} * 2. SKBMOD_F_SWAPMAC * 3. SKBMOD_F_ECN * SKBMOD_F_ECN only works with IP packets; all other flags only work with Ethernet * packets. */ if (flags == SKBMOD_F_ECN) { switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): case cpu_to_be16(ETH_P_IPV6): max_edit_len += skb_network_header_len(skb); break; default: goto out; } } else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) { goto out; } err = skb_ensure_writable(skb, max_edit_len); if (unlikely(err)) /* best policy is to drop on the floor */ goto drop; if (flags & SKBMOD_F_DMAC) ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); if (flags & SKBMOD_F_SMAC) ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src); if (flags & SKBMOD_F_ETYPE) eth_hdr(skb)->h_proto = p->eth_type; if (flags & SKBMOD_F_SWAPMAC) { u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */ /*XXX: I am sure we can come up with more efficient swapping*/ ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest); ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source); ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr); } if (flags & SKBMOD_F_ECN) INET_ECN_set_ce(skb); out: return action; drop: qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); return TC_ACT_SHOT; } static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { [TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) }, [TCA_SKBMOD_DMAC] = { .len = ETH_ALEN }, [TCA_SKBMOD_SMAC] = { .len = ETH_ALEN }, [TCA_SKBMOD_ETYPE] = { .type = NLA_U16 }, }; static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id); bool ovr = flags & TCA_ACT_FLAGS_REPLACE; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SKBMOD_MAX + 1]; struct tcf_skbmod_params *p, *p_old; struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; u32 lflags = 0, index; struct tcf_skbmod *d; bool exists = false; u8 *daddr = NULL; u8 *saddr = NULL; u16 eth_type = 0; int ret = 0, err; if (!nla) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_SKBMOD_MAX, nla, skbmod_policy, NULL); if (err < 0) return err; if (!tb[TCA_SKBMOD_PARMS]) return -EINVAL; if (tb[TCA_SKBMOD_DMAC]) { daddr = nla_data(tb[TCA_SKBMOD_DMAC]); lflags |= SKBMOD_F_DMAC; } if (tb[TCA_SKBMOD_SMAC]) { saddr = nla_data(tb[TCA_SKBMOD_SMAC]); lflags |= SKBMOD_F_SMAC; } if (tb[TCA_SKBMOD_ETYPE]) { eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]); lflags |= SKBMOD_F_ETYPE; } parm = nla_data(tb[TCA_SKBMOD_PARMS]); index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; if (parm->flags & SKBMOD_F_ECN) lflags = SKBMOD_F_ECN; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!lflags) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_skbmod_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; d = to_skbmod(*a); p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); if (unlikely(!p)) { err = -ENOMEM; goto put_chain; } p->flags = lflags; if (ovr) spin_lock_bh(&d->tcf_lock); /* Protected by tcf_lock if overwriting existing action. */ goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p_old = rcu_dereference_protected(d->skbmod_p, 1); if (lflags & SKBMOD_F_DMAC) ether_addr_copy(p->eth_dst, daddr); if (lflags & SKBMOD_F_SMAC) ether_addr_copy(p->eth_src, saddr); if (lflags & SKBMOD_F_ETYPE) p->eth_type = htons(eth_type); rcu_assign_pointer(d->skbmod_p, p); if (ovr) spin_unlock_bh(&d->tcf_lock); if (p_old) kfree_rcu(p_old, rcu); if (goto_ch) tcf_chain_put_by_act(goto_ch); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static void tcf_skbmod_cleanup(struct tc_action *a) { struct tcf_skbmod *d = to_skbmod(a); struct tcf_skbmod_params *p; p = rcu_dereference_protected(d->skbmod_p, 1); if (p) kfree_rcu(p, rcu); } static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; struct tc_skbmod opt; struct tcf_t t; memset(&opt, 0, sizeof(opt)); opt.index = d->tcf_index; opt.refcnt = refcount_read(&d->tcf_refcnt) - ref; opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; p = rcu_dereference_protected(d->skbmod_p, lockdep_is_held(&d->tcf_lock)); opt.flags = p->flags; if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if ((p->flags & SKBMOD_F_DMAC) && nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; if ((p->flags & SKBMOD_F_SMAC) && nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; if ((p->flags & SKBMOD_F_ETYPE) && nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type))) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD)) goto nla_put_failure; spin_unlock_bh(&d->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", .id = TCA_ACT_SKBMOD, .owner = THIS_MODULE, .act = tcf_skbmod_act, .dump = tcf_skbmod_dump, .init = tcf_skbmod_init, .cleanup = tcf_skbmod_cleanup, .size = sizeof(struct tcf_skbmod), }; MODULE_ALIAS_NET_ACT("skbmod"); static __net_init int skbmod_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id); return tc_action_net_init(net, tn, &act_skbmod_ops); } static void __net_exit skbmod_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_skbmod_ops.net_id); } static struct pernet_operations skbmod_net_ops = { .init = skbmod_init_net, .exit_batch = skbmod_exit_net, .id = &act_skbmod_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>"); MODULE_DESCRIPTION("SKB data mod-ing"); MODULE_LICENSE("GPL"); static int __init skbmod_init_module(void) { return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops); } static void __exit skbmod_cleanup_module(void) { tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops); } module_init(skbmod_init_module); module_exit(skbmod_cleanup_module); |
| 122 3 123 123 3 1 1 120 120 120 120 119 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 | /* * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * Copyright (c) 2005 PathScale, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/module.h> #include <linux/init.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/file.h> #include <linux/cdev.h> #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <rdma/ib.h> #include <rdma/uverbs_std_types.h> #include <rdma/rdma_netlink.h> #include <rdma/ib_ucaps.h> #include "uverbs.h" #include "core_priv.h" #include "rdma_core.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand userspace verbs access"); MODULE_LICENSE("Dual BSD/GPL"); enum { IB_UVERBS_MAJOR = 231, IB_UVERBS_BASE_MINOR = 192, IB_UVERBS_MAX_DEVICES = RDMA_MAX_PORTS, IB_UVERBS_NUM_FIXED_MINOR = 32, IB_UVERBS_NUM_DYNAMIC_MINOR = IB_UVERBS_MAX_DEVICES - IB_UVERBS_NUM_FIXED_MINOR, }; #define IB_UVERBS_BASE_DEV MKDEV(IB_UVERBS_MAJOR, IB_UVERBS_BASE_MINOR) static dev_t dynamic_uverbs_dev; static DEFINE_IDA(uverbs_ida); static int ib_uverbs_add_one(struct ib_device *device); static void ib_uverbs_remove_one(struct ib_device *device, void *client_data); static struct ib_client uverbs_client; static char *uverbs_devnode(const struct device *dev, umode_t *mode) { if (mode) *mode = 0666; return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } static const struct class uverbs_class = { .name = "infiniband_verbs", .devnode = uverbs_devnode, }; /* * Must be called with the ufile->device->disassociate_srcu held, and the lock * must be held until use of the ucontext is finished. */ struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile) { /* * We do not hold the hw_destroy_rwsem lock for this flow, instead * srcu is used. It does not matter if someone races this with * get_context, we get NULL or valid ucontext. */ struct ib_ucontext *ucontext = smp_load_acquire(&ufile->ucontext); if (!srcu_dereference(ufile->device->ib_dev, &ufile->device->disassociate_srcu)) return ERR_PTR(-EIO); if (!ucontext) return ERR_PTR(-EINVAL); return ucontext; } EXPORT_SYMBOL(ib_uverbs_get_ucontext_file); int uverbs_dealloc_mw(struct ib_mw *mw) { struct ib_pd *pd = mw->pd; int ret; ret = mw->device->ops.dealloc_mw(mw); if (ret) return ret; atomic_dec(&pd->usecnt); kfree(mw); return ret; } static void ib_uverbs_release_dev(struct device *device) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); uverbs_destroy_api(dev->uapi); cleanup_srcu_struct(&dev->disassociate_srcu); mutex_destroy(&dev->lists_mutex); mutex_destroy(&dev->xrcd_tree_mutex); kfree(dev); } void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file, struct ib_ucq_object *uobj) { struct ib_uverbs_event *evt, *tmp; if (ev_file) { spin_lock_irq(&ev_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->comp_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&ev_file->ev_queue.lock); uverbs_uobject_put(&ev_file->uobj); } ib_uverbs_release_uevent(&uobj->uevent); } void ib_uverbs_release_uevent(struct ib_uevent_object *uobj) { struct ib_uverbs_async_event_file *async_file = uobj->event_file; struct ib_uverbs_event *evt, *tmp; if (!async_file) return; spin_lock_irq(&async_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->event_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&async_file->ev_queue.lock); uverbs_uobject_put(&async_file->uobj); } void ib_uverbs_detach_umcast(struct ib_qp *qp, struct ib_uqp_object *uobj) { struct ib_uverbs_mcast_entry *mcast, *tmp; list_for_each_entry_safe(mcast, tmp, &uobj->mcast_list, list) { ib_detach_mcast(qp, &mcast->gid, mcast->lid); list_del(&mcast->list); kfree(mcast); } } static void ib_uverbs_comp_dev(struct ib_uverbs_device *dev) { complete(&dev->comp); } void ib_uverbs_release_file(struct kref *ref) { struct ib_uverbs_file *file = container_of(ref, struct ib_uverbs_file, ref); struct ib_device *ib_dev; int srcu_key; release_ufile_idr_uobject(file); srcu_key = srcu_read_lock(&file->device->disassociate_srcu); ib_dev = srcu_dereference(file->device->ib_dev, &file->device->disassociate_srcu); if (ib_dev && !ib_dev->ops.disassociate_ucontext) module_put(ib_dev->ops.owner); srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); if (refcount_dec_and_test(&file->device->refcount)) ib_uverbs_comp_dev(file->device); if (file->default_async_file) uverbs_uobject_put(&file->default_async_file->uobj); put_device(&file->device->dev); if (file->disassociate_page) __free_pages(file->disassociate_page, 0); mutex_destroy(&file->disassociation_lock); mutex_destroy(&file->umap_lock); mutex_destroy(&file->ucontext_lock); kfree(file); } static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, struct file *filp, char __user *buf, size_t count, loff_t *pos, size_t eventsz) { struct ib_uverbs_event *event; int ret = 0; spin_lock_irq(&ev_queue->lock); while (list_empty(&ev_queue->event_list)) { if (ev_queue->is_closed) { spin_unlock_irq(&ev_queue->lock); return -EIO; } spin_unlock_irq(&ev_queue->lock); if (filp->f_flags & O_NONBLOCK) return -EAGAIN; if (wait_event_interruptible(ev_queue->poll_wait, (!list_empty(&ev_queue->event_list) || ev_queue->is_closed))) return -ERESTARTSYS; spin_lock_irq(&ev_queue->lock); } event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list); if (eventsz > count) { ret = -EINVAL; event = NULL; } else { list_del(ev_queue->event_list.next); if (event->counter) { ++(*event->counter); list_del(&event->obj_list); } } spin_unlock_irq(&ev_queue->lock); if (event) { if (copy_to_user(buf, event, eventsz)) ret = -EFAULT; else ret = eventsz; } kfree(event); return ret; } static ssize_t ib_uverbs_async_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_read(&file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_async_event_desc)); } static ssize_t ib_uverbs_comp_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_read(&comp_ev_file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_comp_event_desc)); } static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue, struct file *filp, struct poll_table_struct *wait) { __poll_t pollflags = 0; poll_wait(filp, &ev_queue->poll_wait, wait); spin_lock_irq(&ev_queue->lock); if (!list_empty(&ev_queue->event_list)) pollflags = EPOLLIN | EPOLLRDNORM; else if (ev_queue->is_closed) pollflags = EPOLLERR; spin_unlock_irq(&ev_queue->lock); return pollflags; } static __poll_t ib_uverbs_async_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_poll(&file->ev_queue, filp, wait); } static __poll_t ib_uverbs_comp_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_poll(&comp_ev_file->ev_queue, filp, wait); } static int ib_uverbs_async_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_async_event_file *file = filp->private_data; return fasync_helper(fd, filp, on, &file->ev_queue.async_queue); } static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return fasync_helper(fd, filp, on, &comp_ev_file->ev_queue.async_queue); } const struct file_operations uverbs_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_comp_event_read, .poll = ib_uverbs_comp_event_poll, .release = uverbs_uobject_fd_release, .fasync = ib_uverbs_comp_event_fasync, }; const struct file_operations uverbs_async_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_async_event_read, .poll = ib_uverbs_async_event_poll, .release = uverbs_async_event_release, .fasync = ib_uverbs_async_event_fasync, }; void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) { struct ib_uverbs_event_queue *ev_queue = cq_context; struct ib_ucq_object *uobj; struct ib_uverbs_event *entry; unsigned long flags; if (!ev_queue) return; spin_lock_irqsave(&ev_queue->lock, flags); if (ev_queue->is_closed) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } uobj = cq->uobject; entry->desc.comp.cq_handle = cq->uobject->uevent.uobject.user_handle; entry->counter = &uobj->comp_events_reported; list_add_tail(&entry->list, &ev_queue->event_list); list_add_tail(&entry->obj_list, &uobj->comp_list); spin_unlock_irqrestore(&ev_queue->lock, flags); wake_up_interruptible(&ev_queue->poll_wait); kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN); } void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, __u64 element, __u64 event, struct list_head *obj_list, u32 *counter) { struct ib_uverbs_event *entry; unsigned long flags; if (!async_file) return; spin_lock_irqsave(&async_file->ev_queue.lock, flags); if (async_file->ev_queue.is_closed) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry->desc.async.element = element; entry->desc.async.event_type = event; entry->desc.async.reserved = 0; entry->counter = counter; list_add_tail(&entry->list, &async_file->ev_queue.event_list); if (obj_list) list_add_tail(&entry->obj_list, obj_list); spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); wake_up_interruptible(&async_file->ev_queue.poll_wait); kill_fasync(&async_file->ev_queue.async_queue, SIGIO, POLL_IN); } static void uverbs_uobj_event(struct ib_uevent_object *eobj, struct ib_event *event) { ib_uverbs_async_handler(eobj->event_file, eobj->uobject.user_handle, event->event, &eobj->event_list, &eobj->events_reported); } void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.cq->uobject->uevent, event); } void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr) { /* for XRC target qp's, check that qp is live */ if (!event->element.qp->uobject) return; uverbs_uobj_event(&event->element.qp->uobject->uevent, event); } void ib_uverbs_wq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.wq->uobject->uevent, event); } void ib_uverbs_srq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.srq->uobject->uevent, event); } static void ib_uverbs_event_handler(struct ib_event_handler *handler, struct ib_event *event) { ib_uverbs_async_handler( container_of(handler, struct ib_uverbs_async_event_file, event_handler), event->element.port_num, event->event, NULL, NULL); } void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue) { spin_lock_init(&ev_queue->lock); INIT_LIST_HEAD(&ev_queue->event_list); init_waitqueue_head(&ev_queue->poll_wait); ev_queue->is_closed = 0; ev_queue->async_queue = NULL; } void ib_uverbs_init_async_event_file( struct ib_uverbs_async_event_file *async_file) { struct ib_uverbs_file *uverbs_file = async_file->uobj.ufile; struct ib_device *ib_dev = async_file->uobj.context->device; ib_uverbs_init_event_queue(&async_file->ev_queue); /* The first async_event_file becomes the default one for the file. */ mutex_lock(&uverbs_file->ucontext_lock); if (!uverbs_file->default_async_file) { /* Pairs with the put in ib_uverbs_release_file */ uverbs_uobject_get(&async_file->uobj); smp_store_release(&uverbs_file->default_async_file, async_file); } mutex_unlock(&uverbs_file->ucontext_lock); INIT_IB_EVENT_HANDLER(&async_file->event_handler, ib_dev, ib_uverbs_event_handler); ib_register_event_handler(&async_file->event_handler); } static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr, struct ib_uverbs_ex_cmd_hdr *ex_hdr, size_t count, const struct uverbs_api_write_method *method_elm) { if (method_elm->is_ex) { count -= sizeof(*hdr) + sizeof(*ex_hdr); if ((hdr->in_words + ex_hdr->provider_in_words) * 8 != count) return -EINVAL; if (hdr->in_words * 8 < method_elm->req_size) return -ENOSPC; if (ex_hdr->cmd_hdr_reserved) return -EINVAL; if (ex_hdr->response) { if (!hdr->out_words && !ex_hdr->provider_out_words) return -EINVAL; if (hdr->out_words * 8 < method_elm->resp_size) return -ENOSPC; if (!access_ok(u64_to_user_ptr(ex_hdr->response), (hdr->out_words + ex_hdr->provider_out_words) * 8)) return -EFAULT; } else { if (hdr->out_words || ex_hdr->provider_out_words) return -EINVAL; } return 0; } /* not extended command */ if (hdr->in_words * 4 != count) return -EINVAL; if (count < method_elm->req_size + sizeof(*hdr)) { /* * rdma-core v18 and v19 have a bug where they send DESTROY_CQ * with a 16 byte write instead of 24. Old kernels didn't * check the size so they allowed this. Now that the size is * checked provide a compatibility work around to not break * those userspaces. */ if (hdr->command == IB_USER_VERBS_CMD_DESTROY_CQ && count == 16) { hdr->in_words = 6; return 0; } return -ENOSPC; } if (hdr->out_words * 4 < method_elm->resp_size) return -ENOSPC; return 0; } static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_file *file = filp->private_data; const struct uverbs_api_write_method *method_elm; struct uverbs_api *uapi = file->device->uapi; struct ib_uverbs_ex_cmd_hdr ex_hdr; struct ib_uverbs_cmd_hdr hdr; struct uverbs_attr_bundle bundle; int srcu_key; ssize_t ret; if (!ib_safe_file_access(filp)) { pr_err_once("uverbs_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", task_tgid_vnr(current), current->comm); return -EACCES; } if (count < sizeof(hdr)) return -EINVAL; if (copy_from_user(&hdr, buf, sizeof(hdr))) return -EFAULT; method_elm = uapi_get_method(uapi, hdr.command); if (IS_ERR(method_elm)) return PTR_ERR(method_elm); if (method_elm->is_ex) { if (count < (sizeof(hdr) + sizeof(ex_hdr))) return -EINVAL; if (copy_from_user(&ex_hdr, buf + sizeof(hdr), sizeof(ex_hdr))) return -EFAULT; } ret = verify_hdr(&hdr, &ex_hdr, count, method_elm); if (ret) return ret; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); buf += sizeof(hdr); memset(bundle.attr_present, 0, sizeof(bundle.attr_present)); bundle.ufile = file; bundle.context = NULL; /* only valid if bundle has uobject */ bundle.uobject = NULL; if (!method_elm->is_ex) { size_t in_len = hdr.in_words * 4 - sizeof(hdr); size_t out_len = hdr.out_words * 4; u64 response = 0; if (method_elm->has_udata) { bundle.driver_udata.inlen = in_len - method_elm->req_size; in_len = method_elm->req_size; if (bundle.driver_udata.inlen) bundle.driver_udata.inbuf = buf + in_len; else bundle.driver_udata.inbuf = NULL; } else { memset(&bundle.driver_udata, 0, sizeof(bundle.driver_udata)); } if (method_elm->has_resp) { /* * The macros check that if has_resp is set * then the command request structure starts * with a '__aligned u64 response' member. */ ret = get_user(response, (const u64 __user *)buf); if (ret) goto out_unlock; if (method_elm->has_udata) { bundle.driver_udata.outlen = out_len - method_elm->resp_size; out_len = method_elm->resp_size; if (bundle.driver_udata.outlen) bundle.driver_udata.outbuf = u64_to_user_ptr(response + out_len); else bundle.driver_udata.outbuf = NULL; } } else { bundle.driver_udata.outlen = 0; bundle.driver_udata.outbuf = NULL; } ib_uverbs_init_udata_buf_or_null( &bundle.ucore, buf, u64_to_user_ptr(response), in_len, out_len); } else { buf += sizeof(ex_hdr); ib_uverbs_init_udata_buf_or_null(&bundle.ucore, buf, u64_to_user_ptr(ex_hdr.response), hdr.in_words * 8, hdr.out_words * 8); ib_uverbs_init_udata_buf_or_null( &bundle.driver_udata, buf + bundle.ucore.inlen, u64_to_user_ptr(ex_hdr.response) + bundle.ucore.outlen, ex_hdr.provider_in_words * 8, ex_hdr.provider_out_words * 8); } ret = method_elm->handler(&bundle); if (bundle.uobject) uverbs_finalize_object(bundle.uobject, UVERBS_ACCESS_NEW, true, !ret, &bundle); out_unlock: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return (ret) ? : count; } static const struct vm_operations_struct rdma_umap_ops; static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma) { struct ib_uverbs_file *file = filp->private_data; struct ib_ucontext *ucontext; int ret = 0; int srcu_key; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); ucontext = ib_uverbs_get_ucontext_file(file); if (IS_ERR(ucontext)) { ret = PTR_ERR(ucontext); goto out; } mutex_lock(&file->disassociation_lock); vma->vm_ops = &rdma_umap_ops; ret = ucontext->device->ops.mmap(ucontext, vma); mutex_unlock(&file->disassociation_lock); out: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return ret; } /* * The VMA has been dup'd, initialize the vm_private_data with a new tracking * struct */ static void rdma_umap_open(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *opriv = vma->vm_private_data; struct rdma_umap_priv *priv; if (!opriv) return; /* We are racing with disassociation */ if (!down_read_trylock(&ufile->hw_destroy_rwsem)) goto out_zap; mutex_lock(&ufile->disassociation_lock); /* * Disassociation already completed, the VMA should already be zapped. */ if (!ufile->ucontext) goto out_unlock; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) goto out_unlock; rdma_umap_priv_init(priv, vma, opriv->entry); mutex_unlock(&ufile->disassociation_lock); up_read(&ufile->hw_destroy_rwsem); return; out_unlock: mutex_unlock(&ufile->disassociation_lock); up_read(&ufile->hw_destroy_rwsem); out_zap: /* * We can't allow the VMA to be created with the actual IO pages, that * would break our API contract, and it can't be stopped at this * point, so zap it. */ vma->vm_private_data = NULL; zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); } static void rdma_umap_close(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *priv = vma->vm_private_data; if (!priv) return; /* * The vma holds a reference on the struct file that created it, which * in turn means that the ib_uverbs_file is guaranteed to exist at * this point. */ mutex_lock(&ufile->umap_lock); if (priv->entry) rdma_user_mmap_entry_put(priv->entry); list_del(&priv->list); mutex_unlock(&ufile->umap_lock); kfree(priv); } /* * Once the zap_vma_ptes has been called touches to the VMA will come here and * we return a dummy writable zero page for all the pfns. */ static vm_fault_t rdma_umap_fault(struct vm_fault *vmf) { struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data; struct rdma_umap_priv *priv = vmf->vma->vm_private_data; vm_fault_t ret = 0; if (!priv) return VM_FAULT_SIGBUS; /* Read only pages can just use the system zero page. */ if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) { vmf->page = ZERO_PAGE(vmf->address); get_page(vmf->page); return 0; } mutex_lock(&ufile->umap_lock); if (!ufile->disassociate_page) ufile->disassociate_page = alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0); if (ufile->disassociate_page) { /* * This VMA is forced to always be shared so this doesn't have * to worry about COW. */ vmf->page = ufile->disassociate_page; get_page(vmf->page); } else { ret = VM_FAULT_SIGBUS; } mutex_unlock(&ufile->umap_lock); return ret; } static const struct vm_operations_struct rdma_umap_ops = { .open = rdma_umap_open, .close = rdma_umap_close, .fault = rdma_umap_fault, }; void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) { struct rdma_umap_priv *priv, *next_priv; mutex_lock(&ufile->disassociation_lock); while (1) { struct mm_struct *mm = NULL; /* Get an arbitrary mm pointer that hasn't been cleaned yet */ mutex_lock(&ufile->umap_lock); while (!list_empty(&ufile->umaps)) { int ret; priv = list_first_entry(&ufile->umaps, struct rdma_umap_priv, list); mm = priv->vma->vm_mm; ret = mmget_not_zero(mm); if (!ret) { list_del_init(&priv->list); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } mm = NULL; continue; } break; } mutex_unlock(&ufile->umap_lock); if (!mm) { mutex_unlock(&ufile->disassociation_lock); return; } /* * The umap_lock is nested under mmap_lock since it used within * the vma_ops callbacks, so we have to clean the list one mm * at a time to get the lock ordering right. Typically there * will only be one mm, so no big deal. */ mmap_read_lock(mm); mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { struct vm_area_struct *vma = priv->vma; if (vma->vm_mm != mm) continue; list_del_init(&priv->list); zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } } mutex_unlock(&ufile->umap_lock); mmap_read_unlock(mm); mmput(mm); } mutex_unlock(&ufile->disassociation_lock); } /** * rdma_user_mmap_disassociate() - Revoke mmaps for a device * @device: device to revoke * * This function should be called by drivers that need to disable mmaps for the * device, for instance because it is going to be reset. */ void rdma_user_mmap_disassociate(struct ib_device *device) { struct ib_uverbs_device *uverbs_dev = ib_get_client_data(device, &uverbs_client); struct ib_uverbs_file *ufile; mutex_lock(&uverbs_dev->lists_mutex); list_for_each_entry(ufile, &uverbs_dev->uverbs_file_list, list) { if (ufile->ucontext) uverbs_user_mmap_disassociate(ufile); } mutex_unlock(&uverbs_dev->lists_mutex); } EXPORT_SYMBOL(rdma_user_mmap_disassociate); /* * ib_uverbs_open() does not need the BKL: * * - the ib_uverbs_device structures are properly reference counted and * everything else is purely local to the file being created, so * races against other open calls are not a problem; * - there is no ioctl method to race against; * - the open method will either immediately run -ENXIO, or all * required initialization will be done. */ static int ib_uverbs_open(struct inode *inode, struct file *filp) { struct ib_uverbs_device *dev; struct ib_uverbs_file *file; struct ib_device *ib_dev; int ret; int module_dependent; int srcu_key; dev = container_of(inode->i_cdev, struct ib_uverbs_device, cdev); if (!refcount_inc_not_zero(&dev->refcount)) return -ENXIO; get_device(&dev->dev); srcu_key = srcu_read_lock(&dev->disassociate_srcu); mutex_lock(&dev->lists_mutex); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (!ib_dev) { ret = -EIO; goto err; } if (!rdma_dev_access_netns(ib_dev, current->nsproxy->net_ns)) { ret = -EPERM; goto err; } /* In case IB device supports disassociate ucontext, there is no hard * dependency between uverbs device and its low level device. */ module_dependent = !(ib_dev->ops.disassociate_ucontext); if (module_dependent) { if (!try_module_get(ib_dev->ops.owner)) { ret = -ENODEV; goto err; } } file = kzalloc(sizeof(*file), GFP_KERNEL); if (!file) { ret = -ENOMEM; if (module_dependent) goto err_module; goto err; } file->device = dev; kref_init(&file->ref); mutex_init(&file->ucontext_lock); spin_lock_init(&file->uobjects_lock); INIT_LIST_HEAD(&file->uobjects); init_rwsem(&file->hw_destroy_rwsem); mutex_init(&file->umap_lock); INIT_LIST_HEAD(&file->umaps); mutex_init(&file->disassociation_lock); filp->private_data = file; list_add_tail(&file->list, &dev->uverbs_file_list); mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); setup_ufile_idr_uobject(file); return stream_open(inode, filp); err_module: module_put(ib_dev->ops.owner); err: mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); if (refcount_dec_and_test(&dev->refcount)) ib_uverbs_comp_dev(dev); put_device(&dev->dev); return ret; } static int ib_uverbs_close(struct inode *inode, struct file *filp) { struct ib_uverbs_file *file = filp->private_data; uverbs_destroy_ufile_hw(file, RDMA_REMOVE_CLOSE); mutex_lock(&file->device->lists_mutex); list_del_init(&file->list); mutex_unlock(&file->device->lists_mutex); kref_put(&file->ref, ib_uverbs_release_file); return 0; } static const struct file_operations uverbs_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static const struct file_operations uverbs_mmap_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .mmap = ib_uverbs_mmap, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static int ib_uverbs_get_nl_info(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res) { struct ib_uverbs_device *uverbs_dev = client_data; int ret; if (res->port != -1) return -EINVAL; res->abi = ibdev->ops.uverbs_abi_ver; res->cdev = &uverbs_dev->dev; /* * To support DRIVER_ID binding in userspace some of the driver need * upgrading to expose their PCI dependent revision information * through get_context instead of relying on modalias matching. When * the drivers are fixed they can drop this flag. */ if (!ibdev->ops.uverbs_no_driver_id_binding) { ret = nla_put_u32(res->nl_msg, RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID, ibdev->ops.driver_id); if (ret) return ret; } return 0; } static struct ib_client uverbs_client = { .name = "uverbs", .no_kverbs_req = true, .add = ib_uverbs_add_one, .remove = ib_uverbs_remove_one, .get_nl_info = ib_uverbs_get_nl_info, }; MODULE_ALIAS_RDMA_CLIENT("uverbs"); static ssize_t ibdev_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%s\n", dev_name(&ib_dev->dev)); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(ibdev); static ssize_t abi_version_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%u\n", ib_dev->ops.uverbs_abi_ver); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(abi_version); static struct attribute *ib_dev_attrs[] = { &dev_attr_abi_version.attr, &dev_attr_ibdev.attr, NULL, }; static const struct attribute_group dev_attr_group = { .attrs = ib_dev_attrs, }; static CLASS_ATTR_STRING(abi_version, S_IRUGO, __stringify(IB_USER_VERBS_ABI_VERSION)); static int ib_uverbs_create_uapi(struct ib_device *device, struct ib_uverbs_device *uverbs_dev) { struct uverbs_api *uapi; uapi = uverbs_alloc_api(device); if (IS_ERR(uapi)) return PTR_ERR(uapi); uverbs_dev->uapi = uapi; return 0; } static int ib_uverbs_add_one(struct ib_device *device) { int devnum; dev_t base; struct ib_uverbs_device *uverbs_dev; int ret; if (!device->ops.alloc_ucontext || device->type == RDMA_DEVICE_TYPE_SMI) return -EOPNOTSUPP; uverbs_dev = kzalloc(sizeof(*uverbs_dev), GFP_KERNEL); if (!uverbs_dev) return -ENOMEM; ret = init_srcu_struct(&uverbs_dev->disassociate_srcu); if (ret) { kfree(uverbs_dev); return -ENOMEM; } device_initialize(&uverbs_dev->dev); uverbs_dev->dev.class = &uverbs_class; uverbs_dev->dev.parent = device->dev.parent; uverbs_dev->dev.release = ib_uverbs_release_dev; uverbs_dev->groups[0] = &dev_attr_group; uverbs_dev->dev.groups = uverbs_dev->groups; refcount_set(&uverbs_dev->refcount, 1); init_completion(&uverbs_dev->comp); uverbs_dev->xrcd_tree = RB_ROOT; mutex_init(&uverbs_dev->xrcd_tree_mutex); mutex_init(&uverbs_dev->lists_mutex); INIT_LIST_HEAD(&uverbs_dev->uverbs_file_list); rcu_assign_pointer(uverbs_dev->ib_dev, device); uverbs_dev->num_comp_vectors = device->num_comp_vectors; devnum = ida_alloc_max(&uverbs_ida, IB_UVERBS_MAX_DEVICES - 1, GFP_KERNEL); if (devnum < 0) { ret = -ENOMEM; goto err; } uverbs_dev->devnum = devnum; if (devnum >= IB_UVERBS_NUM_FIXED_MINOR) base = dynamic_uverbs_dev + devnum - IB_UVERBS_NUM_FIXED_MINOR; else base = IB_UVERBS_BASE_DEV + devnum; ret = ib_uverbs_create_uapi(device, uverbs_dev); if (ret) goto err_uapi; uverbs_dev->dev.devt = base; dev_set_name(&uverbs_dev->dev, "uverbs%d", uverbs_dev->devnum); cdev_init(&uverbs_dev->cdev, device->ops.mmap ? &uverbs_mmap_fops : &uverbs_fops); uverbs_dev->cdev.owner = THIS_MODULE; ret = cdev_device_add(&uverbs_dev->cdev, &uverbs_dev->dev); if (ret) goto err_uapi; ib_set_client_data(device, &uverbs_client, uverbs_dev); return 0; err_uapi: ida_free(&uverbs_ida, devnum); err: if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); return ret; } static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, struct ib_device *ib_dev) { struct ib_uverbs_file *file; /* Pending running commands to terminate */ uverbs_disassociate_api_pre(uverbs_dev); mutex_lock(&uverbs_dev->lists_mutex); while (!list_empty(&uverbs_dev->uverbs_file_list)) { file = list_first_entry(&uverbs_dev->uverbs_file_list, struct ib_uverbs_file, list); list_del_init(&file->list); kref_get(&file->ref); /* We must release the mutex before going ahead and calling * uverbs_cleanup_ufile, as it might end up indirectly calling * uverbs_close, for example due to freeing the resources (e.g * mmput). */ mutex_unlock(&uverbs_dev->lists_mutex); uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE); kref_put(&file->ref, ib_uverbs_release_file); mutex_lock(&uverbs_dev->lists_mutex); } mutex_unlock(&uverbs_dev->lists_mutex); uverbs_disassociate_api(uverbs_dev->uapi); } static void ib_uverbs_remove_one(struct ib_device *device, void *client_data) { struct ib_uverbs_device *uverbs_dev = client_data; int wait_clients = 1; cdev_device_del(&uverbs_dev->cdev, &uverbs_dev->dev); ida_free(&uverbs_ida, uverbs_dev->devnum); if (device->ops.disassociate_ucontext) { /* We disassociate HW resources and immediately return. * Userspace will see a EIO errno for all future access. * Upon returning, ib_device may be freed internally and is not * valid any more. * uverbs_device is still available until all clients close * their files, then the uverbs device ref count will be zero * and its resources will be freed. * Note: At this point no more files can be opened since the * cdev was deleted, however active clients can still issue * commands and close their open files. */ ib_uverbs_free_hw_resources(uverbs_dev, device); wait_clients = 0; } if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); if (wait_clients) wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); } static int __init ib_uverbs_init(void) { int ret; ret = register_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR, "infiniband_verbs"); if (ret) { pr_err("user_verbs: couldn't register device number\n"); goto out; } ret = alloc_chrdev_region(&dynamic_uverbs_dev, 0, IB_UVERBS_NUM_DYNAMIC_MINOR, "infiniband_verbs"); if (ret) { pr_err("couldn't register dynamic device number\n"); goto out_alloc; } ret = class_register(&uverbs_class); if (ret) { pr_err("user_verbs: couldn't create class infiniband_verbs\n"); goto out_chrdev; } ret = class_create_file(&uverbs_class, &class_attr_abi_version.attr); if (ret) { pr_err("user_verbs: couldn't create abi_version attribute\n"); goto out_class; } ret = ib_register_client(&uverbs_client); if (ret) { pr_err("user_verbs: couldn't register client\n"); goto out_class; } return 0; out_class: class_unregister(&uverbs_class); out_chrdev: unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); out_alloc: unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); out: return ret; } static void __exit ib_uverbs_cleanup(void) { ib_unregister_client(&uverbs_client); class_unregister(&uverbs_class); unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); ib_cleanup_ucaps(); mmu_notifier_synchronize(); } module_init(ib_uverbs_init); module_exit(ib_uverbs_cleanup); |
| 77 82 1 2 1 78 77 77 39 38 77 76 76 77 39 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf_ids.h> #include <linux/bpf_local_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) static struct bpf_local_storage_map_bucket * select_bucket(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; } static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (!map->ops->map_local_storage_charge) return 0; return map->ops->map_local_storage_charge(smap, owner, size); } static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (map->ops->map_local_storage_uncharge) map->ops->map_local_storage_uncharge(smap, owner, size); } static struct bpf_local_storage __rcu ** owner_storage(struct bpf_local_storage_map *smap, void *owner) { struct bpf_map *map = &smap->map; return map->ops->map_owner_storage_ptr(owner); } static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->snode); } static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->map_node); } static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); } struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool charge_mem, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_elem *selem; if (charge_mem && mem_charge(smap, owner, smap->elem_size)) return NULL; if (smap->bpf_ma) { selem = bpf_mem_cache_alloc_flags(&smap->selem_ma, gfp_flags); if (selem) /* Keep the original bpf_map_kzalloc behavior * before started using the bpf_mem_cache_alloc. * * No need to use zero_map_value. The bpf_selem_free() * only does bpf_mem_cache_free when there is * no other bpf prog is using the selem. */ memset(SDATA(selem)->data, 0, smap->map.value_size); } else { selem = bpf_map_kzalloc(&smap->map, smap->elem_size, gfp_flags | __GFP_NOWARN); } if (selem) { if (value) { /* No need to call check_and_init_map_value as memory is zero init */ copy_map_value(&smap->map, SDATA(selem)->data, value); if (swap_uptrs) bpf_obj_swap_uptrs(smap->map.record, SDATA(selem)->data, value); } return selem; } if (charge_mem) mem_uncharge(smap, owner, smap->elem_size); return NULL; } /* rcu tasks trace callback for bpf_ma == false */ static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; /* If RCU Tasks Trace grace period implies RCU grace period, do * kfree(), else do kfree_rcu(). */ local_storage = container_of(rcu, struct bpf_local_storage, rcu); if (rcu_trace_implies_rcu_gp()) kfree(local_storage); else kfree_rcu(local_storage, rcu); } static void bpf_local_storage_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; local_storage = container_of(rcu, struct bpf_local_storage, rcu); bpf_mem_cache_raw_free(local_storage); } static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_local_storage_free_rcu(rcu); else call_rcu(rcu, bpf_local_storage_free_rcu); } /* Handle bpf_ma == false */ static void __bpf_local_storage_free(struct bpf_local_storage *local_storage, bool vanilla_rcu) { if (vanilla_rcu) kfree_rcu(local_storage, rcu); else call_rcu_tasks_trace(&local_storage->rcu, __bpf_local_storage_free_trace_rcu); } static void bpf_local_storage_free(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool bpf_ma, bool reuse_now) { if (!local_storage) return; if (!bpf_ma) { __bpf_local_storage_free(local_storage, reuse_now); return; } if (!reuse_now) { call_rcu_tasks_trace(&local_storage->rcu, bpf_local_storage_free_trace_rcu); return; } if (smap) bpf_mem_cache_free(&smap->storage_ma, local_storage); else /* smap could be NULL if the selem that triggered * this 'local_storage' creation had been long gone. * In this case, directly do call_rcu(). */ call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu); } /* rcu tasks trace callback for bpf_ma == false */ static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); if (rcu_trace_implies_rcu_gp()) kfree(selem); else kfree_rcu(selem, rcu); } /* Handle bpf_ma == false */ static void __bpf_selem_free(struct bpf_local_storage_elem *selem, bool vanilla_rcu) { if (vanilla_rcu) kfree_rcu(selem, rcu); else call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu); } static void bpf_selem_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); /* The bpf_local_storage_map_free will wait for rcu_barrier */ smap = rcu_dereference_check(SDATA(selem)->smap, 1); migrate_disable(); bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); migrate_enable(); bpf_mem_cache_raw_free(selem); } static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_selem_free_rcu(rcu); else call_rcu(rcu, bpf_selem_free_rcu); } void bpf_selem_free(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, bool reuse_now) { if (!smap->bpf_ma) { /* Only task storage has uptrs and task storage * has moved to bpf_mem_alloc. Meaning smap->bpf_ma == true * for task storage, so this bpf_obj_free_fields() won't unpin * any uptr. */ bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); __bpf_selem_free(selem, reuse_now); return; } if (reuse_now) { /* reuse_now == true only happens when the storage owner * (e.g. task_struct) is being destructed or the map itself * is being destructed (ie map_free). In both cases, * no bpf prog can have a hold on the selem. It is * safe to unpin the uptrs and free the selem now. */ bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); /* Instead of using the vanilla call_rcu(), * bpf_mem_cache_free will be able to reuse selem * immediately. */ bpf_mem_cache_free(&smap->selem_ma, selem); return; } call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); } static void bpf_selem_free_list(struct hlist_head *list, bool reuse_now) { struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; struct hlist_node *n; /* The "_safe" iteration is needed. * The loop is not removing the selem from the list * but bpf_selem_free will use the selem->rcu_head * which is union-ized with the selem->free_node. */ hlist_for_each_entry_safe(selem, n, list, free_node) { smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); bpf_selem_free(selem, smap, reuse_now); } } /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, bool uncharge_mem, struct hlist_head *free_selem_list) { struct bpf_local_storage_map *smap; bool free_local_storage; void *owner; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); owner = local_storage->owner; /* All uncharging on the owner must be done first. * The owner may be freed once the last selem is unlinked * from local_storage. */ if (uncharge_mem) mem_uncharge(smap, owner, smap->elem_size); free_local_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); if (free_local_storage) { mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); local_storage->owner = NULL; /* After this RCU_INIT, owner may be freed and cannot be used */ RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); /* local_storage is not freed now. local_storage->lock is * still held and raw_spin_unlock_bh(&local_storage->lock) * will be done by the caller. * * Although the unlock will be done under * rcu_read_lock(), it is more intuitive to * read if the freeing of the storage is done * after the raw_spin_unlock_bh(&local_storage->lock). * * Hence, a "bool free_local_storage" is returned * to the caller which then calls then frees the storage after * all the RCU grace periods have expired. */ } hlist_del_init_rcu(&selem->snode); if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); hlist_add_head(&selem->free_node, free_selem_list); if (rcu_access_pointer(local_storage->smap) == smap) RCU_INIT_POINTER(local_storage->smap, NULL); return free_local_storage; } static bool check_storage_bpf_ma(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *storage_smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *selem_smap; /* local_storage->smap may be NULL. If it is, get the bpf_ma * from any selem in the local_storage->list. The bpf_ma of all * local_storage and selem should have the same value * for the same map type. * * If the local_storage->list is already empty, the caller will not * care about the bpf_ma value also because the caller is not * responsible to free the local_storage. */ if (storage_smap) return storage_smap->bpf_ma; if (!selem) { struct hlist_node *n; n = rcu_dereference_check(hlist_first_rcu(&local_storage->list), bpf_rcu_lock_held()); if (!n) return false; selem = hlist_entry(n, struct bpf_local_storage_elem, snode); } selem_smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); return selem_smap->bpf_ma; } static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, bool reuse_now) { struct bpf_local_storage_map *storage_smap; struct bpf_local_storage *local_storage; bool bpf_ma, free_local_storage = false; HLIST_HEAD(selem_free_list); unsigned long flags; if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, selem); raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, true, &selem_free_list); raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&selem_free_list, reuse_now); if (free_local_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, reuse_now); } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem) { RCU_INIT_POINTER(selem->local_storage, local_storage); hlist_add_head_rcu(&selem->snode, &local_storage->list); } static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; unsigned long flags; if (unlikely(!selem_linked_to_map_lockless(selem))) /* selem has already be unlinked from smap */ return; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); b = select_bucket(smap, selem); raw_spin_lock_irqsave(&b->lock, flags); if (likely(selem_linked_to_map(selem))) hlist_del_init_rcu(&selem->map_node); raw_spin_unlock_irqrestore(&b->lock, flags); } void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); unsigned long flags; raw_spin_lock_irqsave(&b->lock, flags); RCU_INIT_POINTER(SDATA(selem)->smap, smap); hlist_add_head_rcu(&selem->map_node, &b->list); raw_spin_unlock_irqrestore(&b->lock, flags); } void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ bpf_selem_unlink_map(selem); bpf_selem_unlink_storage(selem, reuse_now); } void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { unsigned long flags; /* spinlock is needed to avoid racing with the * parallel delete. Otherwise, publishing an already * deleted sdata to the cache will become a use-after-free * problem in the next bpf_local_storage_lookup(). */ raw_spin_lock_irqsave(&local_storage->lock, flags); if (selem_linked_to_storage(selem)) rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); raw_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, u64 map_flags) { if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; return 0; } int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *first_selem, gfp_t gfp_flags) { struct bpf_local_storage *prev_storage, *storage; struct bpf_local_storage **owner_storage_ptr; int err; err = mem_charge(smap, owner, sizeof(*storage)); if (err) return err; if (smap->bpf_ma) storage = bpf_mem_cache_alloc_flags(&smap->storage_ma, gfp_flags); else storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), gfp_flags | __GFP_NOWARN); if (!storage) { err = -ENOMEM; goto uncharge; } RCU_INIT_POINTER(storage->smap, smap); INIT_HLIST_HEAD(&storage->list); raw_spin_lock_init(&storage->lock); storage->owner = owner; bpf_selem_link_storage_nolock(storage, first_selem); bpf_selem_link_map(smap, first_selem); owner_storage_ptr = (struct bpf_local_storage **)owner_storage(smap, owner); /* Publish storage to the owner. * Instead of using any lock of the kernel object (i.e. owner), * cmpxchg will work with any kernel object regardless what * the running context is, bh, irq...etc. * * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) * is protected by the storage->lock. Hence, when freeing * the owner->storage, the storage->lock must be held before * setting owner->storage ptr to NULL. */ prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); if (unlikely(prev_storage)) { bpf_selem_unlink_map(first_selem); err = -EAGAIN; goto uncharge; /* Note that even first_selem was linked to smap's * bucket->list, first_selem can be freed immediately * (instead of kfree_rcu) because * bpf_local_storage_map_free() does a * synchronize_rcu_mult (waiting for both sleepable and * normal programs) before walking the bucket->list. * Hence, no one is accessing selem from the * bucket->list under rcu_read_lock(). */ } return 0; uncharge: bpf_local_storage_free(storage, smap, smap->bpf_ma, true); mem_uncharge(smap, owner, sizeof(*storage)); return err; } /* sk cannot be going away because it is linking new elem * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). * Otherwise, it will become a leak (and other memory issues * during map destruction). */ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_data *old_sdata = NULL; struct bpf_local_storage_elem *alloc_selem, *selem = NULL; struct bpf_local_storage *local_storage; HLIST_HEAD(old_selem_free_list); unsigned long flags; int err; /* BPF_EXIST and BPF_NOEXIST cannot be both set */ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ unlikely((map_flags & BPF_F_LOCK) && !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) return ERR_PTR(-EINVAL); if (gfp_flags == GFP_KERNEL && (map_flags & ~BPF_F_LOCK) != BPF_NOEXIST) return ERR_PTR(-EINVAL); local_storage = rcu_dereference_check(*owner_storage(smap, owner), bpf_rcu_lock_held()); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); if (err) return ERR_PTR(err); selem = bpf_selem_alloc(smap, owner, value, true, swap_uptrs, gfp_flags); if (!selem) return ERR_PTR(-ENOMEM); err = bpf_local_storage_alloc(owner, smap, selem, gfp_flags); if (err) { bpf_selem_free(selem, smap, true); mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } return SDATA(selem); } if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { /* Hoping to find an old_sdata to do inline update * such that it can avoid taking the local_storage->lock * and changing the lists. */ old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; } } /* A lookup has just been done before and concluded a new selem is * needed. The chance of an unnecessary alloc is unlikely. */ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, swap_uptrs, gfp_flags); if (!alloc_selem) return ERR_PTR(-ENOMEM); raw_spin_lock_irqsave(&local_storage->lock, flags); /* Recheck local_storage->list under local_storage->lock */ if (unlikely(hlist_empty(&local_storage->list))) { /* A parallel del is happening and local_storage is going * away. It has just been checked before, so very * unlikely. Return instead of retry to keep things * simple. */ err = -EAGAIN; goto unlock; } old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) goto unlock; if (old_sdata && (map_flags & BPF_F_LOCK)) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); selem = SELEM(old_sdata); goto unlock; } alloc_selem = NULL; /* First, link the new selem to the map */ bpf_selem_link_map(smap, selem); /* Second, link (and publish) the new selem to local_storage */ bpf_selem_link_storage_nolock(local_storage, selem); /* Third, remove old selem, SELEM(old_sdata) */ if (old_sdata) { bpf_selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), true, &old_selem_free_list); } unlock: raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&old_selem_free_list, false); if (alloc_selem) { mem_uncharge(smap, owner, smap->elem_size); bpf_selem_free(alloc_selem, smap, true); } return err ? ERR_PTR(err) : SDATA(selem); } static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; spin_lock(&cache->idx_lock); for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { if (cache->idx_usage_counts[i] < min_usage) { min_usage = cache->idx_usage_counts[i]; res = i; /* Found a free cache_idx */ if (!min_usage) break; } } cache->idx_usage_counts[res]++; spin_unlock(&cache->idx_lock); return res; } static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, u16 idx) { spin_lock(&cache->idx_lock); cache->idx_usage_counts[idx]--; spin_unlock(&cache->idx_lock); } int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->max_entries || attr->key_size != sizeof(int) || !attr->value_size || /* Enforce BTF for userspace sk dumping */ !attr->btf_key_type_id || !attr->btf_value_type_id) return -EINVAL; if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) return -E2BIG; return 0; } int bpf_local_storage_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { u32 int_data; if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) return -EINVAL; int_data = *(u32 *)(key_type + 1); if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) return -EINVAL; return 0; } void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) { struct bpf_local_storage_map *storage_smap; struct bpf_local_storage_elem *selem; bool bpf_ma, free_storage = false; HLIST_HEAD(free_selem_list); struct hlist_node *n; unsigned long flags; storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, NULL); /* Neither the bpf_prog nor the bpf_map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added to or deleted from the * local_storage->list by the bpf_prog or by the bpf_map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the local_storage->list and * the map's bucket->list. */ raw_spin_lock_irqsave(&local_storage->lock, flags); hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { /* Always unlink from map before unlinking from * local_storage. */ bpf_selem_unlink_map(selem); /* If local_storage list has only one element, the * bpf_selem_unlink_storage_nolock() will return true. * Otherwise, it will return false. The current loop iteration * intends to remove all local storage. So the last iteration * of the loop will set the free_cgroup_storage to true. */ free_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, true, &free_selem_list); } raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&free_selem_list, true); if (free_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, true); } u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) { struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map; u64 usage = sizeof(*smap); /* The dynamically callocated selems are not counted currently. */ usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); return usage; } /* When bpf_ma == true, the bpf_mem_alloc is used to allocate and free memory. * A deadlock free allocator is useful for storage that the bpf prog can easily * get a hold of the owner PTR_TO_BTF_ID in any context. eg. bpf_get_current_task_btf. * The task and cgroup storage fall into this case. The bpf_mem_alloc reuses * memory immediately. To be reuse-immediate safe, the owner destruction * code path needs to go through a rcu grace period before calling * bpf_local_storage_destroy(). * * When bpf_ma == false, the kmalloc and kfree are used. */ struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, struct bpf_local_storage_cache *cache, bool bpf_ma) { struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; int err; smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets, sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN); if (!smap->buckets) { err = -ENOMEM; goto free_smap; } for (i = 0; i < nbuckets; i++) { INIT_HLIST_HEAD(&smap->buckets[i].list); raw_spin_lock_init(&smap->buckets[i].lock); } smap->elem_size = offsetof(struct bpf_local_storage_elem, sdata.data[attr->value_size]); /* In PREEMPT_RT, kmalloc(GFP_ATOMIC) is still not safe in non * preemptible context. Thus, enforce all storages to use * bpf_mem_alloc when CONFIG_PREEMPT_RT is enabled. */ smap->bpf_ma = IS_ENABLED(CONFIG_PREEMPT_RT) ? true : bpf_ma; if (smap->bpf_ma) { err = bpf_mem_alloc_init(&smap->selem_ma, smap->elem_size, false); if (err) goto free_smap; err = bpf_mem_alloc_init(&smap->storage_ma, sizeof(struct bpf_local_storage), false); if (err) { bpf_mem_alloc_destroy(&smap->selem_ma); goto free_smap; } } smap->cache_idx = bpf_local_storage_cache_idx_get(cache); return &smap->map; free_smap: kvfree(smap->buckets); bpf_map_area_free(smap); return ERR_PTR(err); } void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache, int __percpu *busy_counter) { struct bpf_local_storage_map_bucket *b; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; unsigned int i; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(cache, smap->cache_idx); /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone * RCU read section to finish before proceeding. New RCU * read sections should be prevented via bpf_map_inc_not_zero. */ synchronize_rcu(); /* bpf prog and the userspace can no longer access this map * now. No new selem (of this map) can be added * to the owner->storage or to the map bucket's list. * * The elem of this map can be cleaned up here * or when the storage is freed e.g. * by bpf_sk_storage_free() during __sk_destruct(). */ for (i = 0; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); /* No one is adding to b->list now */ while ((selem = hlist_entry_safe( rcu_dereference_raw(hlist_first_rcu(&b->list)), struct bpf_local_storage_elem, map_node))) { if (busy_counter) this_cpu_inc(*busy_counter); bpf_selem_unlink(selem, true); if (busy_counter) this_cpu_dec(*busy_counter); cond_resched_rcu(); } rcu_read_unlock(); } /* While freeing the storage we may still need to access the map. * * e.g. when bpf_sk_storage_free() has unlinked selem from the map * which then made the above while((selem = ...)) loop * exit immediately. * * However, while freeing the storage one still needs to access the * smap->elem_size to do the uncharging in * bpf_selem_unlink_storage_nolock(). * * Hence, wait another rcu grace period for the storage to be freed. */ synchronize_rcu(); if (smap->bpf_ma) { rcu_barrier_tasks_trace(); if (!rcu_trace_implies_rcu_gp()) rcu_barrier(); bpf_mem_alloc_destroy(&smap->selem_ma); bpf_mem_alloc_destroy(&smap->storage_ma); } kvfree(smap->buckets); bpf_map_area_free(smap); } |
| 7 2 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 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | // SPDX-License-Identifier: GPL-2.0-only /* IP tables module for matching IPsec policy * * Copyright (c) 2004,2005 Patrick McHardy, <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/init.h> #include <net/xfrm.h> #include <linux/netfilter.h> #include <linux/netfilter/xt_policy.h> #include <linux/netfilter/x_tables.h> MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Xtables: IPsec policy match"); MODULE_LICENSE("GPL"); static inline bool xt_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *m, const union nf_inet_addr *a2, unsigned short family) { switch (family) { case NFPROTO_IPV4: return ((a1->ip ^ a2->ip) & m->ip) == 0; case NFPROTO_IPV6: return ipv6_masked_addr_cmp(&a1->in6, &m->in6, &a2->in6) == 0; } return false; } static bool match_xfrm_state(const struct xfrm_state *x, const struct xt_policy_elem *e, unsigned short family) { #define MATCH_ADDR(x,y,z) (!e->match.x || \ (xt_addr_cmp(&e->x, &e->y, (const union nf_inet_addr *)(z), family) \ ^ e->invert.x)) #define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) return MATCH_ADDR(saddr, smask, &x->props.saddr) && MATCH_ADDR(daddr, dmask, &x->id.daddr) && MATCH(proto, x->id.proto) && MATCH(mode, x->props.mode) && MATCH(spi, x->id.spi) && MATCH(reqid, x->props.reqid); } static int match_policy_in(const struct sk_buff *skb, const struct xt_policy_info *info, unsigned short family) { const struct xt_policy_elem *e; const struct sec_path *sp = skb_sec_path(skb); int strict = info->flags & XT_POLICY_MATCH_STRICT; int i, pos; if (sp == NULL) return -1; if (strict && info->len != sp->len) return 0; for (i = sp->len - 1; i >= 0; i--) { pos = strict ? i - sp->len + 1 : 0; if (pos >= info->len) return 0; e = &info->pol[pos]; if (match_xfrm_state(sp->xvec[i], e, family)) { if (!strict) return 1; } else if (strict) return 0; } return strict ? 1 : 0; } static int match_policy_out(const struct sk_buff *skb, const struct xt_policy_info *info, unsigned short family) { const struct xt_policy_elem *e; const struct dst_entry *dst = skb_dst(skb); int strict = info->flags & XT_POLICY_MATCH_STRICT; int i, pos; if (dst->xfrm == NULL) return -1; for (i = 0; dst && dst->xfrm; dst = ((struct xfrm_dst *)dst)->child, i++) { pos = strict ? i : 0; if (pos >= info->len) return 0; e = &info->pol[pos]; if (match_xfrm_state(dst->xfrm, e, family)) { if (!strict) return 1; } else if (strict) return 0; } return strict ? i == info->len : 0; } static bool policy_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_policy_info *info = par->matchinfo; int ret; if (info->flags & XT_POLICY_MATCH_IN) ret = match_policy_in(skb, info, xt_family(par)); else ret = match_policy_out(skb, info, xt_family(par)); if (ret < 0) ret = info->flags & XT_POLICY_MATCH_NONE ? true : false; else if (info->flags & XT_POLICY_MATCH_NONE) ret = false; return ret; } static int policy_mt_check(const struct xt_mtchk_param *par) { const struct xt_policy_info *info = par->matchinfo; const char *errmsg = "neither incoming nor outgoing policy selected"; if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) goto err; if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && info->flags & XT_POLICY_MATCH_OUT) { errmsg = "output policy not valid in PREROUTING and INPUT"; goto err; } if (par->hook_mask & ((1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT)) && info->flags & XT_POLICY_MATCH_IN) { errmsg = "input policy not valid in POSTROUTING and OUTPUT"; goto err; } if (info->len > XT_POLICY_MAX_ELEM) { errmsg = "too many policy elements"; goto err; } return 0; err: pr_info_ratelimited("%s\n", errmsg); return -EINVAL; } static struct xt_match policy_mt_reg[] __read_mostly = { { .name = "policy", .family = NFPROTO_IPV4, .checkentry = policy_mt_check, .match = policy_mt, .matchsize = sizeof(struct xt_policy_info), .me = THIS_MODULE, }, { .name = "policy", .family = NFPROTO_IPV6, .checkentry = policy_mt_check, .match = policy_mt, .matchsize = sizeof(struct xt_policy_info), .me = THIS_MODULE, }, }; static int __init policy_mt_init(void) { return xt_register_matches(policy_mt_reg, ARRAY_SIZE(policy_mt_reg)); } static void __exit policy_mt_exit(void) { xt_unregister_matches(policy_mt_reg, ARRAY_SIZE(policy_mt_reg)); } module_init(policy_mt_init); module_exit(policy_mt_exit); MODULE_ALIAS("ipt_policy"); MODULE_ALIAS("ip6t_policy"); |
| 309 279 31 31 53 2 30 183 3 180 183 2 252 40 216 252 213 49 19 129 54 5 7 40 30 11 58 42 14 1 56 55 1 56 4 6 2 4 2 1 42 43 1 1 1 1 1 3 10 7 11 5 11 5 11 11 11 11 15 10 2 13 15 5 10 15 15 15 8 5 11 43 15 2 3 3 3 3 41 41 3 41 77 22 11 6 79 20 15 6 41 11 21 10 59 1 144 144 144 142 7 3 7 34 5 1 9 27 5 22 21 7 5 6 4 6 1 6 1 9 3 11 43 137 71 67 54 34 5 1 9 3 5 54 89 22 42 5 41 1 2 38 43 35 17 35 6 24 7 1 1 7 7 1 1 1 3 2 1 24 1 16 6 13 23 7 2 7 57 54 5 6 38 16 2 7 51 7 1 9 3 3 37 40 40 1 1 2 1 42 4 1 109 1 36 2 1 1 1 176 146 73 176 175 176 176 327 327 206 206 136 195 47 8 323 5 1 2 2 1 1 3 1 2 1 1 2 2 1 1 1 1008 927 91 1 6 6 5 952 696 161 112 98 954 43 376 545 156 77 690 690 691 690 690 691 690 398 51 61 26 21 12 7 60 3 11 9 35 21 58 29 29 35 7 1 2 3 8 7 1 6 58 49 15 1 5 1 51 41 54 3 3 55 30 1 10 15 55 56 41 15 54 10 52 49 1 3 101 5 152 2 3 1 1 6 9 5 3 5 6 3 5 8 4 13 1 50 1 1 212 88 33 92 343 5 88 258 181 164 335 336 1 334 23 65 71 173 7 2 85 246 328 327 327 326 173 15 137 264 23 29 268 152 372 19 354 144 2 142 141 133 14 142 108 34 132 10 142 110 36 142 59 42 19 2 2 27 36 33 24 55 10 21 34 55 1 36 25 55 2 53 26 5 3 2 61 2 2 57 80 1 79 66 12 78 36 2 4 33 27 6 11 24 3 3 26 29 6 3 20 19 4 8 9 1 1 9 1 29 3 1 1 1 5 2 3 1 13 1 1 29 16 1 4 31 30 21 3 1 18 1 3 4 1 18 18 15 9 8 2 1 5 2 131 12 12 259 1 138 3 30 1 21 9 2 1 1 1 1 1 3 2 1 1 2 1 1 1 2 2 1 1 2 1 1 2 1 6 2 3 2 2 1 1 60 1 57 1 24 1 1 1 2 2 1 1 2 1 1 2 28 1 1 1 1 1 1 1 1 2 1 1 1 4 1 1 1 1 1 1 1 1 2 1 1 2 2 19 4171 4172 586 283 31 331 27 26 30 23 129 3 2 4172 30 69 65 1 2 1 29 23 6 29 25 4 8 8 11 11 56 27 29 23 77 77 118 44 1 95 2 73 12 1 2 83 2 1 2 77 4 4 10 59 57 48 79 103 7 96 103 48 79 102 1 1 56 18 3 15 15 8 7 1 7 7 7 7 7 7 7 7 7 7 7 4 509 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PACKET - implements raw packet sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Alan Cox : verify_area() now used correctly * Alan Cox : new skbuff lists, look ma no backlogs! * Alan Cox : tidied skbuff lists. * Alan Cox : Now uses generic datagram routines I * added. Also fixed the peek/read crash * from all old Linux datagram code. * Alan Cox : Uses the improved datagram code. * Alan Cox : Added NULL's for socket options. * Alan Cox : Re-commented the code. * Alan Cox : Use new kernel side addressing * Rob Janssen : Correct MTU usage. * Dave Platt : Counter leaks caused by incorrect * interrupt locking and some slightly * dubious gcc output. Can you read * compiler: it said _VOLATILE_ * Richard Kooijman : Timestamp fixes. * Alan Cox : New buffers. Use sk->mac.raw. * Alan Cox : sendmsg/recvmsg support. * Alan Cox : Protocol setting support * Alexey Kuznetsov : Untied from IPv4 stack. * Cyrus Durgin : Fixed kerneld for kmod. * Michal Ostrowski : Module initialization cleanup. * Ulises Alonso : Frame number limit removal and * packet_set_ring memory leak. * Eric Biederman : Allow for > 8 byte hardware addresses. * The convention is that longer addresses * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. * Chetan Loke : Implemented TPACKET_V3 block abstraction * layer. * Copyright (C) 2011, <lokec@ccs.neu.edu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/if_vlan.h> #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> #include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif #include <linux/bpf.h> #include <net/compat.h> #include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - If the device has no dev->header_ops->create, there is no LL header visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. For example, a WiFi driver pretending to be an Ethernet driver should set its hard_header_len to be the Ethernet header length, and set its needed_headroom to be (the real WiFi header length - the fake Ethernet header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. On transmit: ------------ dev_has_header(dev) == true mac_header -> ll header data -> ll header dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data We should set network_header on output to the correct position, packet classifier depends on it. */ /* Private packet socket structures. */ /* identical to struct packet_mreq except it has * a longer address field. */ struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; unsigned char mr_address[MAX_ADDR_LEN]; }; union tpacket_uhdr { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; struct tpacket3_hdr *h3; void *raw; }; static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) #define BLK_PLUS_PRIV(sz_of_priv) \ (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) #define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) #define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) #define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, struct packet_sock *, unsigned int status); static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); static void prb_retire_rx_blk_timer_expired(struct timer_list *); static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { struct sockaddr_pkt pkt; union { /* Trick: alias skb original length with * ll.sll_family and ll.protocol in order * to save room. */ unsigned int origlen; struct sockaddr_ll ll; }; } sa; }; #define vio_le() virtio_legacy_is_little_endian() #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) #define GET_PBLOCK_DESC(x, bid) \ ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) #define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) #define GET_NEXT_PRB_BLK_NUM(x) \ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ ((x)->kactive_blk_num+1) : 0) static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); #ifdef CONFIG_NETFILTER_EGRESS static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) { struct sk_buff *next, *head = NULL, *tail; int rc; rcu_read_lock(); for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); if (!nf_hook_egress(skb, &rc, skb->dev)) continue; if (!head) head = skb; else tail->next = skb; tail = skb; } rcu_read_unlock(); return head; } #endif static int packet_xmit(const struct packet_sock *po, struct sk_buff *skb) { if (!packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS)) return dev_queue_xmit(skb); #ifdef CONFIG_NETFILTER_EGRESS if (nf_hook_egress_active()) { skb = nf_hook_direct_egress(skb); if (!skb) return NET_XMIT_DROP; } #endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(po->cached_dev); dev_hold(dev); rcu_read_unlock(); return dev; } static void packet_cached_dev_assign(struct packet_sock *po, struct net_device *dev) { rcu_assign_pointer(po->cached_dev, dev); } static void packet_cached_dev_reset(struct packet_sock *po) { RCU_INIT_POINTER(po->cached_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; int cpu = raw_smp_processor_id(); u16 queue_index; #ifdef CONFIG_XPS skb->sender_cpu = cpu + 1; #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); if (!packet_sock_flag(po, PACKET_SOCK_RUNNING)) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 1); } } static void register_prot_hook(struct sock *sk) { lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); __register_prot_hook(sk); } /* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the * callers responsibility to take care of this. */ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); lockdep_assert_held_once(&po->bind_lock); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 0); if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); __sock_put(sk); if (sync) { spin_unlock(&po->bind_lock); synchronize_net(); spin_lock(&po->bind_lock); } } static void unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) __unregister_prot_hook(sk, sync); } static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } smp_wmb(); } static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; smp_rmb(); /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } } static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, unsigned int flags) { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (shhwtstamps && (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; if ((flags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; } static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, struct sk_buff *skb) { union tpacket_uhdr h; struct timespec64 ts; __u32 ts_status; if (!(ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp)))) return 0; h.raw = frame; /* * versions 1 through 3 overflow the timestamps in y2106, since they * all store the seconds in a 32-bit unsigned integer. * If we create a version 4, that should have a 64-bit timestamp, * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit * nanoseconds. */ switch (po->tp_version) { case TPACKET_V1: h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; break; case TPACKET_V2: h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; break; case TPACKET_V3: h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } /* one flush is safe, as both fields always lie on the same cacheline */ flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); smp_wmb(); return ts_status; } static void *packet_lookup_frame(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; h.raw = rb->pg_vec[pg_vec_pos].buffer + (frame_offset * rb->frame_size); if (status != __packet_get_status(po, h.raw)) return NULL; return h.raw; } static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev) { struct vlan_hdr vhdr, *vh; unsigned int header_len; if (!dev) return 0; /* In the SOCK_DGRAM scenario, skb data starts at the network * protocol, which is after the VLAN headers. The outer VLAN * header is at the hard_header_len offset in non-variable * length link layer headers. If it's a VLAN device, the * min_header_len should be used to exclude the VLAN header * size. */ if (dev->min_header_len == dev->hard_header_len) header_len = dev->hard_header_len; else if (is_vlan_dev(dev)) header_len = dev->min_header_len; else return 0; vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len, sizeof(vhdr), &vhdr); if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) { __be16 proto = skb->protocol; if (unlikely(eth_type_vlan(proto))) proto = __vlan_get_protocol_offset(skb, proto, skb_mac_offset(skb), NULL); return proto; } static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { timer_delete_sync(&pkc->retire_blk_timer); } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } static void prb_setup_retire_blk_timer(struct packet_sock *po) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, 0); pkc->retire_blk_timer.expires = jiffies; } static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); if (unlikely(!dev)) { rtnl_unlock(); return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); if (err) return DEFAULT_PRB_RETIRE_TOV; /* If the link speed is so slow you don't really * need to worry about perf anyways */ if (ecmd.base.speed < SPEED_1000 || ecmd.base.speed == SPEED_UNKNOWN) return DEFAULT_PRB_RETIRE_TOV; div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; if (div) return mbits + 1; return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, union tpacket_req_u *req_u) { p1->feature_req_word = req_u->req3.tp_feature_req_word; } static void init_prb_bdqc(struct packet_sock *po, struct packet_ring_buffer *rb, struct pgv *pg_vec, union tpacket_req_u *req_u) { struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; p1->last_kactive_blk_num = 0; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; else p1->retire_blk_tov = prb_calc_retire_blk_tmo(po, req_u->req3.tp_block_size); p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po); prb_open_block(p1, pbd); } /* Do NOT update the last_blk_num first. * Assumes sk_buff_head lock is held. */ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) { mod_timer(&pkc->retire_blk_timer, jiffies + pkc->tov_in_jiffies); pkc->last_kactive_blk_num = pkc->kactive_blk_num; } /* * Timer logic: * 1) We refresh the timer only when we open a block. * By doing this we don't waste cycles refreshing the timer * on packet-by-packet basis. * * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * * So, if the user sets the 'tmo' to 10ms then the timer * will never fire while the block is still getting filled * (which is what we want). However, the user could choose * to close a block early and that's fine. * * But when the timer does fire, we check whether or not to refresh it. * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. * */ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) { struct packet_sock *po = timer_container_of(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; spin_lock(&po->sk.sk_receive_queue.lock); frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); if (unlikely(pkc->delete_blk_timer)) goto out; /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() * copy_bits() is in progress ... * timer fires on other cpu: * we can't retire the current block because copy_bits * is in progress. * */ if (BLOCK_NUM_PKTS(pbd)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { if (!frozen) { if (!BLOCK_NUM_PKTS(pbd)) { /* An empty block. Just refresh the timer. */ goto refresh_timer; } prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); if (!prb_dispatch_next_block(pkc, po)) goto refresh_timer; else goto out; } else { /* Case 1. Queue was frozen because user-space was * lagging behind. */ if (prb_curr_blk_in_use(pbd)) { /* * Ok, user-space is still behind. * So just refresh the timer. */ goto refresh_timer; } else { /* Case 2. queue was frozen,user-space caught up, * now the link went idle && the timer fired. * We don't have a block to close.So we open this * block and restart the timer. * opening a block thaws the queue,restarts timer * Thawing/timer-refresh is a side effect. */ prb_open_block(pkc, pbd); goto out; } } } refresh_timer: _prb_refresh_rx_retire_blk_timer(pkc); out: spin_unlock(&po->sk.sk_receive_queue.lock); } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, __u32 status) { /* Flush everything minus the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 u8 *start, *end; start = (u8 *)pbd1; /* Skip the block header(we know header WILL fit in 4K) */ start += PAGE_SIZE; end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); for (; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif /* Now update the block status. */ BLOCK_STATUS(pbd1) = status; /* Flush the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 start = (u8 *)pbd1; flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif } /* * Side effect: * * 1) flush the block * 2) Increment active_blk_num * * Note:We DONT refresh the timer on purpose. * Because almost always the next block will be opened. */ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, struct packet_sock *po, unsigned int stat) { __u32 status = TP_STATUS_USER | stat; struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; last_pkt->tp_next_offset = 0; /* Get the ts of the last pkt */ if (BLOCK_NUM_PKTS(pbd1)) { h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; } else { /* Ok, we tmo'd - so get the current time. * * It shouldn't really happen as we don't close empty * blocks. See prb_retire_rx_blk_timer_expired(). */ struct timespec64 ts; ktime_get_real_ts64(&ts); h1->ts_last_pkt.ts_sec = ts.tv_sec; h1->ts_last_pkt.ts_nsec = ts.tv_nsec; } smp_wmb(); /* Flush the block */ prb_flush_block(pkc1, pbd1, status); sk->sk_data_ready(sk); pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); } static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) { pkc->reset_pending_on_curr_blk = 0; } /* * Side effect of opening a block: * * 1) prb_queue is thawed. * 2) retire_blk_timer is refreshed. * */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) { struct timespec64 ts; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; smp_rmb(); /* We could have just memset this but we will lose the * flexibility of making the priv area sticky */ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; BLOCK_NUM_PKTS(pbd1) = 0; BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); ktime_get_real_ts64(&ts); h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; pkc1->prev = pkc1->nxt_offset; pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); _prb_refresh_rx_retire_blk_timer(pkc1); smp_wmb(); } /* * Queue freeze logic: * 1) Assume tp_block_nr = 8 blocks. * 2) At time 't0', user opens Rx ring. * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 * 4) user-space is either sleeping or processing block '0'. * 5) tpacket_rcv is currently filling block '7', since there is no space left, * it will close block-7,loop around and try to fill block '0'. * call-flow: * __packet_lookup_frame_in_block * prb_retire_current_block() * prb_dispatch_next_block() * |->(BLOCK_STATUS == USER) evaluates to true * 5.1) Since block-0 is currently in-use, we just freeze the queue. * 6) Now there are two cases: * 6.1) Link goes idle right after the queue is frozen. * But remember, the last open_block() refreshed the timer. * When this timer expires,it will refresh itself so that we can * re-open block-0 in near future. * 6.2) Link is busy and keeps on receiving packets. This is a simple * case and __packet_lookup_frame_in_block will check if block-0 * is free and can now be re-used. */ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) /* * If the next block is free then we will dispatch it * and return a good offset. * Else, we will freeze the queue. * So, caller must check the return value. */ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { struct tpacket_block_desc *pbd; smp_rmb(); /* 1. Get current block num */ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* 2. If this block is currently in_use then freeze the queue */ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { prb_freeze_queue(pkc, po); return NULL; } /* * 3. * open this block and return the offset where the first packet * needs to get stored. */ prb_open_block(pkc, pbd); return (void *)pkc->nxt_offset; } static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po, unsigned int status) { struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* retire/close the current block */ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { /* * Plug the case where copy_bits() is in progress on * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't * have space to copy the pkt in the current block and * called prb_retire_current_block() * * We don't need to worry about the TMO case because * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; } } static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) { return pkc->reset_pending_on_curr_blk; } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = 0; } static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) prb_fill_rxhash(pkc, ppd); else prb_clear_rxhash(pkc, ppd); } static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; ppd = (struct tpacket3_hdr *)curr; ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); pkc->prev = curr; pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } /* Assumes caller has the sk->rx_queue.lock */ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct sk_buff *skb, unsigned int len ) { struct tpacket_kbdq_core *pkc; struct tpacket_block_desc *pbd; char *curr, *end; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ if (prb_queue_frozen(pkc)) { /* * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { /* * Ok, the block was released by user-space. * Now let's open that block. * opening a block also thaws the queue. * Thawing is a side effect. */ prb_open_block(pkc, pbd); } } smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* Ok, close the current block */ prb_retire_current_block(pkc, po, 0); /* Now, try to dispatch the next block */ curr = (char *)prb_dispatch_next_block(pkc, po); if (curr) { pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* * No free blocks are available.user_space hasn't caught up yet. * Queue was just frozen and now this packet will get dropped. */ return NULL; } static void *packet_current_rx_frame(struct packet_sock *po, struct sk_buff *skb, int status, unsigned int len) { char *curr = NULL; switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: curr = packet_lookup_frame(po, &po->rx_ring, po->rx_ring.head, status); return curr; case TPACKET_V3: return __packet_lookup_frame_in_block(po, skb, len); default: WARN(1, "TPACKET version not supported\n"); BUG(); return NULL; } } static void *prb_lookup_block(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; return pbd; } static int prb_previous_blk_num(struct packet_ring_buffer *rb) { unsigned int prev; if (rb->prb_bdqc.kactive_blk_num) prev = rb->prb_bdqc.kactive_blk_num-1; else prev = rb->prb_bdqc.knum_blocks-1; return prev; } /* Assumes caller has held the rx_queue.lock */ static void *__prb_previous_block(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = prb_previous_blk_num(rb); return prb_lookup_block(po, rb, previous, status); } static void *packet_previous_rx_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { if (po->tp_version <= TPACKET_V2) return packet_previous_frame(po, rb, status); return __prb_previous_block(po, rb, status); } static void packet_increment_rx_head(struct packet_sock *po, struct packet_ring_buffer *rb) { switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: return packet_increment_head(rb); case TPACKET_V3: default: WARN(1, "TPACKET version not supported.\n"); BUG(); return; } } static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; return packet_lookup_frame(po, rb, previous, status); } static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } static void packet_inc_pending(struct packet_ring_buffer *rb) { this_cpu_inc(*rb->pending_refcnt); } static void packet_dec_pending(struct packet_ring_buffer *rb) { this_cpu_dec(*rb->pending_refcnt); } static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) { unsigned int refcnt = 0; int cpu; /* We don't use pending refcount in rx_ring. */ if (rb->pending_refcnt == NULL) return 0; for_each_possible_cpu(cpu) refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); return refcnt; } static int packet_alloc_pending(struct packet_sock *po) { po->rx_ring.pending_refcnt = NULL; po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); if (unlikely(po->tx_ring.pending_refcnt == NULL)) return -ENOBUFS; return 0; } static void packet_free_pending(struct packet_sock *po) { free_percpu(po->tx_ring.pending_refcnt); } #define ROOM_POW_OFF 2 #define ROOM_NONE 0x0 #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.frame_max) + 1; idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static int __packet_rcv_has_room(const struct packet_sock *po, const struct sk_buff *skb) { const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { int rcvbuf = READ_ONCE(sk->sk_rcvbuf); int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) - (skb ? skb->truesize : 0); if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; else return ROOM_NONE; } if (po->tp_version == TPACKET_V3) { if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_v3_has_room(po, 0)) ret = ROOM_LOW; } else { if (__tpacket_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_has_room(po, 0)) ret = ROOM_LOW; } return ret; } static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { bool pressure; int ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) != pressure) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); return; } } static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { u32 *history = po->rollover->history; u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) if (READ_ONCE(history[i]) == rxhash) count++; victim = get_random_u32_below(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) WRITE_ONCE(history[victim], rxhash); return count > (ROLLOVER_HLEN >> 1); } static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { unsigned int val = atomic_inc_return(&f->rr_cur); return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return smp_processor_id() % num; } static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return get_random_u32_below(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, unsigned int idx, bool try_self, unsigned int num) { struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); if (room == ROOM_NORMAL || (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) return idx; po_skip = po; } i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !packet_sock_flag(po_next, PACKET_SOCK_PRESSURE) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; atomic_long_inc(&po->rollover->num); if (room == ROOM_LOW) atomic_long_inc(&po->rollover->num_huge); return i; } if (++i == num) i = 0; } while (i != j); atomic_long_inc(&po->rollover->num_failed); return idx; } static unsigned int fanout_demux_qm(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return skb_get_queue_mapping(skb) % num; } static unsigned int fanout_demux_bpf(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { struct bpf_prog *prog; unsigned int ret = 0; rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; } static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } switch (f->type) { case PACKET_FANOUT_HASH: default: idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: idx = fanout_demux_cpu(f, skb, num); break; case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; case PACKET_FANOUT_QM: idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: idx = fanout_demux_bpf(f, skb, num); break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } DEFINE_MUTEX(fanout_mutex); EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static u16 fanout_next_id; static void __fanout_link(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; spin_lock(&f->lock); rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } static void __fanout_unlink(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; int i; spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { if (rcu_dereference_protected(f->arr[i], lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); rcu_assign_pointer(f->arr[i], rcu_dereference_protected(f->arr[f->num_members - 1], lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { if (sk->sk_family != PF_PACKET) return false; return ptype->af_packet_priv == pkt_sk(sk)->fanout; } static void fanout_init_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_LB: atomic_set(&f->rr_cur, 0); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: RCU_INIT_POINTER(f->bpf_prog, NULL); break; } } static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) { struct bpf_prog *old; spin_lock(&f->lock); old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); rcu_assign_pointer(f->bpf_prog, new); spin_unlock(&f->lock); if (old) { synchronize_net(); bpf_prog_destroy(old); } } static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; struct sock_fprog fprog; int ret; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; ret = copy_bpf_fprog_from_user(&fprog, data, len); if (ret) return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; u32 fd; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; if (len != sizeof(fd)) return -EINVAL; if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(new)) return PTR_ERR(new); __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { case PACKET_FANOUT_CBPF: return fanout_set_data_cbpf(po, data, len); case PACKET_FANOUT_EBPF: return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; } } static void fanout_release_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) { struct packet_fanout *f; list_for_each_entry(f, &fanout_list, list) { if (f->id == candidate_id && read_pnet(&f->net) == sock_net(sk)) { return false; } } return true; } static bool fanout_find_new_id(struct sock *sk, u16 *new_id) { u16 id = fanout_next_id; do { if (__fanout_id_is_free(sk, id)) { *new_id = id; fanout_next_id = id + 1; return true; } id++; } while (id != fanout_next_id); return false; } static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: break; default: return -EINVAL; } mutex_lock(&fanout_mutex); err = -EALREADY; if (po->fanout) goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { err = -ENOMEM; rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); if (!rollover) goto out; atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); } if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) { if (id != 0) { err = -EINVAL; goto out; } if (!fanout_find_new_id(sk, &id)) { err = -ENOMEM; goto out; } /* ephemeral flag for the first socket in the group: drop it */ flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8); } match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && read_pnet(&f->net) == sock_net(sk)) { match = f; break; } } err = -EINVAL; if (match) { if (match->flags != flags) goto out; if (args->max_num_members && args->max_num_members != match->max_num_members) goto out; } else { if (args->max_num_members > PACKET_FANOUT_MAX) goto out; if (!args->max_num_members) /* legacy PACKET_FANOUT_MAX */ args->max_num_members = 256; err = -ENOMEM; match = kvzalloc(struct_size(match, arr, args->max_num_members), GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (po->num && match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ WRITE_ONCE(po->fanout, match); po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __dev_remove_pack(&po->prot_hook); __fanout_link(sk, po); } err = 0; } } spin_unlock(&po->bind_lock); if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); kvfree(match); } out: kfree(rollover); mutex_unlock(&fanout_mutex); return err; } /* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. * It is the responsibility of the caller to call fanout_release_data() and * free the returned packet_fanout (after synchronize_net()) */ static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; mutex_lock(&fanout_mutex); f = po->fanout; if (f) { po->fanout = NULL; if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; } mutex_unlock(&fanout_mutex); return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, struct sk_buff *skb) { /* Earlier code assumed this would be a VLAN pkt, double-check * this now that we have the actual packet in hand. We can only * do this check on Ethernet devices. */ if (unlikely(dev->type != ARPHRD_ETHER)) return false; skb_reset_mac_header(skb); return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); } static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; /* * When we registered the protocol we saved the socket in the data * field for just this event. */ sk = pt->af_packet_priv; /* * Yank back the headers [hope the device set this * right or kerboom...] * * Incoming packets have ll header pulled, * push it back. * * For outgoing ones skb->data == skb_mac_header(skb) * so that this procedure is noop. */ if (skb->pkt_type == PACKET_LOOPBACK) goto out; if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) goto oom; /* drop any routing info */ skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; skb_push(skb, skb->data - skb_mac_header(skb)); /* * The SOCK_PACKET socket receives _all_ frames. */ spkt->spkt_family = dev->type; strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* * Charge the memory to the socket. This is done specifically * to prevent sockets using all the memory up. */ if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: kfree_skb(skb); oom: return 0; } static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } /* * Output a raw packet to a device layer. This bypasses all the other * protocol layers and you must therefore supply it with a complete frame */ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return -EINVAL; if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) proto = saddr->spkt_protocol; } else return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard * header at transmission time by themselves. PPP is the notable * one here. This should really be fixed at the driver level. */ skb_reserve(skb, reserved); skb_reset_network_header(skb); /* Try to align data part correctly */ if (hhlen) { skb->data -= hhlen; skb->tail -= hhlen; if (len < hhlen) skb_reset_network_header(skb); } err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) goto out_free; goto retry; } if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } skb->protocol = proto; skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, &sockc); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); dev_queue_xmit(skb); rcu_read_unlock(); return len; out_unlock: rcu_read_unlock(); out_free: kfree_skb(skb); return err; } static unsigned int run_filter(struct sk_buff *skb, const struct sock *sk, unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr_mrg_rxbuf vnet_hdr = { .num_buffers = 0 }; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz); } /* * This function makes lazy skb cloning in hope that most of packets * are discarded by BPF. * * Note tricky part: we DO mangle shared skb! skb->data, skb->len * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * * Otherwise, the device hides details of its frame * structure, so that corresponding packet head is * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; if (snaplen > res) snaplen = res; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (nskb == NULL) goto drop_n_acct; if (skb_head != skb->data) { skb->data = skb_head; skb->len = skb_len; } consume_skb(skb); skb = nskb; } sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; sll->sll_halen = dev_parse_header(skb, sll->sll_addr); /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). * Use their space for storing the original skb length. */ PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; skb_set_owner_r(skb, sk); skb->dev = NULL; skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, hdrlen; unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; unsigned int slot_id = 0; int vnet_hdr_sz = 0; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing * userspace to call getsockopt(..., PACKET_HDRLEN, ...). */ BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; /* If we are flooded, just give up */ if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); if (vnet_hdr_sz) netoff += vnet_hdr_sz; macoff = netoff - maclen; } if (netoff > USHRT_MAX) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { copy_skb = skb_get(skb); skb_head = skb->data; } if (copy_skb) { memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { snaplen = 0; vnet_hdr_sz = 0; } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { u32 nval; nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", snaplen, nval, macoff); snaplen = nval; if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; vnet_hdr_sz = 0; } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; if (po->tp_version <= TPACKET_V2) { slot_id = po->rx_ring.head; if (test_bit(slot_id, po->rx_ring.rx_owner_map)) goto drop_n_account; __set_bit(slot_id, po->rx_ring.rx_owner_map); } if (vnet_hdr_sz && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true, 0)) { if (po->tp_version == TPACKET_V3) prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* * LOSING will be reported till you read the stats, * because it's COR - Clear On Read. * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); /* Always timestamp; prefer an existing software timestamp taken * closer to the time of capture. */ ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp) | SOF_TIMESTAMPING_SOFTWARE); if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: h.h2->tp_len = skb->len; h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (skb_vlan_tag_present(skb)) { h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); h.h2->tp_vlan_tpid = ntohs(skb->protocol); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; } memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: /* tp_nxt_offset,vlan are already populated above. * So DONT clear those fields here */ h.h3->tp_status |= status; h.h3->tp_len = skb->len; h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: BUG(); } sll = h.raw + TPACKET_ALIGN(hdrlen); sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 if (po->tp_version <= TPACKET_V2) { u8 *start, *end; end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); } smp_wmb(); #endif if (po->tp_version <= TPACKET_V2) { spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); if (likely(po->tx_ring.pg_vec)) { void *ph; __u32 ts; ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); complete(&po->skb_completion); } sock_wfree(skb); } static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) { if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 > __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len))) vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(), __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2); if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len) return -EINVAL; return 0; } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { int ret; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; ret = __packet_snd_vnet_parse(vnet_hdr, *len); if (ret) return ret; /* move iter to point to the start of mac header */ if (vnet_hdr_sz != sizeof(struct virtio_net_hdr)) iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); return 0; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; int err; ph.raw = frame; skb->protocol = proto; skb->dev = dev; skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); to_write = tp_len; if (sock->type == SOCK_DGRAM) { err = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; if (!dev_validate_header(dev, skb->data, hdrlen)) return -EINVAL; data += hdrlen; to_write -= hdrlen; } offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { pr_err("Packet exceed the number of skb frags(%u)\n", (unsigned int)MAX_SKB_FRAGS); return -EFAULT; } page = pgv_to_page(data); data += len; flush_dcache_page(page); get_page(page); skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; len = ((to_write > len_max) ? len_max : to_write); } packet_parse_headers(skb, sock); return tp_len; } static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; int tp_len, off; ph.raw = frame; switch (po->tp_version) { case TPACKET_V3: if (ph.h3->tp_next_offset != 0) { pr_warn_once("variable sized slot not supported"); return -EINVAL; } tp_len = ph.h3->tp_len; break; case TPACKET_V2: tp_len = ph.h2->tp_len; break; default: tp_len = ph.h1->tp_len; break; } if (unlikely(tp_len > size_max)) { pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } if (unlikely(packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF))) { int off_min, off_max; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; if (po->sk.sk_type == SOCK_DGRAM) { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_net; break; case TPACKET_V2: off = ph.h2->tp_net; break; default: off = ph.h1->tp_net; break; } } else { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_mac; break; case TPACKET_V2: off = ph.h2->tp_mac; break; default: off = ph.h1->tp_mac; break; } } if (unlikely((off < off_min) || (off_max < off))) return -EINVAL; } else { off = po->tp_hdrlen - sizeof(struct sockaddr_ll); } *data = frame + off; return tp_len; } static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); unsigned char *addr = NULL; int tp_len, size_max; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo = 0; mutex_lock(&po->pg_vec_lock); /* packet_sendmsg() check on tx_ring.pg_vec was lockless, * we need to confirm it under protection of pg_vec_lock. */ if (unlikely(!po->tx_ring.pg_vec)) { err = -EBUSY; goto out; } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (po->sk.sk_socket->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_put; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) goto out_put; } if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { if (need_wait && skb) { timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } } /* check for additional frames */ continue; } skb = NULL; tp_len = tpacket_parse_header(po, ph, size_max, &data); if (tp_len < 0) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { vnet_hdr = data; data += vnet_hdr_sz; tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; goto tpacket_error; } copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { /* we assume the socket was initially writeable ... */ if (likely(len_sum > 0)) err = len_sum; goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) { __packet_set_status(po, ph, TP_STATUS_AVAILABLE); packet_increment_head(&po->tx_ring); kfree_skb(skb); continue; } else { status = TP_STATUS_WRONG_FORMAT; err = tp_len; goto out_status; } } if (vnet_hdr_sz) { if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { tp_len = -EINVAL; goto tpacket_error; } virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ skb = NULL; goto out_status; } /* * skb was dropped but not destructed yet; * let's treat it like congestion or err < 0 */ err = 0; } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || /* Note: packet_read_pending() might be slow if we have * to call it as it's per_cpu variable, but in fast-path * we already short-circuit the loop with the first * condition, and luckily don't have to go that path * anyway. */ (need_wait && packet_read_pending(&po->tx_ring)))); err = len_sum; goto out_put; out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; } static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, size_t linear, int noblock, int *err) { struct sk_buff *skb; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) 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 NULL; skb_reserve(skb, reserve); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); int hlen, tlen, linear; int extra_len = 0; /* * Get and verify the address. */ if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (sock->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_unlock; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out_unlock; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); linear = max(linear, min_t(int, len, dev->hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } /* Returns -EFAULT on error */ err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; if ((sock->type == SOCK_RAW && !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, &sockc); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_free; } skb->protocol = proto; skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); if (vnet_hdr_sz) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err) goto out_unlock; } dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: dev_put(dev); out: return err; } static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. * tpacket_snd() will redo the check safely. */ if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); return packet_snd(sock, msg, len); } /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. */ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; if (!sk) return 0; net = sock_net(sk); po = pkt_sk(sk); mutex_lock(&net->packet.sklist_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); packet_flush_mclist(sk); lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); } if (po->tx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } release_sock(sk); f = fanout_release(sk); synchronize_net(); kfree(po->rollover); if (f) { fanout_release_data(f); kvfree(f); } /* * Now the socket is dead. No more input will appear. */ sock_orphan(sk); sock->sk = NULL; /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); packet_free_pending(po); sock_put(sk); return 0; } /* * Attach a packet hook. */ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); struct net_device *dev = NULL; bool unlisted = false; bool need_rehook; int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); if (!proto) proto = po->num; rcu_read_lock(); if (po->fanout) { ret = -EINVAL; goto out_unlock; } if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { ret = -ENODEV; goto out_unlock; } } else if (ifindex) { dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (!dev) { ret = -ENODEV; goto out_unlock; } } need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { dev_hold(dev); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(packet_sock_flag(po, PACKET_SOCK_RUNNING)); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { netdev_hold(dev, &po->prot_hook.dev_tracker, GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } dev_put(dev); } if (proto == 0 || !need_rehook) goto out_unlock; if (!unlisted && (!dev || (dev->flags & IFF_UP))) { register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } out_unlock: rcu_read_unlock(); spin_unlock(&po->bind_lock); release_sock(sk); return ret; } /* * Bind a packet socket to a device */ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality */ if (addr_len != sizeof(struct sockaddr)) return -EINVAL; /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; /* * Check legality */ if (addr_len < sizeof(struct sockaddr_ll)) return -EINVAL; if (sll->sll_family != AF_PACKET) return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { .name = "PACKET", .owner = THIS_MODULE, .obj_size = sizeof(struct packet_sock), }; /* * Create a packet of type SOCK_PACKET. */ static int packet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct packet_sock *po; __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) return -ESOCKTNOSUPPORT; sock->state = SS_UNCONNECTED; err = -ENOBUFS; sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; sock->ops = &packet_ops; if (sock->type == SOCK_PACKET) sock->ops = &packet_ops_spkt; po = pkt_sk(sk); err = packet_alloc_pending(po); if (err) goto out_sk_free; sock_init_data(sock, sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; /* * Attach a protocol block */ spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, &packet_proto, 1); return 0; out_sk_free: sk_free(sk); out: return err; } /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. */ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = READ_ONCE(pkt_sk(sk)->vnet_hdr_sz); unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) goto out; #if 0 /* What error should we return now? EUNATTACH? */ if (pkt_sk(sk)->ifindex < 0) return -ENODEV; #endif if (flags & MSG_ERRQUEUE) { err = sock_recv_errqueue(sk, msg, len, SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } /* * Call the generic datagram receiver. This handles all sorts * of horrible races and re-entrancy so we can forget about it * in the protocol layers. * * Now it will return ENETDOWN, if device have just gone down, * but then it will block. */ skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() * handles the blocking we don't see and worry about blocking * retries. */ if (skb == NULL) goto out; packet_rcv_try_clear_pressure(pkt_sk(sk)); if (vnet_hdr_len) { err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; } /* You lose any data beyond the buffer you gave. If it worries * a user program they can ask the device for its MTU * anyway. */ copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; if (sock->type != SOCK_PACKET) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; sll->sll_protocol = (sock->type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { const size_t max_len = min(sizeof(skb->cb), sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); copy_len = msg->msg_namelen; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { memset(msg->msg_name + offsetof(struct sockaddr_ll, sll_addr), 0, sizeof(sll->sll_addr)); msg->msg_namelen = sizeof(struct sockaddr_ll); } } if (WARN_ON_ONCE(copy_len > max_len)) { copy_len = max_len; msg->msg_namelen = copy_len; } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); if (skb_vlan_tag_present(skb)) { aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); if (dev) { aux.tp_vlan_tci = vlan_get_tci(skb, dev); aux.tp_vlan_tpid = ntohs(skb->protocol); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. */ err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied); out_free: skb_free_datagram(sk, skb); out: return err; } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; if (peer) return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); int ifindex; if (peer) return -EOPNOTSUPP; ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; /* Let __fortify_memcpy_chk() know the actual buffer size. */ memcpy(((struct sockaddr_storage *)sll)->__data + offsetof(struct sockaddr_ll, sll_addr) - offsetofend(struct sockaddr_ll, sll_family), dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; } rcu_read_unlock(); return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what) { switch (i->type) { case PACKET_MR_MULTICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_mc_add(dev, i->addr); else return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_uc_add(dev, i->addr); else return dev_uc_del(dev, i->addr); break; default: break; } return 0; } static void packet_dev_mclist_delete(struct net_device *dev, struct packet_mclist **mlp, struct list_head *list) { struct packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { list_add(&ml->remove_list, list); *mlp = ml->next; } else mlp = &ml->next; } } static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml, *i; struct net_device *dev; int err; rtnl_lock(); err = -ENODEV; dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; err = -EINVAL; if (mreq->mr_alen > dev->addr_len) goto done; err = -ENOBUFS; i = kmalloc(sizeof(*i), GFP_KERNEL); if (i == NULL) goto done; err = 0; for (ml = po->mclist; ml; ml = ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { ml->count++; /* Free the new element ... */ kfree(i); goto done; } } i->type = mreq->mr_type; i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; INIT_LIST_HEAD(&i->remove_list); i->next = po->mclist; po->mclist = i; err = packet_dev_mc(dev, i, 1); if (err) { po->mclist = i->next; kfree(i); } done: rtnl_unlock(); return err; } static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_mclist *ml, **mlp; rtnl_lock(); for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) packet_dev_mc(dev, ml, -1); kfree(ml); } break; } } rtnl_unlock(); return 0; } static void packet_flush_mclist(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml; if (!po->mclist) return; rtnl_lock(); while ((ml = po->mclist) != NULL) { struct net_device *dev; po->mclist = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev != NULL) packet_dev_mc(dev, ml, -1); kfree(ml); } rtnl_unlock(); } static int packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); int ret; if (level != SOL_PACKET) return -ENOPROTOOPT; switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { struct packet_mreq_max mreq; int len = optlen; memset(&mreq, 0, sizeof(mreq)); if (len < sizeof(struct packet_mreq)) return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; if (optname == PACKET_ADD_MEMBERSHIP) ret = packet_mc_add(sk, &mreq); else ret = packet_mc_drop(sk, &mreq); return ret; } case PACKET_RX_RING: case PACKET_TX_RING: { union tpacket_req_u req_u; ret = -EINVAL; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: if (optlen < sizeof(req_u.req)) break; ret = copy_from_sockptr(&req_u.req, optval, sizeof(req_u.req)) ? -EINVAL : 0; break; case TPACKET_V3: default: if (optlen < sizeof(req_u.req3)) break; ret = copy_from_sockptr(&req_u.req3, optval, sizeof(req_u.req3)) ? -EINVAL : 0; break; } if (!ret) ret = packet_set_ring(sk, &req_u, 0, optname == PACKET_TX_RING); release_sock(sk); return ret; } case PACKET_COPY_THRESH: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: break; default: return -EINVAL; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_version = val; ret = 0; } release_sock(sk); return ret; } case PACKET_RESERVE: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_reserve = val; ret = 0; } release_sock(sk); return ret; } case PACKET_LOSS: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { packet_sock_flag_set(po, PACKET_SOCK_TP_LOSS, val); ret = 0; } release_sock(sk); return ret; } case PACKET_AUXDATA: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: case PACKET_VNET_HDR_SZ: { int val, hdr_len; if (sock->type != SOCK_RAW) return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (optname == PACKET_VNET_HDR_SZ) { if (val && val != sizeof(struct virtio_net_hdr) && val != sizeof(struct virtio_net_hdr_mrg_rxbuf)) return -EINVAL; hdr_len = val; } else { hdr_len = val ? sizeof(struct virtio_net_hdr) : 0; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { WRITE_ONCE(po->vnet_hdr_sz, hdr_len); ret = 0; } release_sock(sk); return ret; } case PACKET_TIMESTAMP: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(po->tp_tstamp, val); return 0; } case PACKET_FANOUT: { struct fanout_args args = { 0 }; if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { /* Paired with the WRITE_ONCE() in fanout_add() */ if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); } case PACKET_IGNORE_OUTGOING: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) packet_sock_flag_set(po, PACKET_SOCK_TX_HAS_OFF, val); release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_QDISC_BYPASS, val); return 0; } default: return -ENOPROTOOPT; } } static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); st.stats3.tp_drops = drops; st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); st.stats1.tp_drops = drops; st.stats1.tp_packets += drops; data = &st.stats1; } break; case PACKET_AUXDATA: val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = !!READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; case PACKET_COPY_THRESH: val = READ_ONCE(pkt_sk(sk)->copy_thresh); break; case PACKET_VERSION: val = po->tp_version; break; case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); if (len < sizeof(int)) return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { case TPACKET_V1: val = sizeof(struct tpacket_hdr); break; case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; case TPACKET_V3: val = sizeof(struct tpacket3_hdr); break; default: return -EINVAL; } break; case PACKET_RESERVE: val = po->tp_reserve; break; case PACKET_LOSS: val = packet_sock_flag(po, PACKET_SOCK_TP_LOSS); break; case PACKET_TIMESTAMP: val = READ_ONCE(po->tp_tstamp); break; case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16) | ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_IGNORE_OUTGOING: val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; rstats.tp_all = atomic_long_read(&po->rollover->num); rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); data = &rstats; lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF); break; case PACKET_QDISC_BYPASS: val = packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS); break; default: return -ENOPROTOOPT; } if (len > lv) len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) return -EFAULT; return 0; } static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct packet_mclist *ml, *tmp; LIST_HEAD(mclist); struct sock *sk; rcu_read_lock(); sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist, &mclist); fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); } break; case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->num) register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; } } rcu_read_unlock(); /* packet_dev_mc might grab instance locks so can't run under rcu */ list_for_each_entry_safe(ml, tmp, &mclist, remove_list) { packet_dev_mc(dev, ml, -1); kfree(ml); } return NOTIFY_DONE; } static int packet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: case SIOCDARP: case SIOCGARP: case SIOCSARP: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: return inet_dgram_ops.ioctl(sock, cmd, arg); #endif default: return -ENOIOCTLCMD; } return 0; } static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } /* Dirty? Well, I still did not learn better way to account * for user mmaps. */ static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; static void free_pg_vec(struct pgv *pg_vec, unsigned int order, unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); if (buffer) return buffer; /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* complete and utter failure */ return NULL; } static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; struct pgv *pg_vec; int i; pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; for (i = 0; i < block_nr; i++) { pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } out: return pg_vec; out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; err = -EBUSY; if (!closing) { if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; } if (req->tp_block_nr) { unsigned int min_frame_size; /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V1: po->tp_hdrlen = TPACKET_HDRLEN; break; case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; case TPACKET_V3: po->tp_hdrlen = TPACKET3_HDRLEN; break; } err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && req->tp_block_size < BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V3: /* Block transmit is not supported yet */ if (!tx_ring) { init_prb_bdqc(po, rb, pg_vec, req_u); } else { struct tpacket_req3 *req3 = &req_u->req3; if (req3->tp_retire_blk_tov || req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; goto out_free_pg_vec; } } break; default: if (!tx_ring) { rx_owner_map = bitmap_alloc(req->tp_frame_nr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (!rx_owner_map) goto out_free_pg_vec; } break; } } /* Done */ else { err = -EINVAL; if (unlikely(req->tp_frame_nr)) goto out; } /* Detach socket from network */ spin_lock(&po->bind_lock); was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING); num = po->num; if (was_running) { WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); synchronize_net(); err = -EBUSY; mutex_lock(&po->pg_vec_lock); if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); if (po->tp_version <= TPACKET_V2) swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); if (was_running) { WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } out_free_pg_vec: if (pg_vec) { bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); } out: return err; } static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); unsigned long size, expected_size; struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; if (vma->vm_pgoff) return -EINVAL; mutex_lock(&po->pg_vec_lock); expected_size = 0; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec) { expected_size += rb->pg_vec_len * rb->pg_vec_pages * PAGE_SIZE; } } if (expected_size == 0) goto out; size = vma->vm_end - vma->vm_start; if (size != expected_size) goto out; start = vma->vm_start; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec == NULL) continue; for (i = 0; i < rb->pg_vec_len; i++) { struct page *page; void *kaddr = rb->pg_vec[i].buffer; int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; start += PAGE_SIZE; kaddr += PAGE_SIZE; } } } atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; out: mutex_unlock(&po->pg_vec_lock); return err; } static const struct proto_ops packet_ops_spkt = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind_spkt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops packet_ops = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, }; static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, }; static struct notifier_block packet_netdev_notifier = { .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS static void *packet_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); rcu_read_lock(); return seq_hlist_start_head_rcu(&net->packet.sklist, *pos); } static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); return seq_hlist_next_rcu(v, &net->packet.sklist, pos); } static void packet_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%*sRefCnt Type Proto Iface R Rmem User Inode\n", IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), READ_ONCE(po->ifindex), packet_sock_flag(po, PACKET_SOCK_RUNNING), atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), sock_i_ino(s)); } return 0; } static const struct seq_operations packet_seq_ops = { .start = packet_seq_start, .next = packet_seq_next, .stop = packet_seq_stop, .show = packet_seq_show, }; #endif static int __net_init packet_net_init(struct net *net) { mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); #ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif /* CONFIG_PROC_FS */ return 0; } static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, }; static void __exit packet_exit(void) { sock_unregister(PF_PACKET); proto_unregister(&packet_proto); unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; rc = proto_register(&packet_proto, 0); if (rc) goto out_notifier; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; return 0; out_proto: proto_unregister(&packet_proto); out_notifier: unregister_netdevice_notifier(&packet_netdev_notifier); out_pernet: unregister_pernet_subsys(&packet_net_ops); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_DESCRIPTION("Packet socket support (AF_PACKET)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 3 3 28707 9057 27601 4819 4833 5256 5256 4197 5256 5253 3862 55 3325 3860 3866 236 232 3 3 786 487 785 785 487 487 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 | // 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); |
| 30 29 12 100 32 29 1202 32 153 4 179 179 3 179 179 178 179 179 43 43 179 87 98 9 46 30 32 5006 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2001 Jens Axboe <axboe@suse.de> */ #ifndef __LINUX_BIO_H #define __LINUX_BIO_H #include <linux/mempool.h> /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include <linux/blk_types.h> #include <linux/uio.h> #define BIO_MAX_VECS 256U #define BIO_MAX_INLINE_VECS UIO_MAXIOV struct queue_limits; static inline unsigned int bio_max_segs(unsigned int nr_segs) { return min(nr_segs, BIO_MAX_VECS); } #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) #define bio_iter_page(bio, iter) \ bvec_iter_page((bio)->bi_io_vec, (iter)) #define bio_iter_len(bio, iter) \ bvec_iter_len((bio)->bi_io_vec, (iter)) #define bio_iter_offset(bio, iter) \ bvec_iter_offset((bio)->bi_io_vec, (iter)) #define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) #define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter) #define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter) /* * Return the data direction, READ or WRITE. */ #define bio_data_dir(bio) \ (op_is_write(bio_op(bio)) ? WRITE : READ) /* * Check whether this bio carries any data or not. A NULL bio is allowed. */ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && bio_op(bio) != REQ_OP_DISCARD && bio_op(bio) != REQ_OP_SECURE_ERASE && bio_op(bio) != REQ_OP_WRITE_ZEROES) return true; return false; } static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || bio_op(bio) == REQ_OP_WRITE_ZEROES; } static inline void *bio_data(struct bio *bio) { if (bio_has_data(bio)) return page_address(bio_page(bio)) + bio_offset(bio); return NULL; } static inline bool bio_next_segment(const struct bio *bio, struct bvec_iter_all *iter) { if (iter->idx >= bio->bi_vcnt) return false; bvec_advance(&bio->bi_io_vec[iter->idx], iter); return true; } /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) static inline void bio_advance_iter(const struct bio *bio, struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ } /* @bytes should be less or equal to bvec[i->bi_idx].bv_len */ static inline void bio_advance_iter_single(const struct bio *bio, struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance_single(bio->bi_io_vec, iter, bytes); } void __bio_advance(struct bio *, unsigned bytes); /** * bio_advance - increment/complete a bio by some number of bytes * @bio: bio to advance * @nbytes: number of bytes to complete * * This updates bi_sector, bi_size and bi_idx; if the number of bytes to * complete doesn't align with a bvec boundary, then bv_len and bv_offset will * be updated on the last bvec as well. * * @bio will then represent the remaining, uncompleted portion of the io. */ static inline void bio_advance(struct bio *bio, unsigned int nbytes) { if (nbytes == bio->bi_iter.bi_size) { bio->bi_iter.bi_size = 0; return; } __bio_advance(bio, nbytes); } #define __bio_for_each_segment(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bio_iter_iovec((bio), (iter))), 1); \ bio_advance_iter_single((bio), &(iter), (bvl).bv_len)) #define bio_for_each_segment(bvl, bio, iter) \ __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) #define __bio_for_each_bvec(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \ bio_advance_iter_single((bio), &(iter), (bvl).bv_len)) /* iterate over multi-page bvec */ #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) /* * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the * same reasons as bio_for_each_segment_all(). */ #define bio_for_each_bvec_all(bvl, bio, i) \ for (i = 0, bvl = bio_first_bvec_all(bio); \ i < (bio)->bi_vcnt; i++, bvl++) #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) { unsigned segs = 0; struct bio_vec bv; struct bvec_iter iter; /* * We special case discard/write same/write zeroes, because they * interpret bi_size differently: */ switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; default: break; } bio_for_each_segment(bv, bio, iter) segs++; return segs; } /* * get a reference to a bio, so it won't disappear. the intended use is * something like: * * bio_get(bio); * submit_bio(rw, bio); * if (bio->bi_flags ...) * do_something * bio_put(bio); * * without the bio_get(), it could potentially complete I/O before submit_bio * returns. and then bio would be freed memory when if (bio->bi_flags ...) * runs */ static inline void bio_get(struct bio *bio) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb__before_atomic(); atomic_inc(&bio->__bi_cnt); } static inline void bio_cnt_set(struct bio *bio, unsigned int count) { if (count != 1) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb(); } atomic_set(&bio->__bi_cnt, count); } static inline bool bio_flagged(struct bio *bio, unsigned int bit) { return bio->bi_flags & (1U << bit); } static inline void bio_set_flag(struct bio *bio, unsigned int bit) { bio->bi_flags |= (1U << bit); } static inline void bio_clear_flag(struct bio *bio, unsigned int bit) { bio->bi_flags &= ~(1U << bit); } static inline struct bio_vec *bio_first_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return bio->bi_io_vec; } static inline struct page *bio_first_page_all(struct bio *bio) { return bio_first_bvec_all(bio)->bv_page; } static inline struct folio *bio_first_folio_all(struct bio *bio) { return page_folio(bio_first_page_all(bio)); } static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return &bio->bi_io_vec[bio->bi_vcnt - 1]; } /** * struct folio_iter - State for iterating all folios in a bio. * @folio: The current folio we're iterating. NULL after the last folio. * @offset: The byte offset within the current folio. * @length: The number of bytes in this iteration (will not cross folio * boundary). */ struct folio_iter { struct folio *folio; size_t offset; size_t length; /* private: for use by the iterator */ struct folio *_next; size_t _seg_count; int _i; }; static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, int i) { struct bio_vec *bvec = bio_first_bvec_all(bio) + i; if (unlikely(i >= bio->bi_vcnt)) { fi->folio = NULL; return; } fi->folio = page_folio(bvec->bv_page); fi->offset = bvec->bv_offset + PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); fi->_next = folio_next(fi->folio); fi->_i = i; } static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) { fi->_seg_count -= fi->length; if (fi->_seg_count) { fi->folio = fi->_next; fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); fi->_next = folio_next(fi->folio); } else { bio_first_folio(fi, bio, fi->_i + 1); } } /** * bio_for_each_folio_all - Iterate over each folio in a bio. * @fi: struct folio_iter which is updated for each folio. * @bio: struct bio to iterate over. */ #define bio_for_each_folio_all(fi, bio) \ for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio)) void bio_trim(struct bio *bio, sector_t offset, sector_t size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim, unsigned *segs, unsigned max_bytes); /** * bio_next_split - get next @sectors from a bio, splitting if necessary * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Return: a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { if (sectors >= bio_sectors(bio)) return bio; return bio_split(bio, sectors, gfp, bs); } enum { BIOSET_NEED_BVECS = BIT(0), BIOSET_NEED_RESCUER = BIT(1), BIOSET_PERCPU_CACHE = BIT(2), }; extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp_mask, struct bio_set *bs); struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, gfp_t gfp, struct bio_set *bs); int bio_init_clone(struct block_device *bdev, struct bio *bio, struct bio *bio_src, gfp_t gfp); extern struct bio_set fs_bio_set; static inline struct bio *bio_alloc(struct block_device *bdev, unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp_mask) { return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set); } void submit_bio(struct bio *bio); extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } static inline void bio_wouldblock_error(struct bio *bio) { bio_set_flag(bio, BIO_QUIET); bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } /* * Calculate number of bvec segments that should be allocated to fit data * pointed by @iter. If @iter is backed by bvec it's going to be reused * instead of allocating a new one. */ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) { if (iov_iter_is_bvec(iter)) return 0; return iov_iter_npages(iter, max_segs); } struct request_queue; void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, unsigned short max_vecs, blk_opf_t opf); extern void bio_uninit(struct bio *); void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf); void bio_chain(struct bio *, struct bio *); int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len, unsigned off); bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t off); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, size_t off); void bio_add_virt_nofail(struct bio *bio, void *vaddr, unsigned len); /** * bio_add_max_vecs - number of bio_vecs needed to add data to a bio * @kaddr: kernel virtual address to add * @len: length in bytes to add * * Calculate how many bio_vecs need to be allocated to add the kernel virtual * address range in [@kaddr:@len] in the worse case. */ static inline unsigned int bio_add_max_vecs(void *kaddr, unsigned int len) { if (is_vmalloc_addr(kaddr)) return DIV_ROUND_UP(offset_in_page(kaddr) + len, PAGE_SIZE); return 1; } unsigned int bio_add_vmalloc_chunk(struct bio *bio, void *vaddr, unsigned len); bool bio_add_vmalloc(struct bio *bio, void *vaddr, unsigned int len); int submit_bio_wait(struct bio *bio); int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data, size_t len, enum req_op op); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); void guard_bio_eod(struct bio *bio); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); static inline void zero_fill_bio(struct bio *bio) { zero_fill_bio_iter(bio, bio->bi_iter); } static inline void bio_release_pages(struct bio *bio, bool mark_dirty) { if (bio_flagged(bio, BIO_PAGE_PINNED)) __bio_release_pages(bio, mark_dirty); } #define bio_dev(bio) \ disk_devt((bio)->bi_bdev->bd_disk) #ifdef CONFIG_BLK_CGROUP void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); void blkcg_punt_bio_submit(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } static inline void blkcg_punt_bio_submit(struct bio *bio) { submit_bio(bio); } #endif /* CONFIG_BLK_CGROUP */ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) { bio_clear_flag(bio, BIO_REMAPPED); if (bio->bi_bdev != bdev) bio_clear_flag(bio, BIO_BPS_THROTTLED); bio->bi_bdev = bdev; bio_associate_blkg(bio); } /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * * A bio_list anchors a singly-linked list of bios chained through the bi_next * member of the bio. The bio_list also caches the last list member to allow * fast access to the tail. */ struct bio_list { struct bio *head; struct bio *tail; }; static inline int bio_list_empty(const struct bio_list *bl) { return bl->head == NULL; } static inline void bio_list_init(struct bio_list *bl) { bl->head = bl->tail = NULL; } #define BIO_EMPTY_LIST { NULL, NULL } #define bio_list_for_each(bio, bl) \ for (bio = (bl)->head; bio; bio = bio->bi_next) static inline unsigned bio_list_size(const struct bio_list *bl) { unsigned sz = 0; struct bio *bio; bio_list_for_each(bio, bl) sz++; return sz; } static inline void bio_list_add(struct bio_list *bl, struct bio *bio) { bio->bi_next = NULL; if (bl->tail) bl->tail->bi_next = bio; else bl->head = bio; bl->tail = bio; } static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio) { bio->bi_next = bl->head; bl->head = bio; if (!bl->tail) bl->tail = bio; } static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->tail) bl->tail->bi_next = bl2->head; else bl->head = bl2->head; bl->tail = bl2->tail; } static inline void bio_list_merge_init(struct bio_list *bl, struct bio_list *bl2) { bio_list_merge(bl, bl2); bio_list_init(bl2); } static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->head) bl2->tail->bi_next = bl->head; else bl->tail = bl2->tail; bl->head = bl2->head; } static inline struct bio *bio_list_peek(struct bio_list *bl) { return bl->head; } static inline struct bio *bio_list_pop(struct bio_list *bl) { struct bio *bio = bl->head; if (bio) { bl->head = bl->head->bi_next; if (!bl->head) bl->tail = NULL; bio->bi_next = NULL; } return bio; } static inline struct bio *bio_list_get(struct bio_list *bl) { struct bio *bio = bl->head; bl->head = bl->tail = NULL; return bio; } /* * Increment chain count for the bio. Make sure the CHAIN flag update * is visible before the raised count. */ static inline void bio_inc_remaining(struct bio *bio) { bio_set_flag(bio, BIO_CHAIN); smp_mb__before_atomic(); atomic_inc(&bio->__bi_remaining); } /* * bio_set is used to allow other portions of the IO system to * allocate their own private memory pools for bio and iovec structures. * These memory pools in turn all allocate from the bio_slab * and the bvec_slabs[]. */ #define BIO_POOL_SIZE 2 struct bio_set { struct kmem_cache *bio_slab; unsigned int front_pad; /* * per-cpu bio alloc cache */ struct bio_alloc_cache __percpu *cache; mempool_t bio_pool; mempool_t bvec_pool; unsigned int back_pad; /* * Deadlock avoidance for stacking block drivers: see comments in * bio_alloc_bioset() for details */ spinlock_t rescue_lock; struct bio_list rescue_list; struct work_struct rescue_work; struct workqueue_struct *rescue_workqueue; /* * Hot un-plug notifier for the per-cpu cache, if used */ struct hlist_node cpuhp_dead; }; static inline bool bioset_initialized(struct bio_set *bs) { return bs->bio_slab != NULL; } /* * Mark a bio as polled. Note that for async polled IO, the caller must * expect -EWOULDBLOCK if we cannot allocate a request (or other resources). * We cannot block waiting for requests on polled IO, as those completions * must be found by the caller. This is different than IRQ driven IO, where * it's safe to wait for IO to complete. */ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) { bio->bi_opf |= REQ_POLLED; if (kiocb->ki_flags & IOCB_NOWAIT) bio->bi_opf |= REQ_NOWAIT; } static inline void bio_clear_polled(struct bio *bio) { bio->bi_opf &= ~REQ_POLLED; } /** * bio_is_zone_append - is this a zone append bio? * @bio: bio to check * * Check if @bio is a zone append operation. Core block layer code and end_io * handlers must use this instead of an open coded REQ_OP_ZONE_APPEND check * because the block layer can rewrite REQ_OP_ZONE_APPEND to REQ_OP_WRITE if * it is not natively supported. */ static inline bool bio_is_zone_append(struct bio *bio) { if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) return false; return bio_op(bio) == REQ_OP_ZONE_APPEND || bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); } struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); struct bio *blk_alloc_discard_bio(struct block_device *bdev, sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask); #endif /* __LINUX_BIO_H */ |
| 22 22 22 410 409 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2007 Andi Kleen, SUSE Labs. * * This contains most of the x86 vDSO kernel-side code. */ #include <linux/mm.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/random.h> #include <linux/elf.h> #include <linux/cpu.h> #include <linux/ptrace.h> #include <linux/vdso_datastore.h> #include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> #include <asm/tlb.h> #include <asm/page.h> #include <asm/desc.h> #include <asm/cpufeature.h> #include <asm/vdso/vsyscall.h> #include <clocksource/hyperv_timer.h> static_assert(VDSO_NR_PAGES + VDSO_NR_VCLOCK_PAGES == __VDSO_PAGES); unsigned int vclocks_used __read_mostly; #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; #endif int __init init_vdso_image(const struct vdso_image *image) { BUILD_BUG_ON(VDSO_CLOCKMODE_MAX >= 32); BUG_ON(image->size % PAGE_SIZE != 0); apply_alternatives((struct alt_instr *)(image->data + image->alt), (struct alt_instr *)(image->data + image->alt + image->alt_len)); return 0; } struct linux_binprm; static vm_fault_t vdso_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) { const struct vdso_image *image = vma->vm_mm->context.vdso_image; if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size) return VM_FAULT_SIGBUS; vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT)); get_page(vmf->page); return 0; } static void vdso_fix_landing(const struct vdso_image *image, struct vm_area_struct *new_vma) { if (in_ia32_syscall() && image == &vdso_image_32) { struct pt_regs *regs = current_pt_regs(); unsigned long vdso_land = image->sym_int80_landing_pad; unsigned long old_land_addr = vdso_land + (unsigned long)current->mm->context.vdso; /* Fixing userspace landing - look at do_fast_syscall_32 */ if (regs->ip == old_land_addr) regs->ip = new_vma->vm_start + vdso_land; } } static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { const struct vdso_image *image = current->mm->context.vdso_image; vdso_fix_landing(image, new_vma); current->mm->context.vdso = (void __user *)new_vma->vm_start; return 0; } static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) { switch (vmf->pgoff) { #ifdef CONFIG_PARAVIRT_CLOCK case VDSO_PAGE_PVCLOCK_OFFSET: { struct pvclock_vsyscall_time_info *pvti = pvclock_get_pvti_cpu0_va(); if (pvti && vclock_was_used(VDSO_CLOCKMODE_PVCLOCK)) return vmf_insert_pfn_prot(vma, vmf->address, __pa(pvti) >> PAGE_SHIFT, pgprot_decrypted(vma->vm_page_prot)); break; } #endif /* CONFIG_PARAVIRT_CLOCK */ #ifdef CONFIG_HYPERV_TIMER case VDSO_PAGE_HVCLOCK_OFFSET: { unsigned long pfn = hv_get_tsc_pfn(); if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK)) return vmf_insert_pfn(vma, vmf->address, pfn); break; } #endif /* CONFIG_HYPERV_TIMER */ } return VM_FAULT_SIGBUS; } static const struct vm_special_mapping vdso_mapping = { .name = "[vdso]", .fault = vdso_fault, .mremap = vdso_mremap, }; static const struct vm_special_mapping vvar_vclock_mapping = { .name = "[vvar_vclock]", .fault = vvar_vclock_fault, }; /* * Add vdso and vvar mappings to current process. * @image - blob to map * @addr - request a specific address (zero to map at free addr) */ static int map_vdso(const struct vdso_image *image, unsigned long addr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long text_start; int ret = 0; if (mmap_write_lock_killable(mm)) return -EINTR; addr = get_unmapped_area(NULL, addr, image->size + __VDSO_PAGES * PAGE_SIZE, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; } text_start = addr + __VDSO_PAGES * PAGE_SIZE; /* * MAYWRITE to allow gdb to COW and set breakpoints */ vma = _install_special_mapping(mm, text_start, image->size, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| VM_SEALED_SYSMAP, &vdso_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto up_fail; } vma = vdso_install_vvar_mapping(mm, addr); if (IS_ERR(vma)) { ret = PTR_ERR(vma); do_munmap(mm, text_start, image->size, NULL); goto up_fail; } vma = _install_special_mapping(mm, VDSO_VCLOCK_PAGES_START(addr), VDSO_NR_VCLOCK_PAGES * PAGE_SIZE, VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP| VM_PFNMAP|VM_SEALED_SYSMAP, &vvar_vclock_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); do_munmap(mm, text_start, image->size, NULL); do_munmap(mm, addr, image->size, NULL); goto up_fail; } current->mm->context.vdso = (void __user *)text_start; current->mm->context.vdso_image = image; up_fail: mmap_write_unlock(mm); return ret; } int map_vdso_once(const struct vdso_image *image, unsigned long addr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); /* * Check if we have already mapped vdso blob - fail to prevent * abusing from userspace install_special_mapping, which may * not do accounting and rlimit right. * We could search vma near context.vdso, but it's a slowpath, * so let's explicitly check all VMAs to be completely sure. */ for_each_vma(vmi, vma) { if (vma_is_special_mapping(vma, &vdso_mapping) || vma_is_special_mapping(vma, &vdso_vvar_mapping) || vma_is_special_mapping(vma, &vvar_vclock_mapping)) { mmap_write_unlock(mm); return -EEXIST; } } mmap_write_unlock(mm); return map_vdso(image, addr); } static int load_vdso32(void) { if (vdso32_enabled != 1) /* Other values all mean "disabled" */ return 0; return map_vdso(&vdso_image_32, 0); } int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { if (IS_ENABLED(CONFIG_X86_64)) { if (!vdso64_enabled) return 0; return map_vdso(&vdso_image_64, 0); } return load_vdso32(); } #ifdef CONFIG_COMPAT int compat_arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp, bool x32) { if (IS_ENABLED(CONFIG_X86_X32_ABI) && x32) { if (!vdso64_enabled) return 0; return map_vdso(&vdso_image_x32, 0); } if (IS_ENABLED(CONFIG_IA32_EMULATION)) return load_vdso32(); return 0; } #endif bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) { const struct vdso_image *image = current->mm->context.vdso_image; unsigned long vdso = (unsigned long) current->mm->context.vdso; if (in_ia32_syscall() && image == &vdso_image_32) { if (regs->ip == vdso + image->sym_vdso32_sigreturn_landing_pad || regs->ip == vdso + image->sym_vdso32_rt_sigreturn_landing_pad) return true; } return false; } #ifdef CONFIG_X86_64 static __init int vdso_setup(char *s) { vdso64_enabled = simple_strtoul(s, NULL, 0); return 1; } __setup("vdso=", vdso_setup); #endif /* CONFIG_X86_64 */ |
| 813 802 800 457 809 479 470 814 811 4 737 732 731 346 732 110 105 736 732 15 10 10 5 3 7 13 13 6 4 9 23 13 10 30 30 30 30 30 377 6 376 790 4 784 785 7 41 78 275 675 1060 1 1 2 859 1070 1029 43 437 519 6 16 2 23 27 31 2 9 1025 26 27 1082 3 3 1 2 2 1033 1055 1074 1184 3 1184 25 10 8 23 10 721 3 719 11 714 23 2 218 359 531 18 2 16 2 12 1186 1188 1155 1155 2 2 250 213 247 76 88 16 76 92 234 161 9 69 175 16 16 232 10 222 16 16 16 16 16 16 16 4 4 4 4 4 9 7 9 9 9 8 8 9 1 9 8 4 3 3 3 3 3 3 3 6 6 5 6 6 6 5 6 509 509 22 487 509 22 487 509 22 487 884 568 883 883 857 545 857 509 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * x_tables core - Backend for {ip,ip6,arp}_tables * * Copyright (C) 2006-2006 Harald Welte <laforge@netfilter.org> * Copyright (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on existing ip_tables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/audit.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_arp/arp_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define XT_PCPU_BLOCK_SIZE 4096 #define XT_MAX_TABLE_SIZE (512 * 1024 * 1024) struct xt_template { struct list_head list; /* called when table is needed in the given netns */ int (*table_init)(struct net *net); struct module *me; /* A unique name... */ char name[XT_TABLE_MAXNAMELEN]; }; static struct list_head xt_templates[NFPROTO_NUMPROTO]; struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; }; struct compat_delta { unsigned int offset; /* offset in kernel */ int delta; /* delta in 32bit user land */ }; struct xt_af { struct mutex mutex; struct list_head match; struct list_head target; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct mutex compat_mutex; struct compat_delta *compat_tab; unsigned int number; /* number of slots in compat_tab[] */ unsigned int cur; /* number of used slots in compat_tab[] */ #endif }; static unsigned int xt_pernet_id __read_mostly; static struct xt_af *xt __read_mostly; static const char *const xt_prefix[NFPROTO_NUMPROTO] = { [NFPROTO_UNSPEC] = "x", [NFPROTO_IPV4] = "ip", [NFPROTO_ARP] = "arp", [NFPROTO_BRIDGE] = "eb", [NFPROTO_IPV6] = "ip6", }; /* Registration hooks for targets. */ int xt_register_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_add(&target->list, &xt[af].target); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_target); void xt_unregister_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_del(&target->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_target); int xt_register_targets(struct xt_target *target, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_target(&target[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_targets(target, i); return err; } EXPORT_SYMBOL(xt_register_targets); void xt_unregister_targets(struct xt_target *target, unsigned int n) { while (n-- > 0) xt_unregister_target(&target[n]); } EXPORT_SYMBOL(xt_unregister_targets); int xt_register_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_add(&match->list, &xt[af].match); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_match); void xt_unregister_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_del(&match->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_match); int xt_register_matches(struct xt_match *match, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_match(&match[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_matches(match, i); return err; } EXPORT_SYMBOL(xt_register_matches); void xt_unregister_matches(struct xt_match *match, unsigned int n) { while (n-- > 0) xt_unregister_match(&match[n]); } EXPORT_SYMBOL(xt_unregister_matches); /* * These are weird, but module loading must not be done with mutex * held (since they will register), and we have to have a single * function to use. */ /* Find match, grabs ref. Returns ERR_PTR() on error. */ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision) { struct xt_match *m; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision == revision) { if (try_module_get(m->me)) { mutex_unlock(&xt[af].mutex); return m; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_match(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } EXPORT_SYMBOL(xt_find_match); struct xt_match * xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision) { struct xt_match *match; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); match = xt_find_match(nfproto, name, revision); if (IS_ERR(match)) { request_module("%st_%s", xt_prefix[nfproto], name); match = xt_find_match(nfproto, name, revision); } return match; } EXPORT_SYMBOL_GPL(xt_request_find_match); /* Find target, grabs ref. Returns ERR_PTR() on error. */ static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) { struct xt_target *t; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision == revision) { if (try_module_get(t->me)) { mutex_unlock(&xt[af].mutex); return t; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_target(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) { struct xt_target *target; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); target = xt_find_target(af, name, revision); if (IS_ERR(target)) { request_module("%st_%s", xt_prefix[af], name); target = xt_find_target(af, name, revision); } return target; } EXPORT_SYMBOL_GPL(xt_request_find_target); static int xt_obj_to_user(u16 __user *psize, u16 size, void __user *pname, const char *name, u8 __user *prev, u8 rev) { if (put_user(size, psize)) return -EFAULT; if (copy_to_user(pname, name, strlen(name) + 1)) return -EFAULT; if (put_user(rev, prev)) return -EFAULT; return 0; } #define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE) \ xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size, \ U->u.user.name, K->u.kernel.TYPE->name, \ &U->u.user.revision, K->u.kernel.TYPE->revision) int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size) { usersize = usersize ? : size; if (copy_to_user(dst, src, usersize)) return -EFAULT; if (usersize != aligned_size && clear_user(dst + usersize, aligned_size - usersize)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(xt_data_to_user); #define XT_DATA_TO_USER(U, K, TYPE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ K->u.kernel.TYPE->TYPE##size, \ XT_ALIGN(K->u.kernel.TYPE->TYPE##size)) int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u) { return XT_OBJ_TO_USER(u, m, match, 0) || XT_DATA_TO_USER(u, m, match); } EXPORT_SYMBOL_GPL(xt_match_to_user); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u) { return XT_OBJ_TO_USER(u, t, target, 0) || XT_DATA_TO_USER(u, t, target); } EXPORT_SYMBOL_GPL(xt_target_to_user); static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_match *m; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision > *bestp) *bestp = m->revision; if (m->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_target *t; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision > *bestp) *bestp = t->revision; if (t->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } /* Returns true or false (if no such extension at all) */ int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err) { int have_rev, best = -1; if (target == 1) have_rev = target_revfn(af, name, revision, &best); else have_rev = match_revfn(af, name, revision, &best); /* Nothing at all? Return 0 to try loading module. */ if (best == -1) { *err = -ENOENT; return 0; } *err = best; if (!have_rev) *err = -EPROTONOSUPPORT; return 1; } EXPORT_SYMBOL_GPL(xt_find_revision); static char * textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; static const char *const arp_names[] = { "INPUT", "FORWARD", "OUTPUT", }; const char *const *names; unsigned int i, max; char *p = buf; bool np = false; int res; names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : ARRAY_SIZE(inetbr_names); *p = '\0'; for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); if (res > 0) { size -= res; p += res; } np = true; } return buf; } /** * xt_check_proc_name - check that name is suitable for /proc file creation * * @name: file name candidate * @size: length of buffer * * some x_tables modules wish to create a file in /proc. * This function makes sure that the name is suitable for this * purpose, it checks that name is NUL terminated and isn't a 'special' * name, like "..". * * returns negative number on error or 0 if name is useable. */ int xt_check_proc_name(const char *name, unsigned int size) { if (name[0] == '\0') return -EINVAL; if (strnlen(name, size) == size) return -ENAMETOOLONG; if (strcmp(name, ".") == 0 || strcmp(name, "..") == 0 || strchr(name, '/')) return -EINVAL; return 0; } EXPORT_SYMBOL(xt_check_proc_name); int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; if (XT_ALIGN(par->match->matchsize) != size && par->match->matchsize != -1) { /* * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ pr_err_ratelimited("%s_tables: %s.%u match: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->match->name, par->match->revision, XT_ALIGN(par->match->matchsize), size); return -EINVAL; } if (par->match->table != NULL && strcmp(par->match->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s match: only valid in %s table, not %s\n", xt_prefix[par->family], par->match->name, par->match->table, par->table); return -EINVAL; } if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s match: used from hooks %s, but only valid from %s\n", xt_prefix[par->family], par->match->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->match->hooks, par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s match: only valid for protocol %u\n", xt_prefix[par->family], par->match->name, par->match->proto); return -EINVAL; } if (par->match->checkentry != NULL) { ret = par->match->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } EXPORT_SYMBOL_GPL(xt_check_match); /** xt_check_entry_match - check that matches end before start of target * * @match: beginning of xt_entry_match * @target: beginning of this rules target (alleged end of matches) * @alignment: alignment requirement of match structures * * Validates that all matches add up to the beginning of the target, * and that each match covers at least the base structure size. * * Return: 0 on success, negative errno on failure. */ static int xt_check_entry_match(const char *match, const char *target, const size_t alignment) { const struct xt_entry_match *pos; int length = target - match; if (length == 0) /* no matches */ return 0; pos = (struct xt_entry_match *)match; do { if ((unsigned long)pos % alignment) return -EINVAL; if (length < (int)sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size < sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size > length) return -EINVAL; length -= pos->u.match_size; pos = ((void *)((char *)(pos) + (pos)->u.match_size)); } while (length > 0); return 0; } /** xt_check_table_hooks - check hook entry points are sane * * @info xt_table_info to check * @valid_hooks - hook entry points that we can enter from * * Validates that the hook entry and underflows points are set up. * * Return: 0 on success, negative errno on failure. */ int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks) { const char *err = "unsorted underflow"; unsigned int i, max_uflow, max_entry; bool check_hooks = false; BUILD_BUG_ON(ARRAY_SIZE(info->hook_entry) != ARRAY_SIZE(info->underflow)); max_entry = 0; max_uflow = 0; for (i = 0; i < ARRAY_SIZE(info->hook_entry); i++) { if (!(valid_hooks & (1 << i))) continue; if (info->hook_entry[i] == 0xFFFFFFFF) return -EINVAL; if (info->underflow[i] == 0xFFFFFFFF) return -EINVAL; if (check_hooks) { if (max_uflow > info->underflow[i]) goto error; if (max_uflow == info->underflow[i]) { err = "duplicate underflow"; goto error; } if (max_entry > info->hook_entry[i]) { err = "unsorted entry"; goto error; } if (max_entry == info->hook_entry[i]) { err = "duplicate entry"; goto error; } } max_entry = info->hook_entry[i]; max_uflow = info->underflow[i]; check_hooks = true; } return 0; error: pr_err_ratelimited("%s at hook %d\n", err, i); return -EINVAL; } EXPORT_SYMBOL(xt_check_table_hooks); static bool verdict_ok(int verdict) { if (verdict > 0) return true; if (verdict < 0) { int v = -verdict - 1; if (verdict == XT_RETURN) return true; switch (v) { case NF_ACCEPT: return true; case NF_DROP: return true; case NF_QUEUE: return true; default: break; } return false; } return false; } static bool error_tg_ok(unsigned int usersize, unsigned int kernsize, const char *msg, unsigned int msglen) { return usersize == kernsize && strnlen(msg, msglen) < msglen; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { struct xt_af *xp = &xt[af]; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (WARN_ON(!xp->compat_tab)) return -ENOMEM; if (xp->cur >= xp->number) return -EINVAL; if (xp->cur) delta += xp->compat_tab[xp->cur - 1].delta; xp->compat_tab[xp->cur].offset = offset; xp->compat_tab[xp->cur].delta = delta; xp->cur++; return 0; } EXPORT_SYMBOL_GPL(xt_compat_add_offset); void xt_compat_flush_offsets(u_int8_t af) { WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (xt[af].compat_tab) { vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { struct compat_delta *tmp = xt[af].compat_tab; int mid, left = 0, right = xt[af].cur - 1; while (left <= right) { mid = (left + right) >> 1; if (offset > tmp[mid].offset) left = mid + 1; else if (offset < tmp[mid].offset) right = mid - 1; else return mid ? tmp[mid - 1].delta : 0; } return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); int xt_compat_init_offsets(u8 af, unsigned int number) { size_t mem; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (!number || number > (INT_MAX / sizeof(struct compat_delta))) return -EINVAL; if (WARN_ON(xt[af].compat_tab)) return -EINVAL; mem = sizeof(struct compat_delta) * number; if (mem > XT_MAX_TABLE_SIZE) return -ENOMEM; xt[af].compat_tab = vmalloc(mem); if (!xt[af].compat_tab) return -ENOMEM; xt[af].number = number; xt[af].cur = 0; return 0; } EXPORT_SYMBOL(xt_compat_init_offsets); int xt_compat_match_offset(const struct xt_match *match) { u_int16_t csize = match->compatsize ? : match->matchsize; return XT_ALIGN(match->matchsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_match_offset); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; int off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; char name[sizeof(m->u.user.name)]; m = *dstptr; memcpy(m, cm, sizeof(*cm)); if (match->compat_from_user) match->compat_from_user(m->data, cm->data); else memcpy(m->data, cm->data, msize - sizeof(*cm)); msize += off; m->u.user.match_size = msize; strscpy(name, match->name, sizeof(name)); module_put(match->me); strscpy_pad(m->u.user.name, name, sizeof(m->u.user.name)); *size += off; *dstptr += msize; } EXPORT_SYMBOL_GPL(xt_compat_match_from_user); #define COMPAT_XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ C_SIZE, \ COMPAT_XT_ALIGN(C_SIZE)) int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match __user *cm = *dstptr; int off = xt_compat_match_offset(match); u_int16_t msize = m->u.user.match_size - off; if (XT_OBJ_TO_USER(cm, m, match, msize)) return -EFAULT; if (match->compat_to_user) { if (match->compat_to_user((void __user *)cm->data, m->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm))) return -EFAULT; } *size -= off; *dstptr += msize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_match_to_user); /* non-compat version may have padding after verdict */ struct compat_xt_standard_target { struct compat_xt_entry_target t; compat_uint_t verdict; }; struct compat_xt_error_target { struct compat_xt_entry_target t; char errorname[XT_FUNCTION_MAXNAMELEN]; }; int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct compat_xt_entry_target *t; const char *e = base; if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct compat_xt_standard_target *st = (const void *)t; if (COMPAT_XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct compat_xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } /* compat_xt_entry match has less strict alignment requirements, * otherwise they are identical. In case of padding differences * we need to add compat version of xt_check_entry_match. */ BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match)); return xt_check_entry_match(elems, base + target_offset, __alignof__(struct compat_xt_entry_match)); } EXPORT_SYMBOL(xt_compat_check_entry_offsets); #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ /** * xt_check_entry_offsets - validate arp/ip/ip6t_entry * * @base: pointer to arp/ip/ip6t_entry * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems * @target_offset: the arp/ip/ip6_t->target_offset * @next_offset: the arp/ip/ip6_t->next_offset * * validates that target_offset and next_offset are sane and that all * match sizes (if any) align with the target offset. * * This function does not validate the targets or matches themselves, it * only tests that all the offsets and sizes are correct, that all * match structures are aligned, and that the last structure ends where * the target structure begins. * * Also see xt_compat_check_entry_offsets for CONFIG_NETFILTER_XTABLES_COMPAT version. * * The arp/ip/ip6t_entry structure @base must have passed following tests: * - it must point to a valid memory location * - base to base + next_offset must be accessible, i.e. not exceed allocated * length. * * A well-formed entry looks like this: * * ip(6)t_entry match [mtdata] match [mtdata] target [tgdata] ip(6)t_entry * e->elems[]-----' | | * matchsize | | * matchsize | | * | | * target_offset---------------------------------' | * next_offset---------------------------------------------------' * * elems[]: flexible array member at end of ip(6)/arpt_entry struct. * This is where matches (if any) and the target reside. * target_offset: beginning of target. * next_offset: start of the next rule; also: size of this rule. * Since targets have a minimum size, target_offset + minlen <= next_offset. * * Every match stores its size, sum of sizes must not exceed target_offset. * * Return: 0 on success, negative errno on failure. */ int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct xt_entry_target *t; const char *e = base; /* target start is within the ip/ip6/arpt_entry struct */ if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct xt_standard_target *st = (const void *)t; if (XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } return xt_check_entry_match(elems, base + target_offset, __alignof__(struct xt_entry_match)); } EXPORT_SYMBOL(xt_check_entry_offsets); /** * xt_alloc_entry_offsets - allocate array to store rule head offsets * * @size: number of entries * * Return: NULL or zeroed kmalloc'd or vmalloc'd array */ unsigned int *xt_alloc_entry_offsets(unsigned int size) { if (size > XT_MAX_TABLE_SIZE / sizeof(unsigned int)) return NULL; return kvcalloc(size, sizeof(unsigned int), GFP_KERNEL); } EXPORT_SYMBOL(xt_alloc_entry_offsets); /** * xt_find_jump_offset - check if target is a valid jump offset * * @offsets: array containing all valid rule start offsets of a rule blob * @target: the jump target to search for * @size: entries in @offset */ bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size) { int m, low = 0, hi = size; while (hi > low) { m = (low + hi) / 2u; if (offsets[m] > target) hi = m; else if (offsets[m] < target) low = m + 1; else return true; } return false; } EXPORT_SYMBOL(xt_find_jump_offset); int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; if (XT_ALIGN(par->target->targetsize) != size) { pr_err_ratelimited("%s_tables: %s.%u target: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->target->name, par->target->revision, XT_ALIGN(par->target->targetsize), size); return -EINVAL; } if (par->target->table != NULL && strcmp(par->target->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s target: only valid in %s table, not %s\n", xt_prefix[par->family], par->target->name, par->target->table, par->table); return -EINVAL; } if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s target: used from hooks %s, but only usable from %s\n", xt_prefix[par->family], par->target->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->target->hooks, par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s target: only valid for protocol %u\n", xt_prefix[par->family], par->target->name, par->target->proto); return -EINVAL; } if (par->target->checkentry != NULL) { ret = par->target->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } EXPORT_SYMBOL_GPL(xt_check_target); /** * xt_copy_counters - copy counters and metadata from a sockptr_t * * @arg: src sockptr * @len: alleged size of userspace memory * @info: where to store the xt_counters_info metadata * * Copies counter meta data from @user and stores it in @info. * * vmallocs memory to hold the counters, then copies the counter data * from @user to the new memory and returns a pointer to it. * * If called from a compat syscall, @info gets converted automatically to the * 64bit representation. * * The metadata associated with the counters is stored in @info. * * Return: returns pointer that caller has to test via IS_ERR(). * If IS_ERR is false, caller has to vfree the pointer. */ void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info) { size_t offset; void *mem; u64 size; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) { /* structures only differ in size due to alignment */ struct compat_xt_counters_info compat_tmp; if (len <= sizeof(compat_tmp)) return ERR_PTR(-EINVAL); len -= sizeof(compat_tmp); if (copy_from_sockptr(&compat_tmp, arg, sizeof(compat_tmp)) != 0) return ERR_PTR(-EFAULT); memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; offset = sizeof(compat_tmp); } else #endif { if (len <= sizeof(*info)) return ERR_PTR(-EINVAL); len -= sizeof(*info); if (copy_from_sockptr(info, arg, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); offset = sizeof(*info); } info->name[sizeof(info->name) - 1] = '\0'; size = sizeof(struct xt_counters); size *= info->num_counters; if (size != (u64)len) return ERR_PTR(-EINVAL); mem = vmalloc(len); if (!mem) return ERR_PTR(-ENOMEM); if (copy_from_sockptr_offset(mem, arg, offset, len) == 0) return mem; vfree(mem); return ERR_PTR(-EFAULT); } EXPORT_SYMBOL_GPL(xt_copy_counters); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_target_offset(const struct xt_target *target) { u_int16_t csize = target->compatsize ? : target->targetsize; return XT_ALIGN(target->targetsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_target_offset); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; int off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; char name[sizeof(t->u.user.name)]; t = *dstptr; memcpy(t, ct, sizeof(*ct)); if (target->compat_from_user) target->compat_from_user(t->data, ct->data); else unsafe_memcpy(t->data, ct->data, tsize - sizeof(*ct), /* UAPI 0-sized destination */); tsize += off; t->u.user.target_size = tsize; strscpy(name, target->name, sizeof(name)); module_put(target->me); strscpy_pad(t->u.user.name, name, sizeof(t->u.user.name)); *size += off; *dstptr += tsize; } EXPORT_SYMBOL_GPL(xt_compat_target_from_user); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target __user *ct = *dstptr; int off = xt_compat_target_offset(target); u_int16_t tsize = t->u.user.target_size - off; if (XT_OBJ_TO_USER(ct, t, target, tsize)) return -EFAULT; if (target->compat_to_user) { if (target->compat_to_user((void __user *)ct->data, t->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct))) return -EFAULT; } *size -= off; *dstptr += tsize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_target_to_user); #endif struct xt_table_info *xt_alloc_table_info(unsigned int size) { struct xt_table_info *info = NULL; size_t sz = sizeof(*info) + size; if (sz < sizeof(*info) || sz >= XT_MAX_TABLE_SIZE) return NULL; info = kvmalloc(sz, GFP_KERNEL_ACCOUNT); if (!info) return NULL; memset(info, 0, sizeof(*info)); info->size = size; return info; } EXPORT_SYMBOL(xt_alloc_table_info); void xt_free_table_info(struct xt_table_info *info) { int cpu; if (info->jumpstack != NULL) { for_each_possible_cpu(cpu) kvfree(info->jumpstack[cpu]); kvfree(info->jumpstack); } kvfree(info); } EXPORT_SYMBOL(xt_free_table_info); struct xt_table *xt_find_table(struct net *net, u8 af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) { if (strcmp(t->name, name) == 0) { mutex_unlock(&xt[af].mutex); return t; } } mutex_unlock(&xt[af].mutex); return NULL; } EXPORT_SYMBOL(xt_find_table); /* Find table by name, grabs mutex & ref. Returns ERR_PTR on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct module *owner = NULL; struct xt_template *tmpl; struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; /* Table doesn't exist in this netns, check larval list */ list_for_each_entry(tmpl, &xt_templates[af], list) { int err; if (strcmp(tmpl->name, name)) continue; if (!try_module_get(tmpl->me)) goto out; owner = tmpl->me; mutex_unlock(&xt[af].mutex); err = tmpl->table_init(net); if (err < 0) { module_put(owner); return ERR_PTR(err); } mutex_lock(&xt[af].mutex); break; } /* and once again: */ list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && owner == t->me) return t; module_put(owner); out: mutex_unlock(&xt[af].mutex); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(xt_find_table_lock); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_table *t = xt_find_table_lock(net, af, name); #ifdef CONFIG_MODULES if (IS_ERR(t)) { int err = request_module("%stable_%s", xt_prefix[af], name); if (err < 0) return ERR_PTR(err); t = xt_find_table_lock(net, af, name); } #endif return t; } EXPORT_SYMBOL_GPL(xt_request_find_table_lock); void xt_table_unlock(struct xt_table *table) { mutex_unlock(&xt[table->af].mutex); } EXPORT_SYMBOL_GPL(xt_table_unlock); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT void xt_compat_lock(u_int8_t af) { mutex_lock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_lock); void xt_compat_unlock(u_int8_t af) { mutex_unlock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif DEFINE_PER_CPU(seqcount_t, xt_recseq); EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); struct static_key xt_tee_enabled __read_mostly; EXPORT_SYMBOL_GPL(xt_tee_enabled); static int xt_jumpstack_alloc(struct xt_table_info *i) { unsigned int size; int cpu; size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) i->jumpstack = kvzalloc(size, GFP_KERNEL); else i->jumpstack = kzalloc(size, GFP_KERNEL); if (i->jumpstack == NULL) return -ENOMEM; /* ruleset without jumps -- no stack needed */ if (i->stacksize == 0) return 0; /* Jumpstack needs to be able to record two full callchains, one * from the first rule set traversal, plus one table reentrancy * via -j TEE without clobbering the callchain that brought us to * TEE target. * * This is done by allocating two jumpstacks per cpu, on reentry * the upper half of the stack is used. * * see the jumpstack setup in ipt_do_table() for more details. */ size = sizeof(void *) * i->stacksize * 2u; for_each_possible_cpu(cpu) { i->jumpstack[cpu] = kvmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (i->jumpstack[cpu] == NULL) /* * Freeing will be done later on by the callers. The * chain is: xt_replace_table -> __do_replace -> * do_replace -> xt_free_table_info. */ return -ENOMEM; } return 0; } struct xt_counters *xt_counters_alloc(unsigned int counters) { struct xt_counters *mem; if (counters == 0 || counters > INT_MAX / sizeof(*mem)) return NULL; counters *= sizeof(*mem); if (counters > XT_MAX_TABLE_SIZE) return NULL; return vzalloc(counters); } EXPORT_SYMBOL(xt_counters_alloc); struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { struct xt_table_info *private; unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); if (ret < 0) { *error = ret; return NULL; } /* Do the substitution. */ local_bh_disable(); private = table->private; /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; /* * Ensure contents of newinfo are visible before assigning to * private. */ smp_wmb(); table->private = newinfo; /* make sure all cpus see new ->private value */ smp_mb(); /* * Even though table entries have now been swapped, other CPU's * may still be using the old entries... */ local_bh_enable(); /* ... so wait for even xt_recseq on all cpus */ for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); u32 seq = raw_read_seqcount(s); if (seq & 1) { do { cond_resched(); cpu_relax(); } while (seq == raw_read_seqcount(s)); } } audit_log_nfcfg(table->name, table->af, private->number, !private->number ? AUDIT_XT_OP_REGISTER : AUDIT_XT_OP_REPLACE, GFP_KERNEL); return private; } EXPORT_SYMBOL_GPL(xt_replace_table); struct xt_table *xt_register_table(struct net *net, const struct xt_table *input_table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table_info *private; struct xt_table *t, *table; int ret; /* Don't add one object to multiple lists. */ table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); if (!table) { ret = -ENOMEM; goto out; } mutex_lock(&xt[table->af].mutex); /* Don't autoload: we'd eat our tail... */ list_for_each_entry(t, &xt_net->tables[table->af], list) { if (strcmp(t->name, table->name) == 0) { ret = -EEXIST; goto unlock; } } /* Simplifies replace_table code. */ table->private = bootstrap; if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; private = table->private; pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ private->initial_entries = private->number; list_add(&table->list, &xt_net->tables[table->af]); mutex_unlock(&xt[table->af].mutex); return table; unlock: mutex_unlock(&xt[table->af].mutex); kfree(table); out: return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(xt_register_table); void *xt_unregister_table(struct xt_table *table) { struct xt_table_info *private; mutex_lock(&xt[table->af].mutex); private = table->private; list_del(&table->list); mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); kfree(table->ops); kfree(table); return private; } EXPORT_SYMBOL_GPL(xt_unregister_table); #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); mutex_lock(&xt[af].mutex); return seq_list_start(&xt_net->tables[af], *pos); } static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); return seq_list_next(v, &xt_net->tables[af], pos); } static void xt_table_seq_stop(struct seq_file *seq, void *v) { u_int8_t af = (unsigned long)pde_data(file_inode(seq->file)); mutex_unlock(&xt[af].mutex); } static int xt_table_seq_show(struct seq_file *seq, void *v) { struct xt_table *table = list_entry(v, struct xt_table, list); if (*table->name) seq_printf(seq, "%s\n", table->name); return 0; } static const struct seq_operations xt_table_seq_ops = { .start = xt_table_seq_start, .next = xt_table_seq_next, .stop = xt_table_seq_stop, .show = xt_table_seq_show, }; /* * Traverse state for ip{,6}_{tables,matches} for helping crossing * the multi-AF mutexes. */ struct nf_mttg_trav { struct list_head *head, *curr; uint8_t class; }; enum { MTTG_TRAV_INIT, MTTG_TRAV_NFP_UNSPEC, MTTG_TRAV_NFP_SPEC, MTTG_TRAV_DONE, }; static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, bool is_target) { static const uint8_t next_class[] = { [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, }; uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; if (ppos != NULL) ++(*ppos); switch (trav->class) { case MTTG_TRAV_INIT: trav->class = MTTG_TRAV_NFP_UNSPEC; mutex_lock(&xt[NFPROTO_UNSPEC].mutex); trav->head = trav->curr = is_target ? &xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match; break; case MTTG_TRAV_NFP_UNSPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); mutex_lock(&xt[nfproto].mutex); trav->head = trav->curr = is_target ? &xt[nfproto].target : &xt[nfproto].match; trav->class = next_class[trav->class]; break; case MTTG_TRAV_NFP_SPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; fallthrough; default: return NULL; } return trav; } static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, bool is_target) { struct nf_mttg_trav *trav = seq->private; unsigned int j; trav->class = MTTG_TRAV_INIT; for (j = 0; j < *pos; ++j) if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL) return NULL; return trav; } static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); break; case MTTG_TRAV_NFP_SPEC: mutex_unlock(&xt[nfproto].mutex); break; } } static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, false); } static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, false); } static int xt_match_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_match *match; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; match = list_entry(trav->curr, struct xt_match, list); if (*match->name) seq_printf(seq, "%s\n", match->name); } return 0; } static const struct seq_operations xt_match_seq_ops = { .start = xt_match_seq_start, .next = xt_match_seq_next, .stop = xt_mttg_seq_stop, .show = xt_match_seq_show, }; static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, true); } static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, true); } static int xt_target_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_target *target; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; target = list_entry(trav->curr, struct xt_target, list); if (*target->name) seq_printf(seq, "%s\n", target->name); } return 0; } static const struct seq_operations xt_target_seq_ops = { .start = xt_target_seq_start, .next = xt_target_seq_next, .stop = xt_mttg_seq_stop, .show = xt_target_seq_show, }; #define FORMAT_TABLES "_tables_names" #define FORMAT_MATCHES "_tables_matches" #define FORMAT_TARGETS "_tables_targets" #endif /* CONFIG_PROC_FS */ /** * xt_hook_ops_alloc - set up hooks for a new table * @table: table with metadata needed to set up hooks * @fn: Hook function * * This function will create the nf_hook_ops that the x_table needs * to hand to xt_hook_link_net(). */ struct nf_hook_ops * xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) { unsigned int hook_mask = table->valid_hooks; uint8_t i, num_hooks = hweight32(hook_mask); uint8_t hooknum; struct nf_hook_ops *ops; if (!num_hooks) return ERR_PTR(-EINVAL); ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); for (i = 0, hooknum = 0; i < num_hooks && hook_mask != 0; hook_mask >>= 1, ++hooknum) { if (!(hook_mask & 1)) continue; ops[i].hook = fn; ops[i].pf = table->af; ops[i].hooknum = hooknum; ops[i].priority = table->priority; ++i; } return ops; } EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_register_template(const struct xt_table *table, int (*table_init)(struct net *net)) { int ret = -EEXIST, af = table->af; struct xt_template *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (WARN_ON_ONCE(strcmp(table->name, t->name) == 0)) goto out_unlock; } ret = -ENOMEM; t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) goto out_unlock; BUILD_BUG_ON(sizeof(t->name) != sizeof(table->name)); strscpy(t->name, table->name, sizeof(t->name)); t->table_init = table_init; t->me = table->me; list_add(&t->list, &xt_templates[af]); ret = 0; out_unlock: mutex_unlock(&xt[af].mutex); return ret; } EXPORT_SYMBOL_GPL(xt_register_template); void xt_unregister_template(const struct xt_table *table) { struct xt_template *t; int af = table->af; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (strcmp(table->name, t->name)) continue; list_del(&t->list); mutex_unlock(&xt[af].mutex); kfree(t); return; } mutex_unlock(&xt[af].mutex); WARN_ON_ONCE(1); } EXPORT_SYMBOL_GPL(xt_unregister_template); int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; #endif if (af >= ARRAY_SIZE(xt_prefix)) return -EINVAL; #ifdef CONFIG_PROC_FS root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); proc = proc_create_net_data(buf, 0440, net->proc_net, &xt_table_seq_ops, sizeof(struct seq_net_private), (void *)(unsigned long)af); if (!proc) goto out; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_match_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_tables; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_target_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_matches; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif return 0; #ifdef CONFIG_PROC_FS out_remove_matches: strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out_remove_tables: strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out: return -1; #endif } EXPORT_SYMBOL_GPL(xt_proto_init); void xt_proto_fini(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); #endif /*CONFIG_PROC_FS*/ } EXPORT_SYMBOL_GPL(xt_proto_fini); /** * xt_percpu_counter_alloc - allocate x_tables rule counter * * @state: pointer to xt_percpu allocation state * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct * * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then * contain the address of the real (percpu) counter. * * Rule evaluation needs to use xt_get_this_cpu_counter() helper * to fetch the real percpu counter. * * To speed up allocation and improve data locality, a 4kb block is * allocated. Freeing any counter may free an entire block, so all * counters allocated using the same state must be freed at the same * time. * * xt_percpu_counter_alloc_state contains the base address of the * allocated page and the current sub-offset. * * returns false on error. */ bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter) { BUILD_BUG_ON(XT_PCPU_BLOCK_SIZE < (sizeof(*counter) * 2)); if (nr_cpu_ids <= 1) return true; if (!state->mem) { state->mem = __alloc_percpu(XT_PCPU_BLOCK_SIZE, XT_PCPU_BLOCK_SIZE); if (!state->mem) return false; } counter->pcnt = (__force unsigned long)(state->mem + state->off); state->off += sizeof(*counter); if (state->off > (XT_PCPU_BLOCK_SIZE - sizeof(*counter))) { state->mem = NULL; state->off = 0; } return true; } EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc); void xt_percpu_counter_free(struct xt_counters *counters) { unsigned long pcnt = counters->pcnt; if (nr_cpu_ids > 1 && (pcnt & (XT_PCPU_BLOCK_SIZE - 1)) == 0) free_percpu((void __percpu *)pcnt); } EXPORT_SYMBOL_GPL(xt_percpu_counter_free); static int __net_init xt_net_init(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) INIT_LIST_HEAD(&xt_net->tables[i]); return 0; } static void __net_exit xt_net_exit(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); } static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, .id = &xt_pernet_id, .size = sizeof(struct xt_pernet), }; static int __init xt_init(void) { unsigned int i; int rv; for_each_possible_cpu(i) { seqcount_init(&per_cpu(xt_recseq, i)); } xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; for (i = 0; i < NFPROTO_NUMPROTO; i++) { mutex_init(&xt[i].mutex); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT mutex_init(&xt[i].compat_mutex); xt[i].compat_tab = NULL; #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); INIT_LIST_HEAD(&xt_templates[i]); } rv = register_pernet_subsys(&xt_net_ops); if (rv < 0) kfree(xt); return rv; } static void __exit xt_fini(void) { unregister_pernet_subsys(&xt_net_ops); kfree(xt); } module_init(xt_init); module_exit(xt_fini); |
| 3 16 2 2 1 1 2 1 3 1 3 2 1 130 141 4 268 4 1 2282 2309 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 | /* 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 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 int tun_vnet_hdr_get(int sz, unsigned int flags, struct iov_iter *from, struct virtio_net_hdr *hdr) { u16 hdr_len; if (iov_iter_count(from) < sz) return -EINVAL; if (!copy_from_iter_full(hdr, sizeof(*hdr), 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 - sizeof(*hdr)); return hdr_len; } static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { if (unlikely(iov_iter_count(iter) < sz)) return -EINVAL; if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr))) return -EFAULT; if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr)) return -EFAULT; return 0; } 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)); } 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; } #endif /* TUN_VNET_H */ |
| 6 6 1 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Manage send buffer. * Producer: * Copy user space data into send buffer, if send buffer space available. * Consumer: * Trigger RDMA write into RMBE of peer and send CDC, if RMBE space available. * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/sched/signal.h> #include <net/sock.h> #include <net/tcp.h> #include "smc.h" #include "smc_wr.h" #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" #include "smc_stats.h" #include "smc_tracepoint.h" #define SMC_TX_WORK_DELAY 0 /***************************** sndbuf producer *******************************/ /* callback implementation for sk.sk_write_space() * to wakeup sndbuf producers that blocked with smc_tx_wait(). * called under sk_socket lock. */ static void smc_tx_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; struct smc_sock *smc = smc_sk(sk); struct socket_wq *wq; /* similar to sk_stream_write_space */ if (atomic_read(&smc->conn.sndbuf_space) && sock) { if (test_bit(SOCK_NOSPACE, &sock->flags)) SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk); clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } } /* Wakeup sndbuf producers that blocked with smc_tx_wait(). * Cf. tcp_data_snd_check()=>tcp_check_space()=>tcp_new_space(). */ void smc_tx_sndbuf_nonfull(struct smc_sock *smc) { if (smc->sk.sk_socket && test_bit(SOCK_NOSPACE, &smc->sk.sk_socket->flags)) smc->sk.sk_write_space(&smc->sk); } /* blocks sndbuf producer until at least one byte of free space available * or urgent Byte was consumed */ static int smc_tx_wait(struct smc_sock *smc, int flags) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; long timeo; int rc = 0; /* similar to sk_stream_wait_memory */ timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); add_wait_queue(sk_sleep(sk), &wait); while (1) { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN) || conn->killed || conn->local_tx_ctrl.conn_state_flags.peer_done_writing) { rc = -EPIPE; break; } if (smc_cdc_rxed_any_close(conn)) { rc = -ECONNRESET; break; } if (!timeo) { /* ensure EPOLLOUT is subsequently generated */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); rc = -EAGAIN; break; } if (signal_pending(current)) { rc = sock_intr_errno(timeo); break; } sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend) break; /* at least 1 byte of free & no urgent data */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, READ_ONCE(sk->sk_err) || (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || smc_cdc_rxed_any_close(conn) || (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend), &wait); } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static bool smc_tx_is_corked(struct smc_sock *smc) { struct tcp_sock *tp = tcp_sk(smc->clcsock->sk); return (tp->nonagle & TCP_NAGLE_CORK) ? true : false; } /* If we have pending CDC messages, do not send: * Because CQE of this CDC message will happen shortly, it gives * a chance to coalesce future sendmsg() payload in to one RDMA Write, * without need for a timer, and with no latency trade off. * Algorithm here: * 1. First message should never cork * 2. If we have pending Tx CDC messages, wait for the first CDC * message's completion * 3. Don't cork to much data in a single RDMA Write to prevent burst * traffic, total corked message should not exceed sendbuf/2 */ static bool smc_should_autocork(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; int corking_size; corking_size = min_t(unsigned int, conn->sndbuf_desc->len >> 1, sock_net(&smc->sk)->smc.sysctl_autocorking_size); if (atomic_read(&conn->cdc_pend_tx_wr) == 0 || smc_tx_prepared_sends(conn) > corking_size) return false; return true; } static bool smc_tx_should_cork(struct smc_sock *smc, struct msghdr *msg) { struct smc_connection *conn = &smc->conn; if (smc_should_autocork(smc)) return true; /* for a corked socket defer the RDMA writes if * sndbuf_space is still available. The applications * should known how/when to uncork it. */ if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) && atomic_read(&conn->sndbuf_space)) return true; return false; } /* sndbuf producer: main API called by socket layer. * called under sock lock. */ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) { size_t copylen, send_done = 0, send_remaining = len; size_t chunk_len, chunk_off, chunk_len_sum; struct smc_connection *conn = &smc->conn; union smc_host_cursor prep; struct sock *sk = &smc->sk; char *sndbuf_base; int tx_cnt_prep; int writespace; int rc, chunk; /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) { rc = -EPIPE; goto out_err; } if (sk->sk_state == SMC_INIT) return -ENOTCONN; if (len > conn->sndbuf_desc->len) SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk); if (len > conn->peer_rmbe_size) SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk); if (msg->msg_flags & MSG_OOB) SMC_STAT_INC(smc, urg_data_cnt); while (msg_data_left(msg)) { if (smc->sk.sk_shutdown & SEND_SHUTDOWN || (smc->sk.sk_err == ECONNABORTED) || conn->killed) return -EPIPE; if (smc_cdc_rxed_any_close(conn)) return send_done ?: -ECONNRESET; if (msg->msg_flags & MSG_OOB) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { if (send_done) return send_done; rc = smc_tx_wait(smc, msg->msg_flags); if (rc) goto out_err; continue; } /* initialize variables for 1st iteration of subsequent loop */ /* could be just 1 byte, even after smc_tx_wait above */ writespace = atomic_read(&conn->sndbuf_space); /* not more than what user space asked for */ copylen = min_t(size_t, send_remaining, writespace); /* determine start of sndbuf */ sndbuf_base = conn->sndbuf_desc->cpu_addr; smc_curs_copy(&prep, &conn->tx_curs_prep, conn); tx_cnt_prep = prep.count; /* determine chunks where to write into sndbuf */ /* either unwrapped case, or 1st chunk of wrapped case */ chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len - tx_cnt_prep); chunk_len_sum = chunk_len; chunk_off = tx_cnt_prep; for (chunk = 0; chunk < 2; chunk++) { rc = memcpy_from_msg(sndbuf_base + chunk_off, msg, chunk_len); if (rc) { smc_sndbuf_sync_sg_for_device(conn); if (send_done) return send_done; goto out_err; } send_done += chunk_len; send_remaining -= chunk_len; if (chunk_len_sum == copylen) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ chunk_len = copylen - chunk_len; /* remainder */ chunk_len_sum += chunk_len; chunk_off = 0; /* modulo offset in send ring buffer */ } smc_sndbuf_sync_sg_for_device(conn); /* update cursors */ smc_curs_add(conn->sndbuf_desc->len, &prep, copylen); smc_curs_copy(&conn->tx_curs_prep, &prep, conn); /* increased in send tasklet smc_cdc_tx_handler() */ smp_mb__before_atomic(); atomic_sub(copylen, &conn->sndbuf_space); /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ smp_mb__after_atomic(); /* since we just produced more new data into sndbuf, * trigger sndbuf consumer: RDMA write into peer RMBE and CDC */ if ((msg->msg_flags & MSG_OOB) && !send_remaining) conn->urg_tx_pend = true; /* If we need to cork, do nothing and wait for the next * sendmsg() call or push on tx completion */ if (!smc_tx_should_cork(smc, msg)) smc_tx_sndbuf_nonempty(conn); trace_smc_tx_sendmsg(smc, copylen); } /* while (msg_data_left(msg)) */ return send_done; out_err: rc = sk_stream_error(sk, msg->msg_flags, rc); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(rc == -EAGAIN)) sk->sk_write_space(sk); return rc; } /***************************** sndbuf consumer *******************************/ /* sndbuf consumer: actual data transfer of one target chunk with ISM write */ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, u32 offset, int signal) { int rc; rc = smc_ism_write(conn->lgr->smcd, conn->peer_token, conn->peer_rmbe_idx, signal, conn->tx_off + offset, data, len); if (rc) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; return rc; } /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; struct smc_link *link = conn->lnk; int rc; rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); rdma_wr->wr.num_sge = num_sges; rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][link->link_idx].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][link->link_idx].rkey; rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) smcr_link_down_cond_sched(link); return rc; } /* sndbuf consumer */ static inline void smc_tx_advance_cursors(struct smc_connection *conn, union smc_host_cursor *prod, union smc_host_cursor *sent, size_t len) { smc_curs_add(conn->peer_rmbe_size, prod, len); /* increased in recv tasklet smc_cdc_msg_rcv() */ smp_mb__before_atomic(); /* data in flight reduces usable snd_wnd */ atomic_sub(len, &conn->peer_rmbe_space); /* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */ smp_mb__after_atomic(); smc_curs_add(conn->sndbuf_desc->len, sent, len); } /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, size_t dst_off, size_t dst_len, struct smc_rdma_wr *wr_rdma_buf) { struct smc_link *link = conn->lnk; dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[link->link_idx].sgl); u64 virt_addr = (uintptr_t)conn->sndbuf_desc->cpu_addr; int src_len_sum = src_len, dst_len_sum = dst_len; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { struct ib_rdma_wr *wr = &wr_rdma_buf->wr_tx_rdma[dstchunk]; struct ib_sge *sge = wr->wr.sg_list; u64 base_addr = dma_addr; if (dst_len < link->qp_attr.cap.max_inline_data) { base_addr = virt_addr; wr->wr.send_flags |= IB_SEND_INLINE; } else { wr->wr.send_flags &= ~IB_SEND_INLINE; } num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { sge[srcchunk].addr = conn->sndbuf_desc->is_vm ? (virt_addr + src_off) : (base_addr + src_off); sge[srcchunk].length = src_len; if (conn->sndbuf_desc->is_vm) sge[srcchunk].lkey = conn->sndbuf_desc->mr[link->link_idx]->lkey; num_sges++; src_off += src_len; if (src_off >= conn->sndbuf_desc->len) src_off -= conn->sndbuf_desc->len; /* modulo in send ring */ if (src_len_sum == dst_len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } rc = smc_tx_rdma_write(conn, dst_off, num_sges, wr); if (rc) return rc; if (dst_len_sum == len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ dst_off = 0; /* modulo offset in RMBE ring buffer */ dst_len = len - dst_len; /* remainder */ dst_len_sum += dst_len; src_len = min_t(int, dst_len, conn->sndbuf_desc->len - sent_count); src_len_sum = src_len; } return 0; } /* SMC-D helper for smc_tx_rdma_writes() */ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, size_t dst_off, size_t dst_len) { int src_len_sum = src_len, dst_len_sum = dst_len; int srcchunk, dstchunk; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { for (srcchunk = 0; srcchunk < 2; srcchunk++) { void *data = conn->sndbuf_desc->cpu_addr + src_off; rc = smcd_tx_ism_write(conn, data, src_len, dst_off + sizeof(struct smcd_cdc_msg), 0); if (rc) return rc; dst_off += src_len; src_off += src_len; if (src_off >= conn->sndbuf_desc->len) src_off -= conn->sndbuf_desc->len; /* modulo in send ring */ if (src_len_sum == dst_len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } if (dst_len_sum == len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ dst_off = 0; /* modulo offset in RMBE ring buffer */ dst_len = len - dst_len; /* remainder */ dst_len_sum += dst_len; src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off); src_len_sum = src_len; } return 0; } /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ static int smc_tx_rdma_writes(struct smc_connection *conn, struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; struct smc_cdc_producer_flags *pflags; int to_send, rmbespace; int rc; /* source: sndbuf */ smc_curs_copy(&sent, &conn->tx_curs_sent, conn); smc_curs_copy(&prep, &conn->tx_curs_prep, conn); /* cf. wmem_alloc - (snd_max - snd_una) */ to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); if (to_send <= 0) return 0; /* destination: RMBE */ /* cf. snd_wnd */ rmbespace = atomic_read(&conn->peer_rmbe_space); if (rmbespace <= 0) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); return 0; } smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); /* if usable snd_wnd closes ask peer to advertise once it opens again */ pflags = &conn->local_tx_ctrl.prod_flags; pflags->write_blocked = (to_send >= rmbespace); /* cf. usable snd_wnd */ len = min(to_send, rmbespace); /* initialize variables for first iteration of subsequent nested loop */ dst_off = prod.count; if (prod.wrap == cons.wrap) { /* the filled destination area is unwrapped, * hence the available free destination space is wrapped * and we need 2 destination chunks of sum len; start with 1st * which is limited by what's available in sndbuf */ dst_len = min_t(size_t, conn->peer_rmbe_size - prod.count, len); } else { /* the filled destination area is wrapped, * hence the available free destination space is unwrapped * and we need a single destination chunk of entire len */ dst_len = len; } /* dst_len determines the maximum src_len */ if (sent.count + dst_len <= conn->sndbuf_desc->len) { /* unwrapped src case: single chunk of entire dst_len */ src_len = dst_len; } else { /* wrapped src case: 2 chunks of sum dst_len; start with 1st: */ src_len = conn->sndbuf_desc->len - sent.count; } if (conn->lgr->is_smcd) rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len, dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, dst_off, dst_len, wr_rdma_buf); if (rc) return rc; if (conn->urg_tx_pend && len == to_send) pflags->urg_data_present = 1; smc_tx_advance_cursors(conn, &prod, &sent, len); /* update connection's cursors with advanced local cursors */ smc_curs_copy(&conn->local_tx_ctrl.prod, &prod, conn); /* dst: peer RMBE */ smc_curs_copy(&conn->tx_curs_sent, &sent, conn);/* src: local sndbuf */ return 0; } /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; if (!link || !smc_wr_tx_link_hold(link)) return -ENOLINK; rc = smc_cdc_get_free_slot(conn, link, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { smc_wr_tx_link_put(link); if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); if (smc->sk.sk_err == ECONNABORTED) return sock_error(&smc->sk); if (conn->killed) return -EPIPE; rc = 0; mod_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } return rc; } spin_lock_bh(&conn->send_lock); if (link != conn->lnk) { /* link of connection changed, tx_work will restart */ smc_wr_tx_put_slot(link, (struct smc_wr_tx_pend_priv *)pend); rc = -ENOLINK; goto out_unlock; } if (!pflags->urg_data_present) { rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(link, (struct smc_wr_tx_pend_priv *)pend); goto out_unlock; } } rc = smc_cdc_msg_send(conn, wr_buf, pend); if (!rc && pflags->urg_data_present) { pflags->urg_data_pending = 0; pflags->urg_data_present = 0; } out_unlock: spin_unlock_bh(&conn->send_lock); smc_wr_tx_link_put(link); return rc; } static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; int rc = 0; spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); if (!rc && pflags->urg_data_present) { pflags->urg_data_pending = 0; pflags->urg_data_present = 0; } spin_unlock_bh(&conn->send_lock); return rc; } int smc_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc = 0; /* No data in the send queue */ if (unlikely(smc_tx_prepared_sends(conn) <= 0)) goto out; /* Peer don't have RMBE space */ if (unlikely(atomic_read(&conn->peer_rmbe_space) <= 0)) { SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); goto out; } if (conn->killed || conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) { rc = -EPIPE; /* connection being aborted */ goto out; } if (conn->lgr->is_smcd) rc = smcd_tx_sndbuf_nonempty(conn); else rc = smcr_tx_sndbuf_nonempty(conn); if (!rc) { /* trigger socket release if connection is closing */ smc_close_wake_tx_prepared(smc); } out: return rc; } /* Wakeup sndbuf consumers from process context * since there is more data to transmit. The caller * must hold sock lock. */ void smc_tx_pending(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc; if (smc->sk.sk_err) return; rc = smc_tx_sndbuf_nonempty(conn); if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; } /* Wakeup sndbuf consumers from process context * since there is more data to transmit in locked * sock. */ void smc_tx_work(struct work_struct *work) { struct smc_connection *conn = container_of(to_delayed_work(work), struct smc_connection, tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); lock_sock(&smc->sk); smc_tx_pending(conn); release_sock(&smc->sk); } void smc_tx_consumer_update(struct smc_connection *conn, bool force) { union smc_host_cursor cfed, cons, prod; int sender_free = conn->rmb_desc->len; int to_confirm; smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn); smc_curs_copy(&cfed, &conn->rx_curs_confirmed, conn); to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - smc_curs_diff_large(conn->rmb_desc->len, &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || force || ((to_confirm > conn->rmbe_update_limit) && ((sender_free <= (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if (conn->killed || conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) return; if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && !conn->killed) { queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); return; } } if (conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; } /***************************** send initialize *******************************/ /* Initialize send properties on connection establishment. NB: not __init! */ void smc_tx_init(struct smc_sock *smc) { smc->sk.sk_write_space = smc_tx_write_space; } |
| 4902 5088 1 4407 4406 4409 4403 4425 4430 4430 25 4425 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/filesystems.c * * Copyright (C) 1991, 1992 Linus Torvalds * * table of configured filesystems */ #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs_parser.h> /* * Handling of filesystem drivers list. * Rules: * Inclusion to/removals from/scanning of list are protected by spinlock. * During the unload module must call unregister_filesystem(). * We can access the fields of list element if: * 1) spinlock is held or * 2) we hold the reference to the module. * The latter can be guaranteed by call of try_module_get(); if it * returned 0 we must skip the element, otherwise we got the reference. * Once the reference is obtained we can drop the spinlock. */ static struct file_system_type *file_systems; static DEFINE_RWLOCK(file_systems_lock); /* WARNING: This can be used only if we _already_ own a reference */ struct file_system_type *get_filesystem(struct file_system_type *fs) { __module_get(fs->owner); return fs; } void put_filesystem(struct file_system_type *fs) { module_put(fs->owner); } static struct file_system_type **find_filesystem(const char *name, unsigned len) { struct file_system_type **p; for (p = &file_systems; *p; p = &(*p)->next) if (strncmp((*p)->name, name, len) == 0 && !(*p)->name[len]) break; return p; } /** * register_filesystem - register a new filesystem * @fs: the file system structure * * Adds the file system passed to the list of file systems the kernel * is aware of for mount and other syscalls. Returns 0 on success, * or a negative errno code on an error. * * The &struct file_system_type that is passed is linked into the kernel * structures and must not be freed until the file system has been * unregistered. */ int register_filesystem(struct file_system_type * fs) { int res = 0; struct file_system_type ** p; if (fs->parameters && !fs_validate_description(fs->name, fs->parameters)) return -EINVAL; BUG_ON(strchr(fs->name, '.')); if (fs->next) return -EBUSY; write_lock(&file_systems_lock); p = find_filesystem(fs->name, strlen(fs->name)); if (*p) res = -EBUSY; else *p = fs; write_unlock(&file_systems_lock); return res; } EXPORT_SYMBOL(register_filesystem); /** * unregister_filesystem - unregister a file system * @fs: filesystem to unregister * * Remove a file system that was previously successfully registered * with the kernel. An error is returned if the file system is not found. * Zero is returned on a success. * * Once this function has returned the &struct file_system_type structure * may be freed or reused. */ int unregister_filesystem(struct file_system_type * fs) { struct file_system_type ** tmp; write_lock(&file_systems_lock); tmp = &file_systems; while (*tmp) { if (fs == *tmp) { *tmp = fs->next; fs->next = NULL; write_unlock(&file_systems_lock); synchronize_rcu(); return 0; } tmp = &(*tmp)->next; } write_unlock(&file_systems_lock); return -EINVAL; } EXPORT_SYMBOL(unregister_filesystem); #ifdef CONFIG_SYSFS_SYSCALL static int fs_index(const char __user * __name) { struct file_system_type * tmp; struct filename *name; int err, index; name = getname(__name); err = PTR_ERR(name); if (IS_ERR(name)) return err; err = -EINVAL; read_lock(&file_systems_lock); for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) { if (strcmp(tmp->name, name->name) == 0) { err = index; break; } } read_unlock(&file_systems_lock); putname(name); return err; } static int fs_name(unsigned int index, char __user * buf) { struct file_system_type * tmp; int len, res = -EINVAL; read_lock(&file_systems_lock); for (tmp = file_systems; tmp; tmp = tmp->next, index--) { if (index == 0) { if (try_module_get(tmp->owner)) res = 0; break; } } read_unlock(&file_systems_lock); if (res) return res; /* OK, we got the reference, so we can safely block */ len = strlen(tmp->name) + 1; res = copy_to_user(buf, tmp->name, len) ? -EFAULT : 0; put_filesystem(tmp); return res; } static int fs_maxindex(void) { struct file_system_type * tmp; int index; read_lock(&file_systems_lock); for (tmp = file_systems, index = 0 ; tmp ; tmp = tmp->next, index++) ; read_unlock(&file_systems_lock); return index; } /* * Whee.. Weird sysv syscall. */ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) { int retval = -EINVAL; switch (option) { case 1: retval = fs_index((const char __user *) arg1); break; case 2: retval = fs_name(arg1, (char __user *) arg2); break; case 3: retval = fs_maxindex(); break; } return retval; } #endif int __init list_bdev_fs_names(char *buf, size_t size) { struct file_system_type *p; size_t len; int count = 0; read_lock(&file_systems_lock); for (p = file_systems; p; p = p->next) { if (!(p->fs_flags & FS_REQUIRES_DEV)) continue; len = strlen(p->name) + 1; if (len > size) { pr_warn("%s: truncating file system list\n", __func__); break; } memcpy(buf, p->name, len); buf += len; size -= len; count++; } read_unlock(&file_systems_lock); return count; } #ifdef CONFIG_PROC_FS static int filesystems_proc_show(struct seq_file *m, void *v) { struct file_system_type * tmp; read_lock(&file_systems_lock); tmp = file_systems; while (tmp) { seq_printf(m, "%s\t%s\n", (tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev", tmp->name); tmp = tmp->next; } read_unlock(&file_systems_lock); return 0; } static int __init proc_filesystems_init(void) { proc_create_single("filesystems", 0, NULL, filesystems_proc_show); return 0; } module_init(proc_filesystems_init); #endif static struct file_system_type *__get_fs_type(const char *name, int len) { struct file_system_type *fs; read_lock(&file_systems_lock); fs = *(find_filesystem(name, len)); if (fs && !try_module_get(fs->owner)) fs = NULL; read_unlock(&file_systems_lock); return fs; } struct file_system_type *get_fs_type(const char *name) { struct file_system_type *fs; const char *dot = strchr(name, '.'); int len = dot ? dot - name : strlen(name); fs = __get_fs_type(name, len); if (!fs && (request_module("fs-%.*s", len, name) == 0)) { fs = __get_fs_type(name, len); if (!fs) pr_warn_once("request_module fs-%.*s succeeded, but still no fs?\n", len, name); } if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) { put_filesystem(fs); fs = NULL; } return fs; } EXPORT_SYMBOL(get_fs_type); |
| 36 5 170 170 171 138 13 128 6 9 3 10 3 5 3 10 10 19 15 17 76 3 5 7 83 83 82 4 79 79 37 42 1 1 1 1 1 33 33 33 32 2 31 9 9 1 1 17 4 13 1 1 1 2 2 1 3 2 1 2 4 2 2 2 3 2 5 103 104 92 95 92 51 41 10 14 4 5 13 13 10 10 18 78 69 42 28 17 11 27 43 30 30 4 3 1 3 1 2 2 4 137 136 162 33 15 48 5 46 7 45 6 131 38 3 136 137 137 137 136 137 137 137 137 137 137 137 100 89 8 4 1397 1364 11 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Extension Header handling for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Andi Kleen <ak@muc.de> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ /* Changes: * yoshfuji : ensure not to overrun while parsing * tlv options. * Mitsuru KANDA @USAGI and: Remove ipv6_parse_exthdrs(). * YOSHIFUJI Hideaki @USAGI Register inbound extension header * handlers as inet6_protocol{}. */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/icmpv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/dst.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/rawv6.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/calipso.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/xfrm.h> #endif #include <linux/seg6.h> #include <net/seg6.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif #include <net/rpl.h> #include <linux/ioam6.h> #include <linux/ioam6_genl.h> #include <net/ioam6.h> #include <net/dst_metadata.h> #include <linux/uaccess.h> /********************* Generic functions *********************/ /* An unknown option is detected, decide what to do */ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff, bool disallow_unknowns) { if (disallow_unknowns) { /* If unknown TLVs are disallowed by configuration * then always silently drop packet. Note this also * means no ICMP parameter problem is sent which * could be a good property to mitigate a reflection DOS * attack. */ goto drop; } switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) { case 0: /* ignore */ return true; case 1: /* drop packet */ break; case 3: /* Send ICMP if not a multicast address and drop packet */ /* Actually, it is redundant check. icmp_send will recheck in any case. */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; fallthrough; case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob_reason(skb, ICMPV6_UNK_OPTION, optoff, SKB_DROP_REASON_UNHANDLED_PROTO); return false; } drop: kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); return false; } static bool ipv6_hop_ra(struct sk_buff *skb, int optoff); static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff); static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff); static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff); #if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff); #endif /* Parse tlv encoded option header (hop-by-hop or destination) */ static bool ip6_parse_tlv(bool hopbyhop, struct sk_buff *skb, int max_count) { int len = (skb_transport_header(skb)[1] + 1) << 3; const unsigned char *nh = skb_network_header(skb); int off = skb_network_header_len(skb); bool disallow_unknowns = false; int tlv_count = 0; int padlen = 0; if (unlikely(max_count < 0)) { disallow_unknowns = true; max_count = -max_count; } off += 2; len -= 2; while (len > 0) { int optlen, i; if (nh[off] == IPV6_TLV_PAD1) { padlen++; if (padlen > 7) goto bad; off++; len--; continue; } if (len < 2) goto bad; optlen = nh[off + 1] + 2; if (optlen > len) goto bad; if (nh[off] == IPV6_TLV_PADN) { /* RFC 2460 states that the purpose of PadN is * to align the containing header to multiples * of 8. 7 is therefore the highest valid value. * See also RFC 4942, Section 2.1.9.5. */ padlen += optlen; if (padlen > 7) goto bad; /* RFC 4942 recommends receiving hosts to * actively check PadN payload to contain * only zeroes. */ for (i = 2; i < optlen; i++) { if (nh[off + i] != 0) goto bad; } } else { tlv_count++; if (tlv_count > max_count) goto bad; if (hopbyhop) { switch (nh[off]) { case IPV6_TLV_ROUTERALERT: if (!ipv6_hop_ra(skb, off)) return false; break; case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) return false; break; case IPV6_TLV_CALIPSO: if (!ipv6_hop_calipso(skb, off)) return false; break; default: if (!ip6_tlvopt_unknown(skb, off, disallow_unknowns)) return false; break; } } else { switch (nh[off]) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_TLV_HAO: if (!ipv6_dest_hao(skb, off)) return false; break; #endif default: if (!ip6_tlvopt_unknown(skb, off, disallow_unknowns)) return false; break; } } padlen = 0; } off += optlen; len -= optlen; } if (len == 0) return true; bad: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /***************************** Destination options header. *****************************/ #if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) { struct ipv6_destopt_hao *hao; struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); SKB_DR(reason); int ret; if (opt->dsthao) { net_dbg_ratelimited("hao duplicated\n"); goto discard; } opt->dsthao = opt->dst1; opt->dst1 = 0; hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); if (hao->length != 16) { net_dbg_ratelimited("hao invalid option length = %d\n", hao->length); SKB_DR_SET(reason, IP_INHDR); goto discard; } if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) { net_dbg_ratelimited("hao is not an unicast addr: %pI6\n", &hao->addr); SKB_DR_SET(reason, INVALID_PROTO); goto discard; } ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr, (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS); if (unlikely(ret < 0)) { SKB_DR_SET(reason, XFRM_POLICY); goto discard; } if (skb_cloned(skb)) { if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) goto discard; /* update all variable using below by copied skbuff */ hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); ipv6h = ipv6_hdr(skb); } if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; swap(ipv6h->saddr, hao->addr); if (skb->tstamp == 0) __net_timestamp(skb); return true; discard: kfree_skb_reason(skb, reason); return false; } #endif static int ipv6_destopt_rcv(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) __u16 dstbuf; #endif struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(skb->dev); int extlen; if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(dev_net(dst->dev), idev, IPSTATS_MIB_INHDRERRORS); fail_and_free: kfree_skb(skb); return -1; } extlen = (skb_transport_header(skb)[1] + 1) << 3; if (extlen > net->ipv6.sysctl.max_dst_opts_len) goto fail_and_free; opt->lastopt = opt->dst1 = skb_network_header_len(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) dstbuf = opt->dst1; #endif if (ip6_parse_tlv(false, skb, net->ipv6.sysctl.max_dst_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) opt->nhoff = dstbuf; #else opt->nhoff = opt->dst1; #endif return 1; } __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return -1; } static void seg6_update_csum(struct sk_buff *skb) { struct ipv6_sr_hdr *hdr; struct in6_addr *addr; __be32 from, to; /* srh is at transport offset and seg_left is already decremented * but daddr is not yet updated with next segment */ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); addr = hdr->segments + hdr->segments_left; hdr->segments_left++; from = *(__be32 *)hdr; hdr->segments_left--; to = *(__be32 *)hdr; /* update skb csum with diff resulting from seg_left decrement */ update_csum_diff4(skb, from, to); /* compute csum diff between current and next segment and update */ update_csum_diff16(skb, (__be32 *)(&ipv6_hdr(skb)->daddr), (__be32 *)addr); } static int ipv6_srh_rcv(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); struct ipv6_sr_hdr *hdr; struct inet6_dev *idev; struct in6_addr *addr; int accept_seg6; hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); idev = __in6_dev_get(skb->dev); accept_seg6 = min(READ_ONCE(net->ipv6.devconf_all->seg6_enabled), READ_ONCE(idev->cnf.seg6_enabled)); if (!accept_seg6) { kfree_skb(skb); return -1; } #ifdef CONFIG_IPV6_SEG6_HMAC if (!seg6_hmac_validate_skb(skb)) { kfree_skb(skb); return -1; } #endif looped_back: if (hdr->segments_left == 0) { if (hdr->nexthdr == NEXTHDR_IPV6 || hdr->nexthdr == NEXTHDR_IPV4) { int offset = (hdr->hdrlen + 1) << 3; skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull(skb, offset); skb_postpull_rcsum(skb, skb_transport_header(skb), offset); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; if (hdr->nexthdr == NEXTHDR_IPV4) skb->protocol = htons(ETH_P_IP); __skb_tunnel_rx(skb, skb->dev, net); netif_rx(skb); return -1; } opt->srcrt = skb_network_header_len(skb); opt->lastopt = opt->srcrt; skb->transport_header += (hdr->hdrlen + 1) << 3; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } if (hdr->segments_left >= (hdr->hdrlen >> 1)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } if (skb_cloned(skb)) { if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; } hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); } hdr->segments_left--; addr = hdr->segments + hdr->segments_left; skb_push(skb, sizeof(struct ipv6hdr)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); ipv6_hdr(skb)->daddr = *addr; ip6_route_input(skb); if (skb_dst(skb)->error) { dst_input(skb); return -1; } if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; skb_pull(skb, sizeof(struct ipv6hdr)); goto looped_back; } dst_input(skb); return -1; } static int ipv6_rpl_srh_rcv(struct sk_buff *skb) { struct ipv6_rpl_sr_hdr *hdr, *ohdr, *chdr; struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); struct inet6_dev *idev; struct ipv6hdr *oldhdr; unsigned char *buf; int accept_rpl_seg; int i, err; u64 n = 0; u32 r; idev = __in6_dev_get(skb->dev); accept_rpl_seg = net->ipv6.devconf_all->rpl_seg_enabled; if (accept_rpl_seg > idev->cnf.rpl_seg_enabled) accept_rpl_seg = idev->cnf.rpl_seg_enabled; if (!accept_rpl_seg) { kfree_skb(skb); return -1; } looped_back: hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); if (hdr->segments_left == 0) { if (hdr->nexthdr == NEXTHDR_IPV6) { int offset = (hdr->hdrlen + 1) << 3; skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull(skb, offset); skb_postpull_rcsum(skb, skb_transport_header(skb), offset); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; __skb_tunnel_rx(skb, skb->dev, net); netif_rx(skb); return -1; } opt->srcrt = skb_network_header_len(skb); opt->lastopt = opt->srcrt; skb->transport_header += (hdr->hdrlen + 1) << 3; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } n = (hdr->hdrlen << 3) - hdr->pad - (16 - hdr->cmpre); r = do_div(n, (16 - hdr->cmpri)); /* checks if calculation was without remainder and n fits into * unsigned char which is segments_left field. Should not be * higher than that. */ if (r || (n + 1) > 255) { kfree_skb(skb); return -1; } if (hdr->segments_left > n + 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } hdr->segments_left--; i = n - hdr->segments_left; buf = kcalloc(struct_size(hdr, segments.addr, n + 2), 2, GFP_ATOMIC); if (unlikely(!buf)) { kfree_skb(skb); return -1; } ohdr = (struct ipv6_rpl_sr_hdr *)buf; ipv6_rpl_srh_decompress(ohdr, hdr, &ipv6_hdr(skb)->daddr, n); chdr = (struct ipv6_rpl_sr_hdr *)(buf + ((ohdr->hdrlen + 1) << 3)); if (ipv6_addr_is_multicast(&ohdr->rpl_segaddr[i])) { kfree_skb(skb); kfree(buf); return -1; } err = ipv6_chk_rpl_srh_loop(net, ohdr->rpl_segaddr, n + 1); if (err) { icmpv6_send(skb, ICMPV6_PARAMPROB, 0, 0); kfree_skb(skb); kfree(buf); return -1; } swap(ipv6_hdr(skb)->daddr, ohdr->rpl_segaddr[i]); ipv6_rpl_srh_compress(chdr, ohdr, &ipv6_hdr(skb)->daddr, n); oldhdr = ipv6_hdr(skb); skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); if (unlikely(!hdr->segments_left)) { if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); kfree(buf); return -1; } oldhdr = ipv6_hdr(skb); } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); memmove(ipv6_hdr(skb), oldhdr, sizeof(struct ipv6hdr)); memcpy(skb_transport_header(skb), chdr, (chdr->hdrlen + 1) << 3); ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, ipv6_hdr(skb), sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3)); kfree(buf); ip6_route_input(skb); if (skb_dst(skb)->error) { dst_input(skb); return -1; } if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; skb_pull(skb, sizeof(struct ipv6hdr)); goto looped_back; } dst_input(skb); return -1; } /******************************** Routing header. ********************************/ /* called with rcu_read_lock() */ static int ipv6_rthdr_rcv(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); struct in6_addr *addr = NULL; int n, i; struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; struct net *net = dev_net(skb->dev); int accept_source_route; accept_source_route = READ_ONCE(net->ipv6.devconf_all->accept_source_route); if (idev) accept_source_route = min(accept_source_route, READ_ONCE(idev->cnf.accept_source_route)); if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } switch (hdr->type) { case IPV6_SRCRT_TYPE_4: /* segment routing */ return ipv6_srh_rcv(skb); case IPV6_SRCRT_TYPE_3: /* rpl segment routing */ return ipv6_rpl_srh_rcv(skb); default: break; } looped_back: if (hdr->segments_left == 0) { switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: /* Silently discard type 2 header unless it was * processed by own */ if (!addr) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } break; #endif default: break; } opt->lastopt = opt->srcrt = skb_network_header_len(skb); skb->transport_header += (hdr->hdrlen + 1) << 3; opt->dst0 = opt->dst1; opt->dst1 = 0; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (accept_source_route < 0) goto unknown_rh; /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } break; #endif default: goto unknown_rh; } /* * This is the routing header forwarding algorithm from * RFC 2460, page 16. */ n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } /* We are about to mangle packet header. Be careful! Do not damage packets queued somewhere. */ if (skb_cloned(skb)) { /* the copy is a forwarded packet */ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; } hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); } if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; i = n - --hdr->segments_left; rthdr = (struct rt0_hdr *) hdr; addr = rthdr->addr; addr += i - 1; switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, IPPROTO_ROUTING) < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } break; #endif default: break; } if (ipv6_addr_is_multicast(addr)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } swap(*addr, ipv6_hdr(skb)->daddr); ip6_route_input(skb); if (skb_dst(skb)->error) { skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; } if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; goto looped_back; } skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; unknown_rh: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; } static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol destopt_protocol = { .handler = ipv6_destopt_rcv, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol nodata_protocol = { .handler = dst_discard, .flags = INET6_PROTO_NOPOLICY, }; int __init ipv6_exthdrs_init(void) { int ret; ret = inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING); if (ret) goto out; ret = inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS); if (ret) goto out_rthdr; ret = inet6_add_protocol(&nodata_protocol, IPPROTO_NONE); if (ret) goto out_destopt; out: return ret; out_destopt: inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); out_rthdr: inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); goto out; }; void ipv6_exthdrs_exit(void) { inet6_del_protocol(&nodata_protocol, IPPROTO_NONE); inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); } /********************************** Hop-by-hop options. **********************************/ /* Router Alert as of RFC 2711 */ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] == 2) { IP6CB(skb)->flags |= IP6SKB_ROUTERALERT; memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra)); return true; } net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n", nh[optoff + 1]); kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /* IOAM */ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) { struct ioam6_trace_hdr *trace; struct ioam6_namespace *ns; struct ioam6_hdr *hdr; /* Bad alignment (must be 4n-aligned) */ if (optoff & 3) goto drop; /* Ignore if IOAM is not enabled on ingress */ if (!READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_enabled)) goto ignore; /* Truncated Option header */ hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff); if (hdr->opt_len < 2) goto drop; switch (hdr->type) { case IOAM6_TYPE_PREALLOC: /* Truncated Pre-allocated Trace header */ if (hdr->opt_len < 2 + sizeof(*trace)) goto drop; /* Malformed Pre-allocated Trace header */ trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr)); if (hdr->opt_len < 2 + sizeof(*trace) + trace->remlen * 4) goto drop; /* Ignore if the IOAM namespace is unknown */ ns = ioam6_namespace(dev_net(skb->dev), trace->namespace_id); if (!ns) goto ignore; if (!skb_valid_dst(skb)) ip6_route_input(skb); /* About to mangle packet header */ if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) goto drop; /* Trace pointer may have changed */ trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + optoff + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); ioam6_event(IOAM6_EVENT_TRACE, dev_net(skb->dev), GFP_ATOMIC, (void *)trace, hdr->opt_len - 2); break; default: break; } ignore: return true; drop: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /* Jumbo payload */ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); SKB_DR(reason); u32 pkt_len; if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", nh[optoff+1]); SKB_DR_SET(reason, IP_INHDR); goto drop; } pkt_len = ntohl(*(__be32 *)(nh + optoff + 2)); if (pkt_len <= IPV6_MAXPLEN) { icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff + 2, SKB_DROP_REASON_IP_INHDR); return false; } if (ipv6_hdr(skb)->payload_len) { icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff, SKB_DROP_REASON_IP_INHDR); return false; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { SKB_DR_SET(reason, PKT_TOO_SMALL); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) goto drop; IP6CB(skb)->flags |= IP6SKB_JUMBOGRAM; return true; drop: kfree_skb_reason(skb, reason); return false; } /* CALIPSO RFC 5570 */ static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] < 8) goto drop; if (nh[optoff + 6] * 4 + 8 > nh[optoff + 1]) goto drop; if (!calipso_validate(skb, nh + optoff)) goto drop; return true; drop: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } int ipv6_parse_hopopts(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); int extlen; /* * skb_network_header(skb) is equal to skb->data, and * skb_network_header_len(skb) is always equal to * sizeof(struct ipv6hdr) by definition of * hop-by-hop options. */ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) || !pskb_may_pull(skb, (sizeof(struct ipv6hdr) + ((skb_transport_header(skb)[1] + 1) << 3)))) { fail_and_free: kfree_skb(skb); return -1; } extlen = (skb_transport_header(skb)[1] + 1) << 3; if (extlen > net->ipv6.sysctl.max_hbh_opts_len) goto fail_and_free; opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(true, skb, net->ipv6.sysctl.max_hbh_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); return 1; } return -1; } /* * Creating outbound headers. * * "build" functions work when skb is filled from head to tail (datagram) * "push" functions work when headers are added from tail to head (tcp) * * In both cases we assume, that caller reserved enough room * for headers. */ static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { struct rt0_hdr *phdr, *ihdr; int hops; ihdr = (struct rt0_hdr *) opt; phdr = skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); memcpy(phdr, ihdr, sizeof(struct rt0_hdr)); hops = ihdr->rt_hdr.hdrlen >> 1; if (hops > 1) memcpy(phdr->addr, ihdr->addr + 1, (hops - 1) * sizeof(struct in6_addr)); phdr->addr[hops - 1] = **addr_p; *addr_p = ihdr->addr; phdr->rt_hdr.nexthdr = *proto; *proto = NEXTHDR_ROUTING; } static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { struct ipv6_sr_hdr *sr_phdr, *sr_ihdr; int plen, hops; sr_ihdr = (struct ipv6_sr_hdr *)opt; plen = (sr_ihdr->hdrlen + 1) << 3; sr_phdr = skb_push(skb, plen); memcpy(sr_phdr, sr_ihdr, sizeof(struct ipv6_sr_hdr)); hops = sr_ihdr->first_segment + 1; memcpy(sr_phdr->segments + 1, sr_ihdr->segments + 1, (hops - 1) * sizeof(struct in6_addr)); sr_phdr->segments[0] = **addr_p; *addr_p = &sr_ihdr->segments[sr_ihdr->segments_left]; if (sr_ihdr->hdrlen > hops * 2) { int tlvs_offset, tlvs_length; tlvs_offset = (1 + hops * 2) << 3; tlvs_length = (sr_ihdr->hdrlen - hops * 2) << 3; memcpy((char *)sr_phdr + tlvs_offset, (char *)sr_ihdr + tlvs_offset, tlvs_length); } #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(sr_phdr)) { struct net *net = NULL; if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); WARN_ON(!net); if (net) seg6_push_hmac(net, saddr, sr_phdr); } #endif sr_phdr->nexthdr = *proto; *proto = NEXTHDR_ROUTING; } static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { switch (opt->type) { case IPV6_SRCRT_TYPE_0: case IPV6_SRCRT_STRICT: case IPV6_SRCRT_TYPE_2: ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr); break; case IPV6_SRCRT_TYPE_4: ipv6_push_rthdr4(skb, proto, opt, addr_p, saddr); break; default: break; } } static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt) { struct ipv6_opt_hdr *h = skb_push(skb, ipv6_optlen(opt)); memcpy(h, opt, ipv6_optlen(opt)); h->nexthdr = *proto; *proto = type; } void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto, struct in6_addr **daddr, struct in6_addr *saddr) { if (opt->srcrt) { ipv6_push_rthdr(skb, proto, opt->srcrt, daddr, saddr); /* * IPV6_RTHDRDSTOPTS is ignored * unless IPV6_RTHDR is set (RFC3542). */ if (opt->dst0opt) ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst0opt); } if (opt->hopopt) ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt); } void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto) { if (opt->dst1opt) ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt); } EXPORT_SYMBOL(ipv6_push_frag_opts); struct ipv6_txoptions * ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) { struct ipv6_txoptions *opt2; opt2 = sock_kmemdup(sk, opt, opt->tot_len, GFP_ATOMIC); if (opt2) { long dif = (char *)opt2 - (char *)opt; if (opt2->hopopt) *((char **)&opt2->hopopt) += dif; if (opt2->dst0opt) *((char **)&opt2->dst0opt) += dif; if (opt2->dst1opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; refcount_set(&opt2->refcnt, 1); } return opt2; } EXPORT_SYMBOL_GPL(ipv6_dup_options); static void ipv6_renew_option(int renewtype, struct ipv6_opt_hdr **dest, struct ipv6_opt_hdr *old, struct ipv6_opt_hdr *new, int newtype, char **p) { struct ipv6_opt_hdr *src; src = (renewtype == newtype ? new : old); if (!src) return; memcpy(*p, src, ipv6_optlen(src)); *dest = (struct ipv6_opt_hdr *)*p; *p += CMSG_ALIGN(ipv6_optlen(*dest)); } /** * ipv6_renew_options - replace a specific ext hdr with a new one. * * @sk: sock from which to allocate memory * @opt: original options * @newtype: option type to replace in @opt * @newopt: new option of type @newtype to replace (user-mem) * * Returns a new set of options which is a copy of @opt with the * option type @newtype replaced with @newopt. * * @opt may be NULL, in which case a new set of options is returned * containing just @newopt. * * @newopt may be NULL, in which case the specified option type is * not copied into the new set of options. * * The new set of options is allocated from the socket option memory * buffer of @sk. */ struct ipv6_txoptions * ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt) { int tot_len = 0; char *p; struct ipv6_txoptions *opt2; if (opt) { if (newtype != IPV6_HOPOPTS && opt->hopopt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt)); if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt)); if (newtype != IPV6_RTHDR && opt->srcrt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt)); if (newtype != IPV6_DSTOPTS && opt->dst1opt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); } if (newopt) tot_len += CMSG_ALIGN(ipv6_optlen(newopt)); if (!tot_len) return NULL; tot_len += sizeof(*opt2); opt2 = sock_kmalloc(sk, tot_len, GFP_ATOMIC); if (!opt2) return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); refcount_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt, (opt ? opt->hopopt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt, (opt ? opt->dst0opt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_RTHDR, (struct ipv6_opt_hdr **)&opt2->srcrt, (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt, (opt ? opt->dst1opt : NULL), newopt, newtype, &p); opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) + (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) + (opt2->srcrt ? ipv6_optlen(opt2->srcrt) : 0); opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0); return opt2; } struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) { /* * ignore the dest before srcrt unless srcrt is being included. * --yoshfuji */ if (opt->dst0opt && !opt->srcrt) { if (opt_space != opt) { memcpy(opt_space, opt, sizeof(*opt_space)); opt = opt_space; } opt->opt_nflen -= ipv6_optlen(opt->dst0opt); opt->dst0opt = NULL; } return opt; } EXPORT_SYMBOL_GPL(__ipv6_fixup_options); /** * fl6_update_dst - update flowi destination address with info given * by srcrt option, if any. * * @fl6: flowi6 for which daddr is to be updated * @opt: struct ipv6_txoptions in which to look for srcrt opt * @orig: copy of original daddr address if modified * * Returns NULL if no txoptions or no srcrt, otherwise returns orig * and initial value of fl6->daddr set in orig */ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig) { if (!opt || !opt->srcrt) return NULL; *orig = fl6->daddr; switch (opt->srcrt->type) { case IPV6_SRCRT_TYPE_0: case IPV6_SRCRT_STRICT: case IPV6_SRCRT_TYPE_2: fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; break; case IPV6_SRCRT_TYPE_4: { struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)opt->srcrt; fl6->daddr = srh->segments[srh->segments_left]; break; } default: return NULL; } return orig; } EXPORT_SYMBOL_GPL(fl6_update_dst); |
| 64 64 60 60 60 93 103 145 146 25 134 1 44 43 100 57 17 134 57 131 5 131 44 58 54 4 93 129 129 129 26 19 35 130 130 75 68 76 76 59 25 4 40 133 133 144 3 44 16 6 139 112 140 4 3 4 4 4 2 133 106 53 133 69 133 133 133 133 133 40 106 50 20 50 144 91 144 74 76 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 | // SPDX-License-Identifier: GPL-2.0 /* * fs/mpage.c * * Copyright (C) 2002, Linus Torvalds. * * Contains functions related to preparing and submitting BIOs which contain * multiple pagecache pages. * * 15May2002 Andrew Morton * Initial version * 27Jun2002 axboe@suse.de * use bio_add_page() to build bio's just the right size */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/kdev_t.h> #include <linux/gfp.h> #include <linux/bio.h> #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/blkdev.h> #include <linux/highmem.h> #include <linux/prefetch.h> #include <linux/mpage.h> #include <linux/mm_inline.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include "internal.h" /* * I/O completion handler for multipage BIOs. * * The mpage code never puts partial pages into a BIO (except for end-of-file). * If a page does not map to a contiguous run of blocks then it simply falls * back to block_read_full_folio(). * * Why is this? If a page's completion depends on a number of different BIOs * which can complete in any order (or at the same time) then determining the * status of that page is hard. See end_buffer_async_read() for the details. * There is no point in duplicating all that complexity. */ static void mpage_read_end_io(struct bio *bio) { struct folio_iter fi; int err = blk_status_to_errno(bio->bi_status); bio_for_each_folio_all(fi, bio) folio_end_read(fi.folio, err == 0); bio_put(bio); } static void mpage_write_end_io(struct bio *bio) { struct folio_iter fi; int err = blk_status_to_errno(bio->bi_status); bio_for_each_folio_all(fi, bio) { if (err) mapping_set_error(fi.folio->mapping, err); folio_end_writeback(fi.folio); } bio_put(bio); } static struct bio *mpage_bio_submit_read(struct bio *bio) { bio->bi_end_io = mpage_read_end_io; guard_bio_eod(bio); submit_bio(bio); return NULL; } static struct bio *mpage_bio_submit_write(struct bio *bio) { bio->bi_end_io = mpage_write_end_io; guard_bio_eod(bio); submit_bio(bio); return NULL; } /* * support function for mpage_readahead. The fs supplied get_block might * return an up to date buffer. This is used to map that buffer into * the page, which allows read_folio to avoid triggering a duplicate call * to get_block. * * The idea is to avoid adding buffers to pages that don't already have * them. So when the buffer is up to date and the page size == block size, * this marks the page up to date instead of adding new buffers. */ static void map_buffer_to_folio(struct folio *folio, struct buffer_head *bh, int page_block) { struct inode *inode = folio->mapping->host; struct buffer_head *page_bh, *head; int block = 0; head = folio_buffers(folio); if (!head) { /* * don't make any buffers if there is only one buffer on * the folio and the folio just needs to be set up to date */ if (inode->i_blkbits == folio_shift(folio) && buffer_uptodate(bh)) { folio_mark_uptodate(folio); return; } head = create_empty_buffers(folio, i_blocksize(inode), 0); } page_bh = head; do { if (block == page_block) { page_bh->b_state = bh->b_state; page_bh->b_bdev = bh->b_bdev; page_bh->b_blocknr = bh->b_blocknr; break; } page_bh = page_bh->b_this_page; block++; } while (page_bh != head); } struct mpage_readpage_args { struct bio *bio; struct folio *folio; unsigned int nr_pages; bool is_readahead; sector_t last_block_in_bio; struct buffer_head map_bh; unsigned long first_logical_block; get_block_t *get_block; }; /* * This is the worker routine which does all the work of mapping the disk * blocks and constructs largest possible bios, submits them for IO if the * blocks are not contiguous on the disk. * * We pass a buffer_head back and forth and use its buffer_mapped() flag to * represent the validity of its disk mapping and to decide when to do the next * get_block() call. */ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) { struct folio *folio = args->folio; struct inode *inode = folio->mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocks_per_folio = folio_size(folio) >> blkbits; const unsigned blocksize = 1 << blkbits; struct buffer_head *map_bh = &args->map_bh; sector_t block_in_file; sector_t last_block; sector_t last_block_in_file; sector_t first_block; unsigned page_block; unsigned first_hole = blocks_per_folio; struct block_device *bdev = NULL; int length; int fully_mapped = 1; blk_opf_t opf = REQ_OP_READ; unsigned nblocks; unsigned relative_block; gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL); if (args->is_readahead) { opf |= REQ_RAHEAD; gfp |= __GFP_NORETRY | __GFP_NOWARN; } if (folio_buffers(folio)) goto confused; block_in_file = folio_pos(folio) >> blkbits; last_block = block_in_file + ((args->nr_pages * PAGE_SIZE) >> blkbits); last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; if (last_block > last_block_in_file) last_block = last_block_in_file; page_block = 0; /* * Map blocks using the result from the previous get_blocks call first. */ nblocks = map_bh->b_size >> blkbits; if (buffer_mapped(map_bh) && block_in_file > args->first_logical_block && block_in_file < (args->first_logical_block + nblocks)) { unsigned map_offset = block_in_file - args->first_logical_block; unsigned last = nblocks - map_offset; first_block = map_bh->b_blocknr + map_offset; for (relative_block = 0; ; relative_block++) { if (relative_block == last) { clear_buffer_mapped(map_bh); break; } if (page_block == blocks_per_folio) break; page_block++; block_in_file++; } bdev = map_bh->b_bdev; } /* * Then do more get_blocks calls until we are done with this folio. */ map_bh->b_folio = folio; while (page_block < blocks_per_folio) { map_bh->b_state = 0; map_bh->b_size = 0; if (block_in_file < last_block) { map_bh->b_size = (last_block-block_in_file) << blkbits; if (args->get_block(inode, block_in_file, map_bh, 0)) goto confused; args->first_logical_block = block_in_file; } if (!buffer_mapped(map_bh)) { fully_mapped = 0; if (first_hole == blocks_per_folio) first_hole = page_block; page_block++; block_in_file++; continue; } /* some filesystems will copy data into the page during * the get_block call, in which case we don't want to * read it again. map_buffer_to_folio copies the data * we just collected from get_block into the folio's buffers * so read_folio doesn't have to repeat the get_block call */ if (buffer_uptodate(map_bh)) { map_buffer_to_folio(folio, map_bh, page_block); goto confused; } if (first_hole != blocks_per_folio) goto confused; /* hole -> non-hole */ /* Contiguous blocks? */ if (!page_block) first_block = map_bh->b_blocknr; else if (first_block + page_block != map_bh->b_blocknr) goto confused; nblocks = map_bh->b_size >> blkbits; for (relative_block = 0; ; relative_block++) { if (relative_block == nblocks) { clear_buffer_mapped(map_bh); break; } else if (page_block == blocks_per_folio) break; page_block++; block_in_file++; } bdev = map_bh->b_bdev; } if (first_hole != blocks_per_folio) { folio_zero_segment(folio, first_hole << blkbits, folio_size(folio)); if (first_hole == 0) { folio_mark_uptodate(folio); folio_unlock(folio); goto out; } } else if (fully_mapped) { folio_set_mappedtodisk(folio); } /* * This folio will go to BIO. Do we need to send this BIO off first? */ if (args->bio && (args->last_block_in_bio != first_block - 1)) args->bio = mpage_bio_submit_read(args->bio); alloc_new: if (args->bio == NULL) { args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), opf, gfp); if (args->bio == NULL) goto confused; args->bio->bi_iter.bi_sector = first_block << (blkbits - 9); } length = first_hole << blkbits; if (!bio_add_folio(args->bio, folio, length, 0)) { args->bio = mpage_bio_submit_read(args->bio); goto alloc_new; } relative_block = block_in_file - args->first_logical_block; nblocks = map_bh->b_size >> blkbits; if ((buffer_boundary(map_bh) && relative_block == nblocks) || (first_hole != blocks_per_folio)) args->bio = mpage_bio_submit_read(args->bio); else args->last_block_in_bio = first_block + blocks_per_folio - 1; out: return args->bio; confused: if (args->bio) args->bio = mpage_bio_submit_read(args->bio); if (!folio_test_uptodate(folio)) block_read_full_folio(folio, args->get_block); else folio_unlock(folio); goto out; } /** * mpage_readahead - start reads against pages * @rac: Describes which pages to read. * @get_block: The filesystem's block mapper function. * * This function walks the pages and the blocks within each page, building and * emitting large BIOs. * * If anything unusual happens, such as: * * - encountering a page which has buffers * - encountering a page which has a non-hole after a hole * - encountering a page with non-contiguous blocks * * then this code just gives up and calls the buffer_head-based read function. * It does handle a page which has holes at the end - that is a common case: * the end-of-file on blocksize < PAGE_SIZE setups. * * BH_Boundary explanation: * * There is a problem. The mpage read code assembles several pages, gets all * their disk mappings, and then submits them all. That's fine, but obtaining * the disk mappings may require I/O. Reads of indirect blocks, for example. * * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be * submitted in the following order: * * 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16 * * because the indirect block has to be read to get the mappings of blocks * 13,14,15,16. Obviously, this impacts performance. * * So what we do it to allow the filesystem's get_block() function to set * BH_Boundary when it maps block 11. BH_Boundary says: mapping of the block * after this one will require I/O against a block which is probably close to * this one. So you should push what I/O you have currently accumulated. * * This all causes the disk requests to be issued in the correct order. */ void mpage_readahead(struct readahead_control *rac, get_block_t get_block) { struct folio *folio; struct mpage_readpage_args args = { .get_block = get_block, .is_readahead = true, }; while ((folio = readahead_folio(rac))) { prefetchw(&folio->flags); args.folio = folio; args.nr_pages = readahead_count(rac); args.bio = do_mpage_readpage(&args); } if (args.bio) mpage_bio_submit_read(args.bio); } EXPORT_SYMBOL(mpage_readahead); /* * This isn't called much at all */ int mpage_read_folio(struct folio *folio, get_block_t get_block) { struct mpage_readpage_args args = { .folio = folio, .nr_pages = folio_nr_pages(folio), .get_block = get_block, }; args.bio = do_mpage_readpage(&args); if (args.bio) mpage_bio_submit_read(args.bio); return 0; } EXPORT_SYMBOL(mpage_read_folio); /* * Writing is not so simple. * * If the page has buffers then they will be used for obtaining the disk * mapping. We only support pages which are fully mapped-and-dirty, with a * special case for pages which are unmapped at the end: end-of-file. * * If the page has no buffers (preferred) then the page is mapped here. * * If all blocks are found to be contiguous then the page can go into the * BIO. Otherwise fall back to the mapping's writepage(). * * FIXME: This code wants an estimate of how many pages are still to be * written, so it can intelligently allocate a suitably-sized BIO. For now, * just allocate full-size (16-page) BIOs. */ struct mpage_data { struct bio *bio; sector_t last_block_in_bio; get_block_t *get_block; }; /* * We have our BIO, so we can now mark the buffers clean. Make * sure to only clean buffers which we know we'll be writing. */ static void clean_buffers(struct folio *folio, unsigned first_unmapped) { unsigned buffer_counter = 0; struct buffer_head *bh, *head = folio_buffers(folio); if (!head) return; bh = head; do { if (buffer_counter++ == first_unmapped) break; clear_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); /* * we cannot drop the bh if the page is not uptodate or a concurrent * read_folio would fail to serialize with the bh and it would read from * disk before we reach the platter. */ if (buffer_heads_over_limit && folio_test_uptodate(folio)) try_to_free_buffers(folio); } static int mpage_write_folio(struct writeback_control *wbc, struct folio *folio, struct mpage_data *mpd) { struct bio *bio = mpd->bio; struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocks_per_folio = folio_size(folio) >> blkbits; sector_t last_block; sector_t block_in_file; sector_t first_block; unsigned page_block; unsigned first_unmapped = blocks_per_folio; struct block_device *bdev = NULL; int boundary = 0; sector_t boundary_block = 0; struct block_device *boundary_bdev = NULL; size_t length; struct buffer_head map_bh; loff_t i_size = i_size_read(inode); int ret = 0; struct buffer_head *head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; /* If they're all mapped and dirty, do it */ page_block = 0; do { BUG_ON(buffer_locked(bh)); if (!buffer_mapped(bh)) { /* * unmapped dirty buffers are created by * block_dirty_folio -> mmapped data */ if (buffer_dirty(bh)) goto confused; if (first_unmapped == blocks_per_folio) first_unmapped = page_block; continue; } if (first_unmapped != blocks_per_folio) goto confused; /* hole -> non-hole */ if (!buffer_dirty(bh) || !buffer_uptodate(bh)) goto confused; if (page_block) { if (bh->b_blocknr != first_block + page_block) goto confused; } else { first_block = bh->b_blocknr; } page_block++; boundary = buffer_boundary(bh); if (boundary) { boundary_block = bh->b_blocknr; boundary_bdev = bh->b_bdev; } bdev = bh->b_bdev; } while ((bh = bh->b_this_page) != head); if (first_unmapped) goto page_is_mapped; /* * Page has buffers, but they are all unmapped. The page was * created by pagein or read over a hole which was handled by * block_read_full_folio(). If this address_space is also * using mpage_readahead then this can rarely happen. */ goto confused; } /* * The page has no buffers: map it to disk */ BUG_ON(!folio_test_uptodate(folio)); block_in_file = folio_pos(folio) >> blkbits; /* * Whole page beyond EOF? Skip allocating blocks to avoid leaking * space. */ if (block_in_file >= (i_size + (1 << blkbits) - 1) >> blkbits) goto page_is_mapped; last_block = (i_size - 1) >> blkbits; map_bh.b_folio = folio; for (page_block = 0; page_block < blocks_per_folio; ) { map_bh.b_state = 0; map_bh.b_size = 1 << blkbits; if (mpd->get_block(inode, block_in_file, &map_bh, 1)) goto confused; if (!buffer_mapped(&map_bh)) goto confused; if (buffer_new(&map_bh)) clean_bdev_bh_alias(&map_bh); if (buffer_boundary(&map_bh)) { boundary_block = map_bh.b_blocknr; boundary_bdev = map_bh.b_bdev; } if (page_block) { if (map_bh.b_blocknr != first_block + page_block) goto confused; } else { first_block = map_bh.b_blocknr; } page_block++; boundary = buffer_boundary(&map_bh); bdev = map_bh.b_bdev; if (block_in_file == last_block) break; block_in_file++; } BUG_ON(page_block == 0); first_unmapped = page_block; page_is_mapped: /* Don't bother writing beyond EOF, truncate will discard the folio */ if (folio_pos(folio) >= i_size) goto confused; length = folio_size(folio); if (folio_pos(folio) + length > i_size) { /* * The page straddles i_size. It must be zeroed out on each * and every writepage 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." */ length = i_size - folio_pos(folio); folio_zero_segment(folio, length, folio_size(folio)); } /* * This page will go to BIO. Do we need to send this BIO off first? */ if (bio && mpd->last_block_in_bio != first_block - 1) bio = mpage_bio_submit_write(bio); alloc_new: if (bio == NULL) { bio = bio_alloc(bdev, BIO_MAX_VECS, REQ_OP_WRITE | wbc_to_write_flags(wbc), GFP_NOFS); bio->bi_iter.bi_sector = first_block << (blkbits - 9); wbc_init_bio(wbc, bio); bio->bi_write_hint = inode->i_write_hint; } /* * Must try to add the page before marking the buffer clean or * the confused fail path above (OOM) will be very confused when * it finds all bh marked clean (i.e. it will not write anything) */ wbc_account_cgroup_owner(wbc, folio, folio_size(folio)); length = first_unmapped << blkbits; if (!bio_add_folio(bio, folio, length, 0)) { bio = mpage_bio_submit_write(bio); goto alloc_new; } clean_buffers(folio, first_unmapped); BUG_ON(folio_test_writeback(folio)); folio_start_writeback(folio); folio_unlock(folio); if (boundary || (first_unmapped != blocks_per_folio)) { bio = mpage_bio_submit_write(bio); if (boundary_block) { write_boundary_block(boundary_bdev, boundary_block, 1 << blkbits); } } else { mpd->last_block_in_bio = first_block + blocks_per_folio - 1; } goto out; confused: if (bio) bio = mpage_bio_submit_write(bio); /* * The caller has a ref on the inode, so *mapping is stable */ ret = block_write_full_folio(folio, wbc, mpd->get_block); mapping_set_error(mapping, ret); out: mpd->bio = bio; return ret; } /** * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @get_block: the filesystem's block mapper function. * * This is a library function, which implements the writepages() * address_space_operation. */ int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block) { struct mpage_data mpd = { .get_block = get_block, }; struct folio *folio = NULL; struct blk_plug plug; int error; blk_start_plug(&plug); while ((folio = writeback_iter(mapping, wbc, folio, &error))) error = mpage_write_folio(wbc, folio, &mpd); if (mpd.bio) mpage_bio_submit_write(mpd.bio); blk_finish_plug(&plug); return error; } EXPORT_SYMBOL(mpage_writepages); |
| 88 66 240 88 88 239 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Cryptographic scatter and gather helpers. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 Adam J. Richter <adam@yggdrasil.com> * Copyright (c) 2004 Jean-Luc Cooke <jlcooke@certainkey.com> * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_SCATTERWALK_H #define _CRYPTO_SCATTERWALK_H #include <linux/errno.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/scatterlist.h> #include <linux/types.h> struct scatter_walk { /* Must be the first member, see struct skcipher_walk. */ union { void *const addr; /* Private API field, do not touch. */ union crypto_no_such_thing *__addr; }; struct scatterlist *sg; unsigned int offset; }; struct skcipher_walk { union { /* Virtual address of the source. */ struct { struct { const void *const addr; } virt; } src; /* Private field for the API, do not use. */ struct scatter_walk in; }; union { /* Virtual address of the destination. */ struct { struct { void *const addr; } virt; } dst; /* Private field for the API, do not use. */ struct scatter_walk out; }; unsigned int nbytes; unsigned int total; u8 *page; u8 *buffer; u8 *oiv; void *iv; unsigned int ivsize; int flags; unsigned int blocksize; unsigned int stride; unsigned int alignmask; }; static inline void scatterwalk_crypto_chain(struct scatterlist *head, struct scatterlist *sg, int num) { if (sg) sg_chain(head, num, sg); else sg_mark_end(head); } static inline void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg) { walk->sg = sg; walk->offset = sg->offset; } /* * This is equivalent to scatterwalk_start(walk, sg) followed by * scatterwalk_skip(walk, pos). */ static inline void scatterwalk_start_at_pos(struct scatter_walk *walk, struct scatterlist *sg, unsigned int pos) { while (pos > sg->length) { pos -= sg->length; sg = sg_next(sg); } walk->sg = sg; walk->offset = sg->offset + pos; } static inline unsigned int scatterwalk_clamp(struct scatter_walk *walk, unsigned int nbytes) { unsigned int len_this_sg; unsigned int limit; if (walk->offset >= walk->sg->offset + walk->sg->length) scatterwalk_start(walk, sg_next(walk->sg)); len_this_sg = walk->sg->offset + walk->sg->length - walk->offset; /* * HIGHMEM case: the page may have to be mapped into memory. To avoid * the complexity of having to map multiple pages at once per sg entry, * clamp the returned length to not cross a page boundary. * * !HIGHMEM case: no mapping is needed; all pages of the sg entry are * already mapped contiguously in the kernel's direct map. For improved * performance, allow the walker to return data segments that cross a * page boundary. Do still cap the length to PAGE_SIZE, since some * users rely on that to avoid disabling preemption for too long when * using SIMD. It's also needed for when skcipher_walk uses a bounce * page due to the data not being aligned to the algorithm's alignmask. */ if (IS_ENABLED(CONFIG_HIGHMEM)) limit = PAGE_SIZE - offset_in_page(walk->offset); else limit = PAGE_SIZE; return min3(nbytes, len_this_sg, limit); } /* * Create a scatterlist that represents the remaining data in a walk. Uses * chaining to reference the original scatterlist, so this uses at most two * entries in @sg_out regardless of the number of entries in the original list. * Assumes that sg_init_table() was already done. */ static inline void scatterwalk_get_sglist(struct scatter_walk *walk, struct scatterlist sg_out[2]) { if (walk->offset >= walk->sg->offset + walk->sg->length) scatterwalk_start(walk, sg_next(walk->sg)); sg_set_page(sg_out, sg_page(walk->sg), walk->sg->offset + walk->sg->length - walk->offset, walk->offset); scatterwalk_crypto_chain(sg_out, sg_next(walk->sg), 2); } static inline void scatterwalk_map(struct scatter_walk *walk) { struct page *base_page = sg_page(walk->sg); unsigned int offset = walk->offset; void *addr; if (IS_ENABLED(CONFIG_HIGHMEM)) { struct page *page; page = nth_page(base_page, offset >> PAGE_SHIFT); offset = offset_in_page(offset); addr = kmap_local_page(page) + offset; } else { /* * When !HIGHMEM we allow the walker to return segments that * span a page boundary; see scatterwalk_clamp(). To make it * clear that in this case we're working in the linear buffer of * the whole sg entry in the kernel's direct map rather than * within the mapped buffer of a single page, compute the * address as an offset from the page_address() of the first * page of the sg entry. Either way the result is the address * in the direct map, but this makes it clearer what is really * going on. */ addr = page_address(base_page) + offset; } walk->__addr = addr; } /** * scatterwalk_next() - Get the next data buffer in a scatterlist walk * @walk: the scatter_walk * @total: the total number of bytes remaining, > 0 * * A virtual address for the next segment of data from the scatterlist will * be placed into @walk->addr. The caller must call scatterwalk_done_src() * or scatterwalk_done_dst() when it is done using this virtual address. * * Returns: the next number of bytes available, <= @total */ static inline unsigned int scatterwalk_next(struct scatter_walk *walk, unsigned int total) { unsigned int nbytes = scatterwalk_clamp(walk, total); scatterwalk_map(walk); return nbytes; } static inline void scatterwalk_unmap(struct scatter_walk *walk) { if (IS_ENABLED(CONFIG_HIGHMEM)) kunmap_local(walk->__addr); } static inline void scatterwalk_advance(struct scatter_walk *walk, unsigned int nbytes) { walk->offset += nbytes; } /** * scatterwalk_done_src() - Finish one step of a walk of source scatterlist * @walk: the scatter_walk * @nbytes: the number of bytes processed this step, less than or equal to the * number of bytes that scatterwalk_next() returned. * * Use this if the mapped address was not written to, i.e. it is source data. */ static inline void scatterwalk_done_src(struct scatter_walk *walk, unsigned int nbytes) { scatterwalk_unmap(walk); scatterwalk_advance(walk, nbytes); } /** * scatterwalk_done_dst() - Finish one step of a walk of destination scatterlist * @walk: the scatter_walk * @nbytes: the number of bytes processed this step, less than or equal to the * number of bytes that scatterwalk_next() returned. * * Use this if the mapped address may have been written to, i.e. it is * destination data. */ static inline void scatterwalk_done_dst(struct scatter_walk *walk, unsigned int nbytes) { scatterwalk_unmap(walk); /* * Explicitly check ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE instead of just * relying on flush_dcache_page() being a no-op when not implemented, * since otherwise the BUG_ON in sg_page() does not get optimized out. * This also avoids having to consider whether the loop would get * reliably optimized out or not. */ if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE) { struct page *base_page; unsigned int offset; int start, end, i; base_page = sg_page(walk->sg); offset = walk->offset; start = offset >> PAGE_SHIFT; end = start + (nbytes >> PAGE_SHIFT); end += (offset_in_page(offset) + offset_in_page(nbytes) + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = start; i < end; i++) flush_dcache_page(nth_page(base_page, i)); } scatterwalk_advance(walk, nbytes); } void scatterwalk_skip(struct scatter_walk *walk, unsigned int nbytes); void memcpy_from_scatterwalk(void *buf, struct scatter_walk *walk, unsigned int nbytes); void memcpy_to_scatterwalk(struct scatter_walk *walk, const void *buf, unsigned int nbytes); void memcpy_from_sglist(void *buf, struct scatterlist *sg, unsigned int start, unsigned int nbytes); void memcpy_to_sglist(struct scatterlist *sg, unsigned int start, const void *buf, unsigned int nbytes); void memcpy_sglist(struct scatterlist *dst, struct scatterlist *src, unsigned int nbytes); /* In new code, please use memcpy_{from,to}_sglist() directly instead. */ static inline void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg, unsigned int start, unsigned int nbytes, int out) { if (out) memcpy_to_sglist(sg, start, buf, nbytes); else memcpy_from_sglist(buf, sg, start, nbytes); } struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2], struct scatterlist *src, unsigned int len); int skcipher_walk_first(struct skcipher_walk *walk, bool atomic); int skcipher_walk_done(struct skcipher_walk *walk, int res); static inline void skcipher_walk_abort(struct skcipher_walk *walk) { skcipher_walk_done(walk, -ECANCELED); } #endif /* _CRYPTO_SCATTERWALK_H */ |
| 1 1 653 1 2 1 1 7 1 3 1 2 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | // SPDX-License-Identifier: GPL-2.0 #include "io_uring.h" #include "napi.h" #ifdef CONFIG_NET_RX_BUSY_POLL /* Timeout for cleanout of stale entries. */ #define NAPI_TIMEOUT (60 * SEC_CONVERSION) struct io_napi_entry { unsigned int napi_id; struct list_head list; unsigned long timeout; struct hlist_node node; struct rcu_head rcu; }; static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list, unsigned int napi_id) { struct io_napi_entry *e; hlist_for_each_entry_rcu(e, hash_list, node) { if (e->napi_id != napi_id) continue; return e; } return NULL; } static inline ktime_t net_to_ktime(unsigned long t) { /* napi approximating usecs, reverse busy_loop_current_time */ return ns_to_ktime(t << 10); } int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) { struct hlist_head *hash_list; struct io_napi_entry *e; /* Non-NAPI IDs can be rejected. */ if (!napi_id_valid(napi_id)) return -EINVAL; hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))]; scoped_guard(rcu) { e = io_napi_hash_find(hash_list, napi_id); if (e) { WRITE_ONCE(e->timeout, jiffies + NAPI_TIMEOUT); return -EEXIST; } } e = kmalloc(sizeof(*e), GFP_NOWAIT); if (!e) return -ENOMEM; e->napi_id = napi_id; e->timeout = jiffies + NAPI_TIMEOUT; /* * guard(spinlock) is not used to manually unlock it before calling * kfree() */ spin_lock(&ctx->napi_lock); if (unlikely(io_napi_hash_find(hash_list, napi_id))) { spin_unlock(&ctx->napi_lock); kfree(e); return -EEXIST; } hlist_add_tail_rcu(&e->node, hash_list); list_add_tail_rcu(&e->list, &ctx->napi_list); spin_unlock(&ctx->napi_lock); return 0; } static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int napi_id) { struct hlist_head *hash_list; struct io_napi_entry *e; /* Non-NAPI IDs can be rejected. */ if (!napi_id_valid(napi_id)) return -EINVAL; hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))]; guard(spinlock)(&ctx->napi_lock); e = io_napi_hash_find(hash_list, napi_id); if (!e) return -ENOENT; list_del_rcu(&e->list); hash_del_rcu(&e->node); kfree_rcu(e, rcu); return 0; } static void __io_napi_remove_stale(struct io_ring_ctx *ctx) { struct io_napi_entry *e; guard(spinlock)(&ctx->napi_lock); /* * list_for_each_entry_safe() is not required as long as: * 1. list_del_rcu() does not reset the deleted node next pointer * 2. kfree_rcu() delays the memory freeing until the next quiescent * state */ list_for_each_entry(e, &ctx->napi_list, list) { if (time_after(jiffies, READ_ONCE(e->timeout))) { list_del_rcu(&e->list); hash_del_rcu(&e->node); kfree_rcu(e, rcu); } } } static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale) { if (is_stale) __io_napi_remove_stale(ctx); } static inline bool io_napi_busy_loop_timeout(ktime_t start_time, ktime_t bp) { if (bp) { ktime_t end_time = ktime_add(start_time, bp); ktime_t now = net_to_ktime(busy_loop_current_time()); return ktime_after(now, end_time); } return true; } static bool io_napi_busy_loop_should_end(void *data, unsigned long start_time) { struct io_wait_queue *iowq = data; if (signal_pending(current)) return true; if (io_should_wake(iowq) || io_has_work(iowq->ctx)) return true; if (io_napi_busy_loop_timeout(net_to_ktime(start_time), iowq->napi_busy_poll_dt)) return true; return false; } /* * never report stale entries */ static bool static_tracking_do_busy_loop(struct io_ring_ctx *ctx, bool (*loop_end)(void *, unsigned long), void *loop_end_arg) { struct io_napi_entry *e; list_for_each_entry_rcu(e, &ctx->napi_list, list) napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg, ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET); return false; } static bool dynamic_tracking_do_busy_loop(struct io_ring_ctx *ctx, bool (*loop_end)(void *, unsigned long), void *loop_end_arg) { struct io_napi_entry *e; bool is_stale = false; list_for_each_entry_rcu(e, &ctx->napi_list, list) { napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg, ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET); if (time_after(jiffies, READ_ONCE(e->timeout))) is_stale = true; } return is_stale; } static inline bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx, bool (*loop_end)(void *, unsigned long), void *loop_end_arg) { if (READ_ONCE(ctx->napi_track_mode) == IO_URING_NAPI_TRACKING_STATIC) return static_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); } static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { unsigned long start_time = busy_loop_current_time(); bool (*loop_end)(void *, unsigned long) = NULL; void *loop_end_arg = NULL; bool is_stale = false; /* Singular lists use a different napi loop end check function and are * only executed once. */ if (list_is_singular(&ctx->napi_list)) { loop_end = io_napi_busy_loop_should_end; loop_end_arg = iowq; } scoped_guard(rcu) { do { is_stale = __io_napi_do_busy_loop(ctx, loop_end, loop_end_arg); } while (!io_napi_busy_loop_should_end(iowq, start_time) && !loop_end_arg); } io_napi_remove_stale(ctx, is_stale); } /* * io_napi_init() - Init napi settings * @ctx: pointer to io-uring context structure * * Init napi settings in the io-uring context. */ void io_napi_init(struct io_ring_ctx *ctx) { u64 sys_dt = READ_ONCE(sysctl_net_busy_poll) * NSEC_PER_USEC; INIT_LIST_HEAD(&ctx->napi_list); spin_lock_init(&ctx->napi_lock); ctx->napi_prefer_busy_poll = false; ctx->napi_busy_poll_dt = ns_to_ktime(sys_dt); ctx->napi_track_mode = IO_URING_NAPI_TRACKING_INACTIVE; } /* * io_napi_free() - Deallocate napi * @ctx: pointer to io-uring context structure * * Free the napi list and the hash table in the io-uring context. */ void io_napi_free(struct io_ring_ctx *ctx) { struct io_napi_entry *e; guard(spinlock)(&ctx->napi_lock); list_for_each_entry(e, &ctx->napi_list, list) { hash_del_rcu(&e->node); kfree_rcu(e, rcu); } INIT_LIST_HEAD_RCU(&ctx->napi_list); } static int io_napi_register_napi(struct io_ring_ctx *ctx, struct io_uring_napi *napi) { switch (napi->op_param) { case IO_URING_NAPI_TRACKING_DYNAMIC: case IO_URING_NAPI_TRACKING_STATIC: break; default: return -EINVAL; } /* clean the napi list for new settings */ io_napi_free(ctx); WRITE_ONCE(ctx->napi_track_mode, napi->op_param); WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC); WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll); return 0; } /* * io_napi_register() - Register napi with io-uring * @ctx: pointer to io-uring context structure * @arg: pointer to io_uring_napi structure * * Register napi in the io-uring context. */ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) { const struct io_uring_napi curr = { .busy_poll_to = ktime_to_us(ctx->napi_busy_poll_dt), .prefer_busy_poll = ctx->napi_prefer_busy_poll, .op_param = ctx->napi_track_mode }; struct io_uring_napi napi; if (ctx->flags & IORING_SETUP_IOPOLL) return -EINVAL; if (copy_from_user(&napi, arg, sizeof(napi))) return -EFAULT; if (napi.pad[0] || napi.pad[1] || napi.resv) return -EINVAL; if (copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT; switch (napi.opcode) { case IO_URING_NAPI_REGISTER_OP: return io_napi_register_napi(ctx, &napi); case IO_URING_NAPI_STATIC_ADD_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; return __io_napi_add_id(ctx, napi.op_param); case IO_URING_NAPI_STATIC_DEL_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; return __io_napi_del_id(ctx, napi.op_param); default: return -EINVAL; } } /* * io_napi_unregister() - Unregister napi with io-uring * @ctx: pointer to io-uring context structure * @arg: pointer to io_uring_napi structure * * Unregister napi. If arg has been specified copy the busy poll timeout and * prefer busy poll setting to the passed in structure. */ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) { const struct io_uring_napi curr = { .busy_poll_to = ktime_to_us(ctx->napi_busy_poll_dt), .prefer_busy_poll = ctx->napi_prefer_busy_poll }; if (arg && copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT; WRITE_ONCE(ctx->napi_busy_poll_dt, 0); WRITE_ONCE(ctx->napi_prefer_busy_poll, false); WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); return 0; } /* * __io_napi_busy_loop() - execute busy poll loop * @ctx: pointer to io-uring context structure * @iowq: pointer to io wait queue * * Execute the busy poll loop and merge the spliced off list. */ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { if (ctx->flags & IORING_SETUP_SQPOLL) return; iowq->napi_busy_poll_dt = READ_ONCE(ctx->napi_busy_poll_dt); if (iowq->timeout != KTIME_MAX) { ktime_t dt = ktime_sub(iowq->timeout, io_get_time(ctx)); iowq->napi_busy_poll_dt = min_t(u64, iowq->napi_busy_poll_dt, dt); } iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll); io_napi_blocking_busy_loop(ctx, iowq); } /* * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll * @ctx: pointer to io-uring context structure * * Splice of the napi list and execute the napi busy poll loop. */ int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx) { bool is_stale = false; if (!READ_ONCE(ctx->napi_busy_poll_dt)) return 0; if (list_empty_careful(&ctx->napi_list)) return 0; scoped_guard(rcu) { is_stale = __io_napi_do_busy_loop(ctx, NULL, NULL); } io_napi_remove_stale(ctx, is_stale); return 1; } #endif |
| 25 182 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_LE_H_ #define _ASM_GENERIC_BITOPS_LE_H_ #include <asm/types.h> #include <asm/byteorder.h> #if defined(__LITTLE_ENDIAN) #define BITOP_LE_SWIZZLE 0 #elif defined(__BIG_ENDIAN) #define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) #endif static inline int test_bit_le(int nr, const void *addr) { return test_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void set_bit_le(int nr, void *addr) { set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void clear_bit_le(int nr, void *addr) { clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __set_bit_le(int nr, void *addr) { __set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __clear_bit_le(int nr, void *addr) { __clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_set_bit_le(int nr, void *addr) { return test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_clear_bit_le(int nr, void *addr) { return test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_set_bit_le(int nr, void *addr) { return __test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_clear_bit_le(int nr, void *addr) { return __test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } #endif /* _ASM_GENERIC_BITOPS_LE_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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Stubs for the Network PHY library */ #include <linux/rtnetlink.h> struct ethtool_eth_phy_stats; struct ethtool_link_ext_stats; struct ethtool_phy_stats; struct kernel_hwtstamp_config; struct netlink_ext_ack; struct phy_device; #if IS_ENABLED(CONFIG_PHYLIB) extern const struct phylib_stubs *phylib_stubs; struct phylib_stubs { int (*hwtstamp_get)(struct phy_device *phydev, struct kernel_hwtstamp_config *config); int (*hwtstamp_set)(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); void (*get_phy_stats)(struct phy_device *phydev, struct ethtool_eth_phy_stats *phy_stats, struct ethtool_phy_stats *phydev_stats); void (*get_link_ext_stats)(struct phy_device *phydev, struct ethtool_link_ext_stats *link_stats); }; static inline int phy_hwtstamp_get(struct phy_device *phydev, struct kernel_hwtstamp_config *config) { /* phylib_register_stubs() and phylib_unregister_stubs() * also run under rtnl_lock(). */ ASSERT_RTNL(); if (!phylib_stubs) return -EOPNOTSUPP; return phylib_stubs->hwtstamp_get(phydev, config); } static inline int phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack) { /* phylib_register_stubs() and phylib_unregister_stubs() * also run under rtnl_lock(). */ ASSERT_RTNL(); if (!phylib_stubs) return -EOPNOTSUPP; return phylib_stubs->hwtstamp_set(phydev, config, extack); } static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, struct ethtool_eth_phy_stats *phy_stats, struct ethtool_phy_stats *phydev_stats) { ASSERT_RTNL(); if (!phylib_stubs) return; phylib_stubs->get_phy_stats(phydev, phy_stats, phydev_stats); } static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, struct ethtool_link_ext_stats *link_stats) { ASSERT_RTNL(); if (!phylib_stubs) return; phylib_stubs->get_link_ext_stats(phydev, link_stats); } #else static inline int phy_hwtstamp_get(struct phy_device *phydev, struct kernel_hwtstamp_config *config) { return -EOPNOTSUPP; } static inline int phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, struct ethtool_eth_phy_stats *phy_stats, struct ethtool_phy_stats *phydev_stats) { } static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, struct ethtool_link_ext_stats *link_stats) { } #endif |
| 2123 45 22 1503 17 229 383 79 234 396 396 6556 1619 4129 1851 20 1260 1243 640 100 6 7 84 100 29 100 100 89 86 33 6 8 17 8 8 100 100 1774 762 1043 933 51 51 74 4 72 2 2 1 17 2 57 1044 55 1 1 1 1 51 5 5 84 9 43 39 9 3 29 10 21 15 72 17 23 72 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Longest prefix match list implementation * * Copyright (c) 2016,2017 Daniel Mack * Copyright (c) 2016 David Herrmann */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <net/ipv6.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> #include <asm/rqspinlock.h> #include <linux/bpf_mem_alloc.h> /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) struct lpm_trie_node; struct lpm_trie_node { struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; u8 data[]; }; struct lpm_trie { struct bpf_map map; struct lpm_trie_node __rcu *root; struct bpf_mem_alloc ma; size_t n_entries; size_t max_prefixlen; size_t data_size; rqspinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to * match IP addresses to a stored set of ranges. * * Data stored in @data of struct bpf_lpm_key and struct lpm_trie_node is * interpreted as big endian, so data[0] stores the most significant byte. * * Match ranges are internally stored in instances of struct lpm_trie_node * which each contain their prefix length as well as two pointers that may * lead to more nodes containing more specific matches. Each node also stores * a value that is defined by and returned to userspace via the update_elem * and lookup functions. * * For instance, let's start with a trie that was created with a prefix length * of 32, so it can be used for IPv4 addresses, and one single element that * matches 192.168.0.0/16. The data array would hence contain * [0xc0, 0xa8, 0x00, 0x00] in big-endian notation. This documentation will * stick to IP-address notation for readability though. * * As the trie is empty initially, the new node (1) will be places as root * node, denoted as (R) in the example below. As there are no other node, both * child pointers are %NULL. * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * * Next, let's add a new node (2) matching 192.168.0.0/24. As there is already * a node with the same data and a smaller prefix (ie, a less specific one), * node (2) will become a child of (1). In child index depends on the next bit * that is outside of what (1) matches, and that bit is 0, so (2) will be * child[0] of (1): * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | * +----------------+ * | (2) | * | 192.168.0.0/24 | * | value: 2 | * | [0] [1] | * +----------------+ * * The child[1] slot of (1) could be filled with another node which has bit #17 * (the next bit after the ones that (1) matches on) set to 1. For instance, * 192.168.128.0/24: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (2) | | (3) | * | 192.168.0.0/24 | | 192.168.128.0/24 | * | value: 2 | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * * Let's add another node (4) to the game for 192.168.1.0/24. In order to place * it, node (1) is looked at first, and because (4) of the semantics laid out * above (bit #17 is 0), it would normally be attached to (1) as child[0]. * However, that slot is already allocated, so a new node is needed in between. * That node does not have a value attached to it and it will never be * returned to users as result of a lookup. It is only there to differentiate * the traversal further. It will get a prefix as wide as necessary to * distinguish its two children: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (4) (I) | | (3) | * | 192.168.0.0/23 | | 192.168.128.0/24 | * | value: --- | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * | | * +----------------+ +----------------+ * | (2) | | (5) | * | 192.168.0.0/24 | | 192.168.1.0/24 | * | value: 2 | | value: 5 | * | [0] [1] | | [0] [1] | * +----------------+ +----------------+ * * 192.168.1.1/32 would be a child of (5) etc. * * An intermediate node will be turned into a 'real' node on demand. In the * example above, (4) would be re-used if 192.168.0.0/23 is added to the trie. * * A fully populated trie would have a height of 32 nodes, as the trie was * created with a prefix length of 32. * * The lookup starts at the root node. If the current node matches and if there * is a child that can be used to become more specific, the trie is traversed * downwards. The last node in the traversal that is a non-intermediate one is * returned. */ static inline int extract_bit(const u8 *data, size_t index) { return !!(data[index / 8] & (1 << (7 - (index % 8)))); } /** * __longest_prefix_match() - determine the longest prefix * @trie: The trie to get internal sizes from * @node: The node to operate on * @key: The key to compare to @node * * Determine the longest prefix of @node that matches the bits in @key. */ static __always_inline size_t __longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, const struct bpf_lpm_trie_key_u8 *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key_u8, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) /* data_size >= 16 has very small probability. * We do not use a loop for optimal code generation. */ if (trie->data_size >= 8) { u64 diff = be64_to_cpu(*(__be64 *)node->data ^ *(__be64 *)key->data); prefixlen = 64 - fls64(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i = 8; } #endif while (trie->data_size >= i + 4) { u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^ *(__be32 *)&key->data[i]); prefixlen += 32 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 4; } if (trie->data_size >= i + 2) { u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^ *(__be16 *)&key->data[i]); prefixlen += 16 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 2; } if (trie->data_size >= i + 1) { prefixlen += 8 - fls(node->data[i] ^ key->data[i]); if (prefixlen >= limit) return limit; } return prefixlen; } static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, const struct bpf_lpm_trie_key_u8 *key) { return __longest_prefix_match(trie, node, key); } /* Called from syscall or from eBPF program */ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; struct bpf_lpm_trie_key_u8 *key = _key; if (key->prefixlen > trie->max_prefixlen) return NULL; /* Start walking the trie from the root node ... */ for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held()); node;) { unsigned int next_bit; size_t matchlen; /* Determine the longest prefix of @node that matches @key. * If it's the maximum possible prefix for this trie, we have * an exact match and can return it directly. */ matchlen = __longest_prefix_match(trie, node, key); if (matchlen == trie->max_prefixlen) { found = node; break; } /* If the number of bits that match is smaller than the prefix * length of @node, bail out and return the node we have seen * last in the traversal (ie, the parent). */ if (matchlen < node->prefixlen) break; /* Consider this node as return candidate unless it is an * artificially added intermediate one. */ if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) found = node; /* If the node match is fully satisfied, let's see if we can * become more specific. Determine the next bit in the key and * traverse down. */ next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference_check(node->child[next_bit], rcu_read_lock_bh_held()); } if (!found) return NULL; return found->data + trie->data_size; } static struct lpm_trie_node *lpm_trie_node_alloc(struct lpm_trie *trie, const void *value) { struct lpm_trie_node *node; node = bpf_mem_cache_alloc(&trie->ma); if (!node) return NULL; node->flags = 0; if (value) memcpy(node->data + trie->data_size, value, trie->map.value_size); return node; } static int trie_check_add_elem(struct lpm_trie *trie, u64 flags) { if (flags == BPF_EXIST) return -ENOENT; if (trie->n_entries == trie->map.max_entries) return -ENOSPC; trie->n_entries++; return 0; } /* Called from syscall or from eBPF program */ static long trie_update_elem(struct bpf_map *map, void *_key, void *value, u64 flags) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node, *new_node; struct lpm_trie_node *free_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key_u8 *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (unlikely(flags > BPF_EXIST)) return -EINVAL; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; /* Allocate and fill a new node */ new_node = lpm_trie_node_alloc(trie, value); if (!new_node) return -ENOMEM; ret = raw_res_spin_lock_irqsave(&trie->lock, irq_flags); if (ret) goto out_free; new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); RCU_INIT_POINTER(new_node->child[1], NULL); memcpy(new_node->data, key->data, trie->data_size); /* Now find a slot to attach the new node. To do that, walk the tree * from the root and match as many bits as possible for each node until * we either find an empty slot or a slot that needs to be replaced by * an intermediate node. */ slot = &trie->root; while ((node = rcu_dereference(*slot))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); slot = &node->child[next_bit]; } /* If the slot is empty (a free child pointer or an empty root), * simply assign the @new_node to that slot and be done. */ if (!node) { ret = trie_check_add_elem(trie, flags); if (ret) goto out; rcu_assign_pointer(*slot, new_node); goto out; } /* If the slot we picked already exists, replace it with @new_node * which already has the correct data array set. */ if (node->prefixlen == matchlen) { if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) { if (flags == BPF_NOEXIST) { ret = -EEXIST; goto out; } } else { ret = trie_check_add_elem(trie, flags); if (ret) goto out; } new_node->child[0] = node->child[0]; new_node->child[1] = node->child[1]; rcu_assign_pointer(*slot, new_node); free_node = node; goto out; } ret = trie_check_add_elem(trie, flags); if (ret) goto out; /* If the new node matches the prefix completely, it must be inserted * as an ancestor. Simply insert it between @node and *@slot. */ if (matchlen == key->prefixlen) { next_bit = extract_bit(node->data, matchlen); rcu_assign_pointer(new_node->child[next_bit], node); rcu_assign_pointer(*slot, new_node); goto out; } im_node = lpm_trie_node_alloc(trie, NULL); if (!im_node) { trie->n_entries--; ret = -ENOMEM; goto out; } im_node->prefixlen = matchlen; im_node->flags |= LPM_TREE_NODE_FLAG_IM; memcpy(im_node->data, node->data, trie->data_size); /* Now determine which child to install in which slot */ if (extract_bit(key->data, matchlen)) { rcu_assign_pointer(im_node->child[0], node); rcu_assign_pointer(im_node->child[1], new_node); } else { rcu_assign_pointer(im_node->child[0], new_node); rcu_assign_pointer(im_node->child[1], node); } /* Finally, assign the intermediate node to the determined slot */ rcu_assign_pointer(*slot, im_node); out: raw_res_spin_unlock_irqrestore(&trie->lock, irq_flags); out_free: if (ret) bpf_mem_cache_free(&trie->ma, new_node); bpf_mem_cache_free_rcu(&trie->ma, free_node); return ret; } /* Called from syscall or from eBPF program */ static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *free_node = NULL, *free_parent = NULL; struct bpf_lpm_trie_key_u8 *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; ret = raw_res_spin_lock_irqsave(&trie->lock, irq_flags); if (ret) return ret; /* Walk the tree looking for an exact key/length match and keeping * track of the path we traverse. We will need to know the node * we wish to delete, and the slot that points to the node we want * to delete. We may also need to know the nodes parent and the * slot that contains it. */ trim = &trie->root; trim2 = trim; parent = NULL; while ((node = rcu_dereference(*trim))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; parent = node; trim2 = trim; next_bit = extract_bit(key->data, node->prefixlen); trim = &node->child[next_bit]; } if (!node || node->prefixlen != key->prefixlen || node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; } trie->n_entries--; /* If the node we are removing has two children, simply mark it * as intermediate and we are done. */ if (rcu_access_pointer(node->child[0]) && rcu_access_pointer(node->child[1])) { node->flags |= LPM_TREE_NODE_FLAG_IM; goto out; } /* If the parent of the node we are about to delete is an intermediate * node, and the deleted node doesn't have any children, we can delete * the intermediate parent as well and promote its other child * up the tree. Doing this maintains the invariant that all * intermediate nodes have exactly 2 children and that there are no * unnecessary intermediate nodes in the tree. */ if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) && !node->child[0] && !node->child[1]) { if (node == rcu_access_pointer(parent->child[0])) rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[1])); else rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[0])); free_parent = parent; free_node = node; goto out; } /* The node we are removing has either zero or one child. If there * is a child, move it into the removed node's slot then delete * the node. Otherwise just clear the slot and delete the node. */ if (node->child[0]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0])); else if (node->child[1]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); else RCU_INIT_POINTER(*trim, NULL); free_node = node; out: raw_res_spin_unlock_irqrestore(&trie->lock, irq_flags); bpf_mem_cache_free_rcu(&trie->ma, free_parent); bpf_mem_cache_free_rcu(&trie->ma, free_node); return ret; } #define LPM_DATA_SIZE_MAX 256 #define LPM_DATA_SIZE_MIN 1 #define LPM_VAL_SIZE_MAX (KMALLOC_MAX_SIZE - LPM_DATA_SIZE_MAX - \ sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 #define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key_u8) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) #define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK) static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; size_t leaf_size; int err; /* check sanity of attributes */ if (attr->max_entries == 0 || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->map_flags & ~LPM_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || attr->value_size > LPM_VAL_SIZE_MAX) return ERR_PTR(-EINVAL); trie = bpf_map_area_alloc(sizeof(*trie), NUMA_NO_NODE); if (!trie) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key_u8, data); trie->max_prefixlen = trie->data_size * 8; raw_res_spin_lock_init(&trie->lock); /* Allocate intermediate and leaf nodes from the same allocator */ leaf_size = sizeof(struct lpm_trie_node) + trie->data_size + trie->map.value_size; err = bpf_mem_alloc_init(&trie->ma, leaf_size, false); if (err) goto free_out; return &trie->map; free_out: bpf_map_area_free(trie); return ERR_PTR(err); } static void trie_free(struct bpf_map *map) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent * and start over. */ for (;;) { slot = &trie->root; for (;;) { node = rcu_dereference_protected(*slot, 1); if (!node) goto out; if (rcu_access_pointer(node->child[0])) { slot = &node->child[0]; continue; } if (rcu_access_pointer(node->child[1])) { slot = &node->child[1]; continue; } /* No bpf program may access the map, so freeing the * node without waiting for the extra RCU GP. */ bpf_mem_cache_raw_free(node); RCU_INIT_POINTER(*slot, NULL); break; } } out: bpf_mem_alloc_destroy(&trie->ma); bpf_map_area_free(trie); } static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key_u8 *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; size_t matchlen = 0; /* The get_next_key follows postorder. For the 4 node example in * the top of this file, the trie_get_next_key() returns the following * one after another: * 192.168.0.0/24 * 192.168.1.0/24 * 192.168.128.0/24 * 192.168.0.0/16 * * The idea is to return more specific keys before less specific ones. */ /* Empty trie */ search_root = rcu_dereference(trie->root); if (!search_root) return -ENOENT; /* For invalid key, find the leftmost node in the trie */ if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; node_stack = kmalloc_array(trie->max_prefixlen + 1, sizeof(struct lpm_trie_node *), GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) return -ENOMEM; /* Try to find the exact node for the given key */ for (node = search_root; node;) { node_stack[++stack_ptr] = node; matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } if (!node || node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) goto find_leftmost; /* The node with the exactly-matching key has been found, * find the first node in postorder after the matched node. */ node = node_stack[stack_ptr]; while (stack_ptr > 0) { parent = node_stack[stack_ptr - 1]; if (rcu_dereference(parent->child[0]) == node) { search_root = rcu_dereference(parent->child[1]); if (search_root) goto find_leftmost; } if (!(parent->flags & LPM_TREE_NODE_FLAG_IM)) { next_node = parent; goto do_copy; } node = parent; stack_ptr--; } /* did not find anything */ err = -ENOENT; goto free_stack; find_leftmost: /* Find the leftmost non-intermediate node, all intermediate nodes * have exact two children, so this function will never return NULL. */ for (node = search_root; node;) { if (node->flags & LPM_TREE_NODE_FLAG_IM) { node = rcu_dereference(node->child[0]); } else { next_node = node; node = rcu_dereference(node->child[0]); if (!node) node = rcu_dereference(next_node->child[1]); } } do_copy: next_key->prefixlen = next_node->prefixlen; memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key_u8, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); return err; } static int trie_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { /* Keys must have struct bpf_lpm_trie_key_u8 embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } static u64 trie_mem_usage(const struct bpf_map *map) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); u64 elem_size; elem_size = sizeof(struct lpm_trie_node) + trie->data_size + trie->map.value_size; return elem_size * READ_ONCE(trie->n_entries); } BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie) const struct bpf_map_ops trie_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = trie_alloc, .map_free = trie_free, .map_get_next_key = trie_get_next_key, .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, .map_lookup_batch = generic_map_lookup_batch, .map_update_batch = generic_map_update_batch, .map_delete_batch = generic_map_delete_batch, .map_check_btf = trie_check_btf, .map_mem_usage = trie_mem_usage, .map_btf_id = &trie_map_btf_ids[0], }; |
| 16 448 1 35 3 13 105 22 2 18 4 2 20 20 2 2 2 11 18894 107 36 137 55 101 52 18891 725 18737 8254 10853 10821 144 725 121 3 133 1 1 4 8 69 18320 68 18320 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * VLAN An implementation of 802.1Q VLAN tagging. * * Authors: Ben Greear <greearb@candelatech.com> */ #ifndef _LINUX_IF_VLAN_H_ #define _LINUX_IF_VLAN_H_ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/bug.h> #include <uapi/linux/if_vlan.h> #define VLAN_HLEN 4 /* The additional bytes required by VLAN * (in addition to the Ethernet header) */ #define VLAN_ETH_HLEN 18 /* Total octets in header. */ #define VLAN_ETH_ZLEN 64 /* Min. octets in frame sans FCS */ /* * According to 802.3ac, the packet can be 4 bytes longer. --Klika Jan */ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ #define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_hdr { __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; /** * struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr) * @h_dest: destination ethernet address * @h_source: source ethernet address * @h_vlan_proto: ethernet protocol * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { struct_group(addrs, unsigned char h_dest[ETH_ALEN]; unsigned char h_source[ETH_ALEN]; ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; #include <linux/skbuff.h> static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + vlan_eth_hdr() */ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb->data; } #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); static inline bool is_vlan_dev(const struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } #define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) #define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev); } static inline int vlan_get_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev); } /** * struct vlan_pcpu_stats - VLAN percpu rx/tx stats * @rx_packets: number of received packets * @rx_bytes: number of received bytes * @rx_multicast: number of received multicast packets * @tx_packets: number of transmitted packets * @tx_bytes: number of transmitted bytes * @syncp: synchronization point for 64bit counters * @rx_errors: number of rx errors * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t rx_multicast; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; }; #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); extern int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); /** * struct vlan_priority_tci_mapping - vlan egress priority mappings * @priority: skb priority * @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000 * @next: pointer to next struct */ struct vlan_priority_tci_mapping { u32 priority; u16 vlan_qos; struct vlan_priority_tci_mapping *next; }; struct proc_dir_entry; struct netpoll; /** * struct vlan_dev_priv - VLAN private device data * @nr_ingress_mappings: number of ingress priority mappings * @ingress_priority_map: ingress priority mappings * @nr_egress_mappings: number of egress priority mappings * @egress_priority_map: hash of egress priority mappings * @vlan_proto: VLAN encapsulation protocol * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats * @netpoll: netpoll instance "propagated" down to @real_dev */ struct vlan_dev_priv { unsigned int nr_ingress_mappings; u32 ingress_priority_map[8]; unsigned int nr_egress_mappings; struct vlan_priority_tci_mapping *egress_priority_map[16]; __be16 vlan_proto; u16 vlan_id; u16 flags; struct net_device *real_dev; netdevice_tracker dev_tracker; unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; struct vlan_pcpu_stats __percpu *vlan_pcpu_stats; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) { return netdev_priv(dev); } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { struct vlan_priority_tci_mapping *mp; smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)]; while (mp) { if (mp->priority == skprio) { return mp->vlan_qos; /* This should already be shifted * to mask correctly with the * VLAN's TCI */ } mp = mp->next; } return 0; } extern bool vlan_do_receive(struct sk_buff **skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); extern void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev); extern bool vlan_uses_dev(const struct net_device *dev); #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { return NULL; } static inline int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg) { return 0; } static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); return NULL; } static inline u16 vlan_dev_vlan_id(const struct net_device *dev) { BUG(); return 0; } static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev) { BUG(); return 0; } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { return 0; } static inline bool vlan_do_receive(struct sk_buff **skb) { return false; } static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; } static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { } static inline int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev) { return 0; } static inline void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev) { } static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } #endif /** * eth_type_vlan - check for valid vlan ether type. * @ethertype: ether type to check * * Returns: true if the ether type is a vlan ether type. */ static inline bool eth_type_vlan(__be16 ethertype) { switch (ethertype) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) return true; if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX) return true; return false; } /** * __vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Does not change skb->protocol so this function can be used during receive. * * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { struct vlan_ethhdr *veth; if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; skb_push(skb, VLAN_HLEN); /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); if (skb_mac_header_was_set(skb)) skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); /* first, the ethernet type */ if (likely(mac_len >= ETH_TLEN)) { /* h_vlan_encapsulated_proto should already be populated, and * skb->data has space for h_vlan_proto */ veth->h_vlan_proto = vlan_proto; } else { /* h_vlan_encapsulated_proto should not be populated, and * skb->data has no space for h_vlan_proto */ veth->h_vlan_encapsulated_proto = skb->protocol; } /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); return 0; } /** * __vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Does not change skb->protocol so this function can be used during receive. * * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { int err; err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len); if (err) { dev_kfree_skb_any(skb); return NULL; } return skb; } /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_tag_set_proto - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb = vlan_insert_tag(skb, vlan_proto, vlan_tci); if (skb) skb->protocol = vlan_proto; return skb; } /** * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info * @skb: skbuff to clear * * Clears the VLAN information from @skb */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_all = 0; } /** * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb * @dst: skbuff to copy to * @src: skbuff to copy from * * Copies VLAN information from @src to @dst (for branchless code) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { dst->vlan_all = src->vlan_all; } /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag * * Pushes the VLAN tag from @skb->vlan_tci inside to the payload. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) { skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (likely(skb)) __vlan_hwaccel_clear_tag(skb); return skb; } /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest */ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; } /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if the skb is not of VLAN type */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; } /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if @skb->vlan_tci is not set correctly */ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb_vlan_tag_present(skb)) { *vlan_tci = skb_vlan_tag_get(skb); return 0; } else { *vlan_tci = 0; return -ENODATA; } } /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if the skb is not VLAN tagged */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_get_tag(skb, vlan_tci); } else { return __vlan_get_tag(skb, vlan_tci); } } /** * __vlan_get_protocol_offset() - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb, __be16 type, int mac_offset, int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at * ETH_HLEN otherwise */ if (eth_type_vlan(type)) { if (vlan_depth) { if (WARN_ON(vlan_depth < VLAN_HLEN)) return 0; vlan_depth -= VLAN_HLEN; } else { vlan_depth = ETH_HLEN; } do { struct vlan_hdr vhdr, *vh; vh = skb_header_pointer(skb, mac_offset + vlan_depth, sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); } if (depth) *depth = vlan_depth; return type; } static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { return __vlan_get_protocol_offset(skb, type, 0, depth); } /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } /* This version of __vlan_get_protocol() also pulls mac header in skb->head */ static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, __be16 type, int *depth) { int maclen; type = __vlan_get_protocol(skb, type, &maclen); if (type) { if (!pskb_may_pull(skb, maclen)) type = 0; else if (depth) *depth = maclen; } return type; } /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) { if (!skip_vlan) /* VLAN acceleration strips the VLAN header from the skb and * moves it to skb->vlan_proto */ return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; return vlan_get_protocol(skb); } static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { __be16 proto; unsigned short *rawp; /* * Was a VLAN packet, grab the encapsulated protocol, which the layer * three protocols care about. */ proto = vhdr->h_vlan_encapsulated_proto; if (eth_proto_is_802_3(proto)) { skb->protocol = proto; return; } rawp = (unsigned short *)(vhdr + 1); if (*rawp == 0xFFFF) /* * This is a magic hack to spot IPX packets. Older Novell * breaks the protocol design and runs IPX over 802.3 without * an 802.2 LLC layer. We look for FFFF which isn't a used * 802.2 SSAP/DSAP. This won't work for fault tolerant netware * but does for the rest. */ skb->protocol = htons(ETH_P_802_3); else /* * Real 802.2 LLC */ skb->protocol = htons(ETH_P_802_2); } /** * vlan_remove_tag - remove outer VLAN tag from payload * @skb: skbuff to remove tag from * @vlan_tci: buffer to store value * * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. * * Returns: a new pointer to skb->data, or NULL on failure to pull. */ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); vlan_set_encap_proto(skb, vhdr); return __skb_pull(skb, VLAN_HLEN); } /** * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * * Returns: true if the skb is tagged, regardless of whether it is hardware * accelerated or not. */ static inline bool skb_vlan_tagged(const struct sk_buff *skb) { if (!skb_vlan_tag_present(skb) && likely(!eth_type_vlan(skb->protocol))) return false; return true; } /** * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. * @skb: skbuff to query * * Returns: true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) { __be16 protocol = skb->protocol; if (!skb_vlan_tag_present(skb)) { struct vlan_ethhdr *veh; if (likely(!eth_type_vlan(protocol))) return false; if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) return false; veh = skb_vlan_eth_hdr(skb); protocol = veh->h_vlan_encapsulated_proto; } if (!eth_type_vlan(protocol)) return false; return true; } /** * vlan_features_check - drop unsafe features for skb with multiple tags. * @skb: skbuff to query * @features: features to be checked * * Returns: features without unsafe ones if the skb has multiple tags. */ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tagged_multi(skb)) { /* In the case of multi-tagged packets, use a direct mask * instead of using netdev_interesect_features(), to make * sure that only devices supporting NETIF_F_HW_CSUM will * have checksum offloading support. */ features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } return features; } /** * compare_vlan_header - Compare two vlan headers * @h1: Pointer to vlan header * @h2: Pointer to vlan header * * Compare two vlan headers. * * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. * * Return: 0 if equal, arbitrary non-zero value if not equal. */ static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, const struct vlan_hdr *h2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return *(u32 *)h1 ^ *(u32 *)h2; #else return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | ((__force u32)h1->h_vlan_encapsulated_proto ^ (__force u32)h2->h_vlan_encapsulated_proto); #endif } #endif /* !(_LINUX_IF_VLAN_H_) */ |
| 13 1 10 108 7 162 11 1 1 4 1 3 37 1 8 22 328 48 54 1425 48 61 289 289 1487 1771 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H #include <linux/unaligned.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_tables.h> #include <linux/u64_stats_sync.h> #include <linux/rhashtable.h> #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> #include <net/flow_offload.h> #include <net/netns/generic.h> #define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) struct module; #define NFT_JUMP_STACK_SIZE 16 enum { NFT_PKTINFO_L4PROTO = (1 << 0), NFT_PKTINFO_INNER = (1 << 1), NFT_PKTINFO_INNER_FULL = (1 << 2), }; struct nft_pktinfo { struct sk_buff *skb; const struct nf_hook_state *state; u8 flags; u8 tprot; u16 fragoff; u16 thoff; u16 inneroff; }; static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) { return pkt->state->sk; } static inline unsigned int nft_thoff(const struct nft_pktinfo *pkt) { return pkt->thoff; } static inline struct net *nft_net(const struct nft_pktinfo *pkt) { return pkt->state->net; } static inline unsigned int nft_hook(const struct nft_pktinfo *pkt) { return pkt->state->hook; } static inline u8 nft_pf(const struct nft_pktinfo *pkt) { return pkt->state->pf; } static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt) { return pkt->state->in; } static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt) { return pkt->state->out; } static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, struct sk_buff *skb, const struct nf_hook_state *state) { pkt->skb = skb; pkt->state = state; } static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt) { pkt->flags = 0; pkt->tprot = 0; pkt->thoff = 0; pkt->fragoff = 0; } /** * struct nft_verdict - nf_tables verdict * * @code: nf_tables/netfilter verdict code * @chain: destination chain for NFT_JUMP/NFT_GOTO */ struct nft_verdict { u32 code; struct nft_chain *chain; }; struct nft_data { union { u32 data[4]; struct nft_verdict verdict; }; } __attribute__((aligned(__alignof__(u64)))); #define NFT_REG32_NUM 20 /** * struct nft_regs - nf_tables register set * * @data: data registers * @verdict: verdict register * * The first four data registers alias to the verdict register. */ struct nft_regs { union { u32 data[NFT_REG32_NUM]; struct nft_verdict verdict; }; }; struct nft_regs_track { struct { const struct nft_expr *selector; const struct nft_expr *bitwise; u8 num_reg; } regs[NFT_REG32_NUM]; const struct nft_expr *cur; const struct nft_expr *last; }; /* Store/load an u8, u16 or u64 integer to/from the u32 data register. * * Note, when using concatenations, register allocation happens at 32-bit * level. So for store instruction, pad the rest part with zero to avoid * garbage values. */ static inline void nft_reg_store8(u32 *dreg, u8 val) { *dreg = 0; *(u8 *)dreg = val; } static inline u8 nft_reg_load8(const u32 *sreg) { return *(u8 *)sreg; } static inline void nft_reg_store16(u32 *dreg, u16 val) { *dreg = 0; *(u16 *)dreg = val; } static inline void nft_reg_store_be16(u32 *dreg, __be16 val) { nft_reg_store16(dreg, (__force __u16)val); } static inline u16 nft_reg_load16(const u32 *sreg) { return *(u16 *)sreg; } static inline __be16 nft_reg_load_be16(const u32 *sreg) { return (__force __be16)nft_reg_load16(sreg); } static inline __be32 nft_reg_load_be32(const u32 *sreg) { return *(__force __be32 *)sreg; } static inline void nft_reg_store64(u64 *dreg, u64 val) { put_unaligned(val, dreg); } static inline u64 nft_reg_load64(const u32 *sreg) { return get_unaligned((u64 *)sreg); } static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { if (len % NFT_REG32_SIZE) dst[len / NFT_REG32_SIZE] = 0; memcpy(dst, src, len); } /** * struct nft_ctx - nf_tables rule/set context * * @net: net namespace * @table: the table the chain is contained in * @chain: the chain the rule is contained in * @nla: netlink attributes * @portid: netlink portID of the original message * @seq: netlink sequence number * @flags: modifiers to new request * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message * @reg_inited: bitmap of initialised registers */ struct nft_ctx { struct net *net; struct nft_table *table; struct nft_chain *chain; const struct nlattr * const *nla; u32 portid; u32 seq; u16 flags; u8 family; u8 level; bool report; DECLARE_BITMAP(reg_inited, NFT_REG32_NUM); }; enum nft_data_desc_flags { NFT_DATA_DESC_SETELEM = (1 << 0), }; struct nft_data_desc { enum nft_data_types type; unsigned int size; unsigned int len; unsigned int flags; }; int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla); void nft_data_hold(const struct nft_data *data, enum nft_data_types type); void nft_data_release(const struct nft_data *data, enum nft_data_types type); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, enum nft_data_types type, unsigned int len); static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg) { return reg == NFT_REG_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; } static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) { return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE; } int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); int nft_parse_register_load(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *sreg, u32 len); 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); /** * struct nft_userdata - user defined data associated with an object * * @len: length of the data * @data: content * * The presence of user data is indicated in an object specific fashion, * so a length of zero can't occur and the value "len" indicates data * of length len + 1. */ struct nft_userdata { u8 len; unsigned char data[]; }; /* placeholder structure for opaque set element backend representation. */ struct nft_elem_priv { }; /** * struct nft_set_elem - generic representation of set elements * * @key: element key * @key_end: closing element key * @data: element data * @priv: element private data and extensions */ struct nft_set_elem { union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } key; union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } key_end; union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } data; struct nft_elem_priv *priv; }; static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) { return (void *)priv; } /** * enum nft_iter_type - nftables set iterator type * * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state */ enum nft_iter_type { NFT_ITER_UNSPEC, NFT_ITER_READ, NFT_ITER_UPDATE, }; struct nft_set; struct nft_set_iter { u8 genmask; enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; int (*fn)(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv); }; /** * struct nft_set_desc - description of set elements * * @ktype: key type * @klen: key length * @dtype: data type * @dlen: data length * @objtype: object type * @size: number of set elements * @policy: set policy * @gc_int: garbage collector interval * @timeout: element timeout * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @expr: set must support for expressions */ struct nft_set_desc { u32 ktype; unsigned int klen; u32 dtype; unsigned int dlen; u32 objtype; unsigned int size; u32 policy; u32 gc_int; u64 timeout; u8 field_len[NFT_REG32_COUNT]; u8 field_count; bool expr; }; /** * enum nft_set_class - performance class * * @NFT_SET_CLASS_O_1: constant, O(1) * @NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N) * @NFT_SET_CLASS_O_N: linear, O(N) */ enum nft_set_class { NFT_SET_CLASS_O_1, NFT_SET_CLASS_O_LOG_N, NFT_SET_CLASS_O_N, }; /** * struct nft_set_estimate - estimation of memory and performance * characteristics * * @size: required memory * @lookup: lookup performance class * @space: memory class */ struct nft_set_estimate { u64 size; enum nft_set_class lookup; enum nft_set_class space; }; #define NFT_EXPR_MAXATTR 16 #define NFT_EXPR_SIZE(size) (sizeof(struct nft_expr) + \ ALIGN(size, __alignof__(struct nft_expr))) /** * struct nft_expr - nf_tables expression * * @ops: expression ops * @data: expression private data */ struct nft_expr { const struct nft_expr_ops *ops; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_expr_priv(const struct nft_expr *expr) { return (void *)expr->data; } struct nft_expr_info; int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info); int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr, bool reset); bool nft_expr_reduce_bitwise(struct nft_regs_track *track, const struct nft_expr *expr); struct nft_set_ext; /** * struct nft_set_ops - nf_tables set operations * * @lookup: look up an element within the set * @update: update an element if exists, add it if doesn't exist * @delete: delete an element * @insert: insert new element into set * @activate: activate new element in the next generation * @deactivate: lookup for element and deactivate it in the next generation * @flush: deactivate element in the next generation * @remove: remove element from set * @walk: iterate over all set elements * @get: get set elements * @ksize: kernel set size * @usize: userspace set size * @adjust_maxsize: delta to adjust maximum set size * @commit: commit set elements * @abort: abort set elements * @privsize: function to return size of set private data * @estimate: estimate the required memory size and the lookup complexity class * @init: initialize private data of new set instance * @destroy: destroy private data of set instance * @gc_init: initialize garbage collection * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster * and currently only used in the packet path. All the rest are slower, * control plane functions. */ struct nft_set_ops { bool (*lookup)(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool (*update)(struct nft_set *set, const u32 *key, struct nft_elem_priv * (*new)(struct nft_set *, const struct nft_expr *, struct nft_regs *), const struct nft_expr *expr, struct nft_regs *regs, const struct nft_set_ext **ext); bool (*delete)(const struct nft_set *set, const u32 *key); int (*insert)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **priv); void (*activate)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); struct nft_elem_priv * (*deactivate)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem); void (*flush)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *priv); void (*remove)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); void (*walk)(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter); struct nft_elem_priv * (*get)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); u32 (*ksize)(u32 size); u32 (*usize)(u32 size); u32 (*adjust_maxsize)(const struct nft_set *set); void (*commit)(struct nft_set *set); void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); void (*destroy)(const struct nft_ctx *ctx, const struct nft_set *set); void (*gc_init)(const struct nft_set *set); unsigned int elemsize; }; /** * struct nft_set_type - nf_tables set type * * @ops: set ops for this type * @features: features supported by the implementation */ struct nft_set_type { const struct nft_set_ops ops; u32 features; }; #define to_set_type(o) container_of(o, struct nft_set_type, ops) struct nft_set_elem_expr { u8 size; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; #define nft_setelem_expr_at(__elem_expr, __offset) \ ((struct nft_expr *)&__elem_expr->data[__offset]) #define nft_setelem_expr_foreach(__expr, __elem_expr, __size) \ for (__expr = nft_setelem_expr_at(__elem_expr, 0), __size = 0; \ __size < (__elem_expr)->size; \ __size += (__expr)->ops->size, __expr = ((void *)(__expr)) + (__expr)->ops->size) #define NFT_SET_EXPR_MAX 2 /** * struct nft_set - nf_tables set instance * * @list: table set list node * @bindings: list of set bindings * @refs: internal refcounting for async set destruction * @table: table this set belongs to * @net: netnamespace this set belongs to * @name: name of the set * @handle: unique handle of the set * @ktype: key type (numeric type defined by userspace, not used in the kernel) * @dtype: data type (verdict or numeric type defined by userspace) * @objtype: object type (see NFT_OBJECT_* definitions) * @size: maximum set size * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @use: number of rules references to this set * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length * @udata: user data * @pending_update: list of pending update set element * @ops: set ops * @flags: set flags * @dead: set will be freed, never cleared * @genmask: generation mask * @klen: key length * @dlen: data length * @num_exprs: numbers of exprs * @exprs: stateful expression * @catchall_list: list of catch-all set element * @data: private set data */ struct nft_set { struct list_head list; struct list_head bindings; refcount_t refs; struct nft_table *table; possible_net_t net; char *name; u64 handle; u32 ktype; u32 dtype; u32 objtype; u32 size; u8 field_len[NFT_REG32_COUNT]; u8 field_count; u32 use; atomic_t nelems; u32 ndeact; u64 timeout; u32 gc_int; u16 policy; u16 udlen; unsigned char *udata; struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; u16 flags:13, dead:1, genmask:2; u8 klen; u8 dlen; u8 num_exprs; struct nft_expr *exprs[NFT_SET_EXPR_MAX]; struct list_head catchall_list; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline bool nft_set_is_anonymous(const struct nft_set *set) { return set->flags & NFT_SET_ANONYMOUS; } static inline void *nft_set_priv(const struct nft_set *set) { return (void *)set->data; } static inline enum nft_data_types nft_set_datatype(const struct nft_set *set) { return set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; } static inline bool nft_set_gc_is_pending(const struct nft_set *s) { return refcount_read(&s->refs) != 1; } static inline struct nft_set *nft_set_container_of(const void *priv) { return (void *)priv - offsetof(struct nft_set, data); } 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_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { u32 gc_int = READ_ONCE(set->gc_int); return gc_int ? msecs_to_jiffies(gc_int) : HZ; } /** * struct nft_set_binding - nf_tables set binding * * @list: set bindings list node * @chain: chain containing the rule bound to the set * @flags: set action flags * * A set binding contains all information necessary for validation * of new elements added to a bound set. */ struct nft_set_binding { struct list_head list; const struct nft_chain *chain; u32 flags; }; enum nft_trans_phase; void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *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); int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** * enum nft_set_extensions - set extension type IDs * * @NFT_SET_EXT_KEY: element key * @NFT_SET_EXT_KEY_END: upper bound element key, for ranges * @NFT_SET_EXT_DATA: mapping data * @NFT_SET_EXT_FLAGS: element flags * @NFT_SET_EXT_TIMEOUT: element timeout * @NFT_SET_EXT_USERDATA: user data associated with the element * @NFT_SET_EXT_EXPRESSIONS: expressions associated with the element * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ enum nft_set_extensions { NFT_SET_EXT_KEY, NFT_SET_EXT_KEY_END, NFT_SET_EXT_DATA, NFT_SET_EXT_FLAGS, NFT_SET_EXT_TIMEOUT, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPRESSIONS, NFT_SET_EXT_OBJREF, NFT_SET_EXT_NUM }; /** * struct nft_set_ext_type - set extension type * * @len: fixed part length of the extension * @align: alignment requirements of the extension */ struct nft_set_ext_type { u8 len; u8 align; }; extern const struct nft_set_ext_type nft_set_ext_types[]; /** * struct nft_set_ext_tmpl - set extension template * * @len: length of extension area * @offset: offsets of individual extension types * @ext_len: length of the expected extension(used to sanity check) */ struct nft_set_ext_tmpl { u16 len; u8 offset[NFT_SET_EXT_NUM]; u8 ext_len[NFT_SET_EXT_NUM]; }; /** * struct nft_set_ext - set extensions * * @genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT) * @offset: offsets of individual extension types * @data: beginning of extension data * * This structure must be aligned to word size, otherwise atomic bitops * on genmask field can cause alignment failure on some archs. */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; } __aligned(BITS_PER_LONG / 8); static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { memset(tmpl, 0, sizeof(*tmpl)); tmpl->len = sizeof(struct nft_set_ext); } static inline int nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, unsigned int len) { tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); if (tmpl->len > U8_MAX) return -EINVAL; tmpl->offset[id] = tmpl->len; tmpl->ext_len[id] = nft_set_ext_types[id].len + len; tmpl->len += tmpl->ext_len[id]; return 0; } static inline int nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) { return nft_set_ext_add_length(tmpl, id, 0); } static inline void nft_set_ext_init(struct nft_set_ext *ext, const struct nft_set_ext_tmpl *tmpl) { memcpy(ext->offset, tmpl->offset, sizeof(ext->offset)); } static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) { return !!ext->offset[id]; } static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) { return ext && __nft_set_ext_exists(ext, id); } static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id) { return (void *)ext + ext->offset[id]; } static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_KEY); } static inline struct nft_data *nft_set_ext_key_end(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_KEY_END); } static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_DATA); } static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_FLAGS); } struct nft_timeout { u64 timeout; u64 expiration; }; static inline struct nft_timeout *nft_set_ext_timeout(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); } static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_USERDATA); } static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS); } static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, u64 tstamp) { if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) || READ_ONCE(nft_set_ext_timeout(ext)->timeout) == 0) return false; return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration)); } static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) { return __nft_set_elem_expired(ext, get_jiffies_64()); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, const struct nft_elem_priv *elem_priv) { return (void *)elem_priv + set->ops->elemsize; } static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_OBJREF); } struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr); 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); int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); void nft_set_elem_destroy(const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool destroy_expr); 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_expr_ops; /** * struct nft_expr_type - nf_tables expression type * * @select_ops: function to select nft_expr_ops * @release_ops: release nft_expr_ops * @ops: default ops, used when no select_ops functions is present * @inner_ops: inner ops, used for inner packet operation * @list: used internally * @name: Identifier * @owner: module reference * @policy: netlink attribute policy * @maxattr: highest netlink attribute number * @family: address family for AF-specific types * @flags: expression type flags */ struct nft_expr_type { const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *, const struct nlattr * const tb[]); void (*release_ops)(const struct nft_expr_ops *ops); const struct nft_expr_ops *ops; const struct nft_expr_ops *inner_ops; struct list_head list; const char *name; struct module *owner; const struct nla_policy *policy; unsigned int maxattr; u8 family; u8 flags; }; #define NFT_EXPR_STATEFUL 0x1 #define NFT_EXPR_GC 0x2 enum nft_trans_phase { NFT_TRANS_PREPARE, NFT_TRANS_PREPARE_ERROR, NFT_TRANS_ABORT, NFT_TRANS_COMMIT, NFT_TRANS_RELEASE }; struct nft_flow_rule; struct nft_offload_ctx; /** * struct nft_expr_ops - nf_tables expression operations * * @eval: Expression evaluation function * @clone: Expression clone function * @size: full expression size, including private data size * @init: initialization function * @activate: activate expression in the next generation * @deactivate: deactivate expression in next generation * @destroy: destruction function, called after synchronize_rcu * @destroy_clone: destruction clone function * @dump: function to dump parameters * @validate: validate expression, called during loop detection * @reduce: reduce expression * @gc: garbage collection expression * @offload: hardware offload expression * @offload_action: function to report true/false to allocate one slot or not in the flow * offload array * @offload_stats: function to synchronize hardware stats via updating the counter expression * @type: expression type * @data: extra data to attach to this expression operation */ struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); int (*clone)(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp); unsigned int size; int (*init)(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); void (*activate)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*deactivate)(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase); void (*destroy)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*destroy_clone)(const struct nft_ctx *ctx, const struct nft_expr *expr); int (*dump)(struct sk_buff *skb, const struct nft_expr *expr, bool reset); int (*validate)(const struct nft_ctx *ctx, const struct nft_expr *expr); bool (*reduce)(struct nft_regs_track *track, const struct nft_expr *expr); bool (*gc)(struct net *net, const struct nft_expr *expr); int (*offload)(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr); bool (*offload_action)(const struct nft_expr *expr); void (*offload_stats)(struct nft_expr *expr, const struct flow_stats *stats); const struct nft_expr_type *type; void *data; }; /** * struct nft_rule - nf_tables rule * * @list: used internally * @handle: rule handle * @genmask: generation mask * @dlen: length of expression data * @udata: user data is appended to the rule * @data: expression data */ struct nft_rule { struct list_head list; u64 handle:42, genmask:2, dlen:12, udata:1; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[0]; } static inline struct nft_expr *nft_expr_next(const struct nft_expr *expr) { return ((void *)expr) + expr->ops->size; } static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[rule->dlen]; } static inline bool nft_expr_more(const struct nft_rule *rule, const struct nft_expr *expr) { return expr != nft_expr_last(rule) && expr->ops; } static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) { return (void *)&rule->data[rule->dlen]; } void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, enum nft_trans_phase phase); void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule); static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_set_elem_expr *elem_expr; struct nft_expr *expr; u32 size; if (__nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) { elem_expr = nft_set_ext_expr(ext); nft_setelem_expr_foreach(expr, elem_expr, size) { expr->ops->eval(expr, regs, pkt); if (regs->verdict.code == NFT_BREAK) return; } } } /* * The last pointer isn't really necessary, but the compiler isn't able to * determine that the result of nft_expr_last() is always the same since it * can't assume that the dlen value wasn't changed within calls in the loop. */ #define nft_rule_for_each_expr(expr, last, rule) \ for ((expr) = nft_expr_first(rule), (last) = nft_expr_last(rule); \ (expr) != (last); \ (expr) = nft_expr_next(expr)) #define NFT_CHAIN_POLICY_UNSET U8_MAX struct nft_rule_dp { u64 is_last:1, dlen:12, handle:42; /* for tracing */ unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; struct nft_rule_dp_last { struct nft_rule_dp end; /* end of nft_rule_blob marker */ struct rcu_head h; /* call_rcu head */ struct nft_rule_blob *blob; /* ptr to free via call_rcu */ const struct nft_chain *chain; /* for nftables tracing */ }; static inline const struct nft_rule_dp *nft_rule_next(const struct nft_rule_dp *rule) { return (void *)rule + sizeof(*rule) + rule->dlen; } struct nft_rule_blob { unsigned long size; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_rule_dp)))); }; /** * struct nft_chain - nf_tables chain * * @blob_gen_0: rule blob pointer to the current generation * @blob_gen_1: rule blob pointer to the future generation * @rules: list of rules in the chain * @list: used internally * @rhlhead: used internally * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain * @flags: bitmask of enum NFTA_CHAIN_FLAGS * @bound: bind or not * @genmask: generation mask * @name: name of the chain * @udlen: user data length * @udata: user data in the chain * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; struct nft_rule_blob __rcu *blob_gen_1; struct list_head rules; struct list_head list; struct rhlist_head rhlhead; struct nft_table *table; u64 handle; u32 use; u8 flags:5, bound:1, genmask:2; char *name; u16 udlen; u8 *udata; /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); 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); int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); struct nft_hook; void nf_tables_chain_device_notify(const struct nft_chain *chain, const struct nft_hook *hook, const struct net_device *dev, int event); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, NFT_CHAIN_T_ROUTE, NFT_CHAIN_T_NAT, NFT_CHAIN_T_MAX }; /** * struct nft_chain_type - nf_tables chain type info * * @name: name of the type * @type: numeric identifier * @family: address family * @owner: module owner * @hook_mask: mask of valid hooks * @hooks: array of hook functions * @ops_register: base chain register function * @ops_unregister: base chain unregister function */ struct nft_chain_type { const char *name; enum nft_chain_types type; int family; struct module *owner; unsigned int hook_mask; nf_hookfn *hooks[NFT_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); }; int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_types type); int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); static inline bool nft_chain_binding(const struct nft_chain *chain) { return chain->flags & NFT_CHAIN_BINDING; } static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; } int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_chain *chain); struct nft_stats { u64 bytes; u64 pkts; struct u64_stats_sync syncp; }; struct nft_hook { struct list_head list; struct list_head ops_list; struct rcu_head rcu; char ifname[IFNAMSIZ]; u8 ifnamelen; }; struct nf_hook_ops *nft_hook_find_ops(const struct nft_hook *hook, const struct net_device *dev); struct nf_hook_ops *nft_hook_find_ops_rcu(const struct nft_hook *hook, const struct net_device *dev); /** * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops * @hook_list: list of netfilter hooks (for NFPROTO_NETDEV family) * @type: chain type * @policy: default policy * @flags: indicate the base chain disabled or not * @stats: per-cpu chain stats * @chain: the chain * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; struct list_head hook_list; const struct nft_chain_type *type; u8 policy; u8 flags; struct nft_stats __percpu *stats; struct nft_chain chain; struct flow_block flow_block; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) { return container_of(chain, struct nft_base_chain, chain); } static inline bool nft_is_base_chain(const struct nft_chain *chain) { return chain->flags & NFT_CHAIN_BASE; } unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); static inline bool nft_use_inc(u32 *use) { if (*use == UINT_MAX) return false; (*use)++; return true; } static inline void nft_use_dec(u32 *use) { WARN_ON_ONCE((*use)-- == 0); } /* For error and abort path: restore use counter to previous state. */ static inline void nft_use_inc_restore(u32 *use) { WARN_ON_ONCE(!nft_use_inc(use)); } #define nft_use_dec_restore nft_use_dec /** * struct nft_table - nf_tables table * * @list: used internally * @chains_ht: chains in the table * @chains: same, for stable walks * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table * @family:address family * @flags: table flag (see enum nft_table_flags) * @genmask: generation mask * @nlpid: netlink port ID * @name: name of the table * @udlen: length of the user data * @udata: user data * @validate_state: internal, set when transaction adds jumps */ struct nft_table { struct list_head list; struct rhltable chains_ht; struct list_head chains; struct list_head sets; struct list_head objects; struct list_head flowtables; u64 hgenerator; u64 handle; u32 use; u16 family:6, flags:8, genmask:2; u32 nlpid; char *name; u16 udlen; u8 *udata; u8 validate_state; }; static inline bool nft_table_has_owner(const struct nft_table *table) { return table->flags & NFT_TABLE_F_OWNER; } static inline bool nft_table_is_orphan(const struct nft_table *table) { return (table->flags & (NFT_TABLE_F_OWNER | NFT_TABLE_F_PERSIST)) == NFT_TABLE_F_PERSIST; } static inline bool nft_base_chain_netdev(int family, u32 hooknum) { return family == NFPROTO_NETDEV || (family == NFPROTO_INET && hooknum == NF_INET_INGRESS); } void nft_register_chain_type(const struct nft_chain_type *); void nft_unregister_chain_type(const struct nft_chain_type *); int nft_register_expr(struct nft_expr_type *); void nft_unregister_expr(struct nft_expr_type *); int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v); /** * struct nft_object_hash_key - key to lookup nft_object * * @name: name of the stateful object to look up * @table: table the object belongs to */ struct nft_object_hash_key { const char *name; const struct nft_table *table; }; /** * struct nft_object - nf_tables stateful object * * @list: table stateful object list node * @rhlhead: nft_objname_ht node * @key: keys that identify this object * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle * @udlen: length of user data * @udata: user data * @ops: object operations * @data: object data, layout depends on type */ struct nft_object { struct list_head list; struct rhlist_head rhlhead; struct nft_object_hash_key key; u32 genmask:2; u32 use; u64 handle; u16 udlen; u8 *udata; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_obj_data(const struct nft_object *obj) { return (void *)obj->data; } #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) struct nft_object *nft_obj_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); 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 nft_object_type - stateful object type * * @select_ops: function to select nft_object_ops * @ops: default ops, used when no select_ops functions is present * @list: list node in list of object types * @type: stateful object numeric type * @owner: module owner * @maxattr: maximum netlink attribute * @family: address family for AF-specific object types * @policy: netlink attribute policy */ struct nft_object_type { const struct nft_object_ops *(*select_ops)(const struct nft_ctx *, const struct nlattr * const tb[]); const struct nft_object_ops *ops; struct list_head list; u32 type; unsigned int maxattr; u8 family; struct module *owner; const struct nla_policy *policy; }; /** * struct nft_object_ops - stateful object operations * * @eval: stateful object evaluation function * @size: stateful object size * @init: initialize object from netlink attributes * @destroy: release existing stateful object * @dump: netlink dump stateful object * @update: update stateful object * @type: pointer to object type */ struct nft_object_ops { void (*eval)(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt); unsigned int size; int (*init)(const struct nft_ctx *ctx, const struct nlattr *const tb[], struct nft_object *obj); void (*destroy)(const struct nft_ctx *ctx, struct nft_object *obj); int (*dump)(struct sk_buff *skb, struct nft_object *obj, bool reset); void (*update)(struct nft_object *obj, struct nft_object *newobj); const struct nft_object_type *type; }; int nft_register_obj(struct nft_object_type *obj_type); void nft_unregister_obj(struct nft_object_type *obj_type); #define NFT_NETDEVICE_MAX 256 /** * struct nft_flowtable - nf_tables flow table * * @list: flow table list node in table list * @table: the table the flow table is contained in * @name: name of this flow table * @hooknum: hook number * @ops_len: number of hooks in array * @genmask: generation mask * @use: number of references to this flow table * @handle: unique object handle * @hook_list: hook list for hooks per net_device in flowtables * @data: rhashtable and garbage collector */ struct nft_flowtable { struct list_head list; struct nft_table *table; char *name; int hooknum; int ops_len; u32 genmask:2; u32 use; u64 handle; /* runtime data below here */ struct list_head hook_list ____cacheline_aligned; struct nf_flowtable data; }; struct nft_flowtable *nft_flowtable_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask); void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, struct nft_flowtable *flowtable, enum nft_trans_phase phase); void nft_register_flowtable_type(struct nf_flowtable_type *type); void nft_unregister_flowtable_type(struct nf_flowtable_type *type); /** * struct nft_traceinfo - nft tracing information and state * * @trace: other struct members are initialised * @nf_trace: copy of skb->nf_trace before rule evaluation * @type: event type (enum nft_trace_types) * @skbid: hash of skb to be used as trace id * @packet_dumped: packet headers sent in a previous traceinfo message * @basechain: base chain currently processed */ struct nft_traceinfo { bool trace; bool nf_trace; bool packet_dumped; enum nft_trace_types type:8; u32 skbid; const struct nft_base_chain *basechain; }; void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, const struct nft_chain *basechain); void nft_trace_notify(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ MODULE_ALIAS("nft-chain-" __stringify(family) "-" name) #define MODULE_ALIAS_NFT_AF_EXPR(family, name) \ MODULE_ALIAS("nft-expr-" __stringify(family) "-" name) #define MODULE_ALIAS_NFT_EXPR(name) \ MODULE_ALIAS("nft-expr-" name) #define MODULE_ALIAS_NFT_OBJ(type) \ MODULE_ALIAS("nft-obj-" __stringify(type)) #if IS_ENABLED(CONFIG_NF_TABLES) /* * The gencursor defines two generations, the currently active and the * next one. Objects contain a bitmask of 2 bits specifying the generations * they're active in. A set bit means they're inactive in the generation * represented by that bit. * * New objects start out as inactive in the current and active in the * next generation. When committing the ruleset the bitmask is cleared, * meaning they're active in all generations. When removing an object, * it is set inactive in the next generation. After committing the ruleset, * the objects are removed. */ static inline unsigned int nft_gencursor_next(const struct net *net) { return net->nft.gencursor + 1 == 1 ? 1 : 0; } static inline u8 nft_genmask_next(const struct net *net) { return 1 << nft_gencursor_next(net); } static inline u8 nft_genmask_cur(const struct net *net) { /* Use READ_ONCE() to prevent refetching the value for atomicity */ return 1 << READ_ONCE(net->nft.gencursor); } #define NFT_GENMASK_ANY ((1 << 0) | (1 << 1)) /* * Generic transaction helpers */ /* Check if this object is currently active. */ #define nft_is_active(__net, __obj) \ (((__obj)->genmask & nft_genmask_cur(__net)) == 0) /* Check if this object is active in the next generation. */ #define nft_is_active_next(__net, __obj) \ (((__obj)->genmask & nft_genmask_next(__net)) == 0) /* This object becomes active in the next generation. */ #define nft_activate_next(__net, __obj) \ (__obj)->genmask = nft_genmask_cur(__net) /* This object becomes inactive in the next generation. */ #define nft_deactivate_next(__net, __obj) \ (__obj)->genmask = nft_genmask_next(__net) /* After committing the ruleset, clear the stale generation bit. */ #define nft_clear(__net, __obj) \ (__obj)->genmask &= ~nft_genmask_next(__net) #define nft_active_genmask(__obj, __genmask) \ !((__obj)->genmask & __genmask) /* * Set element transaction helpers */ static inline bool nft_set_elem_active(const struct nft_set_ext *ext, u8 genmask) { return !(ext->genmask & genmask); } static inline void nft_set_elem_change_active(const struct net *net, const struct nft_set *set, struct nft_set_ext *ext) { ext->genmask ^= nft_genmask_next(net); } #endif /* IS_ENABLED(CONFIG_NF_TABLES) */ #define NFT_SET_ELEM_DEAD_MASK (1 << 2) #if defined(__LITTLE_ENDIAN_BITFIELD) #define NFT_SET_ELEM_DEAD_BIT 2 #elif defined(__BIG_ENDIAN_BITFIELD) #define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) #else #error #endif static inline void nft_set_elem_dead(struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); set_bit(NFT_SET_ELEM_DEAD_BIT, word); } static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); return test_bit(NFT_SET_ELEM_DEAD_BIT, word); } /** * struct nft_trans - nf_tables object update in transaction * * @list: used internally * @net: struct net * @table: struct nft_table the object resides in * @msg_type: message type * @seq: netlink sequence number * @flags: modifiers to new request * @report: notify via unicast netlink message * @put_net: net needs to be put * * This is the information common to all objects in the transaction, * this must always be the first member of derived sub-types. */ struct nft_trans { struct list_head list; struct net *net; struct nft_table *table; int msg_type; u32 seq; u16 flags; u8 report:1; u8 put_net:1; }; /** * struct nft_trans_binding - nf_tables object with binding support in transaction * @nft_trans: base structure, MUST be first member * @binding_list: list of objects with possible bindings * * This is the base type used by objects that can be bound to a chain. */ struct nft_trans_binding { struct nft_trans nft_trans; struct list_head binding_list; }; struct nft_trans_rule { struct nft_trans nft_trans; struct nft_rule *rule; struct nft_chain *chain; struct nft_flow_rule *flow; u32 rule_id; bool bound; }; #define nft_trans_container_rule(trans) \ container_of(trans, struct nft_trans_rule, nft_trans) #define nft_trans_rule(trans) \ nft_trans_container_rule(trans)->rule #define nft_trans_flow_rule(trans) \ nft_trans_container_rule(trans)->flow #define nft_trans_rule_id(trans) \ nft_trans_container_rule(trans)->rule_id #define nft_trans_rule_bound(trans) \ nft_trans_container_rule(trans)->bound #define nft_trans_rule_chain(trans) \ nft_trans_container_rule(trans)->chain struct nft_trans_set { struct nft_trans_binding nft_trans_binding; struct list_head list_trans_newset; struct nft_set *set; u32 set_id; u32 gc_int; u64 timeout; bool update; bool bound; u32 size; }; #define nft_trans_container_set(t) \ container_of(t, struct nft_trans_set, nft_trans_binding.nft_trans) #define nft_trans_set(trans) \ nft_trans_container_set(trans)->set #define nft_trans_set_id(trans) \ nft_trans_container_set(trans)->set_id #define nft_trans_set_bound(trans) \ nft_trans_container_set(trans)->bound #define nft_trans_set_update(trans) \ nft_trans_container_set(trans)->update #define nft_trans_set_timeout(trans) \ nft_trans_container_set(trans)->timeout #define nft_trans_set_gc_int(trans) \ nft_trans_container_set(trans)->gc_int #define nft_trans_set_size(trans) \ nft_trans_container_set(trans)->size struct nft_trans_chain { struct nft_trans_binding nft_trans_binding; struct nft_chain *chain; char *name; struct nft_stats __percpu *stats; u8 policy; bool update; bool bound; u32 chain_id; struct nft_base_chain *basechain; struct list_head hook_list; }; #define nft_trans_container_chain(t) \ container_of(t, struct nft_trans_chain, nft_trans_binding.nft_trans) #define nft_trans_chain(trans) \ nft_trans_container_chain(trans)->chain #define nft_trans_chain_update(trans) \ nft_trans_container_chain(trans)->update #define nft_trans_chain_name(trans) \ nft_trans_container_chain(trans)->name #define nft_trans_chain_stats(trans) \ nft_trans_container_chain(trans)->stats #define nft_trans_chain_policy(trans) \ nft_trans_container_chain(trans)->policy #define nft_trans_chain_bound(trans) \ nft_trans_container_chain(trans)->bound #define nft_trans_chain_id(trans) \ nft_trans_container_chain(trans)->chain_id #define nft_trans_basechain(trans) \ nft_trans_container_chain(trans)->basechain #define nft_trans_chain_hooks(trans) \ nft_trans_container_chain(trans)->hook_list struct nft_trans_table { struct nft_trans nft_trans; bool update; }; #define nft_trans_container_table(trans) \ container_of(trans, struct nft_trans_table, nft_trans) #define nft_trans_table_update(trans) \ nft_trans_container_table(trans)->update enum nft_trans_elem_flags { NFT_TRANS_UPD_TIMEOUT = (1 << 0), NFT_TRANS_UPD_EXPIRATION = (1 << 1), }; struct nft_elem_update { u64 timeout; u64 expiration; u8 flags; }; struct nft_trans_one_elem { struct nft_elem_priv *priv; struct nft_elem_update *update; }; struct nft_trans_elem { struct nft_trans nft_trans; struct nft_set *set; bool bound; unsigned int nelems; struct nft_trans_one_elem elems[] __counted_by(nelems); }; #define nft_trans_container_elem(t) \ container_of(t, struct nft_trans_elem, nft_trans) #define nft_trans_elem_set(trans) \ nft_trans_container_elem(trans)->set #define nft_trans_elem_set_bound(trans) \ nft_trans_container_elem(trans)->bound struct nft_trans_obj { struct nft_trans nft_trans; struct nft_object *obj; struct nft_object *newobj; bool update; }; #define nft_trans_container_obj(t) \ container_of(t, struct nft_trans_obj, nft_trans) #define nft_trans_obj(trans) \ nft_trans_container_obj(trans)->obj #define nft_trans_obj_newobj(trans) \ nft_trans_container_obj(trans)->newobj #define nft_trans_obj_update(trans) \ nft_trans_container_obj(trans)->update struct nft_trans_flowtable { struct nft_trans nft_trans; struct nft_flowtable *flowtable; struct list_head hook_list; u32 flags; bool update; }; #define nft_trans_container_flowtable(t) \ container_of(t, struct nft_trans_flowtable, nft_trans) #define nft_trans_flowtable(trans) \ nft_trans_container_flowtable(trans)->flowtable #define nft_trans_flowtable_update(trans) \ nft_trans_container_flowtable(trans)->update #define nft_trans_flowtable_hooks(trans) \ nft_trans_container_flowtable(trans)->hook_list #define nft_trans_flowtable_flags(trans) \ nft_trans_container_flowtable(trans)->flags #define NFT_TRANS_GC_BATCHCOUNT 256 struct nft_trans_gc { struct list_head list; struct net *net; struct nft_set *set; u32 seq; u16 count; struct nft_elem_priv *priv[NFT_TRANS_GC_BATCHCOUNT]; struct rcu_head rcu; }; static inline void nft_ctx_update(struct nft_ctx *ctx, const struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_NEWRULE: case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: ctx->chain = nft_trans_rule_chain(trans); break; case NFT_MSG_NEWCHAIN: case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: ctx->chain = nft_trans_chain(trans); break; default: ctx->chain = NULL; break; } ctx->net = trans->net; ctx->table = trans->table; ctx->family = trans->table->family; ctx->report = trans->report; ctx->flags = trans->flags; ctx->seq = trans->seq; } struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, unsigned int gc_seq, gfp_t gfp); void nft_trans_gc_destroy(struct nft_trans_gc *trans); struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp); void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc); struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp); void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, unsigned int gc_seq); struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc); void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); void __init nft_chain_route_init(void); void nft_chain_route_fini(void); void nf_tables_trans_destroy_flush_work(struct net *net); int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); __be64 nf_jiffies64_to_msecs(u64 input); #ifdef CONFIG_MODULES __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, ...); #else static inline int nft_request_module(struct net *net, const char *fmt, ...) { return -ENOENT; } #endif struct nftables_pernet { struct list_head tables; struct list_head commit_list; struct list_head destroy_list; struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; u64 table_handle; u64 tstamp; unsigned int base_seq; unsigned int gc_seq; u8 validate_state; struct work_struct destroy_work; }; extern unsigned int nf_tables_net_id; static inline struct nftables_pernet *nft_pernet(const struct net *net) { return net_generic(net, nf_tables_net_id); } static inline u64 nft_net_tstamp(const struct net *net) { return nft_pernet(net)->tstamp; } #define __NFT_REDUCE_READONLY 1UL #define NFT_REDUCE_READONLY (void *)__NFT_REDUCE_READONLY static inline bool nft_reduce_is_readonly(const struct nft_expr *expr) { return expr->ops->reduce == NFT_REDUCE_READONLY; } void nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 len); void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len); void __nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg); static inline bool nft_reg_track_cmp(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg) { return track->regs[dreg].selector && track->regs[dreg].selector->ops == expr->ops && track->regs[dreg].num_reg == 0; } #endif /* _NET_NF_TABLES_H */ |
| 200 47 153 195 4 23 175 12 179 179 34 10 10 10 10 10 16 4 12 16 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/in6.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; if (cfg->ipv6_v6only) { err = ip6_sock_set_v6only(sock->sk); if (err < 0) goto error; } if (cfg->bind_ifindex) { err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true); if (err < 0) goto error; } udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr), 0); } if (err < 0) goto error; udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums); udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums); *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL_GPL(udp_sock_create6); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck) { struct udphdr *uh; struct ipv6hdr *ip6h; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, label); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6tunnel_xmit(sk, skb, dev); return 0; } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); /** * udp_tunnel6_dst_lookup - perform route lookup on UDP tunnel * @skb: Packet for which lookup is done * @dev: Tunnel device * @net: Network namespace of tunnel device * @sock: Socket which provides route info * @oif: Index of the output interface * @saddr: Memory to store the src ip address * @key: Tunnel information * @sport: UDP source port * @dport: UDP destination port * @dsfield: The traffic class field * @dst_cache: The dst cache to use for lookup * This function performs a route lookup on a UDP tunnel * * It returns a valid dst pointer and stores src address to be used in * tunnel in param saddr on success, else a pointer encoded error code. */ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, struct dst_cache *dst_cache) { struct dst_entry *dst = NULL; struct flowi6 fl6; #ifdef CONFIG_DST_CACHE if (dst_cache) { dst = dst_cache_get_ip6(dst_cache, saddr); if (dst) return dst; } #endif memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; fl6.flowi6_oif = oif; fl6.daddr = key->u.ipv6.dst; fl6.saddr = key->u.ipv6.src; fl6.fl6_sport = sport; fl6.fl6_dport = dport; fl6.flowlabel = ip6_make_flowinfo(dsfield, key->label); dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, NULL); if (IS_ERR(dst)) { netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); return ERR_PTR(-ENETUNREACH); } if (dst->dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); dst_release(dst); return ERR_PTR(-ELOOP); } #ifdef CONFIG_DST_CACHE if (dst_cache) dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); #endif *saddr = fl6.saddr; return dst; } EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); |
| 7 71 5 5 147 36 168 36 6 106 157 4 154 154 269 270 144 43 50 43 154 200 178 97 178 175 113 178 3 121 52 66 31 5 1 3 1 5 22 514 270 364 480 45 121 121 112 13 37 384 3 3 5 18 17 221 10 9 117 352 259 130 130 130 126 258 258 259 340 2 1 344 308 36 344 9 344 9 353 353 353 14 342 353 17 57 41 17 275 11 2 21 116 3 124 5 143 389 5 509 509 41 12 5 6 1 21 20 17 193 94 13 21 135 152 11 141 11 145 75 75 150 12 12 11 1 8 4 12 6 6 1 1 4 12 10 2 9 3 8 4 10 2 6 5 1 3 3 5 1 5 1 4 2 7 5 6 4 2 5 7 8 2 2 8 4 11 1 383 1 156 384 63 13 3 13 35 23 34 17 14 22 14 15 14 22 11 48 1 17 14 33 31 16 51 44 71 103 9 100 5 90 24 58 64 30 1 275 129 147 200 88 5 4 1 2 2 1 2 2 1 8 8 3 2 331 2 1 7 4 5 6 4 5 3 16 7 5 2 22 11 11 357 334 22 21 336 307 50 342 15 1 355 34 29 292 174 119 160 1 23 106 3 2 1 130 159 288 1 1 279 7 9 53 223 2 5 270 64 87 225 196 29 11 389 389 388 33 362 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/inode.c * * Written 1992,1993 by Werner Almesberger * VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner * Rewritten for the constant inumbers support by Al Viro * * Fixes: * * Max Cohan: Fixed invalid FSINFO offset when info_sector is 0 */ #include <linux/module.h> #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/vfs.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/unaligned.h> #include <linux/random.h> #include <linux/iversion.h> #include "fat.h" #ifndef CONFIG_FAT_DEFAULT_IOCHARSET /* if user don't select VFAT, this is undefined. */ #define CONFIG_FAT_DEFAULT_IOCHARSET "" #endif #define KB_IN_SECTORS 2 /* DOS dates from 1980/1/1 through 2107/12/31 */ #define FAT_DATE_MIN (0<<9 | 1<<5 | 1) #define FAT_DATE_MAX (127<<9 | 12<<5 | 31) #define FAT_TIME_MAX (23<<11 | 59<<5 | 29) /* * A deserialized copy of the on-disk structure laid out in struct * fat_boot_sector. */ struct fat_bios_param_block { u16 fat_sector_size; u8 fat_sec_per_clus; u16 fat_reserved; u8 fat_fats; u16 fat_dir_entries; u16 fat_sectors; u16 fat_fat_length; u32 fat_total_sect; u8 fat16_state; u32 fat16_vol_id; u32 fat32_length; u32 fat32_root_cluster; u16 fat32_info_sector; u8 fat32_state; u32 fat32_vol_id; }; static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE; static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET; static struct fat_floppy_defaults { unsigned nr_sectors; unsigned sec_per_clus; unsigned dir_entries; unsigned media; unsigned fat_length; } floppy_defaults[] = { { .nr_sectors = 160 * KB_IN_SECTORS, .sec_per_clus = 1, .dir_entries = 64, .media = 0xFE, .fat_length = 1, }, { .nr_sectors = 180 * KB_IN_SECTORS, .sec_per_clus = 1, .dir_entries = 64, .media = 0xFC, .fat_length = 2, }, { .nr_sectors = 320 * KB_IN_SECTORS, .sec_per_clus = 2, .dir_entries = 112, .media = 0xFF, .fat_length = 1, }, { .nr_sectors = 360 * KB_IN_SECTORS, .sec_per_clus = 2, .dir_entries = 112, .media = 0xFD, .fat_length = 2, }, }; int fat_add_cluster(struct inode *inode) { int err, cluster; err = fat_alloc_clusters(inode, &cluster, 1); if (err) return err; /* FIXME: this cluster should be added after data of this * cluster is writed */ err = fat_chain_add(inode, cluster, 1); if (err) fat_free_clusters(inode, cluster); return err; } static inline int __fat_get_block(struct inode *inode, sector_t iblock, unsigned long *max_blocks, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); unsigned long mapped_blocks; sector_t phys, last_block; int err, offset; err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (phys) { map_bh(bh_result, sb, phys); *max_blocks = min(mapped_blocks, *max_blocks); return 0; } if (!create) return 0; if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) { fat_fs_error(sb, "corrupted file size (i_pos %lld, %lld)", MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); return -EIO; } last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9); offset = (unsigned long)iblock & (sbi->sec_per_clus - 1); /* * allocate a cluster according to the following. * 1) no more available blocks * 2) not part of fallocate region */ if (!offset && !(iblock < last_block)) { /* TODO: multiple cluster allocation would be desirable. */ err = fat_add_cluster(inode); if (err) return err; } /* available blocks on this cluster */ mapped_blocks = sbi->sec_per_clus - offset; *max_blocks = min(mapped_blocks, *max_blocks); MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits; err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (!phys) { fat_fs_error(sb, "invalid FAT chain (i_pos %lld, last_block %llu)", MSDOS_I(inode)->i_pos, (unsigned long long)last_block); return -EIO; } BUG_ON(*max_blocks != mapped_blocks); set_buffer_new(bh_result); map_bh(bh_result, sb, phys); return 0; } static int fat_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; int err; err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create); if (err) return err; bh_result->b_size = max_blocks << sb->s_blocksize_bits; return 0; } static int fat_writepages(struct address_space *mapping, struct writeback_control *wbc) { return mpage_writepages(mapping, wbc, fat_get_block); } static int fat_read_folio(struct file *file, struct folio *folio) { return mpage_read_folio(folio, fat_get_block); } static void fat_readahead(struct readahead_control *rac) { mpage_readahead(rac, fat_get_block); } static void fat_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; if (to > inode->i_size) { truncate_pagecache(inode, inode->i_size); fat_truncate_blocks(inode, inode->i_size); } } static int fat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int err; err = cont_write_begin(file, mapping, pos, len, foliop, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); if (err < 0) fat_write_failed(mapping, pos + len); return err; } static int fat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int err; err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata); if (err < len) fat_write_failed(mapping, pos + len); if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); MSDOS_I(inode)->i_attrs |= ATTR_ARCH; mark_inode_dirty(inode); } return err; } static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; ssize_t ret; if (iov_iter_rw(iter) == WRITE) { /* * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), * so we need to update the ->mmu_private to block boundary. * * But we must fill the remaining area or hole by nul for * updating ->mmu_private. * * Return 0, and fallback to normal buffered write. */ loff_t size = offset + count; if (MSDOS_I(inode)->mmu_private < size) return 0; } /* * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) fat_write_failed(mapping, offset + count); return ret; } static int fat_get_block_bmap(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; int err; sector_t bmap; unsigned long mapped_blocks; BUG_ON(create != 0); err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true); if (err) return err; if (bmap) { map_bh(bh_result, sb, bmap); max_blocks = min(mapped_blocks, max_blocks); } bh_result->b_size = max_blocks << sb->s_blocksize_bits; return 0; } static sector_t _fat_bmap(struct address_space *mapping, sector_t block) { sector_t blocknr; /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ down_read(&MSDOS_I(mapping->host)->truncate_lock); blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap); up_read(&MSDOS_I(mapping->host)->truncate_lock); return blocknr; } /* * fat_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This is required during truncate to physically zeroout the tail end * of that block so it doesn't yield old data if the file is later grown. * Also, avoid causing failure from fsx for cases of "data past EOF" */ int fat_block_truncate_page(struct inode *inode, loff_t from) { return block_truncate_page(inode->i_mapping, from, fat_get_block); } static const struct address_space_operations fat_aops = { .dirty_folio = block_dirty_folio, .invalidate_folio = block_invalidate_folio, .read_folio = fat_read_folio, .readahead = fat_readahead, .writepages = fat_writepages, .write_begin = fat_write_begin, .write_end = fat_write_end, .direct_IO = fat_direct_IO, .bmap = _fat_bmap, .migrate_folio = buffer_migrate_folio, }; /* * New FAT inode stuff. We do the following: * a) i_ino is constant and has nothing with on-disk location. * b) FAT manages its own cache of directory entries. * c) *This* cache is indexed by on-disk location. * d) inode has an associated directory entry, all right, but * it may be unhashed. * e) currently entries are stored within struct inode. That should * change. * f) we deal with races in the following way: * 1. readdir() and lookup() do FAT-dir-cache lookup. * 2. rename() unhashes the F-d-c entry and rehashes it in * a new place. * 3. unlink() and rmdir() unhash F-d-c entry. * 4. fat_write_inode() checks whether the thing is unhashed. * If it is we silently return. If it isn't we do bread(), * check if the location is still valid and retry if it * isn't. Otherwise we do changes. * 5. Spinlock is used to protect hash/unhash/location check/lookup * 6. fat_evict_inode() unhashes the F-d-c entry. * 7. lookup() and readdir() do igrab() if they find a F-d-c entry * and consider negative result as cache miss. */ static void fat_hash_init(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); int i; spin_lock_init(&sbi->inode_hash_lock); for (i = 0; i < FAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); } static inline unsigned long fat_hash(loff_t i_pos) { return hash_32(i_pos, FAT_HASH_BITS); } static void dir_hash_init(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); int i; spin_lock_init(&sbi->dir_hash_lock); for (i = 0; i < FAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->dir_hashtable[i]); } void fat_attach(struct inode *inode, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); if (inode->i_ino != MSDOS_ROOT_INO) { struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); spin_lock(&sbi->inode_hash_lock); MSDOS_I(inode)->i_pos = i_pos; hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head); spin_unlock(&sbi->inode_hash_lock); } /* If NFS support is enabled, cache the mapping of start cluster * to directory inode. This is used during reconnection of * dentries to the filesystem root. */ if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { struct hlist_head *d_head = sbi->dir_hashtable; d_head += fat_dir_hash(MSDOS_I(inode)->i_logstart); spin_lock(&sbi->dir_hash_lock); hlist_add_head(&MSDOS_I(inode)->i_dir_hash, d_head); spin_unlock(&sbi->dir_hash_lock); } } EXPORT_SYMBOL_GPL(fat_attach); void fat_detach(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); spin_lock(&sbi->inode_hash_lock); MSDOS_I(inode)->i_pos = 0; hlist_del_init(&MSDOS_I(inode)->i_fat_hash); spin_unlock(&sbi->inode_hash_lock); if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { spin_lock(&sbi->dir_hash_lock); hlist_del_init(&MSDOS_I(inode)->i_dir_hash); spin_unlock(&sbi->dir_hash_lock); } } EXPORT_SYMBOL_GPL(fat_detach); struct inode *fat_iget(struct super_block *sb, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); struct msdos_inode_info *i; struct inode *inode = NULL; spin_lock(&sbi->inode_hash_lock); hlist_for_each_entry(i, head, i_fat_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_pos != i_pos) continue; inode = igrab(&i->vfs_inode); if (inode) break; } spin_unlock(&sbi->inode_hash_lock); return inode; } static int is_exec(unsigned char *extension) { unsigned char exe_extensions[] = "EXECOMBAT", *walk; for (walk = exe_extensions; *walk; walk += 3) if (!strncmp(extension, walk, 3)) return 1; return 0; } static int fat_calc_dir_size(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int ret, fclus, dclus; inode->i_size = 0; if (MSDOS_I(inode)->i_start == 0) return 0; ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus); if (ret < 0) return ret; inode->i_size = (fclus + 1) << sbi->cluster_bits; return 0; } static int fat_validate_dir(struct inode *dir) { struct super_block *sb = dir->i_sb; if (dir->i_nlink < 2) { /* Directory should have "."/".." entries at least. */ fat_fs_error(sb, "corrupted directory (invalid entries)"); return -EIO; } if (MSDOS_I(dir)->i_start == 0 || MSDOS_I(dir)->i_start == MSDOS_SB(sb)->root_cluster) { /* Directory should point valid cluster. */ fat_fs_error(sb, "corrupted directory (invalid i_start)"); return -EIO; } return 0; } /* doesn't deal with root inode */ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); struct timespec64 mtime; int error; MSDOS_I(inode)->i_pos = 0; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = get_random_u32(); if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { inode->i_generation &= ~1; inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; MSDOS_I(inode)->i_start = fat_get_start(sbi, de); MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; error = fat_calc_dir_size(inode); if (error < 0) return error; MSDOS_I(inode)->mmu_private = inode->i_size; set_nlink(inode, fat_subdirs(inode)); error = fat_validate_dir(inode); if (error < 0) return error; } else { /* not a directory */ inode->i_generation |= 1; inode->i_mode = fat_make_mode(sbi, de->attr, ((sbi->options.showexec && !is_exec(de->name + 8)) ? S_IRUGO|S_IWUGO : S_IRWXUGO)); MSDOS_I(inode)->i_start = fat_get_start(sbi, de); MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; inode->i_size = le32_to_cpu(de->size); inode->i_op = &fat_file_inode_operations; inode->i_fop = &fat_file_operations; inode->i_mapping->a_ops = &fat_aops; MSDOS_I(inode)->mmu_private = inode->i_size; } if (de->attr & ATTR_SYS) { if (sbi->options.sys_immutable) inode->i_flags |= S_IMMUTABLE; } fat_save_attrs(inode, de->attr); inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; fat_time_fat2unix(sbi, &mtime, de->time, de->date, 0); inode_set_mtime_to_ts(inode, mtime); inode_set_ctime_to_ts(inode, mtime); if (sbi->options.isvfat) { struct timespec64 atime; fat_time_fat2unix(sbi, &atime, 0, de->adate, 0); inode_set_atime_to_ts(inode, atime); fat_time_fat2unix(sbi, &MSDOS_I(inode)->i_crtime, de->ctime, de->cdate, de->ctime_cs); } else inode_set_atime_to_ts(inode, fat_truncate_atime(sbi, &mtime)); return 0; } static inline void fat_lock_build_inode(struct msdos_sb_info *sbi) { if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) mutex_lock(&sbi->nfs_build_inode_lock); } static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi) { if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) mutex_unlock(&sbi->nfs_build_inode_lock); } struct inode *fat_build_inode(struct super_block *sb, struct msdos_dir_entry *de, loff_t i_pos) { struct inode *inode; int err; fat_lock_build_inode(MSDOS_SB(sb)); inode = fat_iget(sb, i_pos); if (inode) goto out; inode = new_inode(sb); if (!inode) { inode = ERR_PTR(-ENOMEM); goto out; } inode->i_ino = iunique(sb, MSDOS_ROOT_INO); inode_set_iversion(inode, 1); err = fat_fill_inode(inode, de); if (err) { iput(inode); inode = ERR_PTR(err); goto out; } fat_attach(inode, i_pos); insert_inode_hash(inode); out: fat_unlock_build_inode(MSDOS_SB(sb)); return inode; } EXPORT_SYMBOL_GPL(fat_build_inode); static int __fat_write_inode(struct inode *inode, int wait); static void fat_free_eofblocks(struct inode *inode) { /* Release unwritten fallocated blocks on inode eviction. */ if ((inode->i_blocks << 9) > round_up(MSDOS_I(inode)->mmu_private, MSDOS_SB(inode->i_sb)->cluster_size)) { int err; fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private); /* Fallocate results in updating the i_start/iogstart * for the zero byte file. So, make it return to * original state during evict and commit it to avoid * any corruption on the next access to the cluster * chain for the file. */ err = __fat_write_inode(inode, inode_needs_sync(inode)); if (err) { fat_msg(inode->i_sb, KERN_WARNING, "Failed to " "update on disk inode for unused " "fallocated blocks, inode could be " "corrupted. Please run fsck"); } } } static void fat_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; fat_truncate_blocks(inode, 0); } else fat_free_eofblocks(inode); invalidate_inode_buffers(inode); clear_inode(inode); fat_cache_inval_inode(inode); fat_detach(inode); } static void fat_set_state(struct super_block *sb, unsigned int set, unsigned int force) { struct buffer_head *bh; struct fat_boot_sector *b; struct msdos_sb_info *sbi = MSDOS_SB(sb); /* do not change any thing if mounted read only */ if (sb_rdonly(sb) && !force) return; /* do not change state if fs was dirty */ if (sbi->dirty) { /* warn only on set (mount). */ if (set) fat_msg(sb, KERN_WARNING, "Volume was not properly " "unmounted. Some data may be corrupt. " "Please run fsck."); return; } bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector " "to mark fs as dirty"); return; } b = (struct fat_boot_sector *) bh->b_data; if (is_fat32(sbi)) { if (set) b->fat32.state |= FAT_STATE_DIRTY; else b->fat32.state &= ~FAT_STATE_DIRTY; } else /* fat 16 and 12 */ { if (set) b->fat16.state |= FAT_STATE_DIRTY; else b->fat16.state &= ~FAT_STATE_DIRTY; } mark_buffer_dirty(bh); sync_dirty_buffer(bh); brelse(bh); } static void fat_reset_iocharset(struct fat_mount_options *opts) { if (opts->iocharset != fat_default_iocharset) { /* Note: opts->iocharset can be NULL here */ kfree(opts->iocharset); opts->iocharset = fat_default_iocharset; } } static void delayed_free(struct rcu_head *p) { struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); unload_nls(sbi->nls_disk); unload_nls(sbi->nls_io); fat_reset_iocharset(&sbi->options); kfree(sbi); } static void fat_put_super(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); fat_set_state(sb, 0, 0); iput(sbi->fsinfo_inode); iput(sbi->fat_inode); call_rcu(&sbi->rcu, delayed_free); } static struct kmem_cache *fat_inode_cachep; static struct inode *fat_alloc_inode(struct super_block *sb) { struct msdos_inode_info *ei; ei = alloc_inode_sb(sb, fat_inode_cachep, GFP_NOFS); if (!ei) return NULL; init_rwsem(&ei->truncate_lock); /* Zeroing to allow iput() even if partial initialized inode. */ ei->mmu_private = 0; ei->i_start = 0; ei->i_logstart = 0; ei->i_attrs = 0; ei->i_pos = 0; ei->i_crtime.tv_sec = 0; ei->i_crtime.tv_nsec = 0; return &ei->vfs_inode; } static void fat_free_inode(struct inode *inode) { kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); } static void init_once(void *foo) { struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; spin_lock_init(&ei->cache_lru_lock); ei->nr_caches = 0; ei->cache_valid_id = FAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_fat_hash); INIT_HLIST_NODE(&ei->i_dir_hash); inode_init_once(&ei->vfs_inode); } static int __init fat_init_inodecache(void) { fat_inode_cachep = kmem_cache_create("fat_inode_cache", sizeof(struct msdos_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (fat_inode_cachep == NULL) return -ENOMEM; return 0; } static void __exit fat_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(fat_inode_cachep); } int fat_reconfigure(struct fs_context *fc) { bool new_rdonly; struct super_block *sb = fc->root->d_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); fc->sb_flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME); sync_filesystem(sb); /* make sure we update state on remount. */ new_rdonly = fc->sb_flags & SB_RDONLY; if (new_rdonly != sb_rdonly(sb)) { if (new_rdonly) fat_set_state(sb, 0, 0); else fat_set_state(sb, 1, 1); } return 0; } EXPORT_SYMBOL_GPL(fat_reconfigure); static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); /* If the count of free cluster is still unknown, counts it here. */ if (sbi->free_clusters == -1 || !sbi->free_clus_valid) { int err = fat_count_free_clusters(dentry->d_sb); if (err) return err; } buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = sbi->cluster_size; buf->f_blocks = sbi->max_cluster - FAT_START_ENT; buf->f_bfree = sbi->free_clusters; buf->f_bavail = sbi->free_clusters; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = (sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE; return 0; } static int __fat_write_inode(struct inode *inode, int wait) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct msdos_dir_entry *raw_entry; struct timespec64 mtime; loff_t i_pos; sector_t blocknr; int err, offset; if (inode->i_ino == MSDOS_ROOT_INO) return 0; retry: i_pos = fat_i_pos_read(sbi, inode); if (!i_pos) return 0; fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); bh = sb_bread(sb, blocknr); if (!bh) { fat_msg(sb, KERN_ERR, "unable to read inode block " "for updating (i_pos %lld)", i_pos); return -EIO; } spin_lock(&sbi->inode_hash_lock); if (i_pos != MSDOS_I(inode)->i_pos) { spin_unlock(&sbi->inode_hash_lock); brelse(bh); goto retry; } raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset]; if (S_ISDIR(inode->i_mode)) raw_entry->size = 0; else raw_entry->size = cpu_to_le32(inode->i_size); raw_entry->attr = fat_make_attrs(inode); fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart); mtime = inode_get_mtime(inode); fat_time_unix2fat(sbi, &mtime, &raw_entry->time, &raw_entry->date, NULL); if (sbi->options.isvfat) { struct timespec64 ts = inode_get_atime(inode); __le16 atime; fat_time_unix2fat(sbi, &ts, &atime, &raw_entry->adate, NULL); fat_time_unix2fat(sbi, &MSDOS_I(inode)->i_crtime, &raw_entry->ctime, &raw_entry->cdate, &raw_entry->ctime_cs); } spin_unlock(&sbi->inode_hash_lock); mark_buffer_dirty(bh); err = 0; if (wait) err = sync_dirty_buffer(bh); brelse(bh); return err; } static int fat_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; if (inode->i_ino == MSDOS_FSINFO_INO) { struct super_block *sb = inode->i_sb; mutex_lock(&MSDOS_SB(sb)->s_lock); err = fat_clusters_flush(sb); mutex_unlock(&MSDOS_SB(sb)->s_lock); } else err = __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); return err; } int fat_sync_inode(struct inode *inode) { return __fat_write_inode(inode, 1); } EXPORT_SYMBOL_GPL(fat_sync_inode); static int fat_show_options(struct seq_file *m, struct dentry *root); static const struct super_operations fat_sops = { .alloc_inode = fat_alloc_inode, .free_inode = fat_free_inode, .write_inode = fat_write_inode, .evict_inode = fat_evict_inode, .put_super = fat_put_super, .statfs = fat_statfs, .show_options = fat_show_options, }; static int fat_show_options(struct seq_file *m, struct dentry *root) { struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb); struct fat_mount_options *opts = &sbi->options; int isvfat = opts->isvfat; if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, opts->fs_uid)); if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, opts->fs_gid)); seq_printf(m, ",fmask=%04o", opts->fs_fmask); seq_printf(m, ",dmask=%04o", opts->fs_dmask); if (opts->allow_utime) seq_printf(m, ",allow_utime=%04o", opts->allow_utime); if (sbi->nls_disk) /* strip "cp" prefix from displayed option */ seq_printf(m, ",codepage=%s", &sbi->nls_disk->charset[2]); if (isvfat) { if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); switch (opts->shortname) { case VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=win95"); break; case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT: seq_puts(m, ",shortname=winnt"); break; case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=mixed"); break; case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=lower"); break; default: seq_puts(m, ",shortname=unknown"); break; } } if (opts->name_check != 'n') seq_printf(m, ",check=%c", opts->name_check); if (opts->usefree) seq_puts(m, ",usefree"); if (opts->quiet) seq_puts(m, ",quiet"); if (opts->showexec) seq_puts(m, ",showexec"); if (opts->sys_immutable) seq_puts(m, ",sys_immutable"); if (!isvfat) { if (opts->dotsOK) seq_puts(m, ",dotsOK=yes"); if (opts->nocase) seq_puts(m, ",nocase"); } else { if (opts->utf8) seq_puts(m, ",utf8"); if (opts->unicode_xlate) seq_puts(m, ",uni_xlate"); if (!opts->numtail) seq_puts(m, ",nonumtail"); if (opts->rodir) seq_puts(m, ",rodir"); } if (opts->flush) seq_puts(m, ",flush"); if (opts->tz_set) { if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); else seq_puts(m, ",tz=UTC"); } if (opts->errors == FAT_ERRORS_CONT) seq_puts(m, ",errors=continue"); else if (opts->errors == FAT_ERRORS_PANIC) seq_puts(m, ",errors=panic"); else seq_puts(m, ",errors=remount-ro"); if (opts->nfs == FAT_NFS_NOSTALE_RO) seq_puts(m, ",nfs=nostale_ro"); else if (opts->nfs) seq_puts(m, ",nfs=stale_rw"); if (opts->discard) seq_puts(m, ",discard"); if (opts->dos1xfloppy) seq_puts(m, ",dos1xfloppy"); return 0; } enum { Opt_check, Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_codepage, Opt_usefree, Opt_nocase, Opt_quiet, Opt_showexec, Opt_debug, Opt_immutable, Opt_dots, Opt_dotsOK, Opt_charset, Opt_shortname, Opt_utf8, Opt_utf8_bool, Opt_uni_xl, Opt_uni_xl_bool, Opt_nonumtail, Opt_nonumtail_bool, Opt_obsolete, Opt_flush, Opt_tz, Opt_rodir, Opt_errors, Opt_discard, Opt_nfs, Opt_nfs_enum, Opt_time_offset, Opt_dos1xfloppy, }; static const struct constant_table fat_param_check[] = { {"relaxed", 'r'}, {"r", 'r'}, {"strict", 's'}, {"s", 's'}, {"normal", 'n'}, {"n", 'n'}, {} }; static const struct constant_table fat_param_tz[] = { {"UTC", 0}, {} }; static const struct constant_table fat_param_errors[] = { {"continue", FAT_ERRORS_CONT}, {"panic", FAT_ERRORS_PANIC}, {"remount-ro", FAT_ERRORS_RO}, {} }; static const struct constant_table fat_param_nfs[] = { {"stale_rw", FAT_NFS_STALE_RW}, {"nostale_ro", FAT_NFS_NOSTALE_RO}, {} }; /* * These are all obsolete but we still reject invalid options. * The corresponding values are therefore meaningless. */ static const struct constant_table fat_param_conv[] = { {"binary", 0}, {"text", 0}, {"auto", 0}, {"b", 0}, {"t", 0}, {"a", 0}, {} }; /* Core options. See below for vfat and msdos extras */ const struct fs_parameter_spec fat_param_spec[] = { fsparam_enum ("check", Opt_check, fat_param_check), fsparam_uid ("uid", Opt_uid), fsparam_gid ("gid", Opt_gid), fsparam_u32oct ("umask", Opt_umask), fsparam_u32oct ("dmask", Opt_dmask), fsparam_u32oct ("fmask", Opt_fmask), fsparam_u32oct ("allow_utime", Opt_allow_utime), fsparam_u32 ("codepage", Opt_codepage), fsparam_flag ("usefree", Opt_usefree), fsparam_flag ("nocase", Opt_nocase), fsparam_flag ("quiet", Opt_quiet), fsparam_flag ("showexec", Opt_showexec), fsparam_flag ("debug", Opt_debug), fsparam_flag ("sys_immutable", Opt_immutable), fsparam_flag ("flush", Opt_flush), fsparam_enum ("tz", Opt_tz, fat_param_tz), fsparam_s32 ("time_offset", Opt_time_offset), fsparam_enum ("errors", Opt_errors, fat_param_errors), fsparam_flag ("discard", Opt_discard), fsparam_flag ("nfs", Opt_nfs), fsparam_enum ("nfs", Opt_nfs_enum, fat_param_nfs), fsparam_flag ("dos1xfloppy", Opt_dos1xfloppy), __fsparam(fs_param_is_enum, "conv", Opt_obsolete, fs_param_deprecated, fat_param_conv), __fsparam(fs_param_is_u32, "fat", Opt_obsolete, fs_param_deprecated, NULL), __fsparam(fs_param_is_u32, "blocksize", Opt_obsolete, fs_param_deprecated, NULL), __fsparam(fs_param_is_string, "cvf_format", Opt_obsolete, fs_param_deprecated, NULL), __fsparam(fs_param_is_string, "cvf_options", Opt_obsolete, fs_param_deprecated, NULL), __fsparam(NULL, "posix", Opt_obsolete, fs_param_deprecated, NULL), {} }; EXPORT_SYMBOL_GPL(fat_param_spec); static const struct fs_parameter_spec msdos_param_spec[] = { fsparam_flag_no ("dots", Opt_dots), fsparam_bool ("dotsOK", Opt_dotsOK), {} }; static const struct constant_table fat_param_shortname[] = { {"lower", VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95}, {"win95", VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95}, {"winnt", VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT}, {"mixed", VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95}, {} }; static const struct fs_parameter_spec vfat_param_spec[] = { fsparam_string ("iocharset", Opt_charset), fsparam_enum ("shortname", Opt_shortname, fat_param_shortname), fsparam_flag ("utf8", Opt_utf8), fsparam_bool ("utf8", Opt_utf8_bool), fsparam_flag ("uni_xlate", Opt_uni_xl), fsparam_bool ("uni_xlate", Opt_uni_xl_bool), fsparam_flag ("nonumtail", Opt_nonumtail), fsparam_bool ("nonumtail", Opt_nonumtail_bool), fsparam_flag ("rodir", Opt_rodir), {} }; int fat_parse_param(struct fs_context *fc, struct fs_parameter *param, bool is_vfat) { struct fat_mount_options *opts = fc->fs_private; struct fs_parse_result result; int opt; /* remount options have traditionally been ignored */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) return 0; opt = fs_parse(fc, fat_param_spec, param, &result); /* If option not found in fat_param_spec, try vfat/msdos options */ if (opt == -ENOPARAM) { if (is_vfat) opt = fs_parse(fc, vfat_param_spec, param, &result); else opt = fs_parse(fc, msdos_param_spec, param, &result); } if (opt < 0) return opt; switch (opt) { case Opt_check: opts->name_check = result.uint_32; break; case Opt_usefree: opts->usefree = 1; break; case Opt_nocase: if (!is_vfat) opts->nocase = 1; else { /* for backward compatibility */ opts->shortname = VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95; } break; case Opt_quiet: opts->quiet = 1; break; case Opt_showexec: opts->showexec = 1; break; case Opt_debug: opts->debug = 1; break; case Opt_immutable: opts->sys_immutable = 1; break; case Opt_uid: opts->fs_uid = result.uid; break; case Opt_gid: opts->fs_gid = result.gid; break; case Opt_umask: opts->fs_fmask = opts->fs_dmask = result.uint_32; break; case Opt_dmask: opts->fs_dmask = result.uint_32; break; case Opt_fmask: opts->fs_fmask = result.uint_32; break; case Opt_allow_utime: opts->allow_utime = result.uint_32 & (S_IWGRP | S_IWOTH); break; case Opt_codepage: opts->codepage = result.uint_32; break; case Opt_flush: opts->flush = 1; break; case Opt_time_offset: /* * GMT+-12 zones may have DST corrections so at least * 13 hours difference is needed. Make the limit 24 * just in case someone invents something unusual. */ if (result.int_32 < -24 * 60 || result.int_32 > 24 * 60) return -EINVAL; opts->tz_set = 1; opts->time_offset = result.int_32; break; case Opt_tz: opts->tz_set = 1; opts->time_offset = result.uint_32; break; case Opt_errors: opts->errors = result.uint_32; break; case Opt_nfs: opts->nfs = FAT_NFS_STALE_RW; break; case Opt_nfs_enum: opts->nfs = result.uint_32; break; case Opt_dos1xfloppy: opts->dos1xfloppy = 1; break; /* msdos specific */ case Opt_dots: /* dots / nodots */ opts->dotsOK = !result.negated; break; case Opt_dotsOK: /* dotsOK = yes/no */ opts->dotsOK = result.boolean; break; /* vfat specific */ case Opt_charset: fat_reset_iocharset(opts); opts->iocharset = param->string; param->string = NULL; /* Steal string */ break; case Opt_shortname: opts->shortname = result.uint_32; break; case Opt_utf8: opts->utf8 = 1; break; case Opt_utf8_bool: opts->utf8 = result.boolean; break; case Opt_uni_xl: opts->unicode_xlate = 1; break; case Opt_uni_xl_bool: opts->unicode_xlate = result.boolean; break; case Opt_nonumtail: opts->numtail = 0; /* negated option */ break; case Opt_nonumtail_bool: opts->numtail = !result.boolean; /* negated option */ break; case Opt_rodir: opts->rodir = 1; break; case Opt_discard: opts->discard = 1; break; /* obsolete mount options */ case Opt_obsolete: printk(KERN_INFO "FAT-fs: \"%s\" option is obsolete, " "not supported now", param->key); break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(fat_parse_param); static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = 0; inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; if (is_fat32(sbi)) { MSDOS_I(inode)->i_start = sbi->root_cluster; error = fat_calc_dir_size(inode); if (error < 0) return error; } else { MSDOS_I(inode)->i_start = 0; inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry); } inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; MSDOS_I(inode)->i_logstart = 0; MSDOS_I(inode)->mmu_private = inode->i_size; fat_save_attrs(inode, ATTR_DIR); inode_set_mtime_to_ts(inode, inode_set_atime_to_ts(inode, inode_set_ctime(inode, 0, 0))); set_nlink(inode, fat_subdirs(inode)+2); return 0; } static unsigned long calc_fat_clusters(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); /* Divide first to avoid overflow */ if (!is_fat12(sbi)) { unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; return ent_per_sec * sbi->fat_length; } return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; } static bool fat_bpb_is_zero(struct fat_boot_sector *b) { if (get_unaligned_le16(&b->sector_size)) return false; if (b->sec_per_clus) return false; if (b->reserved) return false; if (b->fats) return false; if (get_unaligned_le16(&b->dir_entries)) return false; if (get_unaligned_le16(&b->sectors)) return false; if (b->media) return false; if (b->fat_length) return false; if (b->secs_track) return false; if (b->heads) return false; return true; } static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b, int silent, struct fat_bios_param_block *bpb) { int error = -EINVAL; /* Read in BPB ... */ memset(bpb, 0, sizeof(*bpb)); bpb->fat_sector_size = get_unaligned_le16(&b->sector_size); bpb->fat_sec_per_clus = b->sec_per_clus; bpb->fat_reserved = le16_to_cpu(b->reserved); bpb->fat_fats = b->fats; bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries); bpb->fat_sectors = get_unaligned_le16(&b->sectors); bpb->fat_fat_length = le16_to_cpu(b->fat_length); bpb->fat_total_sect = le32_to_cpu(b->total_sect); bpb->fat16_state = b->fat16.state; bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id); bpb->fat32_length = le32_to_cpu(b->fat32.length); bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster); bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector); bpb->fat32_state = b->fat32.state; bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id); /* Validate this looks like a FAT filesystem BPB */ if (!bpb->fat_reserved) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of reserved sectors"); goto out; } if (!bpb->fat_fats) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); goto out; } /* * Earlier we checked here that b->secs_track and b->head are nonzero, * but it turns out valid FAT filesystems can have zero there. */ if (!fat_valid_media(b->media)) { if (!silent) fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", (unsigned)b->media); goto out; } if (!is_power_of_2(bpb->fat_sector_size) || (bpb->fat_sector_size < 512) || (bpb->fat_sector_size > 4096)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus logical sector size %u", (unsigned)bpb->fat_sector_size); goto out; } if (!is_power_of_2(bpb->fat_sec_per_clus)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", (unsigned)bpb->fat_sec_per_clus); goto out; } if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of FAT sectors"); goto out; } error = 0; out: return error; } static int fat_read_static_bpb(struct super_block *sb, struct fat_boot_sector *b, int silent, struct fat_bios_param_block *bpb) { static const char *notdos1x = "This doesn't look like a DOS 1.x volume"; sector_t bd_sects = bdev_nr_sectors(sb->s_bdev); struct fat_floppy_defaults *fdefaults = NULL; int error = -EINVAL; unsigned i; /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */ if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) { if (!silent) fat_msg(sb, KERN_ERR, "%s; no bootstrapping code", notdos1x); goto out; } /* * If any value in this region is non-zero, it isn't archaic * DOS. */ if (!fat_bpb_is_zero(b)) { if (!silent) fat_msg(sb, KERN_ERR, "%s; DOS 2.x BPB is non-zero", notdos1x); goto out; } for (i = 0; i < ARRAY_SIZE(floppy_defaults); i++) { if (floppy_defaults[i].nr_sectors == bd_sects) { fdefaults = &floppy_defaults[i]; break; } } if (fdefaults == NULL) { if (!silent) fat_msg(sb, KERN_WARNING, "This looks like a DOS 1.x volume, but isn't a recognized floppy size (%llu sectors)", (u64)bd_sects); goto out; } if (!silent) fat_msg(sb, KERN_INFO, "This looks like a DOS 1.x volume; assuming default BPB values"); memset(bpb, 0, sizeof(*bpb)); bpb->fat_sector_size = SECTOR_SIZE; bpb->fat_sec_per_clus = fdefaults->sec_per_clus; bpb->fat_reserved = 1; bpb->fat_fats = 2; bpb->fat_dir_entries = fdefaults->dir_entries; bpb->fat_sectors = fdefaults->nr_sectors; bpb->fat_fat_length = fdefaults->fat_length; error = 0; out: return error; } /* * Read the super block of an MS-DOS FS. */ int fat_fill_super(struct super_block *sb, struct fs_context *fc, void (*setup)(struct super_block *)) { struct fat_mount_options *opts = fc->fs_private; int silent = fc->sb_flags & SB_SILENT; struct inode *root_inode = NULL, *fat_inode = NULL; struct inode *fsinfo_inode = NULL; struct buffer_head *bh; struct fat_bios_param_block bpb; struct msdos_sb_info *sbi; u16 logical_sector_size; u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; long error; char buf[50]; struct timespec64 ts; /* * GFP_KERNEL is ok here, because while we do hold the * superblock lock, memory pressure can't call back into * the filesystem, since we're only just about to mount * it and have no inodes etc active! */ sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; sb->s_flags |= SB_NODIRATIME; sb->s_magic = MSDOS_SUPER_MAGIC; sb->s_op = &fat_sops; sb->s_export_op = &fat_export_ops; /* * fat timestamps are complex and truncated by fat itself, so * we set 1 here to be fast */ sb->s_time_gran = 1; mutex_init(&sbi->nfs_build_inode_lock); ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); /* UTF-8 doesn't provide FAT semantics */ if (!strcmp(opts->iocharset, "utf8")) { fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset" " for FAT filesystems, filesystem will be" " case sensitive!"); } /* If user doesn't specify allow_utime, it's initialized from dmask. */ if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH); if (opts->unicode_xlate) opts->utf8 = 0; if (opts->nfs == FAT_NFS_NOSTALE_RO) { sb->s_flags |= SB_RDONLY; sb->s_export_op = &fat_export_ops_nostale; } /* Apply parsed options to sbi (structure copy) */ sbi->options = *opts; /* Transfer ownership of iocharset to sbi->options */ opts->iocharset = NULL; setup(sb); /* flavour-specific stuff that needs options */ error = -EIO; sb_min_blocksize(sb, 512); bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector"); goto out_fail; } error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, &bpb); if (error == -EINVAL && sbi->options.dos1xfloppy) error = fat_read_static_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, &bpb); brelse(bh); if (error == -EINVAL) goto out_invalid; else if (error) goto out_fail; logical_sector_size = bpb.fat_sector_size; sbi->sec_per_clus = bpb.fat_sec_per_clus; error = -EIO; if (logical_sector_size < sb->s_blocksize) { fat_msg(sb, KERN_ERR, "logical sector size too small for device" " (logical sector size = %u)", logical_sector_size); goto out_fail; } if (logical_sector_size > sb->s_blocksize) { struct buffer_head *bh_resize; if (!sb_set_blocksize(sb, logical_sector_size)) { fat_msg(sb, KERN_ERR, "unable to set blocksize %u", logical_sector_size); goto out_fail; } /* Verify that the larger boot sector is fully readable */ bh_resize = sb_bread(sb, 0); if (bh_resize == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector" " (logical sector size = %lu)", sb->s_blocksize); goto out_fail; } brelse(bh_resize); } mutex_init(&sbi->s_lock); sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus; sbi->cluster_bits = ffs(sbi->cluster_size) - 1; sbi->fats = bpb.fat_fats; sbi->fat_bits = 0; /* Don't know yet */ sbi->fat_start = bpb.fat_reserved; sbi->fat_length = bpb.fat_fat_length; sbi->root_cluster = 0; sbi->free_clusters = -1; /* Don't know yet */ sbi->free_clus_valid = 0; sbi->prev_free = FAT_START_ENT; sb->s_maxbytes = 0xffffffff; fat_time_fat2unix(sbi, &ts, 0, cpu_to_le16(FAT_DATE_MIN), 0); sb->s_time_min = ts.tv_sec; fat_time_fat2unix(sbi, &ts, cpu_to_le16(FAT_TIME_MAX), cpu_to_le16(FAT_DATE_MAX), 0); sb->s_time_max = ts.tv_sec; if (!sbi->fat_length && bpb.fat32_length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; sbi->fat_length = bpb.fat32_length; sbi->root_cluster = bpb.fat32_root_cluster; /* MC - if info_sector is 0, don't multiply by 0 */ sbi->fsinfo_sector = bpb.fat32_info_sector; if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; fsinfo_bh = sb_bread(sb, sbi->fsinfo_sector); if (fsinfo_bh == NULL) { fat_msg(sb, KERN_ERR, "bread failed, FSINFO block" " (sector = %lu)", sbi->fsinfo_sector); goto out_fail; } fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; if (!IS_FSINFO(fsinfo)) { fat_msg(sb, KERN_WARNING, "Invalid FSINFO signature: " "0x%08x, 0x%08x (sector = %lu)", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); } else { if (sbi->options.usefree) sbi->free_clus_valid = 1; sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters); sbi->prev_free = le32_to_cpu(fsinfo->next_cluster); } brelse(fsinfo_bh); } /* interpret volume ID as a little endian 32 bit integer */ if (is_fat32(sbi)) sbi->vol_id = bpb.fat32_vol_id; else /* fat 16 or 12 */ sbi->vol_id = bpb.fat16_vol_id; __le32 vol_id_le = cpu_to_le32(sbi->vol_id); super_set_uuid(sb, (void *) &vol_id_le, sizeof(vol_id_le)); sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry); sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1; sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length; sbi->dir_entries = bpb.fat_dir_entries; if (sbi->dir_entries & (sbi->dir_per_block - 1)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of directory entries" " (%u)", sbi->dir_entries); goto out_invalid; } rootdir_sectors = sbi->dir_entries * sizeof(struct msdos_dir_entry) / sb->s_blocksize; sbi->data_start = sbi->dir_start + rootdir_sectors; total_sectors = bpb.fat_sectors; if (total_sectors == 0) total_sectors = bpb.fat_total_sect; total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; if (!is_fat32(sbi)) sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ if (is_fat32(sbi)) sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; else /* fat 16 or 12 */ sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY; /* check that FAT table does not overflow */ fat_clusters = calc_fat_clusters(sb); total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); if (total_clusters > max_fat(sb)) { if (!silent) fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", total_clusters); goto out_invalid; } sbi->max_cluster = total_clusters + FAT_START_ENT; /* check the free_clusters, it's not necessarily correct */ if (sbi->free_clusters != -1 && sbi->free_clusters > total_clusters) sbi->free_clusters = -1; /* check the prev_free, it's not necessarily correct */ sbi->prev_free %= sbi->max_cluster; if (sbi->prev_free < FAT_START_ENT) sbi->prev_free = FAT_START_ENT; /* set up enough so that it can read an inode */ fat_hash_init(sb); dir_hash_init(sb); fat_ent_access_init(sb); /* * The low byte of the first FAT entry must have the same value as * the media field of the boot sector. But in real world, too many * devices are writing wrong values. So, removed that validity check. * * The removed check compared the first FAT entry to a value dependent * on the media field like this: * == (0x0F00 | media), for FAT12 * == (0XFF00 | media), for FAT16 * == (0x0FFFFF | media), for FAT32 */ error = -EINVAL; sprintf(buf, "cp%d", sbi->options.codepage); sbi->nls_disk = load_nls(buf); if (!sbi->nls_disk) { fat_msg(sb, KERN_ERR, "codepage %s not found", buf); goto out_fail; } /* FIXME: utf8 is using iocharset for upper/lower conversion */ if (sbi->options.isvfat) { sbi->nls_io = load_nls(sbi->options.iocharset); if (!sbi->nls_io) { fat_msg(sb, KERN_ERR, "IO charset %s not found", sbi->options.iocharset); goto out_fail; } } error = -ENOMEM; fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); root_inode = new_inode(sb); if (!root_inode) goto out_fail; root_inode->i_ino = MSDOS_ROOT_INO; inode_set_iversion(root_inode, 1); error = fat_read_root(root_inode); if (error < 0) { iput(root_inode); goto out_fail; } error = -ENOMEM; insert_inode_hash(root_inode); fat_attach(root_inode, 0); sb->s_root = d_make_root(root_inode); if (!sb->s_root) { fat_msg(sb, KERN_ERR, "get root inode failed"); goto out_fail; } if (sbi->options.discard && !bdev_max_discard_sectors(sb->s_bdev)) fat_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but the device does not support discard"); fat_set_state(sb, 1, 0); return 0; out_invalid: error = -EINVAL; if (!silent) fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); out_fail: iput(fsinfo_inode); iput(fat_inode); unload_nls(sbi->nls_io); unload_nls(sbi->nls_disk); fat_reset_iocharset(&sbi->options); sb->s_fs_info = NULL; kfree(sbi); return error; } EXPORT_SYMBOL_GPL(fat_fill_super); /* * helper function for fat_flush_inodes. This writes both the inode * and the file data blocks, waiting for in flight data blocks before * the start of the call. It does not wait for any io started * during the call */ static int writeback_inode(struct inode *inode) { int ret; /* if we used wait=1, sync_inode_metadata waits for the io for the * inode to finish. So wait=0 is sent down to sync_inode_metadata * and filemap_fdatawrite is used for the data blocks */ ret = sync_inode_metadata(inode, 0); if (!ret) ret = filemap_fdatawrite(inode->i_mapping); return ret; } /* * write data and metadata corresponding to i1 and i2. The io is * started but we do not wait for any of it to finish. * * filemap_flush is used for the block device, so if there is a dirty * page for a block already in flight, we will not wait and start the * io over again */ int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2) { int ret = 0; if (!MSDOS_SB(sb)->options.flush) return 0; if (i1) ret = writeback_inode(i1); if (!ret && i2) ret = writeback_inode(i2); if (!ret) ret = sync_blockdev_nowait(sb->s_bdev); return ret; } EXPORT_SYMBOL_GPL(fat_flush_inodes); int fat_init_fs_context(struct fs_context *fc, bool is_vfat) { struct fat_mount_options *opts; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; opts->isvfat = is_vfat; opts->fs_uid = current_uid(); opts->fs_gid = current_gid(); opts->fs_fmask = opts->fs_dmask = current_umask(); opts->allow_utime = -1; opts->codepage = fat_default_codepage; fat_reset_iocharset(opts); if (is_vfat) { opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; opts->rodir = 0; } else { opts->shortname = 0; opts->rodir = 1; } opts->name_check = 'n'; opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK = 0; opts->unicode_xlate = 0; opts->numtail = 1; opts->usefree = opts->nocase = 0; opts->tz_set = 0; opts->nfs = 0; opts->errors = FAT_ERRORS_RO; opts->debug = 0; opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat; fc->fs_private = opts; /* fc->ops assigned by caller */ return 0; } EXPORT_SYMBOL_GPL(fat_init_fs_context); void fat_free_fc(struct fs_context *fc) { struct fat_mount_options *opts = fc->fs_private; if (opts->iocharset != fat_default_iocharset) kfree(opts->iocharset); kfree(fc->fs_private); } EXPORT_SYMBOL_GPL(fat_free_fc); static int __init init_fat_fs(void) { int err; err = fat_cache_init(); if (err) return err; err = fat_init_inodecache(); if (err) goto failed; return 0; failed: fat_cache_destroy(); return err; } static void __exit exit_fat_fs(void) { fat_cache_destroy(); fat_destroy_inodecache(); } module_init(init_fat_fs) module_exit(exit_fat_fs) MODULE_DESCRIPTION("Core FAT filesystem support"); MODULE_LICENSE("GPL"); |
| 141 141 96 96 16 2 16 16 4 14 7 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2011 Intel Corporation. All rights reserved. */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/nfc.h> #include <net/nfc/nfc.h> #include "nfc.h" #include "llcp.h" static const u8 llcp_tlv_length[LLCP_TLV_MAX] = { 0, 1, /* VERSION */ 2, /* MIUX */ 2, /* WKS */ 1, /* LTO */ 1, /* RW */ 0, /* SN */ 1, /* OPT */ 0, /* SDREQ */ 2, /* SDRES */ }; static u8 llcp_tlv8(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; return tlv[2]; } static u16 llcp_tlv16(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; return be16_to_cpu(*((__be16 *)(tlv + 2))); } static u8 llcp_tlv_version(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_VERSION); } static u16 llcp_tlv_miux(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7ff; } static u16 llcp_tlv_wks(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_WKS); } static u16 llcp_tlv_lto(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_LTO); } static u8 llcp_tlv_opt(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_OPT); } static u8 llcp_tlv_rw(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_RW) & 0xf; } u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length) { u8 *tlv, length; pr_debug("type %d\n", type); if (type >= LLCP_TLV_MAX) return NULL; length = llcp_tlv_length[type]; if (length == 0 && value_length == 0) return NULL; else if (length == 0) length = value_length; *tlv_length = 2 + length; tlv = kzalloc(2 + length, GFP_KERNEL); if (tlv == NULL) return tlv; tlv[0] = type; tlv[1] = length; memcpy(tlv + 2, value, length); return tlv; } struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap) { struct nfc_llcp_sdp_tlv *sdres; u8 value[2]; sdres = kzalloc(sizeof(struct nfc_llcp_sdp_tlv), GFP_KERNEL); if (sdres == NULL) return NULL; value[0] = tid; value[1] = sap; sdres->tlv = nfc_llcp_build_tlv(LLCP_TLV_SDRES, value, 2, &sdres->tlv_len); if (sdres->tlv == NULL) { kfree(sdres); return NULL; } sdres->tid = tid; sdres->sap = sap; INIT_HLIST_NODE(&sdres->node); return sdres; } struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len) { struct nfc_llcp_sdp_tlv *sdreq; pr_debug("uri: %s, len: %zu\n", uri, uri_len); /* sdreq->tlv_len is u8, takes uri_len, + 3 for header, + 1 for NULL */ if (WARN_ON_ONCE(uri_len > U8_MAX - 4)) return NULL; sdreq = kzalloc(sizeof(struct nfc_llcp_sdp_tlv), GFP_KERNEL); if (sdreq == NULL) return NULL; sdreq->tlv_len = uri_len + 3; if (uri[uri_len - 1] == 0) sdreq->tlv_len--; sdreq->tlv = kzalloc(sdreq->tlv_len + 1, GFP_KERNEL); if (sdreq->tlv == NULL) { kfree(sdreq); return NULL; } sdreq->tlv[0] = LLCP_TLV_SDREQ; sdreq->tlv[1] = sdreq->tlv_len - 2; sdreq->tlv[2] = tid; sdreq->tid = tid; sdreq->uri = sdreq->tlv + 3; memcpy(sdreq->uri, uri, uri_len); sdreq->time = jiffies; INIT_HLIST_NODE(&sdreq->node); return sdreq; } void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp) { kfree(sdp->tlv); kfree(sdp); } void nfc_llcp_free_sdp_tlv_list(struct hlist_head *head) { struct nfc_llcp_sdp_tlv *sdp; struct hlist_node *n; hlist_for_each_entry_safe(sdp, n, head, node) { hlist_del(&sdp->node); nfc_llcp_free_sdp_tlv(sdp); } } int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, const u8 *tlv_array, u16 tlv_array_len) { const u8 *tlv = tlv_array; u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); if (local == NULL) return -ENODEV; while (offset < tlv_array_len) { type = tlv[0]; length = tlv[1]; pr_debug("type 0x%x length %d\n", type, length); switch (type) { case LLCP_TLV_VERSION: local->remote_version = llcp_tlv_version(tlv); break; case LLCP_TLV_MIUX: local->remote_miu = llcp_tlv_miux(tlv) + 128; break; case LLCP_TLV_WKS: local->remote_wks = llcp_tlv_wks(tlv); break; case LLCP_TLV_LTO: local->remote_lto = llcp_tlv_lto(tlv) * 10; break; case LLCP_TLV_OPT: local->remote_opt = llcp_tlv_opt(tlv); break; default: pr_err("Invalid gt tlv value 0x%x\n", type); break; } offset += length + 2; tlv += length + 2; } pr_debug("version 0x%x miu %d lto %d opt 0x%x wks 0x%x\n", local->remote_version, local->remote_miu, local->remote_lto, local->remote_opt, local->remote_wks); return 0; } int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, const u8 *tlv_array, u16 tlv_array_len) { const u8 *tlv = tlv_array; u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); if (sock == NULL) return -ENOTCONN; while (offset < tlv_array_len) { type = tlv[0]; length = tlv[1]; pr_debug("type 0x%x length %d\n", type, length); switch (type) { case LLCP_TLV_MIUX: sock->remote_miu = llcp_tlv_miux(tlv) + 128; break; case LLCP_TLV_RW: sock->remote_rw = llcp_tlv_rw(tlv); break; case LLCP_TLV_SN: break; default: pr_err("Invalid gt tlv value 0x%x\n", type); break; } offset += length + 2; tlv += length + 2; } pr_debug("sock %p rw %d miu %d\n", sock, sock->remote_rw, sock->remote_miu); return 0; } static struct sk_buff *llcp_add_header(struct sk_buff *pdu, u8 dsap, u8 ssap, u8 ptype) { u8 header[2]; pr_debug("ptype 0x%x dsap 0x%x ssap 0x%x\n", ptype, dsap, ssap); header[0] = (u8)((dsap << 2) | (ptype >> 2)); header[1] = (u8)((ptype << 6) | ssap); pr_debug("header 0x%x 0x%x\n", header[0], header[1]); skb_put_data(pdu, header, LLCP_HEADER_SIZE); return pdu; } static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, const u8 *tlv, u8 tlv_length) { /* XXX Add an skb length check */ if (tlv == NULL) return NULL; skb_put_data(pdu, tlv, tlv_length); return pdu; } static struct sk_buff *llcp_allocate_pdu(struct nfc_llcp_sock *sock, u8 cmd, u16 size) { struct sk_buff *skb; int err; if (sock->ssap == 0) return NULL; skb = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, size + LLCP_HEADER_SIZE, &err); if (skb == NULL) { pr_err("Could not allocate PDU\n"); return NULL; } skb = llcp_add_header(skb, sock->dsap, sock->ssap, cmd); return skb; } int nfc_llcp_send_disconnect(struct nfc_llcp_sock *sock) { struct sk_buff *skb; struct nfc_dev *dev; struct nfc_llcp_local *local; local = sock->local; if (local == NULL) return -ENODEV; dev = sock->dev; if (dev == NULL) return -ENODEV; skb = llcp_allocate_pdu(sock, LLCP_PDU_DISC, 0); if (skb == NULL) return -ENOMEM; skb_queue_tail(&local->tx_queue, skb); return 0; } int nfc_llcp_send_symm(struct nfc_dev *dev) { struct sk_buff *skb; struct nfc_llcp_local *local; u16 size = 0; int err; local = nfc_llcp_find_local(dev); if (local == NULL) return -ENODEV; size += LLCP_HEADER_SIZE; size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); if (skb == NULL) { err = -ENOMEM; goto out; } skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); skb = llcp_add_header(skb, 0, 0, LLCP_PDU_SYMM); __net_timestamp(skb); nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); err = nfc_data_exchange(dev, local->target_idx, skb, nfc_llcp_recv, local); out: nfc_llcp_local_put(local); return err; } int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; const u8 *service_name_tlv = NULL; const u8 *miux_tlv = NULL; const u8 *rw_tlv = NULL; u8 service_name_tlv_length = 0; u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; local = sock->local; if (local == NULL) return -ENODEV; if (sock->service_name != NULL) { service_name_tlv = nfc_llcp_build_tlv(LLCP_TLV_SN, sock->service_name, sock->service_name_len, &service_name_tlv_length); if (!service_name_tlv) { err = -ENOMEM; goto error_tlv; } size += service_name_tlv_length; } /* If the socket parameters are not set, use the local ones */ miux = be16_to_cpu(sock->miux) > LLCP_MAX_MIUX ? local->miux : sock->miux; rw = sock->rw > LLCP_MAX_RW ? local->rw : sock->rw; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); if (!miux_tlv) { err = -ENOMEM; goto error_tlv; } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); if (!rw_tlv) { err = -ENOMEM; goto error_tlv; } size += rw_tlv_length; pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len); skb = llcp_allocate_pdu(sock, LLCP_PDU_CONNECT, size); if (skb == NULL) { err = -ENOMEM; goto error_tlv; } llcp_add_tlv(skb, service_name_tlv, service_name_tlv_length); llcp_add_tlv(skb, miux_tlv, miux_tlv_length); llcp_add_tlv(skb, rw_tlv, rw_tlv_length); skb_queue_tail(&local->tx_queue, skb); err = 0; error_tlv: if (err) pr_err("error %d\n", err); kfree(service_name_tlv); kfree(miux_tlv); kfree(rw_tlv); return err; } int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; const u8 *miux_tlv = NULL; const u8 *rw_tlv = NULL; u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; local = sock->local; if (local == NULL) return -ENODEV; /* If the socket parameters are not set, use the local ones */ miux = be16_to_cpu(sock->miux) > LLCP_MAX_MIUX ? local->miux : sock->miux; rw = sock->rw > LLCP_MAX_RW ? local->rw : sock->rw; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); if (!miux_tlv) { err = -ENOMEM; goto error_tlv; } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); if (!rw_tlv) { err = -ENOMEM; goto error_tlv; } size += rw_tlv_length; skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size); if (skb == NULL) { err = -ENOMEM; goto error_tlv; } llcp_add_tlv(skb, miux_tlv, miux_tlv_length); llcp_add_tlv(skb, rw_tlv, rw_tlv_length); skb_queue_tail(&local->tx_queue, skb); err = 0; error_tlv: if (err) pr_err("error %d\n", err); kfree(miux_tlv); kfree(rw_tlv); return err; } static struct sk_buff *nfc_llcp_allocate_snl(struct nfc_llcp_local *local, size_t tlv_length) { struct sk_buff *skb; struct nfc_dev *dev; u16 size = 0; if (local == NULL) return ERR_PTR(-ENODEV); dev = local->dev; if (dev == NULL) return ERR_PTR(-ENODEV); size += LLCP_HEADER_SIZE; size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; size += tlv_length; skb = alloc_skb(size, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOMEM); skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); skb = llcp_add_header(skb, LLCP_SAP_SDP, LLCP_SAP_SDP, LLCP_PDU_SNL); return skb; } int nfc_llcp_send_snl_sdres(struct nfc_llcp_local *local, struct hlist_head *tlv_list, size_t tlvs_len) { struct nfc_llcp_sdp_tlv *sdp; struct hlist_node *n; struct sk_buff *skb; skb = nfc_llcp_allocate_snl(local, tlvs_len); if (IS_ERR(skb)) return PTR_ERR(skb); hlist_for_each_entry_safe(sdp, n, tlv_list, node) { skb_put_data(skb, sdp->tlv, sdp->tlv_len); hlist_del(&sdp->node); nfc_llcp_free_sdp_tlv(sdp); } skb_queue_tail(&local->tx_queue, skb); return 0; } int nfc_llcp_send_snl_sdreq(struct nfc_llcp_local *local, struct hlist_head *tlv_list, size_t tlvs_len) { struct nfc_llcp_sdp_tlv *sdreq; struct hlist_node *n; struct sk_buff *skb; skb = nfc_llcp_allocate_snl(local, tlvs_len); if (IS_ERR(skb)) return PTR_ERR(skb); mutex_lock(&local->sdreq_lock); if (hlist_empty(&local->pending_sdreqs)) mod_timer(&local->sdreq_timer, jiffies + msecs_to_jiffies(3 * local->remote_lto)); hlist_for_each_entry_safe(sdreq, n, tlv_list, node) { pr_debug("tid %d for %s\n", sdreq->tid, sdreq->uri); skb_put_data(skb, sdreq->tlv, sdreq->tlv_len); hlist_del(&sdreq->node); hlist_add_head(&sdreq->node, &local->pending_sdreqs); } mutex_unlock(&local->sdreq_lock); skb_queue_tail(&local->tx_queue, skb); return 0; } int nfc_llcp_send_dm(struct nfc_llcp_local *local, u8 ssap, u8 dsap, u8 reason) { struct sk_buff *skb; struct nfc_dev *dev; u16 size = 1; /* Reason code */ pr_debug("Sending DM reason 0x%x\n", reason); if (local == NULL) return -ENODEV; dev = local->dev; if (dev == NULL) return -ENODEV; size += LLCP_HEADER_SIZE; size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); if (skb == NULL) return -ENOMEM; skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); skb = llcp_add_header(skb, dsap, ssap, LLCP_PDU_DM); skb_put_data(skb, &reason, 1); skb_queue_head(&local->tx_queue, skb); return 0; } int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, struct msghdr *msg, size_t len) { struct sk_buff *pdu; struct sock *sk = &sock->sk; struct nfc_llcp_local *local; size_t frag_len = 0, remaining_len; u8 *msg_data, *msg_ptr; u16 remote_miu; pr_debug("Send I frame len %zd\n", len); local = sock->local; if (local == NULL) return -ENODEV; /* Remote is ready but has not acknowledged our frames */ if((sock->remote_ready && skb_queue_len(&sock->tx_pending_queue) >= sock->remote_rw && skb_queue_len(&sock->tx_queue) >= 2 * sock->remote_rw)) { pr_err("Pending queue is full %d frames\n", skb_queue_len(&sock->tx_pending_queue)); return -ENOBUFS; } /* Remote is not ready and we've been queueing enough frames */ if ((!sock->remote_ready && skb_queue_len(&sock->tx_queue) >= 2 * sock->remote_rw)) { pr_err("Tx queue is full %d frames\n", skb_queue_len(&sock->tx_queue)); return -ENOBUFS; } msg_data = kmalloc(len, GFP_USER | __GFP_NOWARN); if (msg_data == NULL) return -ENOMEM; if (memcpy_from_msg(msg_data, msg, len)) { kfree(msg_data); return -EFAULT; } remaining_len = len; msg_ptr = msg_data; do { remote_miu = sock->remote_miu > LLCP_MAX_MIU ? LLCP_DEFAULT_MIU : sock->remote_miu; frag_len = min_t(size_t, remote_miu, remaining_len); pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); pdu = llcp_allocate_pdu(sock, LLCP_PDU_I, frag_len + LLCP_SEQUENCE_SIZE); if (pdu == NULL) { kfree(msg_data); return -ENOMEM; } skb_put(pdu, LLCP_SEQUENCE_SIZE); if (likely(frag_len > 0)) skb_put_data(pdu, msg_ptr, frag_len); skb_queue_tail(&sock->tx_queue, pdu); lock_sock(sk); nfc_llcp_queue_i_frames(sock); release_sock(sk); remaining_len -= frag_len; msg_ptr += frag_len; } while (remaining_len > 0); kfree(msg_data); return len; } int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, struct msghdr *msg, size_t len) { struct sk_buff *pdu; struct nfc_llcp_local *local; size_t frag_len = 0, remaining_len; u8 *msg_ptr, *msg_data; u16 remote_miu; int err; pr_debug("Send UI frame len %zd\n", len); local = sock->local; if (local == NULL) return -ENODEV; msg_data = kmalloc(len, GFP_USER | __GFP_NOWARN); if (msg_data == NULL) return -ENOMEM; if (memcpy_from_msg(msg_data, msg, len)) { kfree(msg_data); return -EFAULT; } remaining_len = len; msg_ptr = msg_data; do { remote_miu = sock->remote_miu > LLCP_MAX_MIU ? local->remote_miu : sock->remote_miu; frag_len = min_t(size_t, remote_miu, remaining_len); pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0, frag_len + LLCP_HEADER_SIZE, &err); if (pdu == NULL) { pr_err("Could not allocate PDU (error=%d)\n", err); len -= remaining_len; if (len == 0) len = err; break; } pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); if (likely(frag_len > 0)) skb_put_data(pdu, msg_ptr, frag_len); /* No need to check for the peer RW for UI frames */ skb_queue_tail(&local->tx_queue, pdu); remaining_len -= frag_len; msg_ptr += frag_len; } while (remaining_len > 0); kfree(msg_data); return len; } int nfc_llcp_send_rr(struct nfc_llcp_sock *sock) { struct sk_buff *skb; struct nfc_llcp_local *local; pr_debug("Send rr nr %d\n", sock->recv_n); local = sock->local; if (local == NULL) return -ENODEV; skb = llcp_allocate_pdu(sock, LLCP_PDU_RR, LLCP_SEQUENCE_SIZE); if (skb == NULL) return -ENOMEM; skb_put(skb, LLCP_SEQUENCE_SIZE); skb->data[2] = sock->recv_n; skb_queue_head(&local->tx_queue, skb); return 0; } |
| 339 281 1 36 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UIDGID_H #define _LINUX_UIDGID_H /* * A set of types for the internal kernel types representing uids and gids. * * The types defined in this header allow distinguishing which uids and gids in * the kernel are values used by userspace and which uid and gid values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/uidgid_types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; struct uid_gid_map; #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } #ifdef CONFIG_MULTIUSER static inline uid_t __kuid_val(kuid_t uid) { return uid.val; } static inline gid_t __kgid_val(kgid_t gid) { return gid.val; } #else static inline uid_t __kuid_val(kuid_t uid) { return 0; } static inline gid_t __kgid_val(kgid_t gid) { return 0; } #endif #define GLOBAL_ROOT_UID KUIDT_INIT(0) #define GLOBAL_ROOT_GID KGIDT_INIT(0) #define INVALID_UID KUIDT_INIT(-1) #define INVALID_GID KGIDT_INIT(-1) static inline bool uid_eq(kuid_t left, kuid_t right) { return __kuid_val(left) == __kuid_val(right); } static inline bool gid_eq(kgid_t left, kgid_t right) { return __kgid_val(left) == __kgid_val(right); } static inline bool uid_gt(kuid_t left, kuid_t right) { return __kuid_val(left) > __kuid_val(right); } static inline bool gid_gt(kgid_t left, kgid_t right) { return __kgid_val(left) > __kgid_val(right); } static inline bool uid_gte(kuid_t left, kuid_t right) { return __kuid_val(left) >= __kuid_val(right); } static inline bool gid_gte(kgid_t left, kgid_t right) { return __kgid_val(left) >= __kgid_val(right); } static inline bool uid_lt(kuid_t left, kuid_t right) { return __kuid_val(left) < __kuid_val(right); } static inline bool gid_lt(kgid_t left, kgid_t right) { return __kgid_val(left) < __kgid_val(right); } static inline bool uid_lte(kuid_t left, kuid_t right) { return __kuid_val(left) <= __kuid_val(right); } static inline bool gid_lte(kgid_t left, kgid_t right) { return __kgid_val(left) <= __kgid_val(right); } static inline bool uid_valid(kuid_t uid) { return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return from_kuid(ns, uid) != (uid_t) -1; } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return from_kgid(ns, gid) != (gid_t) -1; } u32 map_id_down(struct uid_gid_map *map, u32 id); u32 map_id_up(struct uid_gid_map *map, u32 id); u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count); #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); } static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) { return KGIDT_INIT(gid); } static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) { return __kuid_val(kuid); } static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) { return __kgid_val(kgid); } static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) { uid_t uid = from_kuid(to, kuid); if (uid == (uid_t)-1) uid = overflowuid; return uid; } static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) { gid_t gid = from_kgid(to, kgid); if (gid == (gid_t)-1) gid = overflowgid; return gid; } static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return gid_valid(gid); } static inline u32 map_id_down(struct uid_gid_map *map, u32 id) { return id; } static inline u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count) { return id; } static inline u32 map_id_up(struct uid_gid_map *map, u32 id) { return id; } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */ |
| 85 85 2138 495 1886 1870 227 1869 220 1880 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 | // SPDX-License-Identifier: GPL-2.0-only /* * x86-optimized CRC32 functions * * Copyright (C) 2008 Intel Corporation * Copyright 2012 Xyratex Technology Limited * Copyright 2024 Google LLC */ #include <linux/crc32.h> #include <linux/module.h> #include "crc-pclmul-template.h" static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32); static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pclmulqdq); DECLARE_CRC_PCLMUL_FUNCS(crc32_lsb, u32); u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) { CRC_PCLMUL(crc, p, len, crc32_lsb, crc32_lsb_0xedb88320_consts, have_pclmulqdq); return crc32_le_base(crc, p, len); } EXPORT_SYMBOL(crc32_le_arch); #ifdef CONFIG_X86_64 #define CRC32_INST "crc32q %1, %q0" #else #define CRC32_INST "crc32l %1, %0" #endif /* * Use carryless multiply version of crc32c when buffer size is >= 512 to * account for FPU state save/restore overhead. */ #define CRC32C_PCLMUL_BREAKEVEN 512 asmlinkage u32 crc32c_x86_3way(u32 crc, const u8 *buffer, size_t len); u32 crc32c_arch(u32 crc, const u8 *p, size_t len) { size_t num_longs; if (!static_branch_likely(&have_crc32)) return crc32c_base(crc, p, len); if (IS_ENABLED(CONFIG_X86_64) && len >= CRC32C_PCLMUL_BREAKEVEN && static_branch_likely(&have_pclmulqdq) && crypto_simd_usable()) { kernel_fpu_begin(); crc = crc32c_x86_3way(crc, p, len); kernel_fpu_end(); return crc; } for (num_longs = len / sizeof(unsigned long); num_longs != 0; num_longs--, p += sizeof(unsigned long)) asm(CRC32_INST : "+r" (crc) : ASM_INPUT_RM (*(unsigned long *)p)); if (sizeof(unsigned long) > 4 && (len & 4)) { asm("crc32l %1, %0" : "+r" (crc) : ASM_INPUT_RM (*(u32 *)p)); p += 4; } if (len & 2) { asm("crc32w %1, %0" : "+r" (crc) : ASM_INPUT_RM (*(u16 *)p)); p += 2; } if (len & 1) asm("crc32b %1, %0" : "+r" (crc) : ASM_INPUT_RM (*p)); return crc; } EXPORT_SYMBOL(crc32c_arch); u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) { return crc32_be_base(crc, p, len); } EXPORT_SYMBOL(crc32_be_arch); static int __init crc32_x86_init(void) { if (boot_cpu_has(X86_FEATURE_XMM4_2)) static_branch_enable(&have_crc32); if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { static_branch_enable(&have_pclmulqdq); INIT_CRC_PCLMUL(crc32_lsb); } return 0; } subsys_initcall(crc32_x86_init); static void __exit crc32_x86_exit(void) { } module_exit(crc32_x86_exit); u32 crc32_optimizations(void) { u32 optimizations = 0; if (static_key_enabled(&have_crc32)) optimizations |= CRC32C_OPTIMIZATION; if (static_key_enabled(&have_pclmulqdq)) optimizations |= CRC32_LE_OPTIMIZATION; return optimizations; } EXPORT_SYMBOL(crc32_optimizations); MODULE_DESCRIPTION("x86-optimized CRC32 functions"); MODULE_LICENSE("GPL"); |
| 5 17 1 268 29 159 159 193 193 143 70 82 69 5 73 73 82 181 77 7 19 152 57 21 73 110 99 39 9 126 37 37 35 2 2 51 50 5 83 46 44 5 41 66 162 2 34 19 4 20 2 15 11 21 25 9 33 1 11 23 88 89 2 109 79 13 73 79 83 73 109 80 12 3 113 113 1 112 82 73 112 51 23 20 20 23 86 103 11 3 3 11 9 2 3 8 112 69 74 109 109 109 83 73 125 55 11 16 293 293 185 75 96 176 16 16 13 3 4 14 36 36 36 36 1 36 35 74 9 28 7 109 110 7 20 92 146 142 6 119 6 2 2 109 92 112 13 258 257 258 89 146 137 137 136 2 1 2 127 1 8 9 76 16 70 4 125 15 2 73 88 125 1 123 123 2 111 16 4 83 29 110 86 28 2 109 2 28 15 1 75 15 104 110 28 9 5 2 54 35 110 109 8 20 35 53 57 7 41 39 2 92 92 71 71 27 2 20 14 9 20 22 26 19 14 15 15 13 106 1 105 1 101 6 105 105 87 4 104 72 72 101 20 18 55 59 92 75 92 75 105 20 97 35 101 9 72 66 105 105 40 65 3 104 65 1 2 2 3 2 2 2 2 1 1 1 1 1 1 24 504 24 55 124 105 269 22 43 43 121 6 6 4 4174 4031 293 508 507 283 1 1 1 1 1 1 1 124 130 111 21 108 36 36 2 3 34 68 62 67 63 129 1 128 2 130 161 116 66 70 56 15 115 88 466 466 354 598 598 467 6 3 3 2 3 14 2 2 2 3 2 5 5 1 1 2 15 1 2 3 3 3 2 1 222 176 122 202 85 301 112 91 23 222 18 4 15 148 28 124 1 1 8 4 2 3 9 8 8 9 9 9 8 1 1 9 9 3 153 153 12 131 122 12 4 125 62 4 43 31 125 12 1 1 1 12 1 67 67 1 1 6 12 18 1 9 3 1 5 18 18 18 19 19 2 19 5 5 1 14 14 14 14 6 6 6 20 1 19 1 1 2 1 1 197 191 55 103 19 94 102 94 122 1 33 33 9 30 5 33 9 55 55 171 171 54 55 54 55 55 124 124 1 123 171 508 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-1.0+ /* * originally based on the dummy device. * * Copyright 1999, Thomas Davis, tadavis@lbl.gov. * Based on dummy.c, and eql.c devices. * * bonding.c: an Ethernet Bonding driver * * This is useful to talk to a Cisco EtherChannel compatible equipment: * Cisco 5500 * Sun Trunking (Solaris) * Alteon AceDirector Trunks * Linux Bonding * and probably many L2 switches ... * * How it works: * ifconfig bond0 ipaddress netmask up * will setup a network device, with an ip address. No mac address * will be assigned at this time. The hw mac address will come from * the first slave bonded to the channel. All slaves will then use * this hw mac address. * * ifconfig bond0 down * will release all slaves, marking them as down. * * ifenslave bond0 eth0 * will attach eth0 to bond0 as a slave. eth0 hw mac address will either * a: be used as initial mac address * b: if a hw mac address already is there, eth0's hw mac address * will then be set from bond0. * */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/filter.h> #include <linux/interrupt.h> #include <linux/ptrace.h> #include <linux/ioport.h> #include <linux/in.h> #include <net/ip.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/init.h> #include <linux/timer.h> #include <linux/socket.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/bitops.h> #include <linux/io.h> #include <asm/dma.h> #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/rtnetlink.h> #include <linux/smp.h> #include <linux/if_ether.h> #include <net/arp.h> #include <linux/mii.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> #include <linux/if_bonding.h> #include <linux/phy.h> #include <linux/jiffies.h> #include <linux/preempt.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/pkt_sched.h> #include <linux/rculist.h> #include <net/flow_dissector.h> #include <net/xfrm.h> #include <net/bonding.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #if IS_ENABLED(CONFIG_TLS_DEVICE) #include <net/tls.h> #endif #include <net/ip6_route.h> #include <net/netdev_lock.h> #include <net/xdp.h> #include "bonding_priv.h" /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ static int max_bonds = BOND_DEFAULT_MAX_BONDS; static int tx_queues = BOND_DEFAULT_TX_QUEUES; static int num_peer_notif = 1; static int miimon; static int updelay; static int downdelay; static int use_carrier = 1; static char *mode; static char *primary; static char *primary_reselect; static char *lacp_rate; static int min_links; static char *ad_select; static char *xmit_hash_policy; static int arp_interval; static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; static char *arp_validate; static char *arp_all_targets; static char *fail_over_mac; static int all_slaves_active; static struct bond_params bonding_defaults; static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; static int packets_per_slave = 1; static int lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); module_param(tx_queues, int, 0); MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)"); module_param_named(num_grat_arp, num_peer_notif, int, 0644); MODULE_PARM_DESC(num_grat_arp, "Number of peer notifications to send on " "failover event (alias of num_unsol_na)"); module_param_named(num_unsol_na, num_peer_notif, int, 0644); MODULE_PARM_DESC(num_unsol_na, "Number of peer notifications to send on " "failover event (alias of num_grat_arp)"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); MODULE_PARM_DESC(updelay, "Delay before considering link up, in milliseconds"); module_param(downdelay, int, 0); MODULE_PARM_DESC(downdelay, "Delay before considering link down, " "in milliseconds"); module_param(use_carrier, int, 0); MODULE_PARM_DESC(use_carrier, "Use netif_carrier_ok (vs MII ioctls) in miimon; " "0 for off, 1 for on (default)"); module_param(mode, charp, 0); MODULE_PARM_DESC(mode, "Mode of operation; 0 for balance-rr, " "1 for active-backup, 2 for balance-xor, " "3 for broadcast, 4 for 802.3ad, 5 for balance-tlb, " "6 for balance-alb"); module_param(primary, charp, 0); MODULE_PARM_DESC(primary, "Primary network device to use"); module_param(primary_reselect, charp, 0); MODULE_PARM_DESC(primary_reselect, "Reselect primary slave " "once it comes up; " "0 for always (default), " "1 for only if speed of primary is " "better, " "2 for only on active slave " "failure"); module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; " "0 for slow, 1 for fast"); module_param(ad_select, charp, 0); MODULE_PARM_DESC(ad_select, "802.3ad aggregation selection logic; " "0 for stable (default), 1 for bandwidth, " "2 for count"); module_param(min_links, int, 0); MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on carrier"); module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "balance-alb, balance-tlb, balance-xor, 802.3ad hashing method; " "0 for layer 2 (default), 1 for layer 3+4, " "2 for layer 2+3, 3 for encap layer 2+3, " "4 for encap layer 3+4, 5 for vlan+srcmac"); module_param(arp_interval, int, 0); MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds"); module_param_array(arp_ip_target, charp, NULL, 0); MODULE_PARM_DESC(arp_ip_target, "arp targets in n.n.n.n form"); module_param(arp_validate, charp, 0); MODULE_PARM_DESC(arp_validate, "validate src/dst of ARP probes; " "0 for none (default), 1 for active, " "2 for backup, 3 for all"); module_param(arp_all_targets, charp, 0); MODULE_PARM_DESC(arp_all_targets, "fail on any/all arp targets timeout; 0 for any (default), 1 for all"); module_param(fail_over_mac, charp, 0); MODULE_PARM_DESC(fail_over_mac, "For active-backup, do not set all slaves to " "the same MAC; 0 for none (default), " "1 for active, 2 for follow"); module_param(all_slaves_active, int, 0); MODULE_PARM_DESC(all_slaves_active, "Keep all frames received on an interface " "by setting active flag for all slaves; " "0 for never (default), 1 for always."); module_param(resend_igmp, int, 0); MODULE_PARM_DESC(resend_igmp, "Number of IGMP membership reports to send on " "link failure"); module_param(packets_per_slave, int, 0); MODULE_PARM_DESC(packets_per_slave, "Packets to send per slave in balance-rr " "mode; 0 for a random slave, 1 packet per " "slave (default), >1 packets per slave."); module_param(lp_interval, uint, 0); MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where " "the bonding driver sends learning packets to " "each slaves peer switch. The default is 1."); /*----------------------------- Global variables ----------------------------*/ #ifdef CONFIG_NET_POLL_CONTROLLER atomic_t netpoll_block_tx = ATOMIC_INIT(0); #endif unsigned int bond_net_id __read_mostly; static const struct flow_dissector_key flow_keys_bonding_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_ICMP, .offset = offsetof(struct flow_keys, icmp), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static struct flow_dissector flow_keys_bonding __read_mostly; /*-------------------------- Forward declarations ---------------------------*/ static int bond_init(struct net_device *bond_dev); static void bond_uninit(struct net_device *bond_dev); static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats); static void bond_slave_arr_handler(struct work_struct *work); static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod); static void bond_netdev_notify_work(struct work_struct *work); /*---------------------------- General routines -----------------------------*/ const char *bond_mode_name(int mode) { static const char *names[] = { [BOND_MODE_ROUNDROBIN] = "load balancing (round-robin)", [BOND_MODE_ACTIVEBACKUP] = "fault-tolerance (active-backup)", [BOND_MODE_XOR] = "load balancing (xor)", [BOND_MODE_BROADCAST] = "fault-tolerance (broadcast)", [BOND_MODE_8023AD] = "IEEE 802.3ad Dynamic link aggregation", [BOND_MODE_TLB] = "transmit load balancing", [BOND_MODE_ALB] = "adaptive load balancing", }; if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB) return "unknown"; return names[mode]; } /** * bond_dev_queue_xmit - Prepare skb for xmit. * * @bond: bond device that got this skb for tx. * @skb: hw accel VLAN tagged skb to transmit * @slave_dev: slave that is supposed to xmit this skbuff */ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev) { skb->dev = slave_dev; BUILD_BUG_ON(sizeof(skb->queue_mapping) != sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); if (unlikely(netpoll_tx_running(bond->dev))) return bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); return dev_queue_xmit(skb); } static bool bond_sk_check(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_8023AD: case BOND_MODE_XOR: if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34) return true; fallthrough; default: return false; } } bool bond_xdp_check(struct bonding *bond, int mode) { switch (mode) { case BOND_MODE_ROUNDROBIN: case BOND_MODE_ACTIVEBACKUP: return true; case BOND_MODE_8023AD: case BOND_MODE_XOR: /* vlan+srcmac is not supported with XDP as in most cases the 802.1q * payload is not in the packet due to hardware offload. */ if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) return true; fallthrough; default: return false; } } /*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, * We don't protect the slave list iteration with a lock because: * a. This operation is performed in IOCTL context, * b. The operation is protected by the RTNL semaphore in the 8021q code, * c. Holding a lock with BH disabled while directly calling a base driver * entry point is generally a BAD idea. * * The design of synchronization/protection for this operation in the 8021q * module is good for one or more VLAN devices over a single physical device * and cannot be extended for a teaming solution like bonding, so there is a * potential race condition here where a net device from the vlan group might * be referenced (either by a base driver or the 8021q code) while it is being * removed from the system. However, it turns out we're not making matters * worse, and if it works for regular VLAN usage it will work here too. */ /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called * @proto: network protocol ID * @vid: vlan id being added */ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct list_head *iter; int res; bond_for_each_slave(bond, slave, iter) { res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; } return 0; unwind: /* unwind to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { if (rollback_slave == slave) break; vlan_vid_del(rollback_slave->dev, proto, vid); } return res; } /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called * @proto: network protocol ID * @vid: vlan id being removed */ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_for_each_slave(bond, slave, iter) vlan_vid_del(slave->dev, proto, vid); if (bond_is_lb(bond)) bond_alb_clear_vlan(bond, vid); return 0; } /*---------------------------------- XFRM -----------------------------------*/ #ifdef CONFIG_XFRM_OFFLOAD /** * bond_ipsec_dev - Get active device for IPsec offload * @xs: pointer to transformer state struct * * Context: caller must hold rcu_read_lock. * * Return: the device for ipsec offload, or NULL if not exist. **/ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct bonding *bond; struct slave *slave; bond = netdev_priv(bond_dev); if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) return NULL; slave = rcu_dereference(bond->curr_active_slave); if (!slave) return NULL; if (!xs->xso.real_dev) return NULL; if (xs->xso.real_dev != slave->dev) pr_warn_ratelimited("%s: (slave %s): not same with IPsec offload real dev %s\n", bond_dev->name, slave->dev->name, xs->xso.real_dev->name); return slave->dev; } /** * bond_ipsec_add_sa - program device with a security association * @bond_dev: pointer to the bond net device * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ static int bond_ipsec_add_sa(struct net_device *bond_dev, struct xfrm_state *xs, struct netlink_ext_ack *extack) { struct net_device *real_dev; netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; int err; if (!bond_dev) return -EINVAL; rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; netdev_hold(real_dev, &tracker, GFP_ATOMIC); rcu_read_unlock(); if (!real_dev) { err = -ENODEV; goto out; } if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload"); err = -EINVAL; goto out; } ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL); if (!ipsec) { err = -ENOMEM; goto out; } err = real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, xs, extack); if (!err) { xs->xso.real_dev = real_dev; ipsec->xs = xs; INIT_LIST_HEAD(&ipsec->list); mutex_lock(&bond->ipsec_lock); list_add(&ipsec->list, &bond->ipsec_list); mutex_unlock(&bond->ipsec_lock); } else { kfree(ipsec); } out: netdev_put(real_dev, &tracker); return err; } static void bond_ipsec_add_sa_all(struct bonding *bond) { struct net_device *bond_dev = bond->dev; struct net_device *real_dev; struct bond_ipsec *ipsec; struct slave *slave; slave = rtnl_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; if (!real_dev) return; mutex_lock(&bond->ipsec_lock); if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { if (!list_empty(&bond->ipsec_list)) slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_add\n", __func__); goto out; } list_for_each_entry(ipsec, &bond->ipsec_list, list) { /* If new state is added before ipsec_lock acquired */ if (ipsec->xs->xso.real_dev == real_dev) continue; if (real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, ipsec->xs, NULL)) { slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__); continue; } spin_lock_bh(&ipsec->xs->lock); /* xs might have been killed by the user during the migration * to the new dev, but bond_ipsec_del_sa() should have done * nothing, as xso.real_dev is NULL. * Delete it from the device we just added it to. The pending * bond_ipsec_free_sa() call will do the rest of the cleanup. */ if (ipsec->xs->km.state == XFRM_STATE_DEAD && real_dev->xfrmdev_ops->xdo_dev_state_delete) real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, ipsec->xs); ipsec->xs->xso.real_dev = real_dev; spin_unlock_bh(&ipsec->xs->lock); } out: mutex_unlock(&bond->ipsec_lock); } /** * bond_ipsec_del_sa - clear out this specific SA * @bond_dev: pointer to the bond net device * @xs: pointer to transformer state struct **/ static void bond_ipsec_del_sa(struct net_device *bond_dev, struct xfrm_state *xs) { struct net_device *real_dev; if (!bond_dev || !xs->xso.real_dev) return; real_dev = xs->xso.real_dev; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_delete || netif_is_bond_master(real_dev)) { slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); return; } real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, xs); } static void bond_ipsec_del_sa_all(struct bonding *bond) { struct net_device *bond_dev = bond->dev; struct net_device *real_dev; struct bond_ipsec *ipsec; struct slave *slave; slave = rtnl_dereference(bond->curr_active_slave); real_dev = slave ? slave->dev : NULL; if (!real_dev) return; mutex_lock(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (!ipsec->xs->xso.real_dev) continue; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_delete || netif_is_bond_master(real_dev)) { slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__); continue; } spin_lock_bh(&ipsec->xs->lock); ipsec->xs->xso.real_dev = NULL; /* Don't double delete states killed by the user. */ if (ipsec->xs->km.state != XFRM_STATE_DEAD) real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, ipsec->xs); spin_unlock_bh(&ipsec->xs->lock); if (real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, ipsec->xs); } mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_free_sa(struct net_device *bond_dev, struct xfrm_state *xs) { struct net_device *real_dev; struct bond_ipsec *ipsec; struct bonding *bond; if (!bond_dev) return; bond = netdev_priv(bond_dev); mutex_lock(&bond->ipsec_lock); if (!xs->xso.real_dev) goto out; real_dev = xs->xso.real_dev; xs->xso.real_dev = NULL; if (real_dev->xfrmdev_ops && real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, xs); out: list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (ipsec->xs == xs) { list_del(&ipsec->list); kfree(ipsec); break; } } mutex_unlock(&bond->ipsec_lock); } /** * bond_ipsec_offload_ok - can this packet use the xfrm hw offload * @skb: current data packet * @xs: pointer to transformer state struct **/ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev || netif_is_bond_master(real_dev)) { rcu_read_unlock(); return false; } rcu_read_unlock(); return true; } /** * bond_advance_esn_state - ESN support for IPSec HW offload * @xs: pointer to transformer state struct **/ static void bond_advance_esn_state(struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev) goto out; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_advance_esn) { pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_advance_esn(xs); out: rcu_read_unlock(); } /** * bond_xfrm_update_stats - Update xfrm state * @xs: pointer to transformer state struct **/ static void bond_xfrm_update_stats(struct xfrm_state *xs) { struct net_device *real_dev; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev) goto out; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_update_stats) { pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_update_stats\n", __func__, real_dev->name); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_update_stats(xs); out: rcu_read_unlock(); } static const struct xfrmdev_ops bond_xfrmdev_ops = { .xdo_dev_state_add = bond_ipsec_add_sa, .xdo_dev_state_delete = bond_ipsec_del_sa, .xdo_dev_state_free = bond_ipsec_free_sa, .xdo_dev_offload_ok = bond_ipsec_offload_ok, .xdo_dev_state_advance_esn = bond_advance_esn_state, .xdo_dev_state_update_stats = bond_xfrm_update_stats, }; #endif /* CONFIG_XFRM_OFFLOAD */ /*------------------------------- Link status -------------------------------*/ /* Set the carrier state for the master according to the state of its * slaves. If any slaves are up, the master is up. In 802.3ad mode, * do special 802.3ad magic. * * Returns zero if carrier state does not change, nonzero if it does. */ int bond_set_carrier(struct bonding *bond) { struct list_head *iter; struct slave *slave; if (!bond_has_slaves(bond)) goto down; if (BOND_MODE(bond) == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); return 1; } return 0; } } down: if (netif_carrier_ok(bond->dev)) { netif_carrier_off(bond->dev); return 1; } return 0; } /* Get link speed and duplex from the slave's base driver * using ethtool. If for some reason the call fails or the * values are invalid, set speed and duplex to -1, * and return. Return 1 if speed or duplex settings are * UNKNOWN; 0 otherwise. */ static int bond_update_speed_duplex(struct slave *slave) { struct net_device *slave_dev = slave->dev; struct ethtool_link_ksettings ecmd; int res; slave->speed = SPEED_UNKNOWN; slave->duplex = DUPLEX_UNKNOWN; res = __ethtool_get_link_ksettings(slave_dev, &ecmd); if (res < 0) return 1; if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1)) return 1; switch (ecmd.base.duplex) { case DUPLEX_FULL: case DUPLEX_HALF: break; default: return 1; } slave->speed = ecmd.base.speed; slave->duplex = ecmd.base.duplex; return 0; } const char *bond_slave_link_status(s8 link) { switch (link) { case BOND_LINK_UP: return "up"; case BOND_LINK_FAIL: return "going down"; case BOND_LINK_DOWN: return "down"; case BOND_LINK_BACK: return "going back"; default: return "unknown"; } } /* if <dev> supports MII link status reporting, check its link status. * * We either do MII/ETHTOOL ioctls, or check netif_carrier_ok(), * depending upon the setting of the use_carrier parameter. * * Return either BMSR_LSTATUS, meaning that the link is up (or we * can't tell and just pretend it is), or 0, meaning that the link is * down. * * If reporting is non-zero, instead of faking link up, return -1 if * both ETHTOOL and MII ioctls fail (meaning the device does not * support them). If use_carrier is set, return whatever it says. * It'd be nice if there was a good way to tell if a driver supports * netif_carrier, but there really isn't. */ static int bond_check_dev_link(struct bonding *bond, struct net_device *slave_dev, int reporting) { const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct mii_ioctl_data *mii; struct ifreq ifr; int ret; if (!reporting && !netif_running(slave_dev)) return 0; if (bond->params.use_carrier) return netif_carrier_ok(slave_dev) ? BMSR_LSTATUS : 0; /* Try to get link status using Ethtool first. */ if (slave_dev->ethtool_ops->get_link) { netdev_lock_ops(slave_dev); ret = slave_dev->ethtool_ops->get_link(slave_dev); netdev_unlock_ops(slave_dev); return ret ? BMSR_LSTATUS : 0; } /* Ethtool can't be used, fallback to MII ioctls. */ if (slave_ops->ndo_eth_ioctl) { /* TODO: set pointer to correct ioctl on a per team member * bases to make this more efficient. that is, once * we determine the correct ioctl, we will always * call it and not the others for that team * member. */ /* We cannot assume that SIOCGMIIPHY will also read a * register; not all network drivers (e.g., e100) * support that. */ /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ); mii = if_mii(&ifr); if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { mii->reg_num = MII_BMSR; if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0) return mii->val_out & BMSR_LSTATUS; } } /* If reporting, report that either there's no ndo_eth_ioctl, * or both SIOCGMIIREG and get_link failed (meaning that we * cannot report link status). If not reporting, pretend * we're ok. */ return reporting ? -1 : BMSR_LSTATUS; } /*----------------------------- Multicast list ------------------------------*/ /* Push the promiscuity flag down to appropriate slaves */ static int bond_set_promiscuity(struct bonding *bond, int inc) { struct list_head *iter; int err = 0; if (bond_uses_primary(bond)) { struct slave *curr_active = rtnl_dereference(bond->curr_active_slave); if (curr_active) err = dev_set_promiscuity(curr_active->dev, inc); } else { struct slave *slave; bond_for_each_slave(bond, slave, iter) { err = dev_set_promiscuity(slave->dev, inc); if (err) return err; } } return err; } /* Push the allmulti flag down to all slaves */ static int bond_set_allmulti(struct bonding *bond, int inc) { struct list_head *iter; int err = 0; if (bond_uses_primary(bond)) { struct slave *curr_active = rtnl_dereference(bond->curr_active_slave); if (curr_active) err = dev_set_allmulti(curr_active->dev, inc); } else { struct slave *slave; bond_for_each_slave(bond, slave, iter) { err = dev_set_allmulti(slave->dev, inc); if (err) return err; } } return err; } /* Retrieve the list of registered multicast addresses for the bonding * device and retransmit an IGMP JOIN request to the current active * slave. */ static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mcast_work.work); if (!rtnl_trylock()) { queue_delayed_work(bond->wq, &bond->mcast_work, 1); return; } call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev); if (bond->igmp_retrans > 1) { bond->igmp_retrans--; queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); } rtnl_unlock(); } /* Flush bond's hardware addresses from slave */ static void bond_hw_addr_flush(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); dev_uc_unsync(slave_dev, bond_dev); dev_mc_unsync(slave_dev, bond_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) dev_mc_del(slave_dev, lacpdu_mcast_addr); } /*--------------------------- Active slave change ---------------------------*/ /* Update the hardware address list and promisc/allmulti for the new and * old active slaves (if any). Modes that are not using primary keep all * slaves up date at all times; only the modes that use primary need to call * this function to swap these settings during a failover. */ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active) { if (old_active) { if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(old_active->dev, -1); if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); if (bond->dev->flags & IFF_UP) bond_hw_addr_flush(bond->dev, old_active->dev); bond_slave_ns_maddrs_add(bond, old_active); } if (new_active) { /* FIXME: Signal errors upstream. */ if (bond->dev->flags & IFF_PROMISC) dev_set_promiscuity(new_active->dev, 1); if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); if (bond->dev->flags & IFF_UP) { netif_addr_lock_bh(bond->dev); dev_uc_sync(new_active->dev, bond->dev); dev_mc_sync(new_active->dev, bond->dev); netif_addr_unlock_bh(bond->dev); } bond_slave_ns_maddrs_del(bond, new_active); } } /** * bond_set_dev_addr - clone slave's address to bond * @bond_dev: bond net device * @slave_dev: slave net device * * Should be called with RTNL held. */ static int bond_set_dev_addr(struct net_device *bond_dev, struct net_device *slave_dev) { int err; slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", bond_dev, slave_dev, slave_dev->addr_len); err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); if (err) return err; __dev_addr_set(bond_dev, slave_dev->dev_addr, slave_dev->addr_len); bond_dev->addr_assign_type = NET_ADDR_STOLEN; call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev); return 0; } static struct slave *bond_get_old_active(struct bonding *bond, struct slave *new_active) { struct slave *slave; struct list_head *iter; bond_for_each_slave(bond, slave, iter) { if (slave == new_active) continue; if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr)) return slave; } return NULL; } /* bond_do_fail_over_mac * * Perform special MAC address swapping for fail_over_mac settings * * Called with RTNL */ static void bond_do_fail_over_mac(struct bonding *bond, struct slave *new_active, struct slave *old_active) { u8 tmp_mac[MAX_ADDR_LEN]; struct sockaddr_storage ss; int rv; switch (bond->params.fail_over_mac) { case BOND_FOM_ACTIVE: if (new_active) { rv = bond_set_dev_addr(bond->dev, new_active->dev); if (rv) slave_err(bond->dev, new_active->dev, "Error %d setting bond MAC from slave\n", -rv); } break; case BOND_FOM_FOLLOW: /* if new_active && old_active, swap them * if just old_active, do nothing (going to no active slave) * if just new_active, set new_active to bond's MAC */ if (!new_active) return; if (!old_active) old_active = bond_get_old_active(bond, new_active); if (old_active) { bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr, new_active->dev->addr_len); bond_hw_addr_copy(ss.__data, old_active->dev->dev_addr, old_active->dev->addr_len); ss.ss_family = new_active->dev->type; } else { bond_hw_addr_copy(ss.__data, bond->dev->dev_addr, bond->dev->addr_len); ss.ss_family = bond->dev->type; } rv = dev_set_mac_address(new_active->dev, &ss, NULL); if (rv) { slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n", -rv); goto out; } if (!old_active) goto out; bond_hw_addr_copy(ss.__data, tmp_mac, new_active->dev->addr_len); ss.ss_family = old_active->dev->type; rv = dev_set_mac_address(old_active->dev, &ss, NULL); if (rv) slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n", -rv); out: break; default: netdev_err(bond->dev, "bond_do_fail_over_mac impossible: bad policy %d\n", bond->params.fail_over_mac); break; } } /** * bond_choose_primary_or_current - select the primary or high priority slave * @bond: our bonding struct * * - Check if there is a primary link. If the primary link was set and is up, * go on and do link reselection. * * - If primary link is not set or down, find the highest priority link. * If the highest priority link is not current slave, set it as primary * link and do link reselection. */ static struct slave *bond_choose_primary_or_current(struct bonding *bond) { struct slave *prim = rtnl_dereference(bond->primary_slave); struct slave *curr = rtnl_dereference(bond->curr_active_slave); struct slave *slave, *hprio = NULL; struct list_head *iter; if (!prim || prim->link != BOND_LINK_UP) { bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) { hprio = hprio ?: slave; if (slave->prio > hprio->prio) hprio = slave; } } if (hprio && hprio != curr) { prim = hprio; goto link_reselect; } if (!curr || curr->link != BOND_LINK_UP) return NULL; return curr; } if (bond->force_primary) { bond->force_primary = false; return prim; } link_reselect: if (!curr || curr->link != BOND_LINK_UP) return prim; /* At this point, prim and curr are both up */ switch (bond->params.primary_reselect) { case BOND_PRI_RESELECT_ALWAYS: return prim; case BOND_PRI_RESELECT_BETTER: if (prim->speed < curr->speed) return curr; if (prim->speed == curr->speed && prim->duplex <= curr->duplex) return curr; return prim; case BOND_PRI_RESELECT_FAILURE: return curr; default: netdev_err(bond->dev, "impossible primary_reselect %d\n", bond->params.primary_reselect); return curr; } } /** * bond_find_best_slave - select the best available slave to be the active one * @bond: our bonding struct */ static struct slave *bond_find_best_slave(struct bonding *bond) { struct slave *slave, *bestslave = NULL; struct list_head *iter; int mintime = bond->params.updelay; slave = bond_choose_primary_or_current(bond); if (slave) return slave; bond_for_each_slave(bond, slave, iter) { if (slave->link == BOND_LINK_UP) return slave; if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) && slave->delay < mintime) { mintime = slave->delay; bestslave = slave; } } return bestslave; } /* must be called in RCU critical section or with RTNL held */ static bool bond_should_notify_peers(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); if (!slave || !bond->send_peer_notif || bond->send_peer_notif % max(1, bond->params.peer_notif_delay) != 0 || !netif_carrier_ok(bond->dev) || test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n", slave ? slave->dev->name : "NULL"); return true; } /** * bond_change_active_slave - change the active slave into the specified one * @bond: our bonding struct * @new_active: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. * Setting include flags, mc-list, promiscuity, allmulti, etc. * * If @new's link state is %BOND_LINK_BACK we'll set it to %BOND_LINK_UP, * because it is apparently the best available slave we have, even though its * updelay hasn't timed out yet. * * Caller must hold RTNL. */ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) { struct slave *old_active; ASSERT_RTNL(); old_active = rtnl_dereference(bond->curr_active_slave); if (old_active == new_active) return; #ifdef CONFIG_XFRM_OFFLOAD bond_ipsec_del_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ if (new_active) { new_active->last_link_up = jiffies; if (new_active->link == BOND_LINK_BACK) { if (bond_uses_primary(bond)) { slave_info(bond->dev, new_active->dev, "making interface the new active one %d ms earlier\n", (bond->params.updelay - new_active->delay) * bond->params.miimon); } new_active->delay = 0; bond_set_slave_link_state(new_active, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_handle_link_change(new_active, BOND_LINK_UP); if (bond_is_lb(bond)) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } else { if (bond_uses_primary(bond)) slave_info(bond->dev, new_active->dev, "making interface the new active one\n"); } } if (bond_uses_primary(bond)) bond_hw_addr_swap(bond, new_active, old_active); if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); if (old_active) bond_set_slave_inactive_flags(old_active, BOND_SLAVE_NOTIFY_NOW); if (new_active) bond_set_slave_active_flags(new_active, BOND_SLAVE_NOTIFY_NOW); } else { rcu_assign_pointer(bond->curr_active_slave, new_active); } if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { if (old_active) bond_set_slave_inactive_flags(old_active, BOND_SLAVE_NOTIFY_NOW); if (new_active) { bool should_notify_peers = false; bond_set_slave_active_flags(new_active, BOND_SLAVE_NOTIFY_NOW); if (bond->params.fail_over_mac) bond_do_fail_over_mac(bond, new_active, old_active); if (netif_running(bond->dev)) { bond->send_peer_notif = bond->params.num_peer_notif * max(1, bond->params.peer_notif_delay); should_notify_peers = bond_should_notify_peers(bond); } call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); if (should_notify_peers) { bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); } } } #ifdef CONFIG_XFRM_OFFLOAD bond_ipsec_add_sa_all(bond); #endif /* CONFIG_XFRM_OFFLOAD */ /* resend IGMP joins since active slave has changed or * all were sent on curr_active_slave. * resend only if bond is brought up with the affected * bonding modes and the retransmission is enabled */ if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) && ((bond_uses_primary(bond) && new_active) || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN)) { bond->igmp_retrans = bond->params.resend_igmp; queue_delayed_work(bond->wq, &bond->mcast_work, 1); } } /** * bond_select_active_slave - select a new active slave, if needed * @bond: our bonding struct * * This functions should be called when one of the following occurs: * - The old curr_active_slave has been released or lost its link. * - The primary_slave has got its link back. * - A slave has got its link back and there's no old curr_active_slave. * * Caller must hold RTNL. */ void bond_select_active_slave(struct bonding *bond) { struct slave *best_slave; int rv; ASSERT_RTNL(); best_slave = bond_find_best_slave(bond); if (best_slave != rtnl_dereference(bond->curr_active_slave)) { bond_change_active_slave(bond, best_slave); rv = bond_set_carrier(bond); if (!rv) return; if (netif_carrier_ok(bond->dev)) netdev_info(bond->dev, "active interface up!\n"); else netdev_info(bond->dev, "now running without any active interface!\n"); } } #ifdef CONFIG_NET_POLL_CONTROLLER static inline int slave_enable_netpoll(struct slave *slave) { struct netpoll *np; int err = 0; np = kzalloc(sizeof(*np), GFP_KERNEL); err = -ENOMEM; if (!np) goto out; err = __netpoll_setup(np, slave->dev); if (err) { kfree(np); goto out; } slave->np = np; out: return err; } static inline void slave_disable_netpoll(struct slave *slave) { struct netpoll *np = slave->np; if (!np) return; slave->np = NULL; __netpoll_free(np); } static void bond_poll_controller(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; struct list_head *iter; struct ad_info ad_info; if (BOND_MODE(bond) == BOND_MODE_8023AD) if (bond_3ad_get_active_agg_info(bond, &ad_info)) return; bond_for_each_slave_rcu(bond, slave, iter) { if (!bond_slave_is_up(slave)) continue; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg = SLAVE_AD_INFO(slave)->port.aggregator; if (agg && agg->aggregator_identifier != ad_info.aggregator_id) continue; } netpoll_poll_dev(slave->dev); } } static void bond_netpoll_cleanup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_for_each_slave(bond, slave, iter) if (bond_slave_is_up(slave)) slave_disable_netpoll(slave); } static int bond_netpoll_setup(struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; struct slave *slave; int err = 0; bond_for_each_slave(bond, slave, iter) { err = slave_enable_netpoll(slave); if (err) { bond_netpoll_cleanup(dev); break; } } return err; } #else static inline int slave_enable_netpoll(struct slave *slave) { return 0; } static inline void slave_disable_netpoll(struct slave *slave) { } static void bond_netpoll_cleanup(struct net_device *bond_dev) { } #endif /*---------------------------------- IOCTL ----------------------------------*/ static netdev_features_t bond_fix_features(struct net_device *dev, netdev_features_t features) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; netdev_features_t mask; struct slave *slave; mask = features; features = netdev_base_features(features); bond_for_each_slave(bond, slave, iter) { features = netdev_increment_features(features, slave->dev->features, mask); } features = netdev_add_tso_features(features, mask); return features; } #define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_PARTIAL) #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_GSO_SOFTWARE) #define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP) static void bond_compute_features(struct bonding *bond) { netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; #ifdef CONFIG_XFRM_OFFLOAD netdev_features_t xfrm_features = BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ netdev_features_t mpls_features = BOND_MPLS_FEATURES; struct net_device *bond_dev = bond->dev; struct list_head *iter; struct slave *slave; unsigned short max_hard_header_len = ETH_HLEN; unsigned int tso_max_size = TSO_MAX_SIZE; u16 tso_max_segs = TSO_MAX_SEGS; if (!bond_has_slaves(bond)) goto done; vlan_features = netdev_base_features(vlan_features); mpls_features = netdev_base_features(mpls_features); bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, slave->dev->vlan_features, BOND_VLAN_FEATURES); enc_features = netdev_increment_features(enc_features, slave->dev->hw_enc_features, BOND_ENC_FEATURES); #ifdef CONFIG_XFRM_OFFLOAD xfrm_features = netdev_increment_features(xfrm_features, slave->dev->hw_enc_features, BOND_XFRM_FEATURES); #endif /* CONFIG_XFRM_OFFLOAD */ gso_partial_features = netdev_increment_features(gso_partial_features, slave->dev->gso_partial_features, BOND_GSO_PARTIAL_FEATURES); mpls_features = netdev_increment_features(mpls_features, slave->dev->mpls_features, BOND_MPLS_FEATURES); dst_release_flag &= slave->dev->priv_flags; if (slave->dev->hard_header_len > max_hard_header_len) max_hard_header_len = slave->dev->hard_header_len; tso_max_size = min(tso_max_size, slave->dev->tso_max_size); tso_max_segs = min(tso_max_segs, slave->dev->tso_max_segs); } bond_dev->hard_header_len = max_hard_header_len; done: bond_dev->gso_partial_features = gso_partial_features; bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_enc_features |= xfrm_features; #endif /* CONFIG_XFRM_OFFLOAD */ bond_dev->mpls_features = mpls_features; netif_set_tso_max_segs(bond_dev, tso_max_segs); netif_set_tso_max_size(bond_dev, tso_max_size); bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) && dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE; netdev_change_features(bond_dev); } static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { bool was_up = !!(bond_dev->flags & IFF_UP); dev_close(bond_dev); bond_dev->header_ops = slave_dev->header_ops; bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; bond_dev->needed_headroom = slave_dev->needed_headroom; bond_dev->addr_len = slave_dev->addr_len; memcpy(bond_dev->broadcast, slave_dev->broadcast, slave_dev->addr_len); if (slave_dev->flags & IFF_POINTOPOINT) { bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } if (was_up) dev_open(bond_dev, NULL); } /* On bonding slaves other than the currently active slave, suppress * duplicates except for alb non-mcast/bcast. */ static bool bond_should_deliver_exact_match(struct sk_buff *skb, struct slave *slave, struct bonding *bond) { if (bond_is_slave_inactive(slave)) { if (BOND_MODE(bond) == BOND_MODE_ALB && skb->pkt_type != PACKET_BROADCAST && skb->pkt_type != PACKET_MULTICAST) return false; return true; } return false; } static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct slave *slave; struct bonding *bond; int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); int ret = RX_HANDLER_ANOTHER; skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) return RX_HANDLER_CONSUMED; *pskb = skb; slave = bond_slave_get_rcu(skb->dev); bond = slave->bond; recv_probe = READ_ONCE(bond->recv_probe); if (recv_probe) { ret = recv_probe(skb, bond, slave); if (ret == RX_HANDLER_CONSUMED) { consume_skb(skb); return ret; } } /* * For packets determined by bond_should_deliver_exact_match() call to * be suppressed we want to make an exception for link-local packets. * This is necessary for e.g. LLDP daemons to be able to monitor * inactive slave links without being forced to bind to them * explicitly. * * At the same time, packets that are passed to the bonding master * (including link-local ones) can have their originating interface * determined via PACKET_ORIGDEV socket option. */ if (bond_should_deliver_exact_match(skb, slave, bond)) { if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) return RX_HANDLER_PASS; return RX_HANDLER_EXACT; } skb->dev = bond->dev; if (BOND_MODE(bond) == BOND_MODE_ALB && netif_is_bridge_port(bond->dev) && skb->pkt_type == PACKET_HOST) { if (unlikely(skb_cow_head(skb, skb->data - skb_mac_header(skb)))) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, bond->dev->addr_len); } return ret; } static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: return NETDEV_LAG_TX_TYPE_ROUNDROBIN; case BOND_MODE_ACTIVEBACKUP: return NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; case BOND_MODE_BROADCAST: return NETDEV_LAG_TX_TYPE_BROADCAST; case BOND_MODE_XOR: case BOND_MODE_8023AD: return NETDEV_LAG_TX_TYPE_HASH; default: return NETDEV_LAG_TX_TYPE_UNKNOWN; } } static enum netdev_lag_hash bond_lag_hash_type(struct bonding *bond, enum netdev_lag_tx_type type) { if (type != NETDEV_LAG_TX_TYPE_HASH) return NETDEV_LAG_HASH_NONE; switch (bond->params.xmit_policy) { case BOND_XMIT_POLICY_LAYER2: return NETDEV_LAG_HASH_L2; case BOND_XMIT_POLICY_LAYER34: return NETDEV_LAG_HASH_L34; case BOND_XMIT_POLICY_LAYER23: return NETDEV_LAG_HASH_L23; case BOND_XMIT_POLICY_ENCAP23: return NETDEV_LAG_HASH_E23; case BOND_XMIT_POLICY_ENCAP34: return NETDEV_LAG_HASH_E34; case BOND_XMIT_POLICY_VLAN_SRCMAC: return NETDEV_LAG_HASH_VLAN_SRCMAC; default: return NETDEV_LAG_HASH_UNKNOWN; } } static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave, struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; enum netdev_lag_tx_type type; int err; type = bond_lag_tx_type(bond); lag_upper_info.tx_type = type; lag_upper_info.hash_type = bond_lag_hash_type(bond, type); err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave, &lag_upper_info, extack); if (err) return err; slave->dev->flags |= IFF_SLAVE; return 0; } static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave) { netdev_upper_dev_unlink(slave->dev, bond->dev); slave->dev->flags &= ~IFF_SLAVE; } static void slave_kobj_release(struct kobject *kobj) { struct slave *slave = to_slave(kobj); struct bonding *bond = bond_get_bond_by_slave(slave); cancel_delayed_work_sync(&slave->notify_work); if (BOND_MODE(bond) == BOND_MODE_8023AD) kfree(SLAVE_AD_INFO(slave)); kfree(slave); } static struct kobj_type slave_ktype = { .release = slave_kobj_release, #ifdef CONFIG_SYSFS .sysfs_ops = &slave_sysfs_ops, #endif }; static int bond_kobj_init(struct slave *slave) { int err; err = kobject_init_and_add(&slave->kobj, &slave_ktype, &(slave->dev->dev.kobj), "bonding_slave"); if (err) kobject_put(&slave->kobj); return err; } static struct slave *bond_alloc_slave(struct bonding *bond, struct net_device *slave_dev) { struct slave *slave = NULL; slave = kzalloc(sizeof(*slave), GFP_KERNEL); if (!slave) return NULL; slave->bond = bond; slave->dev = slave_dev; INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); if (bond_kobj_init(slave)) return NULL; if (BOND_MODE(bond) == BOND_MODE_8023AD) { SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info), GFP_KERNEL); if (!SLAVE_AD_INFO(slave)) { kobject_put(&slave->kobj); return NULL; } } return slave; } static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info) { info->bond_mode = BOND_MODE(bond); info->miimon = bond->params.miimon; info->num_slaves = bond->slave_cnt; } static void bond_fill_ifslave(struct slave *slave, struct ifslave *info) { strcpy(info->slave_name, slave->dev->name); info->link = slave->link; info->state = bond_slave_state(slave); info->link_failure_count = slave->link_failure_count; } static void bond_netdev_notify_work(struct work_struct *_work) { struct slave *slave = container_of(_work, struct slave, notify_work.work); if (rtnl_trylock()) { struct netdev_bonding_info binfo; bond_fill_ifslave(slave, &binfo.slave); bond_fill_ifbond(slave->bond, &binfo.master); netdev_bonding_info_change(slave->dev, &binfo); rtnl_unlock(); } else { queue_delayed_work(slave->bond->wq, &slave->notify_work, 1); } } void bond_queue_slave_event(struct slave *slave) { queue_delayed_work(slave->bond->wq, &slave->notify_work, 0); } void bond_lower_state_changed(struct slave *slave) { struct netdev_lag_lower_state_info info; info.link_up = slave->link == BOND_LINK_UP || slave->link == BOND_LINK_FAIL; info.tx_enabled = bond_is_active_slave(slave); netdev_lower_state_changed(slave->dev, &info); } #define BOND_NL_ERR(bond_dev, extack, errmsg) do { \ if (extack) \ NL_SET_ERR_MSG(extack, errmsg); \ else \ netdev_err(bond_dev, "Error: %s\n", errmsg); \ } while (0) #define SLAVE_NL_ERR(bond_dev, slave_dev, extack, errmsg) do { \ if (extack) \ NL_SET_ERR_MSG(extack, errmsg); \ else \ slave_err(bond_dev, slave_dev, "Error: %s\n", errmsg); \ } while (0) /* The bonding driver uses ether_setup() to convert a master bond device * to ARPHRD_ETHER, that resets the target netdevice's flags so we always * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP * if they were set */ static void bond_ether_setup(struct net_device *bond_dev) { unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP); ether_setup(bond_dev); bond_dev->flags |= IFF_MASTER | flags; bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; } void bond_xdp_set_features(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); xdp_features_t val = NETDEV_XDP_ACT_MASK; struct list_head *iter; struct slave *slave; ASSERT_RTNL(); if (!bond_xdp_check(bond, BOND_MODE(bond)) || !bond_has_slaves(bond)) { xdp_clear_features_flag(bond_dev); return; } bond_for_each_slave(bond, slave, iter) val &= slave->dev->xdp_features; val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY; xdp_set_features_flag(bond_dev, val); } /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct slave *new_slave = NULL, *prev_slave; struct sockaddr_storage ss; int link_reporting; int res = 0, i; if (slave_dev->flags & IFF_MASTER && !netif_is_bond_master(slave_dev)) { BOND_NL_ERR(bond_dev, extack, "Device type (master device) cannot be enslaved"); return -EPERM; } if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && slave_ops->ndo_eth_ioctl == NULL) { slave_warn(bond_dev, slave_dev, "no link monitoring support\n"); } /* already in-use? */ if (netdev_is_rx_handler_busy(slave_dev)) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device is in use and cannot be enslaved"); return -EBUSY; } if (bond_dev == slave_dev) { BOND_NL_ERR(bond_dev, extack, "Cannot enslave bond to itself."); return -EPERM; } /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { slave_dbg(bond_dev, slave_dev, "is NETIF_F_VLAN_CHALLENGED\n"); if (vlan_uses_dev(bond_dev)) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Can not enslave VLAN challenged device to VLAN enabled bond"); return -EPERM; } else { slave_warn(bond_dev, slave_dev, "enslaved VLAN challenged slave. Adding VLANs will be blocked as long as it is part of bond.\n"); } } else { slave_dbg(bond_dev, slave_dev, "is !NETIF_F_VLAN_CHALLENGED\n"); } if (slave_dev->features & NETIF_F_HW_ESP) slave_dbg(bond_dev, slave_dev, "is esp-hw-offload capable\n"); /* Old ifenslave binaries are no longer supported. These can * be identified with moderate accuracy by the state of the slave: * the current ifenslave will set the interface down prior to * enslaving it; the old ifenslave will not. */ if (slave_dev->flags & IFF_UP) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device can not be enslaved while up"); return -EPERM; } /* set bonding device ether type by slave - bonding netdevices are * created with ether_setup, so when the slave type is not ARPHRD_ETHER * there is a need to override some of the type dependent attribs/funcs. * * bond ether type mutual exclusion - don't allow slaves of dissimilar * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond */ if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n", bond_dev->type, slave_dev->type); res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, bond_dev); res = notifier_to_errno(res); if (res) { slave_err(bond_dev, slave_dev, "refused to change device type\n"); return -EBUSY; } /* Flush unicast and multicast addresses */ dev_uc_flush(bond_dev); dev_mc_flush(bond_dev); if (slave_dev->type != ARPHRD_ETHER) bond_setup_by_slave(bond_dev, slave_dev); else bond_ether_setup(bond_dev); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, bond_dev); } } else if (bond_dev->type != slave_dev->type) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Device type is different from other slaves"); return -EINVAL; } if (slave_dev->type == ARPHRD_INFINIBAND && BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Only active-backup mode is supported for infiniband slaves"); res = -EOPNOTSUPP; goto err_undo_flags; } if (!slave_ops->ndo_set_mac_address || slave_dev->type == ARPHRD_INFINIBAND) { slave_warn(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address\n"); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && bond->params.fail_over_mac != BOND_FOM_ACTIVE) { if (!bond_has_slaves(bond)) { bond->params.fail_over_mac = BOND_FOM_ACTIVE; slave_warn(bond_dev, slave_dev, "Setting fail_over_mac to active for active-backup mode\n"); } else { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active"); res = -EOPNOTSUPP; goto err_undo_flags; } } } call_netdevice_notifiers(NETDEV_JOIN, slave_dev); /* If this is the first slave, then we need to set the master's hardware * address to be the same as the slave's. */ if (!bond_has_slaves(bond) && bond->dev->addr_assign_type == NET_ADDR_RANDOM) { res = bond_set_dev_addr(bond->dev, slave_dev); if (res) goto err_undo_flags; } new_slave = bond_alloc_slave(bond, slave_dev); if (!new_slave) { res = -ENOMEM; goto err_undo_flags; } /* Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. */ new_slave->queue_id = 0; /* Save slave's original mtu and then set it to match the bond */ new_slave->original_mtu = slave_dev->mtu; res = dev_set_mtu(slave_dev, bond->dev->mtu); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling dev_set_mtu\n", res); goto err_free; } /* Save slave's original ("permanent") mac address for modes * that need it, and for restoring it upon release, and then * set it to the master's address */ bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr, slave_dev->addr_len); if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* Set slave to master's mac address. The application already * set the master's mac address to that of the first slave */ memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len); } else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) { /* Set slave to random address to avoid duplicate mac * address in later fail over. */ eth_random_addr(ss.__data); } else { goto skip_mac_set; } ss.ss_family = slave_dev->type; res = dev_set_mac_address(slave_dev, &ss, extack); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); goto err_restore_mtu; } skip_mac_set: /* set no_addrconf flag before open to prevent IPv6 addrconf */ slave_dev->priv_flags |= IFF_NO_ADDRCONF; /* open the slave since the application closed it */ res = dev_open(slave_dev, extack); if (res) { slave_err(bond_dev, slave_dev, "Opening slave failed\n"); goto err_restore_mac; } slave_dev->priv_flags |= IFF_BONDING; /* initialize slave stats */ dev_get_stats(new_slave->dev, &new_slave->slave_stats); if (bond_is_lb(bond)) { /* bond_alb_init_slave() must be called before all other stages since * it might fail and we do not want to have to undo everything */ res = bond_alb_init_slave(bond, new_slave); if (res) goto err_close; } res = vlan_vids_add_by_dev(slave_dev, bond_dev); if (res) { slave_err(bond_dev, slave_dev, "Couldn't add bond vlan ids\n"); goto err_close; } prev_slave = bond_last_slave(bond); new_slave->delay = 0; new_slave->link_failure_count = 0; if (bond_update_speed_duplex(new_slave) && bond_needs_speed_duplex(bond)) new_slave->link = BOND_LINK_DOWN; new_slave->last_rx = jiffies - (msecs_to_jiffies(bond->params.arp_interval) + 1); for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) new_slave->target_last_arp_rx[i] = new_slave->last_rx; new_slave->last_tx = new_slave->last_rx; if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); if ((link_reporting == -1) && !bond->params.arp_interval) { /* miimon is set but a bonded network driver * does not support ETHTOOL/MII and * arp_interval is not set. Note: if * use_carrier is enabled, we will never go * here (because netif_carrier is always * supported); thus, we don't need to change * the messages for netif_carrier. */ slave_warn(bond_dev, slave_dev, "MII and ETHTOOL support not available for slave, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n"); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ slave_warn(bond_dev, slave_dev, "can't get link status from slave; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n"); } } /* check for initial state */ new_slave->link = BOND_LINK_NOCHANGE; if (bond->params.miimon) { if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) { if (bond->params.updelay) { bond_set_slave_link_state(new_slave, BOND_LINK_BACK, BOND_SLAVE_NOTIFY_NOW); new_slave->delay = bond->params.updelay; } else { bond_set_slave_link_state(new_slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); } } else { bond_set_slave_link_state(new_slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); } } else if (bond->params.arp_interval) { bond_set_slave_link_state(new_slave, (netif_carrier_ok(slave_dev) ? BOND_LINK_UP : BOND_LINK_DOWN), BOND_SLAVE_NOTIFY_NOW); } else { bond_set_slave_link_state(new_slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); } if (new_slave->link != BOND_LINK_DOWN) new_slave->last_link_up = jiffies; slave_dbg(bond_dev, slave_dev, "Initial state of slave is BOND_LINK_%s\n", new_slave->link == BOND_LINK_DOWN ? "DOWN" : (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); if (bond_uses_primary(bond) && bond->params.primary[0]) { /* if there is a primary slave, remember it */ if (strcmp(bond->params.primary, new_slave->dev->name) == 0) { rcu_assign_pointer(bond->primary_slave, new_slave); bond->force_primary = true; } } switch (BOND_MODE(bond)) { case BOND_MODE_ACTIVEBACKUP: bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism * will activate the slaves in the selected * aggregator */ bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); /* if this is the first slave */ if (!prev_slave) { SLAVE_AD_INFO(new_slave)->id = 1; /* Initialize AD with the number of times that the AD timer is called in 1 second * can be called only after the mac address of the bond is set */ bond_3ad_initialize(bond); } else { SLAVE_AD_INFO(new_slave)->id = SLAVE_AD_INFO(prev_slave)->id + 1; } bond_3ad_bind_slave(new_slave); break; case BOND_MODE_TLB: case BOND_MODE_ALB: bond_set_active_slave(new_slave); bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: slave_dbg(bond_dev, slave_dev, "This slave is always active in trunk mode\n"); /* always active in trunk mode */ bond_set_active_slave(new_slave); /* In trunking mode there is little meaning to curr_active_slave * anyway (it holds no special properties of the bond device), * so we can change it without calling change_active_interface() */ if (!rcu_access_pointer(bond->curr_active_slave) && new_slave->link == BOND_LINK_UP) rcu_assign_pointer(bond->curr_active_slave, new_slave); break; } /* switch(bond_mode) */ #ifdef CONFIG_NET_POLL_CONTROLLER if (bond->dev->npinfo) { if (slave_enable_netpoll(new_slave)) { slave_info(bond_dev, slave_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n"); res = -EBUSY; goto err_detach; } } #endif if (!(bond_dev->features & NETIF_F_LRO)) dev_disable_lro(slave_dev); res = netdev_rx_handler_register(slave_dev, bond_handle_frame, new_slave); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling netdev_rx_handler_register\n", res); goto err_detach; } res = bond_master_upper_dev_link(bond, new_slave, extack); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling bond_master_upper_dev_link\n", res); goto err_unregister; } bond_lower_state_changed(new_slave); res = bond_sysfs_slave_add(new_slave); if (res) { slave_dbg(bond_dev, slave_dev, "Error %d calling bond_sysfs_slave_add\n", res); goto err_upper_unlink; } /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ if (!bond_uses_primary(bond)) { /* set promiscuity level to new slave */ if (bond_dev->flags & IFF_PROMISC) { res = dev_set_promiscuity(slave_dev, 1); if (res) goto err_sysfs_del; } /* set allmulti level to new slave */ if (bond_dev->flags & IFF_ALLMULTI) { res = dev_set_allmulti(slave_dev, 1); if (res) { if (bond_dev->flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); goto err_sysfs_del; } } if (bond_dev->flags & IFF_UP) { netif_addr_lock_bh(bond_dev); dev_mc_sync_multiple(slave_dev, bond_dev); dev_uc_sync_multiple(slave_dev, bond_dev); netif_addr_unlock_bh(bond_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) dev_mc_add(slave_dev, lacpdu_mcast_addr); } } bond->slave_cnt++; bond_compute_features(bond); bond_set_carrier(bond); /* Needs to be called before bond_select_active_slave(), which will * remove the maddrs if the slave is selected as active slave. */ bond_slave_ns_maddrs_add(bond, new_slave); if (bond_uses_primary(bond)) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { if (bond->xdp_prog) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave does not support XDP"); res = -EOPNOTSUPP; goto err_sysfs_del; } } else if (bond->xdp_prog) { struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = bond->xdp_prog, .extack = extack, }; if (dev_xdp_prog_count(slave_dev) > 0) { SLAVE_NL_ERR(bond_dev, slave_dev, extack, "Slave has XDP program loaded, please unload before enslaving"); res = -EOPNOTSUPP; goto err_sysfs_del; } res = dev_xdp_propagate(slave_dev, &xdp); if (res < 0) { /* ndo_bpf() sets extack error message */ slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); goto err_sysfs_del; } if (bond->xdp_prog) bpf_prog_inc(bond->xdp_prog); } bond_xdp_set_features(bond_dev); slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", bond_is_active_slave(new_slave) ? "an active" : "a backup", new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); /* enslave is successful */ bond_queue_slave_event(new_slave); return 0; /* Undo stages on error */ err_sysfs_del: bond_sysfs_slave_del(new_slave); err_upper_unlink: bond_upper_dev_unlink(bond, new_slave); err_unregister: netdev_rx_handler_unregister(slave_dev); err_detach: vlan_vids_del_by_dev(slave_dev, bond_dev); if (rcu_access_pointer(bond->primary_slave) == new_slave) RCU_INIT_POINTER(bond->primary_slave, NULL); if (rcu_access_pointer(bond->curr_active_slave) == new_slave) { block_netpoll_tx(); bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); unblock_netpoll_tx(); } /* either primary_slave or curr_active_slave might've changed */ synchronize_rcu(); slave_disable_netpoll(new_slave); err_close: if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_restore_mac: slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* XXX TODO - fom follow mode needs to change master's * MAC if this slave's MAC is in use by the bond, or at * least print a warning. */ bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr, new_slave->dev->addr_len); ss.ss_family = slave_dev->type; dev_set_mac_address(slave_dev, &ss, NULL); } err_restore_mtu: dev_set_mtu(slave_dev, new_slave->original_mtu); err_free: kobject_put(&new_slave->kobj); err_undo_flags: /* Enslave of first slave has failed and we need to fix master's mac */ if (!bond_has_slaves(bond)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr)) eth_hw_addr_random(bond_dev); if (bond_dev->type != ARPHRD_ETHER) { dev_close(bond_dev); bond_ether_setup(bond_dev); } } return res; } /* Try to release the slave device <slave> from the bond device <master> * It is legal to access curr_active_slave without a lock because all the function * is RTNL-locked. If "all" is true it means that the function is being called * while destroying a bond interface and all slaves are being released. * * The rules for slave state should be: * for Active/Backup: * Active stays on all backups go down * for Bonded connections: * The first up interface should be left on and all others downed. */ static int __bond_release_one(struct net_device *bond_dev, struct net_device *slave_dev, bool all, bool unregister) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *oldcurrent; struct sockaddr_storage ss; int old_flags = bond_dev->flags; netdev_features_t old_features = bond_dev->features; /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || !netdev_has_upper_dev(slave_dev, bond_dev)) { slave_dbg(bond_dev, slave_dev, "cannot release slave\n"); return -EINVAL; } block_netpoll_tx(); slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ slave_info(bond_dev, slave_dev, "interface not enslaved\n"); unblock_netpoll_tx(); return -EINVAL; } bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); bond_sysfs_slave_del(slave); /* recompute stats just before removing the slave */ bond_get_stats(bond->dev, &bond->bond_stats); if (bond->xdp_prog) { struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = NULL, .extack = NULL, }; if (dev_xdp_propagate(slave_dev, &xdp)) slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); } /* unregister rx_handler early so bond_handle_frame wouldn't be called * for this slave anymore. */ netdev_rx_handler_unregister(slave_dev); if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_unbind_slave(slave); bond_upper_dev_unlink(bond, slave); if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, slave); slave_info(bond_dev, slave_dev, "Releasing %s interface\n", bond_is_active_slave(slave) ? "active" : "backup"); oldcurrent = rcu_access_pointer(bond->curr_active_slave); RCU_INIT_POINTER(bond->current_arp_slave, NULL); if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && bond_has_slaves(bond)) slave_warn(bond_dev, slave_dev, "the permanent HWaddr of slave - %pM - is still in use by bond - set the HWaddr of slave to a different address to avoid conflicts\n", slave->perm_hwaddr); } if (rtnl_dereference(bond->primary_slave) == slave) RCU_INIT_POINTER(bond->primary_slave, NULL); if (oldcurrent == slave) bond_change_active_slave(bond, NULL); /* Must be called after bond_change_active_slave () as the slave * might change from an active slave to a backup slave. Then it is * necessary to clear the maddrs on the backup slave. */ bond_slave_ns_maddrs_del(bond, slave); if (bond_is_lb(bond)) { /* Must be called only after the slave has been * detached from the list and the curr_active_slave * has been cleared (if our_slave == old_current), * but before a new active slave is selected. */ bond_alb_deinit_slave(bond, slave); } if (all) { RCU_INIT_POINTER(bond->curr_active_slave, NULL); } else if (oldcurrent == slave) { /* Note that we hold RTNL over this sequence, so there * is no concern that another slave add/remove event * will interfere. */ bond_select_active_slave(bond); } bond_set_carrier(bond); if (!bond_has_slaves(bond)) eth_hw_addr_random(bond_dev); unblock_netpoll_tx(); synchronize_rcu(); bond->slave_cnt--; if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); } bond_compute_features(bond); if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && (old_features & NETIF_F_VLAN_CHALLENGED)) slave_info(bond_dev, slave_dev, "last VLAN challenged slave left bond - VLAN blocking is removed\n"); vlan_vids_del_by_dev(slave_dev, bond_dev); /* If the mode uses primary, then this case was handled above by * bond_change_active_slave(..., NULL) */ if (!bond_uses_primary(bond)) { /* unset promiscuity level from slave * NOTE: The NETDEV_CHANGEADDR call above may change the value * of the IFF_PROMISC flag in the bond_dev, but we need the * value of that flag before that change, as that was the value * when this slave was attached, so we cache at the start of the * function and use it here. Same goes for ALLMULTI below */ if (old_flags & IFF_PROMISC) dev_set_promiscuity(slave_dev, -1); /* unset allmulti level from slave */ if (old_flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); if (old_flags & IFF_UP) bond_hw_addr_flush(bond_dev, slave_dev); } slave_disable_netpoll(slave); /* close slave before restoring its mac address */ dev_close(slave_dev); slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; if (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* restore original ("permanent") mac address */ bond_hw_addr_copy(ss.__data, slave->perm_hwaddr, slave->dev->addr_len); ss.ss_family = slave_dev->type; dev_set_mac_address(slave_dev, &ss, NULL); } if (unregister) { netdev_lock_ops(slave_dev); __dev_set_mtu(slave_dev, slave->original_mtu); netdev_unlock_ops(slave_dev); } else { dev_set_mtu(slave_dev, slave->original_mtu); } if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; bond_xdp_set_features(bond_dev); kobject_put(&slave->kobj); return 0; } /* A wrapper used because of ndo_del_link */ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) { return __bond_release_one(bond_dev, slave_dev, false, false); } /* First release a slave and then destroy the bond if no more slaves are left. * Must be under rtnl_lock when this function is called. */ static int bond_release_and_destroy(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); int ret; ret = __bond_release_one(bond_dev, slave_dev, false, true); if (ret == 0 && !bond_has_slaves(bond) && bond_dev->reg_state != NETREG_UNREGISTERING) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); unregister_netdevice(bond_dev); } return ret; } static void bond_info_query(struct net_device *bond_dev, struct ifbond *info) { struct bonding *bond = netdev_priv(bond_dev); bond_fill_ifbond(bond, info); } static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; int i = 0, res = -ENODEV; struct slave *slave; bond_for_each_slave(bond, slave, iter) { if (i++ == (int)info->slave_id) { res = 0; bond_fill_ifslave(slave, info); break; } } return res; } /*-------------------------------- Monitoring -------------------------------*/ /* called with rcu_read_lock() */ static int bond_miimon_inspect(struct bonding *bond) { bool ignore_updelay = false; int link_state, commit = 0; struct list_head *iter; struct slave *slave; if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) { ignore_updelay = !rcu_dereference(bond->curr_active_slave); } else { struct bond_up_slave *usable_slaves; usable_slaves = rcu_dereference(bond->usable_slaves); if (usable_slaves && usable_slaves->count == 0) ignore_updelay = true; } bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); link_state = bond_check_dev_link(bond, slave->dev, 0); switch (slave->link) { case BOND_LINK_UP: if (link_state) continue; bond_propose_link_state(slave, BOND_LINK_FAIL); commit++; slave->delay = bond->params.downdelay; if (slave->delay && net_ratelimit()) { slave_info(bond->dev, slave->dev, "link status down for %sinterface, disabling it in %d ms\n", (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) ? (bond_is_active_slave(slave) ? "active " : "backup ") : "", bond->params.downdelay * bond->params.miimon); } fallthrough; case BOND_LINK_FAIL: if (link_state) { /* recovered before downdelay expired */ bond_propose_link_state(slave, BOND_LINK_UP); slave->last_link_up = jiffies; if (net_ratelimit()) slave_info(bond->dev, slave->dev, "link status up again after %d ms\n", (bond->params.downdelay - slave->delay) * bond->params.miimon); commit++; continue; } if (slave->delay <= 0) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; continue; } slave->delay--; break; case BOND_LINK_DOWN: if (!link_state) continue; bond_propose_link_state(slave, BOND_LINK_BACK); commit++; slave->delay = bond->params.updelay; if (slave->delay && net_ratelimit()) { slave_info(bond->dev, slave->dev, "link status up, enabling it in %d ms\n", ignore_updelay ? 0 : bond->params.updelay * bond->params.miimon); } fallthrough; case BOND_LINK_BACK: if (!link_state) { bond_propose_link_state(slave, BOND_LINK_DOWN); if (net_ratelimit()) slave_info(bond->dev, slave->dev, "link status down again after %d ms\n", (bond->params.updelay - slave->delay) * bond->params.miimon); commit++; continue; } if (ignore_updelay) slave->delay = 0; if (slave->delay <= 0) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; ignore_updelay = false; continue; } slave->delay--; break; } } return commit; } static void bond_miimon_link_change(struct bonding *bond, struct slave *slave, char link) { switch (BOND_MODE(bond)) { case BOND_MODE_8023AD: bond_3ad_handle_link_change(slave, link); break; case BOND_MODE_TLB: case BOND_MODE_ALB: bond_alb_handle_link_change(bond, slave, link); break; case BOND_MODE_XOR: bond_update_slave_arr(bond, NULL); break; } } static void bond_miimon_commit(struct bonding *bond) { struct slave *slave, *primary, *active; bool do_failover = false; struct list_head *iter; ASSERT_RTNL(); bond_for_each_slave(bond, slave, iter) { switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: /* For 802.3ad mode, check current slave speed and * duplex again in case its port was disabled after * invalid speed/duplex reporting but recovered before * link monitoring could make a decision on the actual * link status */ if (BOND_MODE(bond) == BOND_MODE_8023AD && slave->link == BOND_LINK_UP) bond_3ad_adapter_speed_duplex_changed(slave); continue; case BOND_LINK_UP: if (bond_update_speed_duplex(slave) && bond_needs_speed_duplex(bond)) { slave->link = BOND_LINK_DOWN; if (net_ratelimit()) slave_warn(bond->dev, slave->dev, "failed to get link speed/duplex\n"); continue; } bond_set_slave_link_state(slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); slave->last_link_up = jiffies; primary = rtnl_dereference(bond->primary_slave); if (BOND_MODE(bond) == BOND_MODE_8023AD) { /* prevent it from being the active one */ bond_set_backup_slave(slave); } else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ bond_set_active_slave(slave); } slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n", slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, slave->duplex ? "full" : "half"); bond_miimon_link_change(bond, slave, BOND_LINK_UP); active = rtnl_dereference(bond->curr_active_slave); if (!active || slave == primary || slave->prio > active->prio) do_failover = true; continue; case BOND_LINK_DOWN: if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_8023AD) bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n"); bond_miimon_link_change(bond, slave, BOND_LINK_DOWN); if (slave == rcu_access_pointer(bond->curr_active_slave)) do_failover = true; continue; default: slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", slave->link_new_state); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); continue; } } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } bond_set_carrier(bond); } /* bond_mii_monitor * * Really a wrapper that splits the mii monitor into two phases: an * inspection, then (if inspection indicates something needs to be done) * an acquisition of appropriate locks followed by a commit phase to * implement whatever link state changes are indicated. */ static void bond_mii_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, mii_work.work); bool should_notify_peers = false; bool commit; unsigned long delay; struct slave *slave; struct list_head *iter; delay = msecs_to_jiffies(bond->params.miimon); if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); should_notify_peers = bond_should_notify_peers(bond); commit = !!bond_miimon_inspect(bond); if (bond->send_peer_notif) { rcu_read_unlock(); if (rtnl_trylock()) { bond->send_peer_notif--; rtnl_unlock(); } } else { rcu_read_unlock(); } if (commit) { /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { delay = 1; should_notify_peers = false; goto re_arm; } bond_for_each_slave(bond, slave, iter) { bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER); } bond_miimon_commit(bond); rtnl_unlock(); /* might sleep, hold no other locks */ } re_arm: if (bond->params.miimon) queue_delayed_work(bond->wq, &bond->mii_work, delay); if (should_notify_peers) { if (!rtnl_trylock()) return; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); rtnl_unlock(); } } static int bond_upper_dev_walk(struct net_device *upper, struct netdev_nested_priv *priv) { __be32 ip = *(__be32 *)priv->data; return ip == bond_confirm_addr(upper, 0, ip); } static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { struct netdev_nested_priv priv = { .data = (void *)&ip, }; bool ret = false; if (ip == bond_confirm_addr(bond->dev, 0, ip)) return true; rcu_read_lock(); if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv)) ret = true; rcu_read_unlock(); return ret; } #define BOND_VLAN_PROTO_NONE cpu_to_be16(0xffff) static bool bond_handle_vlan(struct slave *slave, struct bond_vlan_tag *tags, struct sk_buff *skb) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct bond_vlan_tag *outer_tag = tags; if (!tags || tags->vlan_proto == BOND_VLAN_PROTO_NONE) return true; tags++; /* Go through all the tags backwards and add them to the packet */ while (tags->vlan_proto != BOND_VLAN_PROTO_NONE) { if (!tags->vlan_id) { tags++; continue; } slave_dbg(bond_dev, slave_dev, "inner tag: proto %X vid %X\n", ntohs(outer_tag->vlan_proto), tags->vlan_id); skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto, tags->vlan_id); if (!skb) { net_err_ratelimited("failed to insert inner VLAN tag\n"); return false; } tags++; } /* Set the outer tag */ if (outer_tag->vlan_id) { slave_dbg(bond_dev, slave_dev, "outer tag: proto %X vid %X\n", ntohs(outer_tag->vlan_proto), outer_tag->vlan_id); __vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto, outer_tag->vlan_id); } return true; } /* We go to the (large) trouble of VLAN tagging ARP frames because * switches in VLAN mode (especially if ports are configured as * "native" to a VLAN) might not pass non-tagged frames. */ static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip, __be32 src_ip, struct bond_vlan_tag *tags) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct sk_buff *skb; slave_dbg(bond_dev, slave_dev, "arp %d on slave: dst %pI4 src %pI4\n", arp_op, &dest_ip, &src_ip); skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, NULL, slave_dev->dev_addr, NULL); if (!skb) { net_err_ratelimited("ARP packet allocation failed\n"); return; } if (bond_handle_vlan(slave, tags, skb)) { slave_update_last_tx(slave); arp_xmit(skb); } return; } /* Validate the device path between the @start_dev and the @end_dev. * The path is valid if the @end_dev is reachable through device * stacking. * When the path is validated, collect any vlan information in the * path. */ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level) { struct bond_vlan_tag *tags; struct net_device *upper; struct list_head *iter; if (start_dev == end_dev) { tags = kcalloc(level + 1, sizeof(*tags), GFP_ATOMIC); if (!tags) return ERR_PTR(-ENOMEM); tags[level].vlan_proto = BOND_VLAN_PROTO_NONE; return tags; } netdev_for_each_upper_dev_rcu(start_dev, upper, iter) { tags = bond_verify_device_path(upper, end_dev, level + 1); if (IS_ERR_OR_NULL(tags)) { if (IS_ERR(tags)) return tags; continue; } if (is_vlan_dev(upper)) { tags[level].vlan_proto = vlan_dev_vlan_proto(upper); tags[level].vlan_id = vlan_dev_vlan_id(upper); } return tags; } return NULL; } static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { struct rtable *rt; struct bond_vlan_tag *tags; __be32 *targets = bond->params.arp_targets, addr; int i; for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { slave_dbg(bond->dev, slave->dev, "%s: target %pI4\n", __func__, &targets[i]); tags = NULL; /* Find out through which dev should the packet go */ rt = ip_route_output(dev_net(bond->dev), targets[i], 0, 0, 0, RT_SCOPE_LINK); if (IS_ERR(rt)) { /* there's no route to target - try to send arp * probe to generate any traffic (arp_validate=0) */ if (bond->params.arp_validate) pr_warn_once("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", bond->dev->name, &targets[i]); bond_arp_send(slave, ARPOP_REQUEST, targets[i], 0, tags); continue; } /* bond device itself */ if (rt->dst.dev == bond->dev) goto found; rcu_read_lock(); tags = bond_verify_device_path(bond->dev, rt->dst.dev, 0); rcu_read_unlock(); if (!IS_ERR_OR_NULL(tags)) goto found; /* Not our device - skip */ slave_dbg(bond->dev, slave->dev, "no path to arp_ip_target %pI4 via rt.dev %s\n", &targets[i], rt->dst.dev ? rt->dst.dev->name : "NULL"); ip_rt_put(rt); continue; found: addr = bond_confirm_addr(rt->dst.dev, targets[i], 0); ip_rt_put(rt); bond_arp_send(slave, ARPOP_REQUEST, targets[i], addr, tags); kfree(tags); } } static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 sip, __be32 tip) { int i; if (!sip || !bond_has_this_ip(bond, tip)) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 tip %pI4 not found\n", __func__, &sip, &tip); return; } i = bond_get_targets_ip(bond->params.arp_targets, sip); if (i == -1) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 not found in targets\n", __func__, &sip); return; } slave->last_rx = jiffies; slave->target_last_arp_rx[i] = jiffies; } static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct arphdr *arp = (struct arphdr *)skb->data; struct slave *curr_active_slave, *curr_arp_slave; unsigned char *arp_ptr; __be32 sip, tip; unsigned int alen; alen = arp_hdr_len(bond->dev); if (alen > skb_headlen(skb)) { arp = kmalloc(alen, GFP_ATOMIC); if (!arp) goto out_unlock; if (skb_copy_bits(skb, 0, arp, alen) < 0) goto out_unlock; } if (arp->ar_hln != bond->dev->addr_len || skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK || arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_pln != 4) goto out_unlock; arp_ptr = (unsigned char *)(arp + 1); arp_ptr += bond->dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4 + bond->dev->addr_len; memcpy(&tip, arp_ptr, 4); slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI4 tip %pI4\n", __func__, slave->dev->name, bond_slave_state(slave), bond->params.arp_validate, slave_do_arp_validate(bond, slave), &sip, &tip); curr_active_slave = rcu_dereference(bond->curr_active_slave); curr_arp_slave = rcu_dereference(bond->current_arp_slave); /* We 'trust' the received ARP enough to validate it if: * * (a) the slave receiving the ARP is active (which includes the * current ARP slave, if any), or * * (b) the receiving slave isn't active, but there is a currently * active slave and it received valid arp reply(s) after it became * the currently active slave, or * * (c) there is an ARP slave that sent an ARP during the prior ARP * interval, and we receive an ARP reply on any slave. We accept * these because switch FDB update delays may deliver the ARP * reply to a slave other than the sender of the ARP request. * * Note: for (b), backup slaves are receiving the broadcast ARP * request, not a reply. This request passes from the sending * slave through the L2 switch(es) to the receiving slave. Since * this is checking the request, sip/tip are swapped for * validation. * * This is done to avoid endless looping when we can't reach the * arp_ip_target and fool ourselves with our own arp requests. */ if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_arp(bond, slave, sip, tip); out_unlock: if (arp != (struct arphdr *)skb->data) kfree(arp); return RX_HANDLER_ANOTHER; } #if IS_ENABLED(CONFIG_IPV6) static void bond_ns_send(struct slave *slave, const struct in6_addr *daddr, const struct in6_addr *saddr, struct bond_vlan_tag *tags) { struct net_device *bond_dev = slave->bond->dev; struct net_device *slave_dev = slave->dev; struct in6_addr mcaddr; struct sk_buff *skb; slave_dbg(bond_dev, slave_dev, "NS on slave: dst %pI6c src %pI6c\n", daddr, saddr); skb = ndisc_ns_create(slave_dev, daddr, saddr, 0); if (!skb) { net_err_ratelimited("NS packet allocation failed\n"); return; } addrconf_addr_solict_mult(daddr, &mcaddr); if (bond_handle_vlan(slave, tags, skb)) { slave_update_last_tx(slave); ndisc_send_skb(skb, &mcaddr, saddr); } } static void bond_ns_send_all(struct bonding *bond, struct slave *slave) { struct in6_addr *targets = bond->params.ns_targets; struct bond_vlan_tag *tags; struct dst_entry *dst; struct in6_addr saddr; struct flowi6 fl6; int i; for (i = 0; i < BOND_MAX_NS_TARGETS && !ipv6_addr_any(&targets[i]); i++) { slave_dbg(bond->dev, slave->dev, "%s: target %pI6c\n", __func__, &targets[i]); tags = NULL; /* Find out through which dev should the packet go */ memset(&fl6, 0, sizeof(struct flowi6)); fl6.daddr = targets[i]; fl6.flowi6_oif = bond->dev->ifindex; dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6); if (dst->error) { dst_release(dst); /* there's no route to target - try to send arp * probe to generate any traffic (arp_validate=0) */ if (bond->params.arp_validate) pr_warn_once("%s: no route to ns_ip6_target %pI6c and arp_validate is set\n", bond->dev->name, &targets[i]); bond_ns_send(slave, &targets[i], &in6addr_any, tags); continue; } /* bond device itself */ if (dst->dev == bond->dev) goto found; rcu_read_lock(); tags = bond_verify_device_path(bond->dev, dst->dev, 0); rcu_read_unlock(); if (!IS_ERR_OR_NULL(tags)) goto found; /* Not our device - skip */ slave_dbg(bond->dev, slave->dev, "no path to ns_ip6_target %pI6c via dst->dev %s\n", &targets[i], dst->dev ? dst->dev->name : "NULL"); dst_release(dst); continue; found: if (!ipv6_dev_get_saddr(dev_net(dst->dev), dst->dev, &targets[i], 0, &saddr)) bond_ns_send(slave, &targets[i], &saddr, tags); else bond_ns_send(slave, &targets[i], &in6addr_any, tags); dst_release(dst); kfree(tags); } } static int bond_confirm_addr6(struct net_device *dev, struct netdev_nested_priv *priv) { struct in6_addr *addr = (struct in6_addr *)priv->data; return ipv6_chk_addr(dev_net(dev), addr, dev, 0); } static bool bond_has_this_ip6(struct bonding *bond, struct in6_addr *addr) { struct netdev_nested_priv priv = { .data = addr, }; int ret = false; if (bond_confirm_addr6(bond->dev, &priv)) return true; rcu_read_lock(); if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_confirm_addr6, &priv)) ret = true; rcu_read_unlock(); return ret; } static void bond_validate_na(struct bonding *bond, struct slave *slave, struct in6_addr *saddr, struct in6_addr *daddr) { int i; /* Ignore NAs that: * 1. Source address is unspecified address. * 2. Dest address is neither all-nodes multicast address nor * exist on bond interface. */ if (ipv6_addr_any(saddr) || (!ipv6_addr_equal(daddr, &in6addr_linklocal_allnodes) && !bond_has_this_ip6(bond, daddr))) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c tip %pI6c not found\n", __func__, saddr, daddr); return; } i = bond_get_targets_ip6(bond->params.ns_targets, saddr); if (i == -1) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c not found in targets\n", __func__, saddr); return; } slave->last_rx = jiffies; slave->target_last_arp_rx[i] = jiffies; } static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct slave *curr_active_slave, *curr_arp_slave; struct in6_addr *saddr, *daddr; struct { struct ipv6hdr ip6; struct icmp6hdr icmp6; } *combined, _combined; if (skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK) goto out; combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || (combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) goto out; saddr = &combined->ip6.saddr; daddr = &combined->ip6.daddr; slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n", __func__, slave->dev->name, bond_slave_state(slave), bond->params.arp_validate, slave_do_arp_validate(bond, slave), saddr, daddr); curr_active_slave = rcu_dereference(bond->curr_active_slave); curr_arp_slave = rcu_dereference(bond->current_arp_slave); /* We 'trust' the received ARP enough to validate it if: * see bond_arp_rcv(). */ if (bond_is_active_slave(slave)) bond_validate_na(bond, slave, saddr, daddr); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_na(bond, slave, daddr, saddr); else if (curr_arp_slave && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_na(bond, slave, saddr, daddr); out: return RX_HANDLER_ANOTHER; } #endif int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { #if IS_ENABLED(CONFIG_IPV6) bool is_ipv6 = skb->protocol == __cpu_to_be16(ETH_P_IPV6); #endif bool is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); slave_dbg(bond->dev, slave->dev, "%s: skb->dev %s\n", __func__, skb->dev->name); /* Use arp validate logic for both ARP and NS */ if (!slave_do_arp_validate(bond, slave)) { if ((slave_do_arp_validate_only(bond) && is_arp) || #if IS_ENABLED(CONFIG_IPV6) (slave_do_arp_validate_only(bond) && is_ipv6) || #endif !slave_do_arp_validate_only(bond)) slave->last_rx = jiffies; return RX_HANDLER_ANOTHER; } else if (is_arp) { return bond_arp_rcv(skb, bond, slave); #if IS_ENABLED(CONFIG_IPV6) } else if (is_ipv6) { return bond_na_rcv(skb, bond, slave); #endif } else { return RX_HANDLER_ANOTHER; } } static void bond_send_validate(struct bonding *bond, struct slave *slave) { bond_arp_send_all(bond, slave); #if IS_ENABLED(CONFIG_IPV6) bond_ns_send_all(bond, slave); #endif } /* function to verify if we're in the arp_interval timeslice, returns true if * (last_act - arp_interval) <= jiffies <= (last_act + mod * arp_interval + * arp_interval/2) . the arp_interval/2 is needed for really fast networks. */ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod) { int delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); return time_in_range(jiffies, last_act - delta_in_ticks, last_act + mod * delta_in_ticks + delta_in_ticks/2); } /* This function is called regularly to monitor each slave's link * ensuring that traffic is being sent and received when arp monitoring * is used in load-balancing mode. if the adapter has been dormant, then an * arp is transmitted to generate traffic. see activebackup_arp_monitor for * arp monitoring in active backup mode. */ static void bond_loadbalance_arp_mon(struct bonding *bond) { struct slave *slave, *oldcurrent; struct list_head *iter; int do_failover = 0, slave_state_changed = 0; if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); oldcurrent = rcu_dereference(bond->curr_active_slave); /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the curr_active_slave does not come into * the picture unless it is null. also, slave->last_link_up is not * needed here because we send an arp on each slave and give a slave * as long as it needs to get the tx/rx within the delta. * TODO: what about up/down delay in arp mode? it wasn't here before * so it can wait */ bond_for_each_slave_rcu(bond, slave, iter) { unsigned long last_tx = slave_last_tx(slave); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_tx, 1) && bond_time_in_interval(bond, slave->last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); slave_state_changed = 1; /* primary_slave has no meaning in round-robin * mode. the window of a slave being up and * curr_active_slave being null after enslaving * is closed. */ if (!oldcurrent) { slave_info(bond->dev, slave->dev, "link status definitely up\n"); do_failover = 1; } else { slave_info(bond->dev, slave->dev, "interface is now up\n"); } } } else { /* slave->link == BOND_LINK_UP */ /* not all switches will respond to an arp request * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) { bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; slave_info(bond->dev, slave->dev, "interface is now down\n"); if (slave == oldcurrent) do_failover = 1; } } /* note: if switch is in round-robin mode, all links * must tx arp to ensure all links rx an arp - otherwise * links may oscillate or not come up at all; if switch is * in something like xor mode, there is nothing we can * do - all replies will be rx'ed on same link causing slaves * to be unstable during low/no traffic periods */ if (bond_slave_is_up(slave)) bond_send_validate(bond, slave); } rcu_read_unlock(); if (do_failover || slave_state_changed) { if (!rtnl_trylock()) goto re_arm; bond_for_each_slave(bond, slave, iter) { if (slave->link_new_state != BOND_LINK_NOCHANGE) slave->link = slave->link_new_state; } if (slave_state_changed) { bond_slave_state_change(bond); if (BOND_MODE(bond) == BOND_MODE_XOR) bond_update_slave_arr(bond, NULL); } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } rtnl_unlock(); } re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, msecs_to_jiffies(bond->params.arp_interval)); } /* Called to inspect slaves for active-backup mode ARP monitor link state * changes. Sets proposed link state in slaves to specify what action * should take place for the slave. Returns 0 if no changes are found, >0 * if changes to link states must be committed. * * Called with rcu_read_lock held. */ static int bond_ab_arp_inspect(struct bonding *bond) { unsigned long last_tx, last_rx; struct list_head *iter; struct slave *slave; int commit = 0; bond_for_each_slave_rcu(bond, slave, iter) { bond_propose_link_state(slave, BOND_LINK_NOCHANGE); last_rx = slave_last_rx(bond, slave); if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; } else if (slave->link == BOND_LINK_BACK) { bond_propose_link_state(slave, BOND_LINK_FAIL); commit++; } continue; } /* Give slaves 2*delta after being enslaved or made * active. This avoids bouncing, as the last receive * times need a full ARP monitor cycle to be updated. */ if (bond_time_in_interval(bond, slave->last_link_up, 2)) continue; /* Backup slave is down if: * - No current_arp_slave AND * - more than (missed_max+1)*delta since last receive AND * - the bond has an IP address * * Note: a non-null current_arp_slave indicates * the curr_active_slave went down and we are * searching for a new one; under this condition * we only take the curr_active_slave down - this * gives each slave a chance to tx/rx traffic * before being taken out */ if (!bond_is_active_slave(slave) && !rcu_access_pointer(bond->current_arp_slave) && !bond_time_in_interval(bond, last_rx, bond->params.missed_max + 1)) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } /* Active slave is down if: * - more than missed_max*delta since transmitting OR * - (more than missed_max*delta since receive AND * the bond has an IP address) */ last_tx = slave_last_tx(slave); if (bond_is_active_slave(slave) && (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, last_rx, bond->params.missed_max))) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } } return commit; } /* Called to commit link state changes noted by inspection step of * active-backup mode ARP monitor. * * Called with RTNL hold. */ static void bond_ab_arp_commit(struct bonding *bond) { bool do_failover = false; struct list_head *iter; unsigned long last_tx; struct slave *slave; bond_for_each_slave(bond, slave, iter) { switch (slave->link_new_state) { case BOND_LINK_NOCHANGE: continue; case BOND_LINK_UP: last_tx = slave_last_tx(slave); if (rtnl_dereference(bond->curr_active_slave) != slave || (!rtnl_dereference(bond->curr_active_slave) && bond_time_in_interval(bond, last_tx, 1))) { struct slave *current_arp_slave; current_arp_slave = rtnl_dereference(bond->current_arp_slave); bond_set_slave_link_state(slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); if (current_arp_slave) { bond_set_slave_inactive_flags( current_arp_slave, BOND_SLAVE_NOTIFY_NOW); RCU_INIT_POINTER(bond->current_arp_slave, NULL); } slave_info(bond->dev, slave->dev, "link status definitely up\n"); if (!rtnl_dereference(bond->curr_active_slave) || slave == rtnl_dereference(bond->primary_slave) || slave->prio > rtnl_dereference(bond->curr_active_slave)->prio) do_failover = true; } continue; case BOND_LINK_DOWN: if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_NOW); bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n"); if (slave == rtnl_dereference(bond->curr_active_slave)) { RCU_INIT_POINTER(bond->current_arp_slave, NULL); do_failover = true; } continue; case BOND_LINK_FAIL: bond_set_slave_link_state(slave, BOND_LINK_FAIL, BOND_SLAVE_NOTIFY_NOW); bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); /* A slave has just been enslaved and has become * the current active slave. */ if (rtnl_dereference(bond->curr_active_slave)) RCU_INIT_POINTER(bond->current_arp_slave, NULL); continue; default: slave_err(bond->dev, slave->dev, "impossible: link_new_state %d on slave\n", slave->link_new_state); continue; } } if (do_failover) { block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); } bond_set_carrier(bond); } /* Send ARP probes for active-backup mode ARP monitor. * * Called with rcu_read_lock held. */ static bool bond_ab_arp_probe(struct bonding *bond) { struct slave *slave, *before = NULL, *new_slave = NULL, *curr_arp_slave = rcu_dereference(bond->current_arp_slave), *curr_active_slave = rcu_dereference(bond->curr_active_slave); struct list_head *iter; bool found = false; bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; if (curr_arp_slave && curr_active_slave) netdev_info(bond->dev, "PROBE: c_arp %s && cas %s BAD\n", curr_arp_slave->dev->name, curr_active_slave->dev->name); if (curr_active_slave) { bond_send_validate(bond, curr_active_slave); return should_notify_rtnl; } /* if we don't have a curr_active_slave, search for the next available * backup slave from the current_arp_slave and make it the candidate * for becoming the curr_active_slave */ if (!curr_arp_slave) { curr_arp_slave = bond_first_slave_rcu(bond); if (!curr_arp_slave) return should_notify_rtnl; } bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && bond_slave_is_up(slave)) before = slave; if (found && !new_slave && bond_slave_is_up(slave)) new_slave = slave; /* if the link state is up at this point, we * mark it down - this can happen if we have * simultaneous link failures and * reselect_active_interface doesn't make this * one the current slave so it is still marked * up when it is actually down */ if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { bond_set_slave_link_state(slave, BOND_LINK_DOWN, BOND_SLAVE_NOTIFY_LATER); if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_LATER); slave_info(bond->dev, slave->dev, "backup interface is now down\n"); } if (slave == curr_arp_slave) found = true; } if (!new_slave && before) new_slave = before; if (!new_slave) goto check_state; bond_set_slave_link_state(new_slave, BOND_LINK_BACK, BOND_SLAVE_NOTIFY_LATER); bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); bond_send_validate(bond, new_slave); new_slave->last_link_up = jiffies; rcu_assign_pointer(bond->current_arp_slave, new_slave); check_state: bond_for_each_slave_rcu(bond, slave, iter) { if (slave->should_notify || slave->should_notify_link) { should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; break; } } return should_notify_rtnl; } static void bond_activebackup_arp_mon(struct bonding *bond) { bool should_notify_peers = false; bool should_notify_rtnl = false; int delta_in_ticks; delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); if (!bond_has_slaves(bond)) goto re_arm; rcu_read_lock(); should_notify_peers = bond_should_notify_peers(bond); if (bond_ab_arp_inspect(bond)) { rcu_read_unlock(); /* Race avoidance with bond_close flush of workqueue */ if (!rtnl_trylock()) { delta_in_ticks = 1; should_notify_peers = false; goto re_arm; } bond_ab_arp_commit(bond); rtnl_unlock(); rcu_read_lock(); } should_notify_rtnl = bond_ab_arp_probe(bond); rcu_read_unlock(); re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); if (should_notify_peers || should_notify_rtnl) { if (!rtnl_trylock()) return; if (should_notify_peers) { bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); } if (should_notify_rtnl) { bond_slave_state_notify(bond); bond_slave_link_notify(bond); } rtnl_unlock(); } } static void bond_arp_monitor(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, arp_work.work); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_activebackup_arp_mon(bond); else bond_loadbalance_arp_mon(bond); } /*-------------------------- netdev event handling --------------------------*/ /* Change device name */ static int bond_event_changename(struct bonding *bond) { bond_remove_proc_entry(bond); bond_create_proc_entry(bond); bond_debug_reregister(bond); return NOTIFY_DONE; } static int bond_master_netdev_event(unsigned long event, struct net_device *bond_dev) { struct bonding *event_bond = netdev_priv(bond_dev); netdev_dbg(bond_dev, "%s called\n", __func__); switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); case NETDEV_UNREGISTER: bond_remove_proc_entry(event_bond); #ifdef CONFIG_XFRM_OFFLOAD xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true); #endif /* CONFIG_XFRM_OFFLOAD */ break; case NETDEV_REGISTER: bond_create_proc_entry(event_bond); break; default: break; } return NOTIFY_DONE; } static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev) { struct slave *slave = bond_slave_get_rtnl(slave_dev), *primary; struct bonding *bond; struct net_device *bond_dev; /* A netdev event can be generated while enslaving a device * before netdev_rx_handler_register is called in which case * slave will be NULL */ if (!slave) { netdev_dbg(slave_dev, "%s called on NULL slave\n", __func__); return NOTIFY_DONE; } bond_dev = slave->bond->dev; bond = slave->bond; primary = rtnl_dereference(bond->primary_slave); slave_dbg(bond_dev, slave_dev, "%s called\n", __func__); switch (event) { case NETDEV_UNREGISTER: if (bond_dev->type != ARPHRD_ETHER) bond_release_and_destroy(bond_dev, slave_dev); else __bond_release_one(bond_dev, slave_dev, false, true); break; case NETDEV_UP: case NETDEV_CHANGE: /* For 802.3ad mode only: * Getting invalid Speed/Duplex values here will put slave * in weird state. Mark it as link-fail if the link was * previously up or link-down if it hasn't yet come up, and * let link-monitoring (miimon) set it right when correct * speeds/duplex are available. */ if (bond_update_speed_duplex(slave) && BOND_MODE(bond) == BOND_MODE_8023AD) { if (slave->last_link_up) slave->link = BOND_LINK_FAIL; else slave->link = BOND_LINK_DOWN; } if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); fallthrough; case NETDEV_DOWN: /* Refresh slave-array if applicable! * If the setup does not use miimon or arpmon (mode-specific!), * then these events will not cause the slave-array to be * refreshed. This will cause xmit to use a slave that is not * usable. Avoid such situation by refeshing the array at these * events. If these (miimon/arpmon) parameters are configured * then array gets refreshed twice and that should be fine! */ if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); break; case NETDEV_CHANGEMTU: /* TODO: Should slaves be allowed to * independently alter their MTU? For * an active-backup bond, slaves need * not be the same type of device, so * MTUs may vary. For other modes, * slaves arguably should have the * same MTUs. To do this, we'd need to * take over the slave's change_mtu * function for the duration of their * servitude. */ break; case NETDEV_CHANGENAME: /* we don't care if we don't have primary set */ if (!bond_uses_primary(bond) || !bond->params.primary[0]) break; if (slave == primary) { /* slave's name changed - he's no longer primary */ RCU_INIT_POINTER(bond->primary_slave, NULL); } else if (!strcmp(slave_dev->name, bond->params.primary)) { /* we have a new primary slave */ rcu_assign_pointer(bond->primary_slave, slave); } else { /* we didn't change primary - exit */ break; } netdev_info(bond->dev, "Primary slave changed to %s, reselecting active slave\n", primary ? slave_dev->name : "none"); block_netpoll_tx(); bond_select_active_slave(bond); unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: if (!bond->notifier_ctx) { bond->notifier_ctx = true; bond_compute_features(bond); bond->notifier_ctx = false; } break; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, slave->bond->dev); break; case NETDEV_XDP_FEAT_CHANGE: bond_xdp_set_features(bond_dev); break; default: break; } return NOTIFY_DONE; } /* bond_netdev_event: handle netdev notifier chain events. * * This function receives events for the netdev chain. The caller (an * ioctl handler calling blocking_notifier_call_chain) holds the necessary * locks for us to safely manipulate the slave devices (RTNL lock, * dev_probe_lock). */ static int bond_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); netdev_dbg(event_dev, "%s received %s\n", __func__, netdev_cmd_to_name(event)); if (!(event_dev->priv_flags & IFF_BONDING)) return NOTIFY_DONE; if (event_dev->flags & IFF_MASTER) { int ret; ret = bond_master_netdev_event(event, event_dev); if (ret != NOTIFY_DONE) return ret; } if (event_dev->flags & IFF_SLAVE) return bond_slave_netdev_event(event, event_dev); return NOTIFY_DONE; } static struct notifier_block bond_netdev_notifier = { .notifier_call = bond_netdev_event, }; /*---------------------------- Hashing Policies -----------------------------*/ /* Helper to access data in a packet, with or without a backing skb. * If skb is given the data is linearized if necessary via pskb_may_pull. */ static inline const void *bond_pull_data(struct sk_buff *skb, const void *data, int hlen, int n) { if (likely(n <= hlen)) return data; else if (skb && likely(pskb_may_pull(skb, n))) return skb->data; return NULL; } /* L2 hash helper */ static inline u32 bond_eth_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { struct ethhdr *ep; data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); if (!data) return 0; ep = (struct ethhdr *)(data + mhoff); return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto); } static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *data, int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34) { const struct ipv6hdr *iph6; const struct iphdr *iph; if (l2_proto == htons(ETH_P_IP)) { data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph)); if (!data) return false; iph = (const struct iphdr *)(data + *nhoff); iph_to_flow_copy_v4addrs(fk, iph); *nhoff += iph->ihl << 2; if (!ip_is_fragment(iph)) *ip_proto = iph->protocol; } else if (l2_proto == htons(ETH_P_IPV6)) { data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6)); if (!data) return false; iph6 = (const struct ipv6hdr *)(data + *nhoff); iph_to_flow_copy_v6addrs(fk, iph6); *nhoff += sizeof(*iph6); *ip_proto = iph6->nexthdr; } else { return false; } if (l34 && *ip_proto >= 0) fk->ports.ports = skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen); return true; } static u32 bond_vlan_srcmac_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { u32 srcmac_vendor = 0, srcmac_dev = 0; struct ethhdr *mac_hdr; u16 vlan = 0; int i; data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); if (!data) return 0; mac_hdr = (struct ethhdr *)(data + mhoff); for (i = 0; i < 3; i++) srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i]; for (i = 3; i < ETH_ALEN; i++) srcmac_dev = (srcmac_dev << 8) | mac_hdr->h_source[i]; if (skb && skb_vlan_tag_present(skb)) vlan = skb_vlan_tag_get(skb); return vlan ^ srcmac_vendor ^ srcmac_dev; } /* Extract the appropriate headers based on bond's xmit policy */ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const void *data, __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk) { bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34; int ip_proto = -1; switch (bond->params.xmit_policy) { case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, fk, data, l2_proto, nhoff, hlen, 0); default: break; } fk->ports.ports = 0; memset(&fk->icmp, 0, sizeof(fk->icmp)); if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34)) return false; /* ICMP error packets contains at least 8 bytes of the header * of the packet which generated the error. Use this information * to correlate ICMP error packets within the same flow which * generated the error. */ if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) { skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen); if (ip_proto == IPPROTO_ICMP) { if (!icmp_is_err(fk->icmp.type)) return true; nhoff += sizeof(struct icmphdr); } else if (ip_proto == IPPROTO_ICMPV6) { if (!icmpv6_is_err(fk->icmp.type)) return true; nhoff += sizeof(struct icmp6hdr); } return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34); } return true; } static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy) { hash ^= (__force u32)flow_get_u32_dst(flow) ^ (__force u32)flow_get_u32_src(flow); hash ^= (hash >> 16); hash ^= (hash >> 8); /* discard lowest hash bit to deal with the common even ports pattern */ if (xmit_policy == BOND_XMIT_POLICY_LAYER34 || xmit_policy == BOND_XMIT_POLICY_ENCAP34) return hash >> 1; return hash; } /* Generate hash based on xmit policy. If @skb is given it is used to linearize * the data as required, but this function can be used without it if the data is * known to be linear (e.g. with xdp_buff). */ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const void *data, __be16 l2_proto, int mhoff, int nhoff, int hlen) { struct flow_keys flow; u32 hash; if (bond->params.xmit_policy == BOND_XMIT_POLICY_VLAN_SRCMAC) return bond_vlan_srcmac_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow)) return bond_eth_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) { hash = bond_eth_hash(skb, data, mhoff, hlen); } else { if (flow.icmp.id) memcpy(&hash, &flow.icmp, sizeof(hash)); else memcpy(&hash, &flow.ports.ports, sizeof(hash)); } return bond_ip_hash(hash, &flow, bond->params.xmit_policy); } /** * bond_xmit_hash - generate a hash value based on the xmit policy * @bond: bonding device * @skb: buffer to use for headers * * This function will extract the necessary headers from the skb buffer and use * them to generate a hash based on the xmit_policy set in the bonding device */ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) { if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && skb->l4_hash) return skb->hash; return __bond_xmit_hash(bond, skb, skb->data, skb->protocol, 0, skb_network_offset(skb), skb_headlen(skb)); } /** * bond_xmit_hash_xdp - generate a hash value based on the xmit policy * @bond: bonding device * @xdp: buffer to use for headers * * The XDP variant of bond_xmit_hash. */ static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp) { struct ethhdr *eth; if (xdp->data + sizeof(struct ethhdr) > xdp->data_end) return 0; eth = (struct ethhdr *)xdp->data; return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0, sizeof(struct ethhdr), xdp->data_end - xdp->data); } /*-------------------------- Device entry points ----------------------------*/ void bond_work_init_all(struct bonding *bond) { INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed); INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor); INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor); INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor); INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler); INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler); } static void bond_work_cancel_all(struct bonding *bond) { cancel_delayed_work_sync(&bond->mii_work); cancel_delayed_work_sync(&bond->arp_work); cancel_delayed_work_sync(&bond->alb_work); cancel_delayed_work_sync(&bond->ad_work); cancel_delayed_work_sync(&bond->mcast_work); cancel_delayed_work_sync(&bond->slave_arr_work); } static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) { bond->rr_tx_counter = alloc_percpu(u32); if (!bond->rr_tx_counter) return -ENOMEM; } /* reset slave->backup and slave->inactive */ if (bond_has_slaves(bond)) { bond_for_each_slave(bond, slave, iter) { if (bond_uses_primary(bond) && slave != rcu_access_pointer(bond->curr_active_slave)) { bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW); } else if (BOND_MODE(bond) != BOND_MODE_8023AD) { bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_NOW); } } } if (bond_is_lb(bond)) { /* bond_alb_initialize must be called before the timer * is started. */ if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB))) return -ENOMEM; if (bond->params.tlb_dynamic_lb || BOND_MODE(bond) == BOND_MODE_ALB) queue_delayed_work(bond->wq, &bond->alb_work, 0); } if (bond->params.miimon) /* link check interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->mii_work, 0); if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); bond->recv_probe = bond_rcv_validate; } if (BOND_MODE(bond) == BOND_MODE_8023AD) { queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ bond->recv_probe = bond_3ad_lacpdu_recv; bond_3ad_initiate_agg_selection(bond, 1); bond_for_each_slave(bond, slave, iter) dev_mc_add(slave->dev, lacpdu_mcast_addr); } if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); return 0; } static int bond_close(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; bond_work_cancel_all(bond); bond->send_peer_notif = 0; if (bond_is_lb(bond)) bond_alb_deinitialize(bond); bond->recv_probe = NULL; if (bond_uses_primary(bond)) { rcu_read_lock(); slave = rcu_dereference(bond->curr_active_slave); if (slave) bond_hw_addr_flush(bond_dev, slave->dev); rcu_read_unlock(); } else { struct list_head *iter; bond_for_each_slave(bond, slave, iter) bond_hw_addr_flush(bond_dev, slave->dev); } return 0; } /* fold stats, assuming all rtnl_link_stats64 fields are u64, but * that some drivers can provide 32bit values only. */ static void bond_fold_stats(struct rtnl_link_stats64 *_res, const struct rtnl_link_stats64 *_new, const struct rtnl_link_stats64 *_old) { const u64 *new = (const u64 *)_new; const u64 *old = (const u64 *)_old; u64 *res = (u64 *)_res; int i; for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) { u64 nv = new[i]; u64 ov = old[i]; s64 delta = nv - ov; /* detects if this particular field is 32bit only */ if (((nv | ov) >> 32) == 0) delta = (s64)(s32)((u32)nv - (u32)ov); /* filter anomalies, some drivers reset their stats * at down/up events. */ if (delta > 0) res[i] += delta; } } #ifdef CONFIG_LOCKDEP static int bond_get_lowest_level_rcu(struct net_device *dev) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int cur = 0, max = 0; now = dev; iter = &dev->adj_list.lower; while (1) { next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; if (max <= cur) max = cur; break; } if (!next) { if (!cur) return max; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return max; } #endif static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { struct bonding *bond = netdev_priv(bond_dev); struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; int nest_level = 0; rcu_read_lock(); #ifdef CONFIG_LOCKDEP nest_level = bond_get_lowest_level_rcu(bond_dev); #endif spin_lock_nested(&bond->stats_lock, nest_level); memcpy(stats, &bond->bond_stats, sizeof(*stats)); bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); bond_fold_stats(stats, new, &slave->slave_stats); /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); rcu_read_unlock(); } static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); struct mii_ioctl_data *mii = NULL; netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCGMIIPHY: mii = if_mii(ifr); if (!mii) return -EINVAL; mii->phy_id = 0; fallthrough; case SIOCGMIIREG: /* We do this again just in case we were called by SIOCGMIIREG * instead of SIOCGMIIPHY. */ mii = if_mii(ifr); if (!mii) return -EINVAL; if (mii->reg_num == 1) { mii->val_out = 0; if (netif_carrier_ok(bond->dev)) mii->val_out = BMSR_LSTATUS; } break; default: return -EOPNOTSUPP; } return 0; } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); struct net_device *slave_dev = NULL; struct ifbond k_binfo; struct ifbond __user *u_binfo = NULL; struct ifslave k_sinfo; struct ifslave __user *u_sinfo = NULL; struct bond_opt_value newval; struct net *net; int res = 0; netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCBONDINFOQUERY: u_binfo = (struct ifbond __user *)ifr->ifr_data; if (copy_from_user(&k_binfo, u_binfo, sizeof(ifbond))) return -EFAULT; bond_info_query(bond_dev, &k_binfo); if (copy_to_user(u_binfo, &k_binfo, sizeof(ifbond))) return -EFAULT; return 0; case SIOCBONDSLAVEINFOQUERY: u_sinfo = (struct ifslave __user *)ifr->ifr_data; if (copy_from_user(&k_sinfo, u_sinfo, sizeof(ifslave))) return -EFAULT; res = bond_slave_info_query(bond_dev, &k_sinfo); if (res == 0 && copy_to_user(u_sinfo, &k_sinfo, sizeof(ifslave))) return -EFAULT; return res; default: break; } net = dev_net(bond_dev); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; slave_dev = __dev_get_by_name(net, ifr->ifr_slave); slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev); if (!slave_dev) return -ENODEV; switch (cmd) { case SIOCBONDENSLAVE: res = bond_enslave(bond_dev, slave_dev, NULL); break; case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); break; case SIOCBONDSETHWADDR: res = bond_set_dev_addr(bond_dev, slave_dev); break; case SIOCBONDCHANGEACTIVE: bond_opt_initstr(&newval, slave_dev->name); res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE, &newval); break; default: res = -EOPNOTSUPP; } return res; } static int bond_siocdevprivate(struct net_device *bond_dev, struct ifreq *ifr, void __user *data, int cmd) { struct ifreq ifrdata = { .ifr_data = data }; switch (cmd) { case BOND_INFO_QUERY_OLD: return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDINFOQUERY); case BOND_SLAVE_INFO_QUERY_OLD: return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDSLAVEINFOQUERY); case BOND_ENSLAVE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDENSLAVE); case BOND_RELEASE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDRELEASE); case BOND_SETHWADDR_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDSETHWADDR); case BOND_CHANGE_ACTIVE_OLD: return bond_do_ioctl(bond_dev, ifr, SIOCBONDCHANGEACTIVE); } return -EOPNOTSUPP; } static void bond_change_rx_flags(struct net_device *bond_dev, int change) { struct bonding *bond = netdev_priv(bond_dev); if (change & IFF_PROMISC) bond_set_promiscuity(bond, bond_dev->flags & IFF_PROMISC ? 1 : -1); if (change & IFF_ALLMULTI) bond_set_allmulti(bond, bond_dev->flags & IFF_ALLMULTI ? 1 : -1); } static void bond_set_rx_mode(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; rcu_read_lock(); if (bond_uses_primary(bond)) { slave = rcu_dereference(bond->curr_active_slave); if (slave) { dev_uc_sync(slave->dev, bond_dev); dev_mc_sync(slave->dev, bond_dev); } } else { bond_for_each_slave_rcu(bond, slave, iter) { dev_uc_sync_multiple(slave->dev, bond_dev); dev_mc_sync_multiple(slave->dev, bond_dev); } } rcu_read_unlock(); } static int bond_neigh_init(struct neighbour *n) { struct bonding *bond = netdev_priv(n->dev); const struct net_device_ops *slave_ops; struct neigh_parms parms; struct slave *slave; int ret = 0; rcu_read_lock(); slave = bond_first_slave_rcu(bond); if (!slave) goto out; slave_ops = slave->dev->netdev_ops; if (!slave_ops->ndo_neigh_setup) goto out; /* TODO: find another way [1] to implement this. * Passing a zeroed structure is fragile, * but at least we do not pass garbage. * * [1] One way would be that ndo_neigh_setup() never touch * struct neigh_parms, but propagate the new neigh_setup() * back to ___neigh_create() / neigh_parms_alloc() */ memset(&parms, 0, sizeof(parms)); ret = slave_ops->ndo_neigh_setup(slave->dev, &parms); if (ret) goto out; if (parms.neigh_setup) ret = parms.neigh_setup(n); out: rcu_read_unlock(); return ret; } /* The bonding ndo_neigh_setup is called at init time beofre any * slave exists. So we must declare proxy setup function which will * be used at run time to resolve the actual slave neigh param setup. * * It's also called by master devices (such as vlans) to setup their * underlying devices. In that case - do nothing, we're already set up from * our init. */ static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) { /* modify only our neigh_parms */ if (parms->dev == dev) parms->neigh_setup = bond_neigh_init; return 0; } /* Change the MTU of all of a master's slaves to match the master */ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct list_head *iter; int res = 0; netdev_dbg(bond_dev, "bond=%p, new_mtu=%d\n", bond, new_mtu); bond_for_each_slave(bond, slave, iter) { slave_dbg(bond_dev, slave->dev, "s %p c_m %p\n", slave, slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); if (res) { /* If we failed to set the slave's mtu to the new value * we must abort the operation even in ACTIVE_BACKUP * mode, because if we allow the backup slaves to have * different mtu values than the active slave we'll * need to change their mtu when doing a failover. That * means changing their mtu from timer context, which * is probably not a good idea. */ slave_dbg(bond_dev, slave->dev, "err %d setting mtu to %d\n", res, new_mtu); goto unwind; } } WRITE_ONCE(bond_dev->mtu, new_mtu); return 0; unwind: /* unwind from head to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; if (rollback_slave == slave) break; tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu); if (tmp_res) slave_dbg(bond_dev, rollback_slave->dev, "unwind err %d\n", tmp_res); } return res; } /* Change HW address * * Note that many devices must be down to change the HW address, and * downing the master releases all slaves. We can make bonds full of * bonding devices to test this, however. */ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *rollback_slave; struct sockaddr_storage *ss = addr, tmp_ss; struct list_head *iter; int res = 0; if (BOND_MODE(bond) == BOND_MODE_ALB) return bond_alb_set_mac_address(bond_dev, addr); netdev_dbg(bond_dev, "%s: bond=%p\n", __func__, bond); /* If fail_over_mac is enabled, do nothing and return success. * Returning an error causes ifenslave to fail. */ if (bond->params.fail_over_mac && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) return 0; if (!is_valid_ether_addr(ss->__data)) return -EADDRNOTAVAIL; bond_for_each_slave(bond, slave, iter) { slave_dbg(bond_dev, slave->dev, "%s: slave=%p\n", __func__, slave); res = dev_set_mac_address(slave->dev, addr, NULL); if (res) { /* TODO: consider downing the slave * and retry ? * User should expect communications * breakage anyway until ARP finish * updating, so... */ slave_dbg(bond_dev, slave->dev, "%s: err %d\n", __func__, res); goto unwind; } } /* success */ dev_addr_set(bond_dev, ss->__data); return 0; unwind: memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len); tmp_ss.ss_family = bond_dev->type; /* unwind from head to the slave that failed */ bond_for_each_slave(bond, rollback_slave, iter) { int tmp_res; if (rollback_slave == slave) break; tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_ss, NULL); if (tmp_res) { slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n", __func__, tmp_res); } } return res; } /** * bond_get_slave_by_id - get xmit slave with slave_id * @bond: bonding device that is transmitting * @slave_id: slave id up to slave_cnt-1 through which to transmit * * This function tries to get slave with slave_id but in case * it fails, it tries to find the first available slave for transmission. */ static struct slave *bond_get_slave_by_id(struct bonding *bond, int slave_id) { struct list_head *iter; struct slave *slave; int i = slave_id; /* Here we start from the slave with slave_id */ bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) { if (bond_slave_can_tx(slave)) return slave; } } /* Here we start from the first slave up to slave_id */ i = slave_id; bond_for_each_slave_rcu(bond, slave, iter) { if (--i < 0) break; if (bond_slave_can_tx(slave)) return slave; } /* no slave that can tx has been found */ return NULL; } /** * bond_rr_gen_slave_id - generate slave id based on packets_per_slave * @bond: bonding device to use * * Based on the value of the bonding device's packets_per_slave parameter * this function generates a slave id, which is usually used as the next * slave to transmit through. */ static u32 bond_rr_gen_slave_id(struct bonding *bond) { u32 slave_id; struct reciprocal_value reciprocal_packets_per_slave; int packets_per_slave = bond->params.packets_per_slave; switch (packets_per_slave) { case 0: slave_id = get_random_u32(); break; case 1: slave_id = this_cpu_inc_return(*bond->rr_tx_counter); break; default: reciprocal_packets_per_slave = bond->params.reciprocal_packets_per_slave; slave_id = this_cpu_inc_return(*bond->rr_tx_counter); slave_id = reciprocal_divide(slave_id, reciprocal_packets_per_slave); break; } return slave_id; } static struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond, struct sk_buff *skb) { struct slave *slave; int slave_cnt; u32 slave_id; /* Start with the curr_active_slave that joined the bond as the * default for sending IGMP traffic. For failover purposes one * needs to maintain some consistency for the interface that will * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ if (skb->protocol == htons(ETH_P_IP)) { int noff = skb_network_offset(skb); struct iphdr *iph; if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) goto non_igmp; iph = ip_hdr(skb); if (iph->protocol == IPPROTO_IGMP) { slave = rcu_dereference(bond->curr_active_slave); if (slave) return slave; return bond_get_slave_by_id(bond, 0); } } non_igmp: slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; return bond_get_slave_by_id(bond, slave_id); } return NULL; } static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond, struct xdp_buff *xdp) { struct slave *slave; int slave_cnt; u32 slave_id; const struct ethhdr *eth; void *data = xdp->data; if (data + sizeof(struct ethhdr) > xdp->data_end) goto non_igmp; eth = (struct ethhdr *)data; data += sizeof(struct ethhdr); /* See comment on IGMP in bond_xmit_roundrobin_slave_get() */ if (eth->h_proto == htons(ETH_P_IP)) { const struct iphdr *iph; if (data + sizeof(struct iphdr) > xdp->data_end) goto non_igmp; iph = (struct iphdr *)data; if (iph->protocol == IPPROTO_IGMP) { slave = rcu_dereference(bond->curr_active_slave); if (slave) return slave; return bond_get_slave_by_id(bond, 0); } } non_igmp: slave_cnt = READ_ONCE(bond->slave_cnt); if (likely(slave_cnt)) { slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; return bond_get_slave_by_id(bond, slave_id); } return NULL; } static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; slave = bond_xmit_roundrobin_slave_get(bond, skb); if (likely(slave)) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(bond_dev, skb); } static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond) { return rcu_dereference(bond->curr_active_slave); } /* In active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. */ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; slave = bond_xmit_activebackup_slave_get(bond); if (slave) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(bond_dev, skb); } /* Use this to update slave_array when (a) it's not appropriate to update * slave_array right away (note that update_slave_array() may sleep) * and / or (b) RTNL is not held. */ void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay) { queue_delayed_work(bond->wq, &bond->slave_arr_work, delay); } /* Slave array work handler. Holds only RTNL */ static void bond_slave_arr_handler(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, slave_arr_work.work); int ret; if (!rtnl_trylock()) goto err; ret = bond_update_slave_arr(bond, NULL); rtnl_unlock(); if (ret) { pr_warn_ratelimited("Failed to update slave array from WT\n"); goto err; } return; err: bond_slave_arr_work_rearm(bond, 1); } static void bond_skip_slave(struct bond_up_slave *slaves, struct slave *skipslave) { int idx; /* Rare situation where caller has asked to skip a specific * slave but allocation failed (most likely!). BTW this is * only possible when the call is initiated from * __bond_release_one(). In this situation; overwrite the * skipslave entry in the array with the last entry from the * array to avoid a situation where the xmit path may choose * this to-be-skipped slave to send a packet out. */ for (idx = 0; slaves && idx < slaves->count; idx++) { if (skipslave == slaves->arr[idx]) { slaves->arr[idx] = slaves->arr[slaves->count - 1]; slaves->count--; break; } } } static void bond_set_slave_arr(struct bonding *bond, struct bond_up_slave *usable_slaves, struct bond_up_slave *all_slaves) { struct bond_up_slave *usable, *all; usable = rtnl_dereference(bond->usable_slaves); rcu_assign_pointer(bond->usable_slaves, usable_slaves); kfree_rcu(usable, rcu); all = rtnl_dereference(bond->all_slaves); rcu_assign_pointer(bond->all_slaves, all_slaves); kfree_rcu(all, rcu); } static void bond_reset_slave_arr(struct bonding *bond) { bond_set_slave_arr(bond, NULL, NULL); } /* Build the usable slaves array in control path for modes that use xmit-hash * to determine the slave interface - * (a) BOND_MODE_8023AD * (b) BOND_MODE_XOR * (c) (BOND_MODE_TLB || BOND_MODE_ALB) && tlb_dynamic_lb == 0 * * The caller is expected to hold RTNL only and NO other lock! */ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) { struct bond_up_slave *usable_slaves = NULL, *all_slaves = NULL; struct slave *slave; struct list_head *iter; int agg_id = 0; int ret = 0; might_sleep(); usable_slaves = kzalloc(struct_size(usable_slaves, arr, bond->slave_cnt), GFP_KERNEL); all_slaves = kzalloc(struct_size(all_slaves, arr, bond->slave_cnt), GFP_KERNEL); if (!usable_slaves || !all_slaves) { ret = -ENOMEM; goto out; } if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info ad_info; spin_lock_bh(&bond->mode_lock); if (bond_3ad_get_active_agg_info(bond, &ad_info)) { spin_unlock_bh(&bond->mode_lock); pr_debug("bond_3ad_get_active_agg_info failed\n"); /* No active aggragator means it's not safe to use * the previous array. */ bond_reset_slave_arr(bond); goto out; } spin_unlock_bh(&bond->mode_lock); agg_id = ad_info.aggregator_id; } bond_for_each_slave(bond, slave, iter) { if (skipslave == slave) continue; all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg; agg = SLAVE_AD_INFO(slave)->port.aggregator; if (!agg || agg->aggregator_identifier != agg_id) continue; } if (!bond_slave_can_tx(slave)) continue; slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n", usable_slaves->count); usable_slaves->arr[usable_slaves->count++] = slave; } bond_set_slave_arr(bond, usable_slaves, all_slaves); return ret; out: if (ret != 0 && skipslave) { bond_skip_slave(rtnl_dereference(bond->all_slaves), skipslave); bond_skip_slave(rtnl_dereference(bond->usable_slaves), skipslave); } kfree_rcu(all_slaves, rcu); kfree_rcu(usable_slaves, rcu); return ret; } static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond, struct sk_buff *skb, struct bond_up_slave *slaves) { struct slave *slave; unsigned int count; u32 hash; hash = bond_xmit_hash(bond, skb); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; slave = slaves->arr[hash % count]; return slave; } static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond, struct xdp_buff *xdp) { struct bond_up_slave *slaves; unsigned int count; u32 hash; hash = bond_xmit_hash_xdp(bond, xdp); slaves = rcu_dereference(bond->usable_slaves); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; return slaves->arr[hash % count]; } /* Use this Xmit function for 3AD as well as XOR modes. The current * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. */ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct bond_up_slave *slaves; struct slave *slave; slaves = rcu_dereference(bond->usable_slaves); slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); if (likely(slave)) return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_tx_drop(dev, skb); } /* in broadcast mode, we send everything to all usable interfaces. */ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; struct list_head *iter; bool xmit_suc = false; bool skb_used = false; bond_for_each_slave_rcu(bond, slave, iter) { struct sk_buff *skb2; if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)) continue; if (bond_is_last_slave(bond, slave)) { skb2 = skb; skb_used = true; } else { skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) { net_err_ratelimited("%s: Error: %s: skb_clone() failed\n", bond_dev->name, __func__); continue; } } if (bond_dev_queue_xmit(bond, skb2, slave->dev) == NETDEV_TX_OK) xmit_suc = true; } if (!skb_used) dev_kfree_skb_any(skb); if (xmit_suc) return NETDEV_TX_OK; dev_core_stats_tx_dropped_inc(bond_dev); return NET_XMIT_DROP; } /*------------------------- Device initialization ---------------------------*/ /* Lookup the slave that corresponds to a qid */ static inline int bond_slave_override(struct bonding *bond, struct sk_buff *skb) { struct slave *slave = NULL; struct list_head *iter; if (!skb_rx_queue_recorded(skb)) return 1; /* Find out if any slaves have the same mapping as this skb. */ bond_for_each_slave_rcu(bond, slave, iter) { if (READ_ONCE(slave->queue_id) == skb_get_queue_mapping(skb)) { if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { bond_dev_queue_xmit(bond, skb, slave->dev); return 0; } /* If the slave isn't UP, use default transmit policy. */ break; } } return 1; } static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to * skb_tx_hash and will put the skbs in the queue we expect on their * way down to the bonding driver. */ u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; /* Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb_get_queue_mapping(skb); if (unlikely(txq >= dev->real_num_tx_queues)) { do { txq -= dev->real_num_tx_queues; } while (txq >= dev->real_num_tx_queues); } return txq; } static struct net_device *bond_xmit_get_slave(struct net_device *master_dev, struct sk_buff *skb, bool all_slaves) { struct bonding *bond = netdev_priv(master_dev); struct bond_up_slave *slaves; struct slave *slave = NULL; switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: slave = bond_xmit_roundrobin_slave_get(bond, skb); break; case BOND_MODE_ACTIVEBACKUP: slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR: if (all_slaves) slaves = rcu_dereference(bond->all_slaves); else slaves = rcu_dereference(bond->usable_slaves); slave = bond_xmit_3ad_xor_slave_get(bond, skb, slaves); break; case BOND_MODE_BROADCAST: break; case BOND_MODE_ALB: slave = bond_xmit_alb_slave_get(bond, skb); break; case BOND_MODE_TLB: slave = bond_xmit_tlb_slave_get(bond, skb); break; default: /* Should never happen, mode already checked */ WARN_ONCE(true, "Unknown bonding mode"); break; } if (slave) return slave->dev; return NULL; } static void bond_sk_to_flow(struct sock *sk, struct flow_keys *flow) { switch (sk->sk_family) { #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: if (ipv6_only_sock(sk) || ipv6_addr_type(&sk->sk_v6_daddr) != IPV6_ADDR_MAPPED) { flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; flow->addrs.v6addrs.src = inet6_sk(sk)->saddr; flow->addrs.v6addrs.dst = sk->sk_v6_daddr; break; } fallthrough; #endif default: /* AF_INET */ flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; flow->addrs.v4addrs.src = inet_sk(sk)->inet_rcv_saddr; flow->addrs.v4addrs.dst = inet_sk(sk)->inet_daddr; break; } flow->ports.src = inet_sk(sk)->inet_sport; flow->ports.dst = inet_sk(sk)->inet_dport; } /** * bond_sk_hash_l34 - generate a hash value based on the socket's L3 and L4 fields * @sk: socket to use for headers * * This function will extract the necessary field from the socket and use * them to generate a hash based on the LAYER34 xmit_policy. * Assumes that sk is a TCP or UDP socket. */ static u32 bond_sk_hash_l34(struct sock *sk) { struct flow_keys flow; u32 hash; bond_sk_to_flow(sk, &flow); /* L4 */ memcpy(&hash, &flow.ports.ports, sizeof(hash)); /* L3 */ return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34); } static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond, struct sock *sk) { struct bond_up_slave *slaves; struct slave *slave; unsigned int count; u32 hash; slaves = rcu_dereference(bond->usable_slaves); count = slaves ? READ_ONCE(slaves->count) : 0; if (unlikely(!count)) return NULL; hash = bond_sk_hash_l34(sk); slave = slaves->arr[hash % count]; return slave->dev; } static struct net_device *bond_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { struct bonding *bond = netdev_priv(dev); struct net_device *lower = NULL; rcu_read_lock(); if (bond_sk_check(bond)) lower = __bond_sk_get_lower_dev(bond, sk); rcu_read_unlock(); return lower; } #if IS_ENABLED(CONFIG_TLS_DEVICE) static netdev_tx_t bond_tls_device_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *dev) { struct net_device *tls_netdev = rcu_dereference(tls_get_ctx(skb->sk)->netdev); /* tls_netdev might become NULL, even if tls_is_skb_tx_device_offloaded * was true, if tls_device_down is running in parallel, but it's OK, * because bond_get_slave_by_dev has a NULL check. */ if (likely(bond_get_slave_by_dev(bond, tls_netdev))) return bond_dev_queue_xmit(bond, skb, tls_netdev); return bond_tx_drop(dev, skb); } #endif static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); if (bond_should_override_tx_queue(bond) && !bond_slave_override(bond, skb)) return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_TLS_DEVICE) if (tls_is_skb_tx_device_offloaded(skb)) return bond_tls_device_xmit(bond, skb, dev); #endif switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: return bond_xmit_roundrobin(skb, dev); case BOND_MODE_ACTIVEBACKUP: return bond_xmit_activebackup(skb, dev); case BOND_MODE_8023AD: case BOND_MODE_XOR: return bond_3ad_xor_xmit(skb, dev); case BOND_MODE_BROADCAST: return bond_xmit_broadcast(skb, dev); case BOND_MODE_ALB: return bond_alb_xmit(skb, dev); case BOND_MODE_TLB: return bond_tlb_xmit(skb, dev); default: /* Should never happen, mode already checked */ netdev_err(dev, "Unknown bonding mode %d\n", BOND_MODE(bond)); WARN_ON_ONCE(1); return bond_tx_drop(dev, skb); } } static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); netdev_tx_t ret = NETDEV_TX_OK; /* If we risk deadlock from transmitting this in the * netpoll path, tell netpoll to queue the frame for later tx */ if (unlikely(is_netpoll_tx_blocked(dev))) return NETDEV_TX_BUSY; rcu_read_lock(); if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else ret = bond_tx_drop(dev, skb); rcu_read_unlock(); return ret; } static struct net_device * bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; /* Caller needs to hold rcu_read_lock() */ switch (BOND_MODE(bond)) { case BOND_MODE_ROUNDROBIN: slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp); break; case BOND_MODE_ACTIVEBACKUP: slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR: slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp); break; default: if (net_ratelimit()) netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond)); return NULL; } if (slave) return slave->dev; return NULL; } static int bond_xdp_xmit(struct net_device *bond_dev, int n, struct xdp_frame **frames, u32 flags) { int nxmit, err = -ENXIO; rcu_read_lock(); for (nxmit = 0; nxmit < n; nxmit++) { struct xdp_frame *frame = frames[nxmit]; struct xdp_frame *frames1[] = {frame}; struct net_device *slave_dev; struct xdp_buff xdp; xdp_convert_frame_to_buff(frame, &xdp); slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp); if (!slave_dev) { err = -ENXIO; break; } err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags); if (err < 1) break; } rcu_read_unlock(); /* If error happened on the first frame then we can pass the error up, otherwise * report the number of frames that were xmitted. */ if (err < 0) return (nxmit == 0 ? err : nxmit); return nxmit; } static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(dev); struct list_head *iter; struct slave *slave, *rollback_slave; struct bpf_prog *old_prog; struct netdev_bpf xdp = { .command = XDP_SETUP_PROG, .flags = 0, .prog = prog, .extack = extack, }; int err; ASSERT_RTNL(); if (!bond_xdp_check(bond, BOND_MODE(bond))) { BOND_NL_ERR(dev, extack, "No native XDP support for the current bonding mode"); return -EOPNOTSUPP; } old_prog = bond->xdp_prog; bond->xdp_prog = prog; bond_for_each_slave(bond, slave, iter) { struct net_device *slave_dev = slave->dev; if (!slave_dev->netdev_ops->ndo_bpf || !slave_dev->netdev_ops->ndo_xdp_xmit) { SLAVE_NL_ERR(dev, slave_dev, extack, "Slave device does not support XDP"); err = -EOPNOTSUPP; goto err; } if (dev_xdp_prog_count(slave_dev) > 0) { SLAVE_NL_ERR(dev, slave_dev, extack, "Slave has XDP program loaded, please unload before enslaving"); err = -EOPNOTSUPP; goto err; } err = dev_xdp_propagate(slave_dev, &xdp); if (err < 0) { /* ndo_bpf() sets extack error message */ slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); goto err; } if (prog) bpf_prog_inc(prog); } if (prog) { static_branch_inc(&bpf_master_redirect_enabled_key); } else if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&bpf_master_redirect_enabled_key); } return 0; err: /* unwind the program changes */ bond->xdp_prog = old_prog; xdp.prog = old_prog; xdp.extack = NULL; /* do not overwrite original error */ bond_for_each_slave(bond, rollback_slave, iter) { struct net_device *slave_dev = rollback_slave->dev; int err_unwind; if (slave == rollback_slave) break; err_unwind = dev_xdp_propagate(slave_dev, &xdp); if (err_unwind < 0) slave_err(dev, slave_dev, "Error %d when unwinding XDP program change\n", err_unwind); else if (xdp.prog) bpf_prog_inc(xdp.prog); } return err; } static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return bond_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) { if (speed == 0 || speed == SPEED_UNKNOWN) speed = slave->speed; else speed = min(speed, slave->speed); return speed; } /* Set the BOND_PHC_INDEX flag to notify user space */ static int bond_set_phc_index_flag(struct kernel_hwtstamp_config *kernel_cfg) { struct ifreq *ifr = kernel_cfg->ifr; struct hwtstamp_config cfg; if (kernel_cfg->copied_to_user) { /* Lower device has a legacy implementation */ if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; cfg.flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX; if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) return -EFAULT; } else { kernel_cfg->flags |= HWTSTAMP_FLAG_BONDED_PHC_INDEX; } return 0; } static int bond_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct bonding *bond = netdev_priv(dev); struct net_device *real_dev; int err; real_dev = bond_option_active_slave_get_rcu(bond); if (!real_dev) return -EOPNOTSUPP; err = generic_hwtstamp_get_lower(real_dev, cfg); if (err) return err; return bond_set_phc_index_flag(cfg); } static int bond_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(dev); struct net_device *real_dev; int err; if (!(cfg->flags & HWTSTAMP_FLAG_BONDED_PHC_INDEX)) return -EOPNOTSUPP; real_dev = bond_option_active_slave_get_rcu(bond); if (!real_dev) return -EOPNOTSUPP; err = generic_hwtstamp_set_lower(real_dev, cfg, extack); if (err) return err; return bond_set_phc_index_flag(cfg); } static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, struct ethtool_link_ksettings *cmd) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; u32 speed = 0; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; /* Since bond_slave_can_tx returns false for all inactive or down slaves, we * do not need to check mode. Though link speed might not represent * the true receive or transmit bandwidth (not all modes are symmetric) * this is an accurate maximum. */ bond_for_each_slave(bond, slave, iter) { if (bond_slave_can_tx(slave)) { bond_update_speed_duplex(slave); if (slave->speed != SPEED_UNKNOWN) { if (BOND_MODE(bond) == BOND_MODE_BROADCAST) speed = bond_mode_bcast_speed(slave, speed); else speed += slave->speed; } if (cmd->base.duplex == DUPLEX_UNKNOWN && slave->duplex != DUPLEX_UNKNOWN) cmd->base.duplex = slave->duplex; } } cmd->base.speed = speed ? : SPEED_UNKNOWN; return 0; } static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d", BOND_ABI_VERSION); } static int bond_ethtool_get_ts_info(struct net_device *bond_dev, struct kernel_ethtool_ts_info *info) { struct bonding *bond = netdev_priv(bond_dev); struct kernel_ethtool_ts_info ts_info; struct net_device *real_dev; bool sw_tx_support = false; struct list_head *iter; struct slave *slave; int ret = 0; rcu_read_lock(); real_dev = bond_option_active_slave_get_rcu(bond); dev_hold(real_dev); rcu_read_unlock(); if (real_dev) { ret = ethtool_get_ts_info_by_layer(real_dev, info); } else { /* Check if all slaves support software tx timestamping */ rcu_read_lock(); bond_for_each_slave_rcu(bond, slave, iter) { ret = ethtool_get_ts_info_by_layer(slave->dev, &ts_info); if (!ret && (ts_info.so_timestamping & SOF_TIMESTAMPING_TX_SOFTWARE)) { sw_tx_support = true; continue; } sw_tx_support = false; break; } rcu_read_unlock(); } if (sw_tx_support) info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE; dev_put(real_dev); return ret; } static const struct ethtool_ops bond_ethtool_ops = { .get_drvinfo = bond_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = bond_ethtool_get_link_ksettings, .get_ts_info = bond_ethtool_get_ts_info, }; static const struct net_device_ops bond_netdev_ops = { .ndo_init = bond_init, .ndo_uninit = bond_uninit, .ndo_open = bond_open, .ndo_stop = bond_close, .ndo_start_xmit = bond_start_xmit, .ndo_select_queue = bond_select_queue, .ndo_get_stats64 = bond_get_stats, .ndo_eth_ioctl = bond_eth_ioctl, .ndo_siocbond = bond_do_ioctl, .ndo_siocdevprivate = bond_siocdevprivate, .ndo_change_rx_flags = bond_change_rx_flags, .ndo_set_rx_mode = bond_set_rx_mode, .ndo_change_mtu = bond_change_mtu, .ndo_set_mac_address = bond_set_mac_address, .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, .ndo_poll_controller = bond_poll_controller, #endif .ndo_add_slave = bond_enslave, .ndo_del_slave = bond_release, .ndo_fix_features = bond_fix_features, .ndo_features_check = passthru_features_check, .ndo_get_xmit_slave = bond_xmit_get_slave, .ndo_sk_get_lower_dev = bond_sk_get_lower_dev, .ndo_bpf = bond_xdp, .ndo_xdp_xmit = bond_xdp_xmit, .ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave, .ndo_hwtstamp_get = bond_hwtstamp_get, .ndo_hwtstamp_set = bond_hwtstamp_set, }; static const struct device_type bond_type = { .name = "bond", }; static void bond_destructor(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); if (bond->wq) destroy_workqueue(bond->wq); free_percpu(bond->rr_tx_counter); } void bond_setup(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); spin_lock_init(&bond->mode_lock); bond->params = bonding_defaults; /* Initialize pointers */ bond->dev = bond_dev; /* Initialize the device entry points */ ether_setup(bond_dev); bond_dev->max_mtu = ETH_MAX_MTU; bond_dev->netdev_ops = &bond_netdev_ops; bond_dev->ethtool_ops = &bond_ethtool_ops; bond_dev->needs_free_netdev = true; bond_dev->priv_destructor = bond_destructor; SET_NETDEV_DEVTYPE(bond_dev, &bond_type); /* Initialize the device options */ bond_dev->flags |= IFF_MASTER; bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT | IFF_NO_QUEUE; bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); #ifdef CONFIG_XFRM_OFFLOAD /* set up xfrm device ops (only supported in active-backup right now) */ bond_dev->xfrmdev_ops = &bond_xfrmdev_ops; INIT_LIST_HEAD(&bond->ipsec_list); mutex_init(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ /* don't acquire bond device's netif_tx_lock when transmitting */ bond_dev->lltx = true; /* Don't allow bond devices to change network namespaces. */ bond_dev->netns_immutable = true; /* By default, we declare the bond to be fully * VLAN hardware accelerated capable. Special * care is taken in the various xmit functions * when there are slaves that are not hw accel * capable */ bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; bond_dev->features |= NETIF_F_GSO_PARTIAL; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_features |= BOND_XFRM_FEATURES; /* Only enable XFRM features if this is an active-backup config */ if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_dev->features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ } /* Destroy a bonding device. * Must be under rtnl_lock when this function is called. */ static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct list_head *iter; struct slave *slave; bond_netpoll_cleanup(bond_dev); /* Release the bonded slaves */ bond_for_each_slave(bond, slave, iter) __bond_release_one(bond_dev, slave->dev, true, true); netdev_info(bond_dev, "Released all slaves\n"); #ifdef CONFIG_XFRM_OFFLOAD mutex_destroy(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ bond_set_slave_arr(bond, NULL, NULL); list_del_rcu(&bond->bond_list); bond_debug_unregister(bond); } /*------------------------- Module initialization ---------------------------*/ static int __init bond_check_params(struct bond_params *params) { int arp_validate_value, fail_over_mac_value, primary_reselect_value, i; struct bond_opt_value newval; const struct bond_opt_value *valptr; int arp_all_targets_value = 0; u16 ad_actor_sys_prio = 0; u16 ad_user_port_key = 0; __be32 arp_target[BOND_MAX_ARP_TARGETS] = { 0 }; int arp_ip_count; int bond_mode = BOND_MODE_ROUNDROBIN; int xmit_hashtype = BOND_XMIT_POLICY_LAYER2; int lacp_fast = 0; int tlb_dynamic_lb; /* Convert string parameters. */ if (mode) { bond_opt_initstr(&newval, mode); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_MODE), &newval); if (!valptr) { pr_err("Error: Invalid bonding mode \"%s\"\n", mode); return -EINVAL; } bond_mode = valptr->value; } if (xmit_hash_policy) { if (bond_mode == BOND_MODE_ROUNDROBIN || bond_mode == BOND_MODE_ACTIVEBACKUP || bond_mode == BOND_MODE_BROADCAST) { pr_info("xmit_hash_policy param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { bond_opt_initstr(&newval, xmit_hash_policy); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH), &newval); if (!valptr) { pr_err("Error: Invalid xmit_hash_policy \"%s\"\n", xmit_hash_policy); return -EINVAL; } xmit_hashtype = valptr->value; } } if (lacp_rate) { if (bond_mode != BOND_MODE_8023AD) { pr_info("lacp_rate param is irrelevant in mode %s\n", bond_mode_name(bond_mode)); } else { bond_opt_initstr(&newval, lacp_rate); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_LACP_RATE), &newval); if (!valptr) { pr_err("Error: Invalid lacp rate \"%s\"\n", lacp_rate); return -EINVAL; } lacp_fast = valptr->value; } } if (ad_select) { bond_opt_initstr(&newval, ad_select); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT), &newval); if (!valptr) { pr_err("Error: Invalid ad_select \"%s\"\n", ad_select); return -EINVAL; } params->ad_select = valptr->value; if (bond_mode != BOND_MODE_8023AD) pr_warn("ad_select param only affects 802.3ad mode\n"); } else { params->ad_select = BOND_AD_STABLE; } if (max_bonds < 0) { pr_warn("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); max_bonds = BOND_DEFAULT_MAX_BONDS; } if (miimon < 0) { pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n", miimon, INT_MAX); miimon = 0; } if (updelay < 0) { pr_warn("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", updelay, INT_MAX); updelay = 0; } if (downdelay < 0) { pr_warn("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", downdelay, INT_MAX); downdelay = 0; } if ((use_carrier != 0) && (use_carrier != 1)) { pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", use_carrier); use_carrier = 1; } if (num_peer_notif < 0 || num_peer_notif > 255) { pr_warn("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", num_peer_notif); num_peer_notif = 1; } /* reset values for 802.3ad/TLB/ALB */ if (!bond_mode_uses_arp(bond_mode)) { if (!miimon) { pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); pr_warn("Forcing miimon to 100msec\n"); miimon = BOND_DEFAULT_MIIMON; } } if (tx_queues < 1 || tx_queues > 255) { pr_warn("Warning: tx_queues (%d) should be between 1 and 255, resetting to %d\n", tx_queues, BOND_DEFAULT_TX_QUEUES); tx_queues = BOND_DEFAULT_TX_QUEUES; } if ((all_slaves_active != 0) && (all_slaves_active != 1)) { pr_warn("Warning: all_slaves_active module parameter (%d), not of valid value (0/1), so it was set to 0\n", all_slaves_active); all_slaves_active = 0; } if (resend_igmp < 0 || resend_igmp > 255) { pr_warn("Warning: resend_igmp (%d) should be between 0 and 255, resetting to %d\n", resend_igmp, BOND_DEFAULT_RESEND_IGMP); resend_igmp = BOND_DEFAULT_RESEND_IGMP; } bond_opt_initval(&newval, packets_per_slave); if (!bond_opt_parse(bond_opt_get(BOND_OPT_PACKETS_PER_SLAVE), &newval)) { pr_warn("Warning: packets_per_slave (%d) should be between 0 and %u resetting to 1\n", packets_per_slave, USHRT_MAX); packets_per_slave = 1; } if (bond_mode == BOND_MODE_ALB) { pr_notice("In ALB mode you might experience client disconnections upon reconnection of a link if the bonding module updelay parameter (%d msec) is incompatible with the forwarding delay time of the switch\n", updelay); } if (!miimon) { if (updelay || downdelay) { /* just warn the user the up/down delay will have * no effect since miimon is zero... */ pr_warn("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", updelay, downdelay); } } else { /* don't allow arp monitoring */ if (arp_interval) { pr_warn("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", miimon, arp_interval); arp_interval = 0; } if ((updelay % miimon) != 0) { pr_warn("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", updelay, miimon, (updelay / miimon) * miimon); } updelay /= miimon; if ((downdelay % miimon) != 0) { pr_warn("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", downdelay, miimon, (downdelay / miimon) * miimon); } downdelay /= miimon; } if (arp_interval < 0) { pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n", arp_interval, INT_MAX); arp_interval = 0; } for (arp_ip_count = 0, i = 0; (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[i]; i++) { __be32 ip; /* not a complete check, but good enough to catch mistakes */ if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) || !bond_is_ip_target_ok(ip)) { pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", arp_ip_target[i]); arp_interval = 0; } else { if (bond_get_targets_ip(arp_target, ip) == -1) arp_target[arp_ip_count++] = ip; else pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n", &ip); } } if (arp_interval && !arp_ip_count) { /* don't allow arping if no arp_ip_target given... */ pr_warn("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", arp_interval); arp_interval = 0; } if (arp_validate) { if (!arp_interval) { pr_err("arp_validate requires arp_interval\n"); return -EINVAL; } bond_opt_initstr(&newval, arp_validate); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_VALIDATE), &newval); if (!valptr) { pr_err("Error: invalid arp_validate \"%s\"\n", arp_validate); return -EINVAL; } arp_validate_value = valptr->value; } else { arp_validate_value = 0; } if (arp_all_targets) { bond_opt_initstr(&newval, arp_all_targets); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_ARP_ALL_TARGETS), &newval); if (!valptr) { pr_err("Error: invalid arp_all_targets_value \"%s\"\n", arp_all_targets); arp_all_targets_value = 0; } else { arp_all_targets_value = valptr->value; } } if (miimon) { pr_info("MII link monitoring set to %d ms\n", miimon); } else if (arp_interval) { valptr = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, arp_validate_value); pr_info("ARP monitoring set to %d ms, validate %s, with %d target(s):", arp_interval, valptr->string, arp_ip_count); for (i = 0; i < arp_ip_count; i++) pr_cont(" %s", arp_ip_target[i]); pr_cont("\n"); } else if (max_bonds) { /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n"); } if (primary && !bond_mode_uses_primary(bond_mode)) { /* currently, using a primary only makes sense * in active backup, TLB or ALB modes */ pr_warn("Warning: %s primary device specified but has no effect in %s mode\n", primary, bond_mode_name(bond_mode)); primary = NULL; } if (primary && primary_reselect) { bond_opt_initstr(&newval, primary_reselect); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_PRIMARY_RESELECT), &newval); if (!valptr) { pr_err("Error: Invalid primary_reselect \"%s\"\n", primary_reselect); return -EINVAL; } primary_reselect_value = valptr->value; } else { primary_reselect_value = BOND_PRI_RESELECT_ALWAYS; } if (fail_over_mac) { bond_opt_initstr(&newval, fail_over_mac); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_FAIL_OVER_MAC), &newval); if (!valptr) { pr_err("Error: invalid fail_over_mac \"%s\"\n", fail_over_mac); return -EINVAL; } fail_over_mac_value = valptr->value; if (bond_mode != BOND_MODE_ACTIVEBACKUP) pr_warn("Warning: fail_over_mac only affects active-backup mode\n"); } else { fail_over_mac_value = BOND_FOM_NONE; } bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse( bond_opt_get(BOND_OPT_AD_ACTOR_SYS_PRIO), &newval); if (!valptr) { pr_err("Error: No ad_actor_sys_prio default value"); return -EINVAL; } ad_actor_sys_prio = valptr->value; valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_USER_PORT_KEY), &newval); if (!valptr) { pr_err("Error: No ad_user_port_key default value"); return -EINVAL; } ad_user_port_key = valptr->value; bond_opt_initstr(&newval, "default"); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval); if (!valptr) { pr_err("Error: No tlb_dynamic_lb default value"); return -EINVAL; } tlb_dynamic_lb = valptr->value; if (lp_interval == 0) { pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; } /* fill params struct with the proper values */ params->mode = bond_mode; params->xmit_policy = xmit_hashtype; params->miimon = miimon; params->num_peer_notif = num_peer_notif; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->arp_all_targets = arp_all_targets_value; params->missed_max = 2; params->updelay = updelay; params->downdelay = downdelay; params->peer_notif_delay = 0; params->use_carrier = use_carrier; params->lacp_active = 1; params->lacp_fast = lacp_fast; params->primary[0] = 0; params->primary_reselect = primary_reselect_value; params->fail_over_mac = fail_over_mac_value; params->tx_queues = tx_queues; params->all_slaves_active = all_slaves_active; params->resend_igmp = resend_igmp; params->min_links = min_links; params->lp_interval = lp_interval; params->packets_per_slave = packets_per_slave; params->tlb_dynamic_lb = tlb_dynamic_lb; params->ad_actor_sys_prio = ad_actor_sys_prio; eth_zero_addr(params->ad_actor_system); params->ad_user_port_key = ad_user_port_key; params->coupled_control = 1; if (packets_per_slave > 0) { params->reciprocal_packets_per_slave = reciprocal_value(packets_per_slave); } else { /* reciprocal_packets_per_slave is unused if * packets_per_slave is 0 or 1, just initialize it */ params->reciprocal_packets_per_slave = (struct reciprocal_value) { 0 }; } if (primary) strscpy_pad(params->primary, primary, sizeof(params->primary)); memcpy(params->arp_targets, arp_target, sizeof(arp_target)); #if IS_ENABLED(CONFIG_IPV6) memset(params->ns_targets, 0, sizeof(struct in6_addr) * BOND_MAX_NS_TARGETS); #endif return 0; } /* Called from registration process */ static int bond_init(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id); netdev_dbg(bond_dev, "Begin bond_init\n"); bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, bond_dev->name); if (!bond->wq) return -ENOMEM; bond->notifier_ctx = false; spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); list_add_tail_rcu(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); bond_debug_register(bond); /* Ensure valid dev_addr */ if (is_zero_ether_addr(bond_dev->dev_addr) && bond_dev->addr_assign_type == NET_ADDR_PERM) eth_hw_addr_random(bond_dev); return 0; } unsigned int bond_get_num_tx_queues(void) { return tx_queues; } /* Create a new bond based on the specified name and bonding parameters. * If name is NULL, obtain a suitable "bond%d" name for us. * Caller must NOT hold rtnl_lock; we need to release it here before we * set up our sysfs entries. */ int bond_create(struct net *net, const char *name) { struct net_device *bond_dev; struct bonding *bond; int res = -ENOMEM; rtnl_lock(); bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "bond%d", NET_NAME_UNKNOWN, bond_setup, tx_queues); if (!bond_dev) goto out; bond = netdev_priv(bond_dev); dev_net_set(bond_dev, net); bond_dev->rtnl_link_ops = &bond_link_ops; res = register_netdevice(bond_dev); if (res < 0) { free_netdev(bond_dev); goto out; } netif_carrier_off(bond_dev); bond_work_init_all(bond); out: rtnl_unlock(); return res; } static int __net_init bond_net_init(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); bn->net = net; INIT_LIST_HEAD(&bn->dev_list); bond_create_proc_dir(bn); bond_create_sysfs(bn); return 0; } /* According to commit 69b0216ac255 ("bonding: fix bonding_masters * race condition in bond unloading") we need to remove sysfs files * before we remove our devices (done later in bond_net_exit_rtnl()) */ static void __net_exit bond_net_pre_exit(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); bond_destroy_sysfs(bn); } static void __net_exit bond_net_exit_rtnl(struct net *net, struct list_head *dev_kill_list) { struct bond_net *bn = net_generic(net, bond_net_id); struct bonding *bond, *tmp_bond; /* Kill off any bonds created after unregistering bond rtnl ops */ list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) unregister_netdevice_queue(bond->dev, dev_kill_list); } /* According to commit 23fa5c2caae0 ("bonding: destroy proc directory * only after all bonds are gone") bond_destroy_proc_dir() is called * after bond_net_exit_rtnl() has completed. */ static void __net_exit bond_net_exit_batch(struct list_head *net_list) { struct bond_net *bn; struct net *net; list_for_each_entry(net, net_list, exit_list) { bn = net_generic(net, bond_net_id); bond_destroy_proc_dir(bn); } } static struct pernet_operations bond_net_ops = { .init = bond_net_init, .pre_exit = bond_net_pre_exit, .exit_rtnl = bond_net_exit_rtnl, .exit_batch = bond_net_exit_batch, .id = &bond_net_id, .size = sizeof(struct bond_net), }; static int __init bonding_init(void) { int i; int res; res = bond_check_params(&bonding_defaults); if (res) goto out; bond_create_debugfs(); res = register_pernet_subsys(&bond_net_ops); if (res) goto err_net_ops; res = bond_netlink_init(); if (res) goto err_link; for (i = 0; i < max_bonds; i++) { res = bond_create(&init_net, NULL); if (res) goto err; } skb_flow_dissector_init(&flow_keys_bonding, flow_keys_bonding_keys, ARRAY_SIZE(flow_keys_bonding_keys)); register_netdevice_notifier(&bond_netdev_notifier); out: return res; err: bond_netlink_fini(); err_link: unregister_pernet_subsys(&bond_net_ops); err_net_ops: bond_destroy_debugfs(); goto out; } static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); bond_netlink_fini(); unregister_pernet_subsys(&bond_net_ops); bond_destroy_debugfs(); #ifdef CONFIG_NET_POLL_CONTROLLER /* Make sure we don't have an imbalance on our netpoll blocking */ WARN_ON(atomic_read(&netpoll_block_tx)); #endif } module_init(bonding_init); module_exit(bonding_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 | // SPDX-License-Identifier: GPL-2.0-only #ifndef _NFT_SET_PIPAPO_H #include <linux/log2.h> #include <net/ipv6.h> /* For the maximum length of a field */ /* Count of concatenated fields depends on count of 32-bit nftables registers */ #define NFT_PIPAPO_MAX_FIELDS NFT_REG32_COUNT /* Restrict usage to multiple fields, make sure rbtree is used otherwise */ #define NFT_PIPAPO_MIN_FIELDS 2 /* Largest supported field size */ #define NFT_PIPAPO_MAX_BYTES (sizeof(struct in6_addr)) #define NFT_PIPAPO_MAX_BITS (NFT_PIPAPO_MAX_BYTES * BITS_PER_BYTE) /* Bits to be grouped together in table buckets depending on set size */ #define NFT_PIPAPO_GROUP_BITS_INIT NFT_PIPAPO_GROUP_BITS_SMALL_SET #define NFT_PIPAPO_GROUP_BITS_SMALL_SET 8 #define NFT_PIPAPO_GROUP_BITS_LARGE_SET 4 #define NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4 \ BUILD_BUG_ON((NFT_PIPAPO_GROUP_BITS_SMALL_SET != 8) || \ (NFT_PIPAPO_GROUP_BITS_LARGE_SET != 4)) #define NFT_PIPAPO_GROUPS_PER_BYTE(f) (BITS_PER_BYTE / (f)->bb) /* If a lookup table gets bigger than NFT_PIPAPO_LT_SIZE_HIGH, switch to the * small group width, and switch to the big group width if the table gets * smaller than NFT_PIPAPO_LT_SIZE_LOW. * * Picking 2MiB as threshold (for a single table) avoids as much as possible * crossing page boundaries on most architectures (x86-64 and MIPS huge pages, * ARMv7 supersections, POWER "large" pages, SPARC Level 1 regions, etc.), which * keeps performance nice in case kvmalloc() gives us non-contiguous areas. */ #define NFT_PIPAPO_LT_SIZE_THRESHOLD (1 << 21) #define NFT_PIPAPO_LT_SIZE_HYSTERESIS (1 << 16) #define NFT_PIPAPO_LT_SIZE_HIGH NFT_PIPAPO_LT_SIZE_THRESHOLD #define NFT_PIPAPO_LT_SIZE_LOW NFT_PIPAPO_LT_SIZE_THRESHOLD - \ NFT_PIPAPO_LT_SIZE_HYSTERESIS /* Fields are padded to 32 bits in input registers */ #define NFT_PIPAPO_GROUPS_PADDED_SIZE(f) \ (round_up((f)->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f), sizeof(u32))) #define NFT_PIPAPO_GROUPS_PADDING(f) \ (NFT_PIPAPO_GROUPS_PADDED_SIZE(f) - (f)->groups / \ NFT_PIPAPO_GROUPS_PER_BYTE(f)) /* Number of buckets given by 2 ^ n, with n bucket bits */ #define NFT_PIPAPO_BUCKETS(bb) (1 << (bb)) /* Each n-bit range maps to up to n * 2 rules */ #define NFT_PIPAPO_MAP_NBITS (const_ilog2(NFT_PIPAPO_MAX_BITS * 2)) /* Use the rest of mapping table buckets for rule indices, but it makes no sense * to exceed 32 bits */ #if BITS_PER_LONG == 64 #define NFT_PIPAPO_MAP_TOBITS 32 #else #define NFT_PIPAPO_MAP_TOBITS (BITS_PER_LONG - NFT_PIPAPO_MAP_NBITS) #endif /* ...which gives us the highest allowed index for a rule */ #define NFT_PIPAPO_RULE0_MAX ((1UL << (NFT_PIPAPO_MAP_TOBITS - 1)) \ - (1UL << NFT_PIPAPO_MAP_NBITS)) /* Definitions for vectorised implementations */ #ifdef NFT_PIPAPO_ALIGN #define NFT_PIPAPO_ALIGN_HEADROOM \ (NFT_PIPAPO_ALIGN - ARCH_KMALLOC_MINALIGN) #define NFT_PIPAPO_LT_ALIGN(lt) (PTR_ALIGN((lt), NFT_PIPAPO_ALIGN)) #else #define NFT_PIPAPO_ALIGN_HEADROOM 0 #define NFT_PIPAPO_LT_ALIGN(lt) (lt) #endif /* NFT_PIPAPO_ALIGN */ #define nft_pipapo_for_each_field(field, index, match) \ for ((field) = (match)->f, (index) = 0; \ (index) < (match)->field_count; \ (index)++, (field)++) /** * union nft_pipapo_map_bucket - Bucket of mapping table * @to: First rule number (in next field) this rule maps to * @n: Number of rules (in next field) this rule maps to * @e: If there's no next field, pointer to element this rule maps to */ union nft_pipapo_map_bucket { struct { #if BITS_PER_LONG == 64 static_assert(NFT_PIPAPO_MAP_TOBITS <= 32); u32 to; static_assert(NFT_PIPAPO_MAP_NBITS <= 32); u32 n; #else unsigned long to:NFT_PIPAPO_MAP_TOBITS; unsigned long n:NFT_PIPAPO_MAP_NBITS; #endif }; struct nft_pipapo_elem *e; }; /** * struct nft_pipapo_field - Lookup, mapping tables and related data for a field * @rules: Number of inserted rules * @bsize: Size of each bucket in lookup table, in longs * @rules_alloc: Number of allocated rules, always >= rules * @groups: Amount of bit groups * @bb: Number of bits grouped together in lookup table buckets * @lt: Lookup table: 'groups' rows of buckets * @mt: Mapping table: one bucket per rule */ struct nft_pipapo_field { unsigned int rules; unsigned int bsize; unsigned int rules_alloc; u8 groups; u8 bb; unsigned long *lt; union nft_pipapo_map_bucket *mt; }; /** * struct nft_pipapo_scratch - percpu data used for lookup and matching * @map_index: Current working bitmap index, toggled between field matches * @align_off: Offset to get the originally allocated address * @map: store partial matching results during lookup */ struct nft_pipapo_scratch { u8 map_index; u32 align_off; unsigned long map[]; }; /** * struct nft_pipapo_match - Data used for lookup and matching * @field_count: Amount of fields in set * @bsize_max: Maximum lookup table bucket size of all fields, in longs * @scratch: Preallocated per-CPU maps for partial matching results * @rcu: Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { u8 field_count; unsigned int bsize_max; struct nft_pipapo_scratch * __percpu *scratch; struct rcu_head rcu; struct nft_pipapo_field f[] __counted_by(field_count); }; /** * struct nft_pipapo - Representation of a set * @match: Currently in-use matching data * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; unsigned long last_gc; }; struct nft_pipapo_elem; /** * struct nft_pipapo_elem - API-facing representation of single set element * @priv: element placeholder * @ext: nftables API extensions */ struct nft_pipapo_elem { struct nft_elem_priv priv; struct nft_set_ext ext; }; int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules, unsigned long *dst, const union nft_pipapo_map_bucket *mt, bool match_only); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets * @f: Field including lookup table * @dst: Area to store result * @data: Input data selecting table buckets */ static inline void pipapo_and_field_buckets_4bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt); int group; for (group = 0; group < f->groups; group += BITS_PER_BYTE / 4, data++) { u8 v; v = *data >> 4; __bitmap_and(dst, dst, lt + v * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(4); v = *data & 0x0f; __bitmap_and(dst, dst, lt + v * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(4); } } /** * pipapo_and_field_buckets_8bit() - Intersect 8-bit buckets * @f: Field including lookup table * @dst: Area to store result * @data: Input data selecting table buckets */ static inline void pipapo_and_field_buckets_8bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt); int group; for (group = 0; group < f->groups; group++, data++) { __bitmap_and(dst, dst, lt + *data * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(8); } } /** * pipapo_estimate_size() - Estimate worst-case for set size * @desc: Set description, element count and field description used here * * The size for this set type can vary dramatically, as it depends on the number * of rules (composing netmasks) the entries expand to. We compute the worst * case here. * * In general, for a non-ranged entry or a single composing netmask, we need * one bit in each of the sixteen NFT_PIPAPO_BUCKETS, for each 4-bit group (that * is, each input bit needs four bits of matching data), plus a bucket in the * mapping table for each field. * * Return: worst-case set size in bytes, 0 on any overflow */ static u64 pipapo_estimate_size(const struct nft_set_desc *desc) { unsigned long entry_size; u64 size; int i; for (i = 0, entry_size = 0; i < desc->field_count; i++) { unsigned long rules; if (desc->field_len[i] > NFT_PIPAPO_MAX_BYTES) return 0; /* Worst-case ranges for each concatenated field: each n-bit * field can expand to up to n * 2 rules in each bucket, and * each rule also needs a mapping bucket. */ rules = ilog2(desc->field_len[i] * BITS_PER_BYTE) * 2; entry_size += rules * NFT_PIPAPO_BUCKETS(NFT_PIPAPO_GROUP_BITS_INIT) / BITS_PER_BYTE; entry_size += rules * sizeof(union nft_pipapo_map_bucket); } /* Rules in lookup and mapping tables are needed for each entry */ size = desc->size * entry_size; if (size && div_u64(size, desc->size) != entry_size) return 0; size += sizeof(struct nft_pipapo) + sizeof(struct nft_pipapo_match) * 2; size += sizeof(struct nft_pipapo_field) * desc->field_count; return size; } /** * pipapo_resmap_init() - Initialise result map before first use * @m: Matching data, including mapping table * @res_map: Result map * * Initialize all bits covered by the first field to one, so that after * the first step, only the matching bits of the first bit group remain. * * If other fields have a large bitmap, set remainder of res_map to 0. */ static inline void pipapo_resmap_init(const struct nft_pipapo_match *m, unsigned long *res_map) { const struct nft_pipapo_field *f = m->f; int i; for (i = 0; i < f->bsize; i++) res_map[i] = ULONG_MAX; for (i = f->bsize; i < m->bsize_max; i++) res_map[i] = 0ul; } #endif /* _NFT_SET_PIPAPO_H */ |
| 49 2 2 54 22 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_PKT_SCHED_H #define __NET_PKT_SCHED_H #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/if_vlan.h> #include <linux/netdevice.h> #include <net/sch_generic.h> #include <net/net_namespace.h> #include <uapi/linux/pkt_sched.h> #define DEFAULT_TX_QUEUE_LEN 1000 #define STAB_SIZE_LOG_MAX 30 struct qdisc_walker { int stop; int skip; int count; int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *); }; #define qdisc_priv(q) \ _Generic(q, \ const struct Qdisc * : (const void *)&q->privdata, \ struct Qdisc * : (void *)&q->privdata) static inline struct Qdisc *qdisc_from_priv(void *priv) { return container_of(priv, struct Qdisc, privdata); } /* Timer resolution MUST BE < 10% of min_schedulable_packet_size/bandwidth Normal IP packet size ~ 512byte, hence: 0.5Kbyte/1Mbyte/sec = 0.5msec, so that we need 50usec timer for 10Mbit ethernet. 10msec resolution -> <50Kbit/sec. The result: [34]86 is not good choice for QoS router :-( The things are not so bad, because we may use artificial clock evaluated by integration of network data flow in the most critical places. */ typedef u64 psched_time_t; typedef long psched_tdiff_t; /* Avoid doing 64 bit divide */ #define PSCHED_SHIFT 6 #define PSCHED_TICKS2NS(x) ((s64)(x) << PSCHED_SHIFT) #define PSCHED_NS2TICKS(x) ((x) >> PSCHED_SHIFT) #define PSCHED_TICKS_PER_SEC PSCHED_NS2TICKS(NSEC_PER_SEC) #define PSCHED_PASTPERFECT 0 static inline psched_time_t psched_get_time(void) { return PSCHED_NS2TICKS(ktime_get_ns()); } struct qdisc_watchdog { struct hrtimer timer; struct Qdisc *qdisc; }; void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, clockid_t clockid); void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns); static inline void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires) { return qdisc_watchdog_schedule_range_ns(wd, expires, 0ULL); } static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) { qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires)); } void qdisc_watchdog_cancel(struct qdisc_watchdog *wd); extern struct Qdisc_ops pfifo_qdisc_ops; extern struct Qdisc_ops bfifo_qdisc_ops; extern struct Qdisc_ops pfifo_head_drop_qdisc_ops; int fifo_set_limit(struct Qdisc *q, unsigned int limit); struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, unsigned int limit, struct netlink_ext_ack *extack); int register_qdisc(struct Qdisc_ops *qops); void unregister_qdisc(struct Qdisc_ops *qops); #define NET_SCH_ALIAS_PREFIX "net-sch-" #define MODULE_ALIAS_NET_SCH(id) MODULE_ALIAS(NET_SCH_ALIAS_PREFIX id) void qdisc_get_default(char *id, size_t len); int qdisc_set_default(const char *id); void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack); void qdisc_put_rtab(struct qdisc_rate_table *tab); void qdisc_put_stab(struct qdisc_size_table *tab); void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc); bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate); void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { if (qdisc_run_begin(q)) { __qdisc_run(q); qdisc_run_end(q); } } extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ static inline unsigned int psched_mtu(const struct net_device *dev) { return READ_ONCE(dev->mtu) + dev->hard_header_len; } static inline struct net *qdisc_net(struct Qdisc *q) { return dev_net(q->dev_queue->dev); } struct tc_query_caps_base { enum tc_setup_type type; void *caps; }; struct tc_cbs_qopt_offload { u8 enable; s32 queue; s32 hicredit; s32 locredit; s32 idleslope; s32 sendslope; }; struct tc_etf_qopt_offload { u8 enable; s32 queue; }; struct tc_mqprio_caps { bool validate_queue_counts:1; }; struct tc_mqprio_qopt_offload { /* struct tc_mqprio_qopt must always be the first element */ struct tc_mqprio_qopt qopt; struct netlink_ext_ack *extack; u16 mode; u16 shaper; u32 flags; u64 min_rate[TC_QOPT_MAX_QUEUE]; u64 max_rate[TC_QOPT_MAX_QUEUE]; unsigned long preemptible_tcs; }; struct tc_taprio_caps { bool supports_queue_max_sdu:1; bool gate_mask_per_txq:1; /* Device expects lower TXQ numbers to have higher priority over higher * TXQs, regardless of their TC mapping. DO NOT USE FOR NEW DRIVERS, * INSTEAD ENFORCE A PROPER TC:TXQ MAPPING COMING FROM USER SPACE. */ bool broken_mqprio:1; }; enum tc_taprio_qopt_cmd { TAPRIO_CMD_REPLACE, TAPRIO_CMD_DESTROY, TAPRIO_CMD_STATS, TAPRIO_CMD_QUEUE_STATS, }; /** * struct tc_taprio_qopt_stats - IEEE 802.1Qbv statistics * @window_drops: Frames that were dropped because they were too large to be * transmitted in any of the allotted time windows (open gates) for their * traffic class. * @tx_overruns: Frames still being transmitted by the MAC after the * transmission gate associated with their traffic class has closed. * Equivalent to `12.29.1.1.2 TransmissionOverrun` from 802.1Q-2018. */ struct tc_taprio_qopt_stats { u64 window_drops; u64 tx_overruns; }; struct tc_taprio_qopt_queue_stats { int queue; struct tc_taprio_qopt_stats stats; }; struct tc_taprio_sched_entry { u8 command; /* TC_TAPRIO_CMD_* */ /* The gate_mask in the offloading side refers to traffic classes */ u32 gate_mask; u32 interval; }; struct tc_taprio_qopt_offload { enum tc_taprio_qopt_cmd cmd; union { /* TAPRIO_CMD_STATS */ struct tc_taprio_qopt_stats stats; /* TAPRIO_CMD_QUEUE_STATS */ struct tc_taprio_qopt_queue_stats queue_stats; /* TAPRIO_CMD_REPLACE */ struct { struct tc_mqprio_qopt_offload mqprio; struct netlink_ext_ack *extack; ktime_t base_time; u64 cycle_time; u64 cycle_time_extension; u32 max_sdu[TC_MAX_QUEUE]; size_t num_entries; struct tc_taprio_sched_entry entries[]; }; }; }; #if IS_ENABLED(CONFIG_NET_SCH_TAPRIO) /* Reference counting */ struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload *offload); void taprio_offload_free(struct tc_taprio_qopt_offload *offload); #else /* Reference counting */ static inline struct tc_taprio_qopt_offload * taprio_offload_get(struct tc_taprio_qopt_offload *offload) { return NULL; } static inline void taprio_offload_free(struct tc_taprio_qopt_offload *offload) { } #endif /* Ensure skb_mstamp_ns, which might have been populated with the txtime, is * not mistaken for a software timestamp, because this will otherwise prevent * the dispatch of hardware timestamps to the socket. */ static inline void skb_txtime_consumed(struct sk_buff *skb) { skb->tstamp = ktime_set(0, 0); } static inline bool tc_qdisc_stats_dump(struct Qdisc *sch, unsigned long cl, struct qdisc_walker *arg) { if (arg->count >= arg->skip && arg->fn(sch, cl, arg) < 0) { arg->stop = 1; return false; } arg->count++; return true; } #endif |
| 55 1530 829 24 833 905 1 913 897 895 894 4 190 3 57 756 57 757 57 1129 643 389 396 1278 1265 142 128 52 140 127 75 81 1496 116 1279 42 1524 1 1516 904 1516 76 234 15 263 89 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 | #ifndef IOU_CORE_H #define IOU_CORE_H #include <linux/errno.h> #include <linux/lockdep.h> #include <linux/resume_user_mode.h> #include <linux/kasan.h> #include <linux/poll.h> #include <linux/io_uring_types.h> #include <uapi/linux/eventpoll.h> #include "alloc_cache.h" #include "io-wq.h" #include "slist.h" #include "filetable.h" #include "opdef.h" #ifndef CREATE_TRACE_POINTS #include <trace/events/io_uring.h> #endif enum { IOU_COMPLETE = 0, IOU_ISSUE_SKIP_COMPLETE = -EIOCBQUEUED, /* * The request has more work to do and should be retried. io_uring will * attempt to wait on the file for eligible opcodes, but otherwise * it'll be handed to iowq for blocking execution. It works for normal * requests as well as for the multi shot mode. */ IOU_RETRY = -EAGAIN, /* * Requeue the task_work to restart operations on this request. The * actual value isn't important, should just be not an otherwise * valid error code, yet less than -MAX_ERRNO and valid internally. */ IOU_REQUEUE = -3072, }; struct io_wait_queue { struct wait_queue_entry wq; struct io_ring_ctx *ctx; unsigned cq_tail; unsigned cq_min_tail; unsigned nr_timeouts; int hit_timeout; ktime_t min_timeout; ktime_t timeout; struct hrtimer t; #ifdef CONFIG_NET_RX_BUSY_POLL ktime_t napi_busy_poll_dt; bool napi_prefer_busy_poll; #endif }; static inline bool io_should_wake(struct io_wait_queue *iowq) { struct io_ring_ctx *ctx = iowq->ctx; int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail; /* * Wake up if we have enough events, or if a timeout occurred since we * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } #define IORING_MAX_ENTRIES 32768 #define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) unsigned long rings_size(unsigned int flags, unsigned int sq_entries, unsigned int cq_entries, size_t *sq_offset); int io_uring_fill_params(unsigned entries, struct io_uring_params *p); bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow); int io_run_task_work_sig(struct io_ring_ctx *ctx); void io_req_defer_failed(struct io_kiocb *req, s32 res); bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags); void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags); bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags); void __io_commit_cqring_flush(struct io_ring_ctx *ctx); void io_req_track_inflight(struct io_kiocb *req); struct file *io_file_get_normal(struct io_kiocb *req, int fd); struct file *io_file_get_fixed(struct io_kiocb *req, int fd, unsigned issue_flags); void __io_req_task_work_add(struct io_kiocb *req, unsigned flags); void io_req_task_work_add_remote(struct io_kiocb *req, unsigned flags); void io_req_task_queue(struct io_kiocb *req); void io_req_task_complete(struct io_kiocb *req, io_tw_token_t tw); void io_req_task_queue_fail(struct io_kiocb *req, int ret); void io_req_task_submit(struct io_kiocb *req, io_tw_token_t tw); struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries); struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count); void tctx_task_work(struct callback_head *cb); __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file, int start, int end); void io_req_queue_iowq(struct io_kiocb *req); int io_poll_issue(struct io_kiocb *req, io_tw_token_t tw); int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr); int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin); void __io_submit_flush_completions(struct io_ring_ctx *ctx); struct io_wq_work *io_wq_free_work(struct io_wq_work *work); void io_wq_submit_work(struct io_wq_work *work); void io_free_req(struct io_kiocb *req); void io_queue_next(struct io_kiocb *req); void io_task_refs_refill(struct io_uring_task *tctx); bool __io_alloc_req_refill(struct io_ring_ctx *ctx); bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx, bool cancel_all); void io_activate_pollwq(struct io_ring_ctx *ctx); static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) { #if defined(CONFIG_PROVE_LOCKING) lockdep_assert(in_task()); if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) lockdep_assert_held(&ctx->uring_lock); if (ctx->flags & IORING_SETUP_IOPOLL) { lockdep_assert_held(&ctx->uring_lock); } else if (!ctx->task_complete) { lockdep_assert_held(&ctx->completion_lock); } else if (ctx->submitter_task) { /* * ->submitter_task may be NULL and we can still post a CQE, * if the ring has been setup with IORING_SETUP_R_DISABLED. * Not from an SQE, as those cannot be submitted, but via * updating tagged resources. */ if (!percpu_ref_is_dying(&ctx->refs)) lockdep_assert(current == ctx->submitter_task); } #endif } static inline bool io_is_compat(struct io_ring_ctx *ctx) { return IS_ENABLED(CONFIG_COMPAT) && unlikely(ctx->compat); } static inline void io_req_task_work_add(struct io_kiocb *req) { __io_req_task_work_add(req, 0); } static inline void io_submit_flush_completions(struct io_ring_ctx *ctx) { if (!wq_list_empty(&ctx->submit_state.compl_reqs) || ctx->submit_state.cq_flush) __io_submit_flush_completions(ctx); } #define io_for_each_link(pos, head) \ for (pos = (head); pos; pos = pos->link) static inline bool io_get_cqe_overflow(struct io_ring_ctx *ctx, struct io_uring_cqe **ret, bool overflow) { io_lockdep_assert_cq_locked(ctx); if (unlikely(ctx->cqe_cached >= ctx->cqe_sentinel)) { if (unlikely(!io_cqe_cache_refill(ctx, overflow))) return false; } *ret = ctx->cqe_cached; ctx->cached_cq_tail++; ctx->cqe_cached++; if (ctx->flags & IORING_SETUP_CQE32) ctx->cqe_cached++; return true; } static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret) { return io_get_cqe_overflow(ctx, ret, false); } static inline bool io_defer_get_uncommited_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **cqe_ret) { io_lockdep_assert_cq_locked(ctx); ctx->submit_state.cq_flush = true; return io_get_cqe(ctx, cqe_ret); } static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx, struct io_kiocb *req) { struct io_uring_cqe *cqe; /* * If we can't get a cq entry, userspace overflowed the * submission (by quite a lot). Increment the overflow count in * the ring. */ if (unlikely(!io_get_cqe(ctx, &cqe))) return false; memcpy(cqe, &req->cqe, sizeof(*cqe)); if (ctx->flags & IORING_SETUP_CQE32) { memcpy(cqe->big_cqe, &req->big_cqe, sizeof(*cqe)); memset(&req->big_cqe, 0, sizeof(req->big_cqe)); } if (trace_io_uring_complete_enabled()) trace_io_uring_complete(req->ctx, req, cqe); return true; } static inline void req_set_fail(struct io_kiocb *req) { req->flags |= REQ_F_FAIL; if (req->flags & REQ_F_CQE_SKIP) { req->flags &= ~REQ_F_CQE_SKIP; req->flags |= REQ_F_SKIP_LINK_CQES; } } static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags) { req->cqe.res = res; req->cqe.flags = cflags; } static inline void *io_uring_alloc_async_data(struct io_alloc_cache *cache, struct io_kiocb *req) { if (cache) { req->async_data = io_cache_alloc(cache, GFP_KERNEL); } else { const struct io_issue_def *def = &io_issue_defs[req->opcode]; WARN_ON_ONCE(!def->async_size); req->async_data = kmalloc(def->async_size, GFP_KERNEL); } if (req->async_data) req->flags |= REQ_F_ASYNC_DATA; return req->async_data; } static inline bool req_has_async_data(struct io_kiocb *req) { return req->flags & REQ_F_ASYNC_DATA; } static inline void io_put_file(struct io_kiocb *req) { if (!(req->flags & REQ_F_FIXED_FILE) && req->file) fput(req->file); } static inline void io_ring_submit_unlock(struct io_ring_ctx *ctx, unsigned issue_flags) { lockdep_assert_held(&ctx->uring_lock); if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) mutex_unlock(&ctx->uring_lock); } static inline void io_ring_submit_lock(struct io_ring_ctx *ctx, unsigned issue_flags) { /* * "Normal" inline submissions always hold the uring_lock, since we * grab it from the system call. Same is true for the SQPOLL offload. * The only exception is when we've detached the request and issue it * from an async worker thread, grab the lock for that case. */ if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) mutex_lock(&ctx->uring_lock); lockdep_assert_held(&ctx->uring_lock); } static inline void io_commit_cqring(struct io_ring_ctx *ctx) { /* order cqe stores with ring update */ smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); } static inline void io_poll_wq_wake(struct io_ring_ctx *ctx) { if (wq_has_sleeper(&ctx->poll_wq)) __wake_up(&ctx->poll_wq, TASK_NORMAL, 0, poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } static inline void io_cqring_wake(struct io_ring_ctx *ctx) { /* * Trigger waitqueue handler on all waiters on our waitqueue. This * won't necessarily wake up all the tasks, io_should_wake() will make * that decision. * * Pass in EPOLLIN|EPOLL_URING_WAKE as the poll wakeup key. The latter * set in the mask so that if we recurse back into our own poll * waitqueue handlers, we know we have a dependency between eventfd or * epoll and should terminate multishot poll at that point. */ if (wq_has_sleeper(&ctx->cq_wait)) __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } static inline bool io_sqring_full(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; /* * SQPOLL must use the actual sqring head, as using the cached_sq_head * is race prone if the SQPOLL thread has grabbed entries but not yet * committed them to the ring. For !SQPOLL, this doesn't matter, but * since this helper is just used for SQPOLL sqring waits (or POLLOUT), * just read the actual sqring head unconditionally. */ return READ_ONCE(r->sq.tail) - READ_ONCE(r->sq.head) == ctx->sq_entries; } static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; unsigned int entries; /* make sure SQ entry isn't read before tail */ entries = smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; return min(entries, ctx->sq_entries); } static inline int io_run_task_work(void) { bool ret = false; /* * Always check-and-clear the task_work notification signal. With how * signaling works for task_work, we can find it set with nothing to * run. We need to clear it for that case, like get_signal() does. */ if (test_thread_flag(TIF_NOTIFY_SIGNAL)) clear_notify_signal(); /* * PF_IO_WORKER never returns to userspace, so check here if we have * notify work that needs processing. */ if (current->flags & PF_IO_WORKER) { if (test_thread_flag(TIF_NOTIFY_RESUME)) { __set_current_state(TASK_RUNNING); resume_user_mode_work(NULL); } if (current->io_uring) { unsigned int count = 0; __set_current_state(TASK_RUNNING); tctx_task_work_run(current->io_uring, UINT_MAX, &count); if (count) ret = true; } } if (task_work_pending(current)) { __set_current_state(TASK_RUNNING); task_work_run(); ret = true; } return ret; } static inline bool io_local_work_pending(struct io_ring_ctx *ctx) { return !llist_empty(&ctx->work_llist) || !llist_empty(&ctx->retry_llist); } static inline bool io_task_work_pending(struct io_ring_ctx *ctx) { return task_work_pending(current) || io_local_work_pending(ctx); } static inline void io_tw_lock(struct io_ring_ctx *ctx, io_tw_token_t tw) { lockdep_assert_held(&ctx->uring_lock); } /* * Don't complete immediately but use deferred completion infrastructure. * Protected by ->uring_lock and can only be used either with * IO_URING_F_COMPLETE_DEFER or inside a tw handler holding the mutex. */ static inline void io_req_complete_defer(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { struct io_submit_state *state = &req->ctx->submit_state; lockdep_assert_held(&req->ctx->uring_lock); wq_list_add_tail(&req->comp_list, &state->compl_reqs); } static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx) { if (unlikely(ctx->off_timeout_used || ctx->has_evfd || ctx->poll_activated)) __io_commit_cqring_flush(ctx); } static inline void io_get_task_refs(int nr) { struct io_uring_task *tctx = current->io_uring; tctx->cached_refs -= nr; if (unlikely(tctx->cached_refs < 0)) io_task_refs_refill(tctx); } static inline bool io_req_cache_empty(struct io_ring_ctx *ctx) { return !ctx->submit_state.free_list.next; } extern struct kmem_cache *req_cachep; static inline struct io_kiocb *io_extract_req(struct io_ring_ctx *ctx) { struct io_kiocb *req; req = container_of(ctx->submit_state.free_list.next, struct io_kiocb, comp_list); wq_stack_extract(&ctx->submit_state.free_list); return req; } static inline bool io_alloc_req(struct io_ring_ctx *ctx, struct io_kiocb **req) { if (unlikely(io_req_cache_empty(ctx))) { if (!__io_alloc_req_refill(ctx)) return false; } *req = io_extract_req(ctx); return true; } static inline bool io_allowed_defer_tw_run(struct io_ring_ctx *ctx) { return likely(ctx->submitter_task == current); } static inline bool io_allowed_run_tw(struct io_ring_ctx *ctx) { return likely(!(ctx->flags & IORING_SETUP_DEFER_TASKRUN) || ctx->submitter_task == current); } /* * Terminate the request if either of these conditions are true: * * 1) It's being executed by the original task, but that task is marked * with PF_EXITING as it's exiting. * 2) PF_KTHREAD is set, in which case the invoker of the task_work is * our fallback task_work. */ static inline bool io_should_terminate_tw(void) { return current->flags & (PF_KTHREAD | PF_EXITING); } static inline void io_req_queue_tw_complete(struct io_kiocb *req, s32 res) { io_req_set_res(req, res, 0); req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); } /* * IORING_SETUP_SQE128 contexts allocate twice the normal SQE size for each * slot. */ static inline size_t uring_sqe_size(struct io_ring_ctx *ctx) { if (ctx->flags & IORING_SETUP_SQE128) return 2 * sizeof(struct io_uring_sqe); return sizeof(struct io_uring_sqe); } static inline bool io_file_can_poll(struct io_kiocb *req) { if (req->flags & REQ_F_CAN_POLL) return true; if (req->file && file_can_poll(req->file)) { req->flags |= REQ_F_CAN_POLL; return true; } return false; } static inline ktime_t io_get_time(struct io_ring_ctx *ctx) { if (ctx->clockid == CLOCK_MONOTONIC) return ktime_get(); return ktime_get_with_offset(ctx->clock_offset); } enum { IO_CHECK_CQ_OVERFLOW_BIT, IO_CHECK_CQ_DROPPED_BIT, }; static inline bool io_has_work(struct io_ring_ctx *ctx) { return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) || io_local_work_pending(ctx); } #endif |
| 689 13 702 702 4 685 683 683 1 7 5 633 37 606 27 217 197 20 264 264 466 343 165 267 4 266 597 594 332 425 332 425 219 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 | // SPDX-License-Identifier: GPL-2.0-only /* * vfsv0 quota IO operations on file */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/dqblk_v2.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/quotaops.h> #include <asm/byteorder.h> #include "quota_tree.h" #include "quotaio_v2.h" MODULE_AUTHOR("Jan Kara"); MODULE_DESCRIPTION("Quota format v2 support"); MODULE_LICENSE("GPL"); static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r0_disk2memdqb(struct dquot *dquot, void *dp); static int v2r0_is_id(void *dp, struct dquot *dquot); static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r1_disk2memdqb(struct dquot *dquot, void *dp); static int v2r1_is_id(void *dp, struct dquot *dquot); static const struct qtree_fmt_operations v2r0_qtree_ops = { .mem2disk_dqblk = v2r0_mem2diskdqb, .disk2mem_dqblk = v2r0_disk2memdqb, .is_id = v2r0_is_id, }; static const struct qtree_fmt_operations v2r1_qtree_ops = { .mem2disk_dqblk = v2r1_mem2diskdqb, .disk2mem_dqblk = v2r1_disk2memdqb, .is_id = v2r1_is_id, }; #define QUOTABLOCK_BITS 10 #define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS) static inline qsize_t v2_stoqb(qsize_t space) { return (space + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS; } static inline qsize_t v2_qbtos(qsize_t blocks) { return blocks << QUOTABLOCK_BITS; } static int v2_read_header(struct super_block *sb, int type, struct v2_disk_dqheader *dqhead) { ssize_t size; size = sb->s_op->quota_read(sb, type, (char *)dqhead, sizeof(struct v2_disk_dqheader), 0); if (size != sizeof(struct v2_disk_dqheader)) { quota_error(sb, "Failed header read: expected=%zd got=%zd", sizeof(struct v2_disk_dqheader), size); if (size < 0) return size; return -EIO; } return 0; } /* Check whether given file is really vfsv0 quotafile */ static int v2_check_quota_file(struct super_block *sb, int type) { struct v2_disk_dqheader dqhead; static const uint quota_magics[] = V2_INITQMAGICS; static const uint quota_versions[] = V2_INITQVERSIONS; if (v2_read_header(sb, type, &dqhead)) return 0; if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] || le32_to_cpu(dqhead.dqh_version) > quota_versions[type]) return 0; return 1; } /* Read information header from quota file */ static int v2_read_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct v2_disk_dqheader dqhead; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo; ssize_t size; unsigned int version; unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = v2_read_header(sb, type, &dqhead); if (ret < 0) goto out; version = le32_to_cpu(dqhead.dqh_version); if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) || (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) { ret = -EINVAL; goto out; } size = sb->s_op->quota_read(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't read info structure"); if (size < 0) ret = size; else ret = -EIO; goto out; } info->dqi_priv = kmalloc(sizeof(struct qtree_mem_dqinfo), GFP_KERNEL); if (!info->dqi_priv) { ret = -ENOMEM; goto out; } qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ info->dqi_max_spc_limit = 0xffffffffLL << QUOTABLOCK_BITS; info->dqi_max_ino_limit = 0xffffffff; } else { /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ info->dqi_max_spc_limit = 0x7fffffffffffffffLL; /* 2^63-1 */ info->dqi_max_ino_limit = 0x7fffffffffffffffLL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); /* No flags currently supported */ info->dqi_flags = 0; qinfo->dqi_sb = sb; qinfo->dqi_type = type; qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); qinfo->dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk); qinfo->dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry); qinfo->dqi_blocksize_bits = V2_DQBLKSIZE_BITS; qinfo->dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS; qinfo->dqi_qtree_depth = qtree_depth(qinfo); if (version == 0) { qinfo->dqi_entry_size = sizeof(struct v2r0_disk_dqblk); qinfo->dqi_ops = &v2r0_qtree_ops; } else { qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk); qinfo->dqi_ops = &v2r1_qtree_ops; } ret = -EUCLEAN; /* Some sanity checks of the read headers... */ if ((loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits > i_size_read(sb_dqopt(sb)->files[type])) { quota_error(sb, "Number of blocks too big for quota file size (%llu > %llu).", (loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits, i_size_read(sb_dqopt(sb)->files[type])); goto out_free; } if (qinfo->dqi_free_blk && (qinfo->dqi_free_blk <= QT_TREEOFF || qinfo->dqi_free_blk >= qinfo->dqi_blocks)) { quota_error(sb, "Free block number %u out of range (%u, %u).", qinfo->dqi_free_blk, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } if (qinfo->dqi_free_entry && (qinfo->dqi_free_entry <= QT_TREEOFF || qinfo->dqi_free_entry >= qinfo->dqi_blocks)) { quota_error(sb, "Block with free entry %u out of range (%u, %u).", qinfo->dqi_free_entry, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } ret = 0; out_free: if (ret) { kfree(info->dqi_priv); info->dqi_priv = NULL; } out: memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } /* Write information header to quota file */ static int v2_write_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo = info->dqi_priv; ssize_t size; unsigned int memalloc; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); spin_lock(&dq_data_lock); info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace); /* No flags currently supported */ dinfo.dqi_flags = cpu_to_le32(0); spin_unlock(&dq_data_lock); dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks); dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk); dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry); size = sb->s_op->quota_write(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't write info structure"); return size < 0 ? size : -EIO; } return 0; } static void v2r0_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r0_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le32_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le32_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le32_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le32_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le32_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r0_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r0_disk_dqblk))) m->dqb_itime = 0; } static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le32(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le32(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le32(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r0_is_id(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static void v2r1_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r1_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le64_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le64_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le64_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le64_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le64_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r1_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r1_disk_dqblk))) m->dqb_itime = 0; } static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le64(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le64(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le64(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le64(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le64(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); d->dqb_pad = 0; if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r1_is_id(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static int v2_read_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; unsigned int memalloc; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_read_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static int v2_write_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; bool alloc = false; unsigned int memalloc; /* * If space for dquot is already allocated, we don't need any * protection as we'll only overwrite the place of dquot. We are * still protected by concurrent writes of the same dquot by * dquot->dq_lock. */ if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); } else { down_read(&dqopt->dqio_sem); } memalloc = memalloc_nofs_save(); ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); if (alloc) up_write(&dqopt->dqio_sem); else up_read(&dqopt->dqio_sem); return ret; } static int v2_release_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); unsigned int memalloc; int ret; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); return ret; } static int v2_free_file_info(struct super_block *sb, int type) { kfree(sb_dqinfo(sb, type)->dqi_priv); return 0; } static int v2_get_next_id(struct super_block *sb, struct kqid *qid) { struct quota_info *dqopt = sb_dqopt(sb); unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static const struct quota_format_ops v2_format_ops = { .check_quota_file = v2_check_quota_file, .read_file_info = v2_read_file_info, .write_file_info = v2_write_file_info, .free_file_info = v2_free_file_info, .read_dqblk = v2_read_dquot, .commit_dqblk = v2_write_dquot, .release_dqblk = v2_release_dquot, .get_next_id = v2_get_next_id, }; static struct quota_format_type v2r0_quota_format = { .qf_fmt_id = QFMT_VFS_V0, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static struct quota_format_type v2r1_quota_format = { .qf_fmt_id = QFMT_VFS_V1, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static int __init init_v2_quota_format(void) { register_quota_format(&v2r0_quota_format); register_quota_format(&v2r1_quota_format); return 0; } static void __exit exit_v2_quota_format(void) { unregister_quota_format(&v2r0_quota_format); unregister_quota_format(&v2r1_quota_format); } module_init(init_v2_quota_format); module_exit(exit_v2_quota_format); |
| 53 12 2 42 3 2 2 37 103 88 14 13 8 2 103 102 100 2 17 1 2 1 8 1 1 1 3 3 3 1 2 1 1 2 2 2 2 2 509 509 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/seg6.h> #include <net/genetlink.h> #include <linux/seg6.h> #include <linux/seg6_genl.h> #include <net/seg6_hmac.h> bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced) { unsigned int tlv_offset; int max_last_entry; int trailing; if (srh->type != IPV6_SRCRT_TYPE_4) return false; if (((srh->hdrlen + 1) << 3) != len) return false; if (!reduced && srh->segments_left > srh->first_segment) { return false; } else { max_last_entry = (srh->hdrlen / 2) - 1; if (srh->first_segment > max_last_entry) return false; if (srh->segments_left > srh->first_segment + 1) return false; } tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); trailing = len - tlv_offset; if (trailing < 0) return false; while (trailing) { struct sr6_tlv *tlv; unsigned int tlv_len; if (trailing < sizeof(*tlv)) return false; tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset); tlv_len = sizeof(*tlv) + tlv->len; trailing -= tlv_len; if (trailing < 0) return false; tlv_offset += tlv_len; } return true; } struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags) { struct ipv6_sr_hdr *srh; int len, srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags) < 0) return NULL; if (!pskb_may_pull(skb, srhoff + sizeof(*srh))) return NULL; srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); len = (srh->hdrlen + 1) << 3; if (!pskb_may_pull(skb, srhoff + len)) return NULL; /* note that pskb_may_pull may change pointers in header; * for this reason it is necessary to reload them when needed. */ srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); if (!seg6_validate_srh(srh, len, true)) return NULL; return srh; } /* Determine if an ICMP invoking packet contains a segment routing * header. If it does, extract the offset to the true destination * address, which is in the first segment address. */ void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt) { __u16 network_header = skb->network_header; struct ipv6_sr_hdr *srh; /* Update network header to point to the invoking packet * inside the ICMP packet, so we can use the seg6_get_srh() * helper. */ skb_reset_network_header(skb); srh = seg6_get_srh(skb, 0); if (!srh) goto out; if (srh->type != IPV6_SRCRT_TYPE_4) goto out; opt->flags |= IP6SKB_SEG6; opt->srhoff = (unsigned char *)srh - skb->data; out: /* Restore the network header back to the ICMP packet */ skb->network_header = network_header; } static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { [SEG6_ATTR_DST] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [SEG6_ATTR_DSTLEN] = { .type = NLA_S32, }, [SEG6_ATTR_HMACKEYID] = { .type = NLA_U32, }, [SEG6_ATTR_SECRET] = { .type = NLA_BINARY, }, [SEG6_ATTR_SECRETLEN] = { .type = NLA_U8, }, [SEG6_ATTR_ALGID] = { .type = NLA_U8, }, [SEG6_ATTR_HMACINFO] = { .type = NLA_NESTED, }, }; #ifdef CONFIG_IPV6_SEG6_HMAC static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct seg6_pernet_data *sdata; struct seg6_hmac_info *hinfo; u32 hmackeyid; char *secret; int err = 0; u8 algid; u8 slen; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_HMACKEYID] || !info->attrs[SEG6_ATTR_SECRETLEN] || !info->attrs[SEG6_ATTR_ALGID]) return -EINVAL; hmackeyid = nla_get_u32(info->attrs[SEG6_ATTR_HMACKEYID]); slen = nla_get_u8(info->attrs[SEG6_ATTR_SECRETLEN]); algid = nla_get_u8(info->attrs[SEG6_ATTR_ALGID]); if (hmackeyid == 0) return -EINVAL; if (slen > SEG6_HMAC_SECRET_LEN) return -EINVAL; mutex_lock(&sdata->lock); hinfo = seg6_hmac_info_lookup(net, hmackeyid); if (!slen) { err = seg6_hmac_info_del(net, hmackeyid); goto out_unlock; } if (!info->attrs[SEG6_ATTR_SECRET]) { err = -EINVAL; goto out_unlock; } if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) { err = -EINVAL; goto out_unlock; } if (hinfo) { err = seg6_hmac_info_del(net, hmackeyid); if (err) goto out_unlock; } secret = (char *)nla_data(info->attrs[SEG6_ATTR_SECRET]); hinfo = kzalloc(sizeof(*hinfo), GFP_KERNEL); if (!hinfo) { err = -ENOMEM; goto out_unlock; } memcpy(hinfo->secret, secret, slen); hinfo->slen = slen; hinfo->alg_id = algid; hinfo->hmackeyid = hmackeyid; err = seg6_hmac_info_add(net, hmackeyid, hinfo); if (err) kfree(hinfo); out_unlock: mutex_unlock(&sdata->lock); return err; } #else static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { return -ENOTSUPP; } #endif static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *val, *t_old, *t_new; struct seg6_pernet_data *sdata; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_DST]) return -EINVAL; val = nla_data(info->attrs[SEG6_ATTR_DST]); t_new = kmemdup(val, sizeof(*val), GFP_KERNEL); if (!t_new) return -ENOMEM; mutex_lock(&sdata->lock); t_old = sdata->tun_src; rcu_assign_pointer(sdata->tun_src, t_new); mutex_unlock(&sdata->lock); synchronize_net(); kfree(t_old); return 0; } static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *tun_src; struct sk_buff *msg; void *hdr; msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &seg6_genl_family, 0, SEG6_CMD_GET_TUNSRC); if (!hdr) goto free_msg; rcu_read_lock(); tun_src = rcu_dereference(seg6_pernet(net)->tun_src); if (nla_put(msg, SEG6_ATTR_DST, sizeof(struct in6_addr), tun_src)) goto nla_put_failure; rcu_read_unlock(); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); free_msg: nlmsg_free(msg); return -ENOMEM; } #ifdef CONFIG_IPV6_SEG6_HMAC static int __seg6_hmac_fill_info(struct seg6_hmac_info *hinfo, struct sk_buff *msg) { if (nla_put_u32(msg, SEG6_ATTR_HMACKEYID, hinfo->hmackeyid) || nla_put_u8(msg, SEG6_ATTR_SECRETLEN, hinfo->slen) || nla_put(msg, SEG6_ATTR_SECRET, hinfo->slen, hinfo->secret) || nla_put_u8(msg, SEG6_ATTR_ALGID, hinfo->alg_id)) return -1; return 0; } static int __seg6_genl_dumphmac_element(struct seg6_hmac_info *hinfo, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &seg6_genl_family, flags, cmd); if (!hdr) return -ENOMEM; if (__seg6_hmac_fill_info(hinfo, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct seg6_pernet_data *sdata; struct rhashtable_iter *iter; sdata = seg6_pernet(net); iter = (struct rhashtable_iter *)cb->args[0]; if (!iter) { iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return -ENOMEM; cb->args[0] = (long)iter; } rhashtable_walk_enter(&sdata->hmac_infos, iter); return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; rhashtable_walk_exit(iter); kfree(iter); return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; struct seg6_hmac_info *hinfo; int ret; rhashtable_walk_start(iter); for (;;) { hinfo = rhashtable_walk_next(iter); if (IS_ERR(hinfo)) { if (PTR_ERR(hinfo) == -EAGAIN) continue; ret = PTR_ERR(hinfo); goto done; } else if (!hinfo) { break; } ret = __seg6_genl_dumphmac_element(hinfo, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, SEG6_CMD_DUMPHMAC); if (ret) goto done; } ret = skb->len; done: rhashtable_walk_stop(iter); return ret; } #else static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { return -ENOTSUPP; } #endif static int __net_init seg6_net_init(struct net *net) { struct seg6_pernet_data *sdata; sdata = kzalloc(sizeof(*sdata), GFP_KERNEL); if (!sdata) return -ENOMEM; mutex_init(&sdata->lock); sdata->tun_src = kzalloc(sizeof(*sdata->tun_src), GFP_KERNEL); if (!sdata->tun_src) { kfree(sdata); return -ENOMEM; } net->ipv6.seg6_data = sdata; if (seg6_hmac_net_init(net)) { kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); return -ENOMEM; } return 0; } static void __net_exit seg6_net_exit(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); seg6_hmac_net_exit(net); kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); } static struct pernet_operations ip6_segments_ops = { .init = seg6_net_init, .exit = seg6_net_exit, }; static const struct genl_ops seg6_genl_ops[] = { { .cmd = SEG6_CMD_SETHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_sethmac, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_DUMPHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .start = seg6_genl_dumphmac_start, .dumpit = seg6_genl_dumphmac, .done = seg6_genl_dumphmac_done, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_SET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_set_tunsrc, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_GET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_get_tunsrc, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family seg6_genl_family __ro_after_init = { .hdrsize = 0, .name = SEG6_GENL_NAME, .version = SEG6_GENL_VERSION, .maxattr = SEG6_ATTR_MAX, .policy = seg6_genl_policy, .netnsok = true, .parallel_ops = true, .ops = seg6_genl_ops, .n_ops = ARRAY_SIZE(seg6_genl_ops), .resv_start_op = SEG6_CMD_GET_TUNSRC + 1, .module = THIS_MODULE, }; int __init seg6_init(void) { int err; err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; err = genl_register_family(&seg6_genl_family); if (err) goto out_unregister_pernet; err = seg6_iptunnel_init(); if (err) goto out_unregister_genl; err = seg6_local_init(); if (err) goto out_unregister_iptun; err = seg6_hmac_init(); if (err) goto out_unregister_seg6; pr_info("Segment Routing with IPv6\n"); out: return err; out_unregister_seg6: seg6_local_exit(); out_unregister_iptun: seg6_iptunnel_exit(); out_unregister_genl: genl_unregister_family(&seg6_genl_family); out_unregister_pernet: unregister_pernet_subsys(&ip6_segments_ops); goto out; } void seg6_exit(void) { seg6_hmac_exit(); seg6_local_exit(); seg6_iptunnel_exit(); genl_unregister_family(&seg6_genl_family); unregister_pernet_subsys(&ip6_segments_ops); } |
| 18 18 989 179 114 116 113 15 9 1041 998 1 1 15 15 15 15 1 1 1041 1041 1 101 101 6 1 3 3 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Process number limiting controller for cgroups. * * Used to allow a cgroup hierarchy to stop any new processes from fork()ing * after a certain limit is reached. * * Since it is trivial to hit the task limit without hitting any kmemcg limits * in place, PIDs are a fundamental resource. As such, PID exhaustion must be * preventable in the scope of a cgroup hierarchy by allowing resource limiting * of the number of tasks in a cgroup. * * In order to use the `pids` controller, set the maximum number of tasks in * pids.max (this is not available in the root cgroup for obvious reasons). The * number of processes currently in the cgroup is given by pids.current. * Organisational operations are not blocked by cgroup policies, so it is * possible to have pids.current > pids.max. However, it is not possible to * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking * would cause a cgroup policy to be violated. * * To set a cgroup to have no limit, set pids.max to "max". This is the default * for all new cgroups (N.B. that PID limits are hierarchical, so the most * stringent limit in the hierarchy is followed). * * pids.current tracks all child cgroup hierarchies, so parent/pids.current is * a superset of parent/child/pids.current. * * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com> */ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cgroup.h> #include <linux/slab.h> #include <linux/sched/task.h> #define PIDS_MAX (PID_MAX_LIMIT + 1ULL) #define PIDS_MAX_STR "max" enum pidcg_event { /* Fork failed in subtree because this pids_cgroup limit was hit. */ PIDCG_MAX, /* Fork failed in this pids_cgroup because ancestor limit was hit. */ PIDCG_FORKFAIL, NR_PIDCG_EVENTS, }; struct pids_cgroup { struct cgroup_subsys_state css; /* * Use 64-bit types so that we can safely represent "max" as * %PIDS_MAX = (%PID_MAX_LIMIT + 1). */ atomic64_t counter; atomic64_t limit; int64_t watermark; /* Handles for pids.events[.local] */ struct cgroup_file events_file; struct cgroup_file events_local_file; atomic64_t events[NR_PIDCG_EVENTS]; atomic64_t events_local[NR_PIDCG_EVENTS]; }; static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css) { return container_of(css, struct pids_cgroup, css); } static struct pids_cgroup *parent_pids(struct pids_cgroup *pids) { return css_pids(pids->css.parent); } static struct cgroup_subsys_state * pids_css_alloc(struct cgroup_subsys_state *parent) { struct pids_cgroup *pids; pids = kzalloc(sizeof(struct pids_cgroup), GFP_KERNEL); if (!pids) return ERR_PTR(-ENOMEM); atomic64_set(&pids->limit, PIDS_MAX); return &pids->css; } static void pids_css_free(struct cgroup_subsys_state *css) { kfree(css_pids(css)); } static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids) { /* * This is racy, but we don't need perfectly accurate tallying of * the watermark, and this lets us avoid extra atomic overhead. */ if (nr_pids > READ_ONCE(p->watermark)) WRITE_ONCE(p->watermark, nr_pids); } /** * pids_cancel - uncharge the local pid count * @pids: the pid cgroup state * @num: the number of pids to cancel * * This function will WARN if the pid count goes under 0, because such a case is * a bug in the pids controller proper. */ static void pids_cancel(struct pids_cgroup *pids, int num) { /* * A negative count (or overflow for that matter) is invalid, * and indicates a bug in the `pids` controller proper. */ WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter)); } /** * pids_uncharge - hierarchically uncharge the pid count * @pids: the pid cgroup state * @num: the number of pids to uncharge */ static void pids_uncharge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; for (p = pids; parent_pids(p); p = parent_pids(p)) pids_cancel(p, num); } /** * pids_charge - hierarchically charge the pid count * @pids: the pid cgroup state * @num: the number of pids to charge * * This function does *not* follow the pid limit set. It cannot fail and the new * pid count may exceed the limit. This is only used for reverting failed * attaches, where there is no other way out than violating the limit. */ static void pids_charge(struct pids_cgroup *pids, int num) { struct pids_cgroup *p; for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); pids_update_watermark(p, new); } } /** * pids_try_charge - hierarchically try to charge the pid count * @pids: the pid cgroup state * @num: the number of pids to charge * @fail: storage of pid cgroup causing the fail * * This function follows the set limit. It will fail if the charge would cause * the new value to exceed the hierarchical limit. Returns 0 if the charge * succeeded, otherwise -EAGAIN. */ static int pids_try_charge(struct pids_cgroup *pids, int num, struct pids_cgroup **fail) { struct pids_cgroup *p, *q; for (p = pids; parent_pids(p); p = parent_pids(p)) { int64_t new = atomic64_add_return(num, &p->counter); int64_t limit = atomic64_read(&p->limit); /* * Since new is capped to the maximum number of pid_t, if * p->limit is %PIDS_MAX then we know that this test will never * fail. */ if (new > limit) { *fail = p; goto revert; } /* * Not technically accurate if we go over limit somewhere up * the hierarchy, but that's tolerable for the watermark. */ pids_update_watermark(p, new); } return 0; revert: for (q = pids; q != p; q = parent_pids(q)) pids_cancel(q, num); pids_cancel(p, num); return -EAGAIN; } static int pids_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *dst_css; cgroup_taskset_for_each(task, dst_css, tset) { struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; /* * No need to pin @old_css between here and cancel_attach() * because cgroup core protects it from being freed before * the migration completes or fails. */ old_css = task_css(task, pids_cgrp_id); old_pids = css_pids(old_css); pids_charge(pids, 1); pids_uncharge(old_pids, 1); } return 0; } static void pids_cancel_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *dst_css; cgroup_taskset_for_each(task, dst_css, tset) { struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; old_css = task_css(task, pids_cgrp_id); old_pids = css_pids(old_css); pids_charge(old_pids, 1); pids_uncharge(pids, 1); } } static void pids_event(struct pids_cgroup *pids_forking, struct pids_cgroup *pids_over_limit) { struct pids_cgroup *p = pids_forking; /* Only log the first time limit is hit. */ if (atomic64_inc_return(&p->events_local[PIDCG_FORKFAIL]) == 1) { pr_info("cgroup: fork rejected by pids controller in "); pr_cont_cgroup_path(p->css.cgroup); pr_cont("\n"); } if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { cgroup_file_notify(&p->events_local_file); return; } atomic64_inc(&pids_over_limit->events_local[PIDCG_MAX]); cgroup_file_notify(&pids_over_limit->events_local_file); for (p = pids_over_limit; parent_pids(p); p = parent_pids(p)) { atomic64_inc(&p->events[PIDCG_MAX]); cgroup_file_notify(&p->events_file); } } /* * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies * on cgroup_threadgroup_change_begin() held by the copy_process(). */ static int pids_can_fork(struct task_struct *task, struct css_set *cset) { struct pids_cgroup *pids, *pids_over_limit; int err; pids = css_pids(cset->subsys[pids_cgrp_id]); err = pids_try_charge(pids, 1, &pids_over_limit); if (err) pids_event(pids, pids_over_limit); return err; } static void pids_cancel_fork(struct task_struct *task, struct css_set *cset) { struct pids_cgroup *pids; pids = css_pids(cset->subsys[pids_cgrp_id]); pids_uncharge(pids, 1); } static void pids_release(struct task_struct *task) { struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id)); pids_uncharge(pids, 1); } static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_subsys_state *css = of_css(of); struct pids_cgroup *pids = css_pids(css); int64_t limit; int err; buf = strstrip(buf); if (!strcmp(buf, PIDS_MAX_STR)) { limit = PIDS_MAX; goto set_limit; } err = kstrtoll(buf, 0, &limit); if (err) return err; if (limit < 0 || limit >= PIDS_MAX) return -EINVAL; set_limit: /* * Limit updates don't need to be mutex'd, since it isn't * critical that any racing fork()s follow the new limit. */ atomic64_set(&pids->limit, limit); return nbytes; } static int pids_max_show(struct seq_file *sf, void *v) { struct cgroup_subsys_state *css = seq_css(sf); struct pids_cgroup *pids = css_pids(css); int64_t limit = atomic64_read(&pids->limit); if (limit >= PIDS_MAX) seq_printf(sf, "%s\n", PIDS_MAX_STR); else seq_printf(sf, "%lld\n", limit); return 0; } static s64 pids_current_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct pids_cgroup *pids = css_pids(css); return atomic64_read(&pids->counter); } static s64 pids_peak_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct pids_cgroup *pids = css_pids(css); return READ_ONCE(pids->watermark); } static int __pids_events_show(struct seq_file *sf, bool local) { struct pids_cgroup *pids = css_pids(seq_css(sf)); enum pidcg_event pe = PIDCG_MAX; atomic64_t *events; if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { pe = PIDCG_FORKFAIL; local = true; } events = local ? pids->events_local : pids->events; seq_printf(sf, "max %lld\n", (s64)atomic64_read(&events[pe])); return 0; } static int pids_events_show(struct seq_file *sf, void *v) { __pids_events_show(sf, false); return 0; } static int pids_events_local_show(struct seq_file *sf, void *v) { __pids_events_show(sf, true); return 0; } static struct cftype pids_files[] = { { .name = "max", .write = pids_max_write, .seq_show = pids_max_show, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .read_s64 = pids_current_read, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, .read_s64 = pids_peak_read, }, { .name = "events", .seq_show = pids_events_show, .file_offset = offsetof(struct pids_cgroup, events_file), .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "events.local", .seq_show = pids_events_local_show, .file_offset = offsetof(struct pids_cgroup, events_local_file), .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; static struct cftype pids_files_legacy[] = { { .name = "max", .write = pids_max_write, .seq_show = pids_max_show, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "current", .read_s64 = pids_current_read, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, .read_s64 = pids_peak_read, }, { .name = "events", .seq_show = pids_events_show, .file_offset = offsetof(struct pids_cgroup, events_file), .flags = CFTYPE_NOT_ON_ROOT, }, { } /* terminate */ }; struct cgroup_subsys pids_cgrp_subsys = { .css_alloc = pids_css_alloc, .css_free = pids_css_free, .can_attach = pids_can_attach, .cancel_attach = pids_cancel_attach, .can_fork = pids_can_fork, .cancel_fork = pids_cancel_fork, .release = pids_release, .legacy_cftypes = pids_files_legacy, .dfl_cftypes = pids_files, .threaded = true, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * usb hub driver head file * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 1999 Johannes Erdfelt * Copyright (C) 1999 Gregory P. Smith * Copyright (C) 2001 Brad Hards (bhards@bigpond.net.au) * Copyright (C) 2012 Intel Corp (tianyu.lan@intel.com) * * move struct usb_hub to this file. */ #include <linux/usb.h> #include <linux/usb/ch11.h> #include <linux/usb/hcd.h> #include <linux/usb/typec.h> #include "usb.h" struct usb_hub { struct device *intfdev; /* the "interface" device */ struct usb_device *hdev; struct kref kref; struct urb *urb; /* for interrupt polling pipe */ /* buffer for urb ... with extra space in case of babble */ u8 (*buffer)[8]; union { struct usb_hub_status hub; struct usb_port_status port; } *status; /* buffer for status reports */ struct mutex status_mutex; /* for the status buffer */ int error; /* last reported error */ int nerrors; /* track consecutive errors */ unsigned long event_bits[1]; /* status change bitmask */ unsigned long change_bits[1]; /* ports with logical connect status change */ unsigned long removed_bits[1]; /* ports with a "removed" device present */ unsigned long wakeup_bits[1]; /* ports that have signaled remote wakeup */ unsigned long power_bits[1]; /* ports that are powered */ unsigned long child_usage_bits[1]; /* ports powered on for children */ unsigned long warm_reset_bits[1]; /* ports requesting warm reset recovery */ #if USB_MAXCHILDREN > 31 /* 8*sizeof(unsigned long) - 1 */ #error event_bits[] is too short! #endif struct usb_hub_descriptor *descriptor; /* class descriptor */ struct usb_tt tt; /* Transaction Translator */ unsigned mA_per_port; /* current for each child */ #ifdef CONFIG_PM unsigned wakeup_enabled_descendants; #endif unsigned limited_power:1; unsigned quiescing:1; unsigned disconnected:1; unsigned in_reset:1; unsigned quirk_disable_autosuspend:1; unsigned quirk_check_port_auto_suspend:1; unsigned has_indicators:1; u8 indicator[USB_MAXCHILDREN]; struct delayed_work leds; struct delayed_work init_work; struct work_struct events; spinlock_t irq_urb_lock; struct timer_list irq_urb_retry; struct usb_port **ports; struct list_head onboard_devs; }; /** * struct usb port - kernel's representation of a usb port * @child: usb device attached to the port * @dev: generic device interface * @port_owner: port's owner * @peer: related usb2 and usb3 ports (share the same connector) * @connector: USB Type-C connector * @req: default pm qos request for hubs without port power control * @connect_type: port's connect type * @state: device state of the usb device attached to the port * @state_kn: kernfs_node of the sysfs attribute that accesses @state * @location: opaque representation of platform connector location * @status_lock: synchronize port_event() vs usb_port_{suspend|resume} * @portnum: port index num based one * @is_superspeed cache super-speed status * @usb3_lpm_u1_permit: whether USB3 U1 LPM is permitted. * @usb3_lpm_u2_permit: whether USB3 U2 LPM is permitted. * @early_stop: whether port initialization will be stopped earlier. * @ignore_event: whether events of the port are ignored. */ struct usb_port { struct usb_device *child; struct device dev; struct usb_dev_state *port_owner; struct usb_port *peer; struct typec_connector *connector; struct dev_pm_qos_request *req; enum usb_port_connect_type connect_type; enum usb_device_state state; struct kernfs_node *state_kn; usb_port_location_t location; struct mutex status_lock; u32 over_current_count; u8 portnum; u32 quirks; unsigned int early_stop:1; unsigned int ignore_event:1; unsigned int is_superspeed:1; unsigned int usb3_lpm_u1_permit:1; unsigned int usb3_lpm_u2_permit:1; }; #define to_usb_port(_dev) \ container_of(_dev, struct usb_port, dev) extern int usb_hub_create_port_device(struct usb_hub *hub, int port1); extern void usb_hub_remove_port_device(struct usb_hub *hub, int port1); extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, int port1, bool set); extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev); extern void hub_get(struct usb_hub *hub); extern void hub_put(struct usb_hub *hub); extern int hub_port_debounce(struct usb_hub *hub, int port1, bool must_be_connected); extern int usb_clear_port_feature(struct usb_device *hdev, int port1, int feature); extern int usb_hub_port_status(struct usb_hub *hub, int port1, u16 *status, u16 *change); extern int usb_port_is_power_on(struct usb_hub *hub, unsigned int portstatus); static inline bool hub_is_port_power_switchable(struct usb_hub *hub) { __le16 hcs; if (!hub) return false; hcs = hub->descriptor->wHubCharacteristics; return (le16_to_cpu(hcs) & HUB_CHAR_LPSM) < HUB_CHAR_NO_LPSM; } static inline int hub_is_superspeed(struct usb_device *hdev) { return hdev->descriptor.bDeviceProtocol == USB_HUB_PR_SS; } static inline int hub_is_superspeedplus(struct usb_device *hdev) { return (hdev->descriptor.bDeviceProtocol == USB_HUB_PR_SS && le16_to_cpu(hdev->descriptor.bcdUSB) >= 0x0310 && hdev->bos && hdev->bos->ssp_cap); } static inline unsigned hub_power_on_good_delay(struct usb_hub *hub) { unsigned delay = hub->descriptor->bPwrOn2PwrGood * 2; if (!hub->hdev->parent) /* root hub */ return delay; else /* Wait at least 100 msec for power to become stable */ return max(delay, 100U); } static inline int hub_port_debounce_be_connected(struct usb_hub *hub, int port1) { return hub_port_debounce(hub, port1, true); } static inline int hub_port_debounce_be_stable(struct usb_hub *hub, int port1) { return hub_port_debounce(hub, port1, false); } |
| 398 2 339 281 721 470 552 11 110 47 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fs.h> #include <linux/quota.h> #include <linux/export.h> /** * qid_eq - Test to see if to kquid values are the same * @left: A qid value * @right: Another quid value * * Return true if the two qid values are equal and false otherwise. */ bool qid_eq(struct kqid left, struct kqid right) { if (left.type != right.type) return false; switch(left.type) { case USRQUOTA: return uid_eq(left.uid, right.uid); case GRPQUOTA: return gid_eq(left.gid, right.gid); case PRJQUOTA: return projid_eq(left.projid, right.projid); default: BUG(); } } EXPORT_SYMBOL(qid_eq); /** * qid_lt - Test to see if one qid value is less than another * @left: The possibly lesser qid value * @right: The possibly greater qid value * * Return true if left is less than right and false otherwise. */ bool qid_lt(struct kqid left, struct kqid right) { if (left.type < right.type) return true; if (left.type > right.type) return false; switch (left.type) { case USRQUOTA: return uid_lt(left.uid, right.uid); case GRPQUOTA: return gid_lt(left.gid, right.gid); case PRJQUOTA: return projid_lt(left.projid, right.projid); default: BUG(); } } EXPORT_SYMBOL(qid_lt); /** * from_kqid - Create a qid from a kqid user-namespace pair. * @targ: The user namespace we want a qid in. * @kqid: The kernel internal quota identifier to start with. * * Map @kqid into the user-namespace specified by @targ and * return the resulting qid. * * There is always a mapping into the initial user_namespace. * * If @kqid has no mapping in @targ (qid_t)-1 is returned. */ qid_t from_kqid(struct user_namespace *targ, struct kqid kqid) { switch (kqid.type) { case USRQUOTA: return from_kuid(targ, kqid.uid); case GRPQUOTA: return from_kgid(targ, kqid.gid); case PRJQUOTA: return from_kprojid(targ, kqid.projid); default: BUG(); } } EXPORT_SYMBOL(from_kqid); /** * from_kqid_munged - Create a qid from a kqid user-namespace pair. * @targ: The user namespace we want a qid in. * @kqid: The kernel internal quota identifier to start with. * * Map @kqid into the user-namespace specified by @targ and * return the resulting qid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kqid from_kqid_munged never fails and always * returns a valid projid. This makes from_kqid_munged * appropriate for use in places where failing to provide * a qid_t is not a good option. * * If @kqid has no mapping in @targ the kqid.type specific * overflow identifier is returned. */ qid_t from_kqid_munged(struct user_namespace *targ, struct kqid kqid) { switch (kqid.type) { case USRQUOTA: return from_kuid_munged(targ, kqid.uid); case GRPQUOTA: return from_kgid_munged(targ, kqid.gid); case PRJQUOTA: return from_kprojid_munged(targ, kqid.projid); default: BUG(); } } EXPORT_SYMBOL(from_kqid_munged); /** * qid_valid - Report if a valid value is stored in a kqid. * @qid: The kernel internal quota identifier to test. */ bool qid_valid(struct kqid qid) { switch (qid.type) { case USRQUOTA: return uid_valid(qid.uid); case GRPQUOTA: return gid_valid(qid.gid); case PRJQUOTA: return projid_valid(qid.projid); default: BUG(); } } EXPORT_SYMBOL(qid_valid); |
| 22 19 34 199 14 269 26 26 6 10 90 33 33 26 26 13 1 8 10 8 4 4 4 4 19 10 4 35 2 33 7 26 89 90 17 17 90 90 89 90 90 89 90 49 1 3 45 10 2 8 6 12 4 9 7 61 62 59 59 23 1 22 4 16 2 2 8 1 7 5 5 5 8 2 1 3 3 3 3 1 27 27 2 7 2 5 2 5 7 44 44 1 4 28 9 41 6 1 5 2 3 13 13 8 3 11 3 1 2 2 4 2 2 2 4 3 1 5 1 1 3 1 2 1 7 2 6 3 3 3 2 8 5 1 25 13 53 52 12 39 50 3 3 1 1 15 1 3 4 7 5 5 5 5 4 2 2 13 1 13 1 1 11 1 2 8 4 4 4 4 4 4 10 334 1 2 1 2 1 329 10 10 19 19 39 39 38 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 | /* * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/completion.h> #include <linux/file.h> #include <linux/mutex.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/idr.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/miscdevice.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/module.h> #include <linux/nsproxy.h> #include <linux/nospec.h> #include <rdma/rdma_user_cm.h> #include <rdma/ib_marshall.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/ib_addr.h> #include <rdma/ib.h> #include <rdma/ib_cm.h> #include <rdma/rdma_netlink.h> #include "core_priv.h" MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("RDMA Userspace Connection Manager Access"); MODULE_LICENSE("Dual BSD/GPL"); static unsigned int max_backlog = 1024; static struct ctl_table_header *ucma_ctl_table_hdr; static struct ctl_table ucma_ctl_table[] = { { .procname = "max_backlog", .data = &max_backlog, .maxlen = sizeof max_backlog, .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, }; struct ucma_file { struct mutex mut; struct file *filp; struct list_head ctx_list; struct list_head event_list; wait_queue_head_t poll_wait; }; struct ucma_context { u32 id; struct completion comp; refcount_t ref; int events_reported; atomic_t backlog; struct ucma_file *file; struct rdma_cm_id *cm_id; struct mutex mutex; u64 uid; struct list_head list; struct list_head mc_list; struct work_struct close_work; }; struct ucma_multicast { struct ucma_context *ctx; u32 id; int events_reported; u64 uid; u8 join_state; struct list_head list; struct sockaddr_storage addr; }; struct ucma_event { struct ucma_context *ctx; struct ucma_context *conn_req_ctx; struct ucma_multicast *mc; struct list_head list; struct rdma_ucm_event_resp resp; }; static DEFINE_XARRAY_ALLOC(ctx_table); static DEFINE_XARRAY_ALLOC(multicast_table); static const struct file_operations ucma_fops; static int ucma_destroy_private_ctx(struct ucma_context *ctx); static inline struct ucma_context *_ucma_find_context(int id, struct ucma_file *file) { struct ucma_context *ctx; ctx = xa_load(&ctx_table, id); if (!ctx) ctx = ERR_PTR(-ENOENT); else if (ctx->file != file) ctx = ERR_PTR(-EINVAL); return ctx; } static struct ucma_context *ucma_get_ctx(struct ucma_file *file, int id) { struct ucma_context *ctx; xa_lock(&ctx_table); ctx = _ucma_find_context(id, file); if (!IS_ERR(ctx)) if (!refcount_inc_not_zero(&ctx->ref)) ctx = ERR_PTR(-ENXIO); xa_unlock(&ctx_table); return ctx; } static void ucma_put_ctx(struct ucma_context *ctx) { if (refcount_dec_and_test(&ctx->ref)) complete(&ctx->comp); } /* * Same as ucm_get_ctx but requires that ->cm_id->device is valid, eg that the * CM_ID is bound. */ static struct ucma_context *ucma_get_ctx_dev(struct ucma_file *file, int id) { struct ucma_context *ctx = ucma_get_ctx(file, id); if (IS_ERR(ctx)) return ctx; if (!ctx->cm_id->device) { ucma_put_ctx(ctx); return ERR_PTR(-EINVAL); } return ctx; } static void ucma_close_id(struct work_struct *work) { struct ucma_context *ctx = container_of(work, struct ucma_context, close_work); /* once all inflight tasks are finished, we close all underlying * resources. The context is still alive till its explicit destryoing * by its creator. This puts back the xarray's reference. */ ucma_put_ctx(ctx); wait_for_completion(&ctx->comp); /* No new events will be generated after destroying the id. */ rdma_destroy_id(ctx->cm_id); /* Reading the cm_id without holding a positive ref is not allowed */ ctx->cm_id = NULL; } static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) { struct ucma_context *ctx; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; INIT_WORK(&ctx->close_work, ucma_close_id); init_completion(&ctx->comp); INIT_LIST_HEAD(&ctx->mc_list); /* So list_del() will work if we don't do ucma_finish_ctx() */ INIT_LIST_HEAD(&ctx->list); ctx->file = file; mutex_init(&ctx->mutex); if (xa_alloc(&ctx_table, &ctx->id, NULL, xa_limit_32b, GFP_KERNEL)) { kfree(ctx); return NULL; } return ctx; } static void ucma_set_ctx_cm_id(struct ucma_context *ctx, struct rdma_cm_id *cm_id) { refcount_set(&ctx->ref, 1); ctx->cm_id = cm_id; } static void ucma_finish_ctx(struct ucma_context *ctx) { lockdep_assert_held(&ctx->file->mut); list_add_tail(&ctx->list, &ctx->file->ctx_list); xa_store(&ctx_table, ctx->id, ctx, GFP_KERNEL); } static void ucma_copy_conn_event(struct rdma_ucm_conn_param *dst, struct rdma_conn_param *src) { if (src->private_data_len) memcpy(dst->private_data, src->private_data, src->private_data_len); dst->private_data_len = src->private_data_len; dst->responder_resources = src->responder_resources; dst->initiator_depth = src->initiator_depth; dst->flow_control = src->flow_control; dst->retry_count = src->retry_count; dst->rnr_retry_count = src->rnr_retry_count; dst->srq = src->srq; dst->qp_num = src->qp_num; } static void ucma_copy_ud_event(struct ib_device *device, struct rdma_ucm_ud_param *dst, struct rdma_ud_param *src) { if (src->private_data_len) memcpy(dst->private_data, src->private_data, src->private_data_len); dst->private_data_len = src->private_data_len; ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr); dst->qp_num = src->qp_num; dst->qkey = src->qkey; } static struct ucma_event *ucma_create_uevent(struct ucma_context *ctx, struct rdma_cm_event *event) { struct ucma_event *uevent; uevent = kzalloc(sizeof(*uevent), GFP_KERNEL); if (!uevent) return NULL; uevent->ctx = ctx; switch (event->event) { case RDMA_CM_EVENT_MULTICAST_JOIN: case RDMA_CM_EVENT_MULTICAST_ERROR: uevent->mc = (struct ucma_multicast *) event->param.ud.private_data; uevent->resp.uid = uevent->mc->uid; uevent->resp.id = uevent->mc->id; break; default: uevent->resp.uid = ctx->uid; uevent->resp.id = ctx->id; break; } uevent->resp.event = event->event; uevent->resp.status = event->status; if (ctx->cm_id->qp_type == IB_QPT_UD) ucma_copy_ud_event(ctx->cm_id->device, &uevent->resp.param.ud, &event->param.ud); else ucma_copy_conn_event(&uevent->resp.param.conn, &event->param.conn); uevent->resp.ece.vendor_id = event->ece.vendor_id; uevent->resp.ece.attr_mod = event->ece.attr_mod; return uevent; } static int ucma_connect_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { struct ucma_context *listen_ctx = cm_id->context; struct ucma_context *ctx; struct ucma_event *uevent; if (!atomic_add_unless(&listen_ctx->backlog, -1, 0)) return -ENOMEM; ctx = ucma_alloc_ctx(listen_ctx->file); if (!ctx) goto err_backlog; ucma_set_ctx_cm_id(ctx, cm_id); uevent = ucma_create_uevent(listen_ctx, event); if (!uevent) goto err_alloc; uevent->conn_req_ctx = ctx; uevent->resp.id = ctx->id; ctx->cm_id->context = ctx; mutex_lock(&ctx->file->mut); ucma_finish_ctx(ctx); list_add_tail(&uevent->list, &ctx->file->event_list); mutex_unlock(&ctx->file->mut); wake_up_interruptible(&ctx->file->poll_wait); return 0; err_alloc: ucma_destroy_private_ctx(ctx); err_backlog: atomic_inc(&listen_ctx->backlog); /* Returning error causes the new ID to be destroyed */ return -ENOMEM; } static int ucma_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { struct ucma_event *uevent; struct ucma_context *ctx = cm_id->context; if (event->event == RDMA_CM_EVENT_CONNECT_REQUEST) return ucma_connect_event_handler(cm_id, event); /* * We ignore events for new connections until userspace has set their * context. This can only happen if an error occurs on a new connection * before the user accepts it. This is okay, since the accept will just * fail later. However, we do need to release the underlying HW * resources in case of a device removal event. */ if (ctx->uid) { uevent = ucma_create_uevent(ctx, event); if (!uevent) return 0; mutex_lock(&ctx->file->mut); list_add_tail(&uevent->list, &ctx->file->event_list); mutex_unlock(&ctx->file->mut); wake_up_interruptible(&ctx->file->poll_wait); } if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) { xa_lock(&ctx_table); if (xa_load(&ctx_table, ctx->id) == ctx) queue_work(system_unbound_wq, &ctx->close_work); xa_unlock(&ctx_table); } return 0; } static ssize_t ucma_get_event(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_get_event cmd; struct ucma_event *uevent; /* * Old 32 bit user space does not send the 4 byte padding in the * reserved field. We don't care, allow it to keep working. */ if (out_len < sizeof(uevent->resp) - sizeof(uevent->resp.reserved) - sizeof(uevent->resp.ece)) return -ENOSPC; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; mutex_lock(&file->mut); while (list_empty(&file->event_list)) { mutex_unlock(&file->mut); if (file->filp->f_flags & O_NONBLOCK) return -EAGAIN; if (wait_event_interruptible(file->poll_wait, !list_empty(&file->event_list))) return -ERESTARTSYS; mutex_lock(&file->mut); } uevent = list_first_entry(&file->event_list, struct ucma_event, list); if (copy_to_user(u64_to_user_ptr(cmd.response), &uevent->resp, min_t(size_t, out_len, sizeof(uevent->resp)))) { mutex_unlock(&file->mut); return -EFAULT; } list_del(&uevent->list); uevent->ctx->events_reported++; if (uevent->mc) uevent->mc->events_reported++; if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST) atomic_inc(&uevent->ctx->backlog); mutex_unlock(&file->mut); kfree(uevent); return 0; } static int ucma_get_qp_type(struct rdma_ucm_create_id *cmd, enum ib_qp_type *qp_type) { switch (cmd->ps) { case RDMA_PS_TCP: *qp_type = IB_QPT_RC; return 0; case RDMA_PS_UDP: case RDMA_PS_IPOIB: *qp_type = IB_QPT_UD; return 0; case RDMA_PS_IB: *qp_type = cmd->qp_type; return 0; default: return -EINVAL; } } static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_create_id cmd; struct rdma_ucm_create_id_resp resp; struct ucma_context *ctx; struct rdma_cm_id *cm_id; enum ib_qp_type qp_type; int ret; if (out_len < sizeof(resp)) return -ENOSPC; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; ret = ucma_get_qp_type(&cmd, &qp_type); if (ret) return ret; ctx = ucma_alloc_ctx(file); if (!ctx) return -ENOMEM; ctx->uid = cmd.uid; cm_id = rdma_create_user_id(ucma_event_handler, ctx, cmd.ps, qp_type); if (IS_ERR(cm_id)) { ret = PTR_ERR(cm_id); goto err1; } ucma_set_ctx_cm_id(ctx, cm_id); resp.id = ctx->id; if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) { ret = -EFAULT; goto err1; } mutex_lock(&file->mut); ucma_finish_ctx(ctx); mutex_unlock(&file->mut); return 0; err1: ucma_destroy_private_ctx(ctx); return ret; } static void ucma_cleanup_multicast(struct ucma_context *ctx) { struct ucma_multicast *mc, *tmp; xa_lock(&multicast_table); list_for_each_entry_safe(mc, tmp, &ctx->mc_list, list) { list_del(&mc->list); /* * At this point mc->ctx->ref is 0 so the mc cannot leave the * lock on the reader and this is enough serialization */ __xa_erase(&multicast_table, mc->id); kfree(mc); } xa_unlock(&multicast_table); } static void ucma_cleanup_mc_events(struct ucma_multicast *mc) { struct ucma_event *uevent, *tmp; rdma_lock_handler(mc->ctx->cm_id); mutex_lock(&mc->ctx->file->mut); list_for_each_entry_safe(uevent, tmp, &mc->ctx->file->event_list, list) { if (uevent->mc != mc) continue; list_del(&uevent->list); kfree(uevent); } mutex_unlock(&mc->ctx->file->mut); rdma_unlock_handler(mc->ctx->cm_id); } static int ucma_cleanup_ctx_events(struct ucma_context *ctx) { int events_reported; struct ucma_event *uevent, *tmp; LIST_HEAD(list); /* Cleanup events not yet reported to the user.*/ mutex_lock(&ctx->file->mut); list_for_each_entry_safe(uevent, tmp, &ctx->file->event_list, list) { if (uevent->ctx != ctx) continue; if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST && xa_cmpxchg(&ctx_table, uevent->conn_req_ctx->id, uevent->conn_req_ctx, XA_ZERO_ENTRY, GFP_KERNEL) == uevent->conn_req_ctx) { list_move_tail(&uevent->list, &list); continue; } list_del(&uevent->list); kfree(uevent); } list_del(&ctx->list); events_reported = ctx->events_reported; mutex_unlock(&ctx->file->mut); /* * If this was a listening ID then any connections spawned from it that * have not been delivered to userspace are cleaned up too. Must be done * outside any locks. */ list_for_each_entry_safe(uevent, tmp, &list, list) { ucma_destroy_private_ctx(uevent->conn_req_ctx); kfree(uevent); } return events_reported; } /* * When this is called the xarray must have a XA_ZERO_ENTRY in the ctx->id (ie * the ctx is not public to the user). This either because: * - ucma_finish_ctx() hasn't been called * - xa_cmpxchg() succeed to remove the entry (only one thread can succeed) */ static int ucma_destroy_private_ctx(struct ucma_context *ctx) { int events_reported; /* * Destroy the underlying cm_id. New work queuing is prevented now by * the removal from the xarray. Once the work is cancled ref will either * be 0 because the work ran to completion and consumed the ref from the * xarray, or it will be positive because we still have the ref from the * xarray. This can also be 0 in cases where cm_id was never set */ cancel_work_sync(&ctx->close_work); if (refcount_read(&ctx->ref)) ucma_close_id(&ctx->close_work); events_reported = ucma_cleanup_ctx_events(ctx); ucma_cleanup_multicast(ctx); WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, XA_ZERO_ENTRY, NULL, GFP_KERNEL) != NULL); mutex_destroy(&ctx->mutex); kfree(ctx); return events_reported; } static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_destroy_id cmd; struct rdma_ucm_destroy_id_resp resp; struct ucma_context *ctx; int ret = 0; if (out_len < sizeof(resp)) return -ENOSPC; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; xa_lock(&ctx_table); ctx = _ucma_find_context(cmd.id, file); if (!IS_ERR(ctx)) { if (__xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY, GFP_KERNEL) != ctx) ctx = ERR_PTR(-ENOENT); } xa_unlock(&ctx_table); if (IS_ERR(ctx)) return PTR_ERR(ctx); resp.events_reported = ucma_destroy_private_ctx(ctx); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; return ret; } static ssize_t ucma_bind_ip(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_bind_ip cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if (!rdma_addr_size_in6(&cmd.addr)) return -EINVAL; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_bind(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_bind cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if (cmd.reserved || !cmd.addr_size || cmd.addr_size != rdma_addr_size_kss(&cmd.addr)) return -EINVAL; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_resolve_ip(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_resolve_ip cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if ((cmd.src_addr.sin6_family && !rdma_addr_size_in6(&cmd.src_addr)) || !rdma_addr_size_in6(&cmd.dst_addr)) return -EINVAL; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, (struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_resolve_addr(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_resolve_addr cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if (cmd.reserved || (cmd.src_size && (cmd.src_size != rdma_addr_size_kss(&cmd.src_addr))) || !cmd.dst_size || (cmd.dst_size != rdma_addr_size_kss(&cmd.dst_addr))) return -EINVAL; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, (struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_resolve_route(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_resolve_route cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; ctx = ucma_get_ctx_dev(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); ret = rdma_resolve_route(ctx->cm_id, cmd.timeout_ms); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp, struct rdma_route *route) { struct rdma_dev_addr *dev_addr; resp->num_paths = route->num_pri_alt_paths; switch (route->num_pri_alt_paths) { case 0: dev_addr = &route->addr.dev_addr; rdma_addr_get_dgid(dev_addr, (union ib_gid *) &resp->ib_route[0].dgid); rdma_addr_get_sgid(dev_addr, (union ib_gid *) &resp->ib_route[0].sgid); resp->ib_route[0].pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); break; case 2: ib_copy_path_rec_to_user(&resp->ib_route[1], &route->path_rec[1]); fallthrough; case 1: ib_copy_path_rec_to_user(&resp->ib_route[0], &route->path_rec[0]); break; default: break; } } static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp, struct rdma_route *route) { resp->num_paths = route->num_pri_alt_paths; switch (route->num_pri_alt_paths) { case 0: rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr, (union ib_gid *)&resp->ib_route[0].dgid); rdma_ip2gid((struct sockaddr *)&route->addr.src_addr, (union ib_gid *)&resp->ib_route[0].sgid); resp->ib_route[0].pkey = cpu_to_be16(0xffff); break; case 2: ib_copy_path_rec_to_user(&resp->ib_route[1], &route->path_rec[1]); fallthrough; case 1: ib_copy_path_rec_to_user(&resp->ib_route[0], &route->path_rec[0]); break; default: break; } } static void ucma_copy_iw_route(struct rdma_ucm_query_route_resp *resp, struct rdma_route *route) { struct rdma_dev_addr *dev_addr; dev_addr = &route->addr.dev_addr; rdma_addr_get_dgid(dev_addr, (union ib_gid *) &resp->ib_route[0].dgid); rdma_addr_get_sgid(dev_addr, (union ib_gid *) &resp->ib_route[0].sgid); } static ssize_t ucma_query_route(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_query cmd; struct rdma_ucm_query_route_resp resp; struct ucma_context *ctx; struct sockaddr *addr; int ret = 0; if (out_len < offsetof(struct rdma_ucm_query_route_resp, ibdev_index)) return -ENOSPC; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); memset(&resp, 0, sizeof resp); addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr; memcpy(&resp.src_addr, addr, addr->sa_family == AF_INET ? sizeof(struct sockaddr_in) : sizeof(struct sockaddr_in6)); addr = (struct sockaddr *) &ctx->cm_id->route.addr.dst_addr; memcpy(&resp.dst_addr, addr, addr->sa_family == AF_INET ? sizeof(struct sockaddr_in) : sizeof(struct sockaddr_in6)); if (!ctx->cm_id->device) goto out; resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid; resp.ibdev_index = ctx->cm_id->device->index; resp.port_num = ctx->cm_id->port_num; if (rdma_cap_ib_sa(ctx->cm_id->device, ctx->cm_id->port_num)) ucma_copy_ib_route(&resp, &ctx->cm_id->route); else if (rdma_protocol_roce(ctx->cm_id->device, ctx->cm_id->port_num)) ucma_copy_iboe_route(&resp, &ctx->cm_id->route); else if (rdma_protocol_iwarp(ctx->cm_id->device, ctx->cm_id->port_num)) ucma_copy_iw_route(&resp, &ctx->cm_id->route); out: mutex_unlock(&ctx->mutex); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, min_t(size_t, out_len, sizeof(resp)))) ret = -EFAULT; ucma_put_ctx(ctx); return ret; } static void ucma_query_device_addr(struct rdma_cm_id *cm_id, struct rdma_ucm_query_addr_resp *resp) { if (!cm_id->device) return; resp->node_guid = (__force __u64) cm_id->device->node_guid; resp->ibdev_index = cm_id->device->index; resp->port_num = cm_id->port_num; resp->pkey = (__force __u16) cpu_to_be16( ib_addr_get_pkey(&cm_id->route.addr.dev_addr)); } static ssize_t ucma_query_addr(struct ucma_context *ctx, void __user *response, int out_len) { struct rdma_ucm_query_addr_resp resp; struct sockaddr *addr; int ret = 0; if (out_len < offsetof(struct rdma_ucm_query_addr_resp, ibdev_index)) return -ENOSPC; memset(&resp, 0, sizeof resp); addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr; resp.src_size = rdma_addr_size(addr); memcpy(&resp.src_addr, addr, resp.src_size); addr = (struct sockaddr *) &ctx->cm_id->route.addr.dst_addr; resp.dst_size = rdma_addr_size(addr); memcpy(&resp.dst_addr, addr, resp.dst_size); ucma_query_device_addr(ctx->cm_id, &resp); if (copy_to_user(response, &resp, min_t(size_t, out_len, sizeof(resp)))) ret = -EFAULT; return ret; } static ssize_t ucma_query_path(struct ucma_context *ctx, void __user *response, int out_len) { struct rdma_ucm_query_path_resp *resp; int i, ret = 0; if (out_len < sizeof(*resp)) return -ENOSPC; resp = kzalloc(out_len, GFP_KERNEL); if (!resp) return -ENOMEM; resp->num_paths = ctx->cm_id->route.num_pri_alt_paths; for (i = 0, out_len -= sizeof(*resp); i < resp->num_paths && out_len > sizeof(struct ib_path_rec_data); i++, out_len -= sizeof(struct ib_path_rec_data)) { struct sa_path_rec *rec = &ctx->cm_id->route.path_rec[i]; resp->path_data[i].flags = IB_PATH_GMP | IB_PATH_PRIMARY | IB_PATH_BIDIRECTIONAL; if (rec->rec_type == SA_PATH_REC_TYPE_OPA) { struct sa_path_rec ib; sa_convert_path_opa_to_ib(&ib, rec); ib_sa_pack_path(&ib, &resp->path_data[i].path_rec); } else { ib_sa_pack_path(rec, &resp->path_data[i].path_rec); } } if (copy_to_user(response, resp, struct_size(resp, path_data, i))) ret = -EFAULT; kfree(resp); return ret; } static ssize_t ucma_query_gid(struct ucma_context *ctx, void __user *response, int out_len) { struct rdma_ucm_query_addr_resp resp; struct sockaddr_ib *addr; int ret = 0; if (out_len < offsetof(struct rdma_ucm_query_addr_resp, ibdev_index)) return -ENOSPC; memset(&resp, 0, sizeof resp); ucma_query_device_addr(ctx->cm_id, &resp); addr = (struct sockaddr_ib *) &resp.src_addr; resp.src_size = sizeof(*addr); if (ctx->cm_id->route.addr.src_addr.ss_family == AF_IB) { memcpy(addr, &ctx->cm_id->route.addr.src_addr, resp.src_size); } else { addr->sib_family = AF_IB; addr->sib_pkey = (__force __be16) resp.pkey; rdma_read_gids(ctx->cm_id, (union ib_gid *)&addr->sib_addr, NULL); addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *) &ctx->cm_id->route.addr.src_addr); } addr = (struct sockaddr_ib *) &resp.dst_addr; resp.dst_size = sizeof(*addr); if (ctx->cm_id->route.addr.dst_addr.ss_family == AF_IB) { memcpy(addr, &ctx->cm_id->route.addr.dst_addr, resp.dst_size); } else { addr->sib_family = AF_IB; addr->sib_pkey = (__force __be16) resp.pkey; rdma_read_gids(ctx->cm_id, NULL, (union ib_gid *)&addr->sib_addr); addr->sib_sid = rdma_get_service_id(ctx->cm_id, (struct sockaddr *) &ctx->cm_id->route.addr.dst_addr); } if (copy_to_user(response, &resp, min_t(size_t, out_len, sizeof(resp)))) ret = -EFAULT; return ret; } static ssize_t ucma_query(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_query cmd; struct ucma_context *ctx; void __user *response; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; response = u64_to_user_ptr(cmd.response); ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); switch (cmd.option) { case RDMA_USER_CM_QUERY_ADDR: ret = ucma_query_addr(ctx, response, out_len); break; case RDMA_USER_CM_QUERY_PATH: ret = ucma_query_path(ctx, response, out_len); break; case RDMA_USER_CM_QUERY_GID: ret = ucma_query_gid(ctx, response, out_len); break; default: ret = -ENOSYS; break; } mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static void ucma_copy_conn_param(struct rdma_cm_id *id, struct rdma_conn_param *dst, struct rdma_ucm_conn_param *src) { dst->private_data = src->private_data; dst->private_data_len = src->private_data_len; dst->responder_resources = src->responder_resources; dst->initiator_depth = src->initiator_depth; dst->flow_control = src->flow_control; dst->retry_count = src->retry_count; dst->rnr_retry_count = src->rnr_retry_count; dst->srq = src->srq; dst->qp_num = src->qp_num & 0xFFFFFF; dst->qkey = (id->route.addr.src_addr.ss_family == AF_IB) ? src->qkey : 0; } static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_conn_param conn_param; struct rdma_ucm_ece ece = {}; struct rdma_ucm_connect cmd; struct ucma_context *ctx; size_t in_size; int ret; if (in_len < offsetofend(typeof(cmd), reserved)) return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; if (!cmd.conn_param.valid) return -EINVAL; ctx = ucma_get_ctx_dev(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param); if (offsetofend(typeof(cmd), ece) <= in_size) { ece.vendor_id = cmd.ece.vendor_id; ece.attr_mod = cmd.ece.attr_mod; } mutex_lock(&ctx->mutex); ret = rdma_connect_ece(ctx->cm_id, &conn_param, &ece); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_listen(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_listen cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); if (cmd.backlog <= 0 || cmd.backlog > max_backlog) cmd.backlog = max_backlog; atomic_set(&ctx->backlog, cmd.backlog); mutex_lock(&ctx->mutex); ret = rdma_listen(ctx->cm_id, cmd.backlog); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_accept cmd; struct rdma_conn_param conn_param; struct rdma_ucm_ece ece = {}; struct ucma_context *ctx; size_t in_size; int ret; if (in_len < offsetofend(typeof(cmd), reserved)) return -EINVAL; in_size = min_t(size_t, in_len, sizeof(cmd)); if (copy_from_user(&cmd, inbuf, in_size)) return -EFAULT; ctx = ucma_get_ctx_dev(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); if (offsetofend(typeof(cmd), ece) <= in_size) { ece.vendor_id = cmd.ece.vendor_id; ece.attr_mod = cmd.ece.attr_mod; } if (cmd.conn_param.valid) { ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param); mutex_lock(&ctx->mutex); rdma_lock_handler(ctx->cm_id); ret = rdma_accept_ece(ctx->cm_id, &conn_param, &ece); if (!ret) { /* The uid must be set atomically with the handler */ ctx->uid = cmd.uid; } rdma_unlock_handler(ctx->cm_id); mutex_unlock(&ctx->mutex); } else { mutex_lock(&ctx->mutex); rdma_lock_handler(ctx->cm_id); ret = rdma_accept_ece(ctx->cm_id, NULL, &ece); rdma_unlock_handler(ctx->cm_id); mutex_unlock(&ctx->mutex); } ucma_put_ctx(ctx); return ret; } static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_reject cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if (!cmd.reason) cmd.reason = IB_CM_REJ_CONSUMER_DEFINED; switch (cmd.reason) { case IB_CM_REJ_CONSUMER_DEFINED: case IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED: break; default: return -EINVAL; } ctx = ucma_get_ctx_dev(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); ret = rdma_reject(ctx->cm_id, cmd.private_data, cmd.private_data_len, cmd.reason); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_disconnect(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_disconnect cmd; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; ctx = ucma_get_ctx_dev(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); ret = rdma_disconnect(ctx->cm_id); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_init_qp_attr(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_init_qp_attr cmd; struct ib_uverbs_qp_attr resp; struct ucma_context *ctx; struct ib_qp_attr qp_attr; int ret; if (out_len < sizeof(resp)) return -ENOSPC; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if (cmd.qp_state > IB_QPS_ERR) return -EINVAL; ctx = ucma_get_ctx_dev(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); resp.qp_attr_mask = 0; memset(&qp_attr, 0, sizeof qp_attr); qp_attr.qp_state = cmd.qp_state; mutex_lock(&ctx->mutex); ret = rdma_init_qp_attr(ctx->cm_id, &qp_attr, &resp.qp_attr_mask); mutex_unlock(&ctx->mutex); if (ret) goto out; ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; out: ucma_put_ctx(ctx); return ret; } static int ucma_set_option_id(struct ucma_context *ctx, int optname, void *optval, size_t optlen) { int ret = 0; switch (optname) { case RDMA_OPTION_ID_TOS: if (optlen != sizeof(u8)) { ret = -EINVAL; break; } rdma_set_service_type(ctx->cm_id, *((u8 *) optval)); break; case RDMA_OPTION_ID_REUSEADDR: if (optlen != sizeof(int)) { ret = -EINVAL; break; } ret = rdma_set_reuseaddr(ctx->cm_id, *((int *) optval) ? 1 : 0); break; case RDMA_OPTION_ID_AFONLY: if (optlen != sizeof(int)) { ret = -EINVAL; break; } ret = rdma_set_afonly(ctx->cm_id, *((int *) optval) ? 1 : 0); break; case RDMA_OPTION_ID_ACK_TIMEOUT: if (optlen != sizeof(u8)) { ret = -EINVAL; break; } ret = rdma_set_ack_timeout(ctx->cm_id, *((u8 *)optval)); break; default: ret = -ENOSYS; } return ret; } static int ucma_set_ib_path(struct ucma_context *ctx, struct ib_path_rec_data *path_data, size_t optlen) { struct sa_path_rec sa_path; struct rdma_cm_event event; int ret; if (optlen % sizeof(*path_data)) return -EINVAL; for (; optlen; optlen -= sizeof(*path_data), path_data++) { if (path_data->flags == (IB_PATH_GMP | IB_PATH_PRIMARY | IB_PATH_BIDIRECTIONAL)) break; } if (!optlen) return -EINVAL; if (!ctx->cm_id->device) return -EINVAL; memset(&sa_path, 0, sizeof(sa_path)); sa_path.rec_type = SA_PATH_REC_TYPE_IB; ib_sa_unpack_path(path_data->path_rec, &sa_path); if (rdma_cap_opa_ah(ctx->cm_id->device, ctx->cm_id->port_num)) { struct sa_path_rec opa; sa_convert_path_ib_to_opa(&opa, &sa_path); mutex_lock(&ctx->mutex); ret = rdma_set_ib_path(ctx->cm_id, &opa); mutex_unlock(&ctx->mutex); } else { mutex_lock(&ctx->mutex); ret = rdma_set_ib_path(ctx->cm_id, &sa_path); mutex_unlock(&ctx->mutex); } if (ret) return ret; memset(&event, 0, sizeof event); event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; return ucma_event_handler(ctx->cm_id, &event); } static int ucma_set_option_ib(struct ucma_context *ctx, int optname, void *optval, size_t optlen) { int ret; switch (optname) { case RDMA_OPTION_IB_PATH: ret = ucma_set_ib_path(ctx, optval, optlen); break; default: ret = -ENOSYS; } return ret; } static int ucma_set_option_level(struct ucma_context *ctx, int level, int optname, void *optval, size_t optlen) { int ret; switch (level) { case RDMA_OPTION_ID: mutex_lock(&ctx->mutex); ret = ucma_set_option_id(ctx, optname, optval, optlen); mutex_unlock(&ctx->mutex); break; case RDMA_OPTION_IB: ret = ucma_set_option_ib(ctx, optname, optval, optlen); break; default: ret = -ENOSYS; } return ret; } static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_set_option cmd; struct ucma_context *ctx; void *optval; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if (unlikely(cmd.optlen > KMALLOC_MAX_SIZE)) return -EINVAL; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); optval = memdup_user(u64_to_user_ptr(cmd.optval), cmd.optlen); if (IS_ERR(optval)) { ret = PTR_ERR(optval); goto out; } ret = ucma_set_option_level(ctx, cmd.level, cmd.optname, optval, cmd.optlen); kfree(optval); out: ucma_put_ctx(ctx); return ret; } static ssize_t ucma_notify(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_notify cmd; struct ucma_context *ctx; int ret = -EINVAL; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mutex_lock(&ctx->mutex); if (ctx->cm_id->device) ret = rdma_notify(ctx->cm_id, (enum ib_event_type)cmd.event); mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } static ssize_t ucma_process_join(struct ucma_file *file, struct rdma_ucm_join_mcast *cmd, int out_len) { struct rdma_ucm_create_id_resp resp; struct ucma_context *ctx; struct ucma_multicast *mc; struct sockaddr *addr; int ret; u8 join_state; if (out_len < sizeof(resp)) return -ENOSPC; addr = (struct sockaddr *) &cmd->addr; if (cmd->addr_size != rdma_addr_size(addr)) return -EINVAL; if (cmd->join_flags == RDMA_MC_JOIN_FLAG_FULLMEMBER) join_state = BIT(FULLMEMBER_JOIN); else if (cmd->join_flags == RDMA_MC_JOIN_FLAG_SENDONLY_FULLMEMBER) join_state = BIT(SENDONLY_FULLMEMBER_JOIN); else return -EINVAL; ctx = ucma_get_ctx_dev(file, cmd->id); if (IS_ERR(ctx)) return PTR_ERR(ctx); mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) { ret = -ENOMEM; goto err_put_ctx; } mc->ctx = ctx; mc->join_state = join_state; mc->uid = cmd->uid; memcpy(&mc->addr, addr, cmd->addr_size); xa_lock(&multicast_table); if (__xa_alloc(&multicast_table, &mc->id, NULL, xa_limit_32b, GFP_KERNEL)) { ret = -ENOMEM; goto err_free_mc; } list_add_tail(&mc->list, &ctx->mc_list); xa_unlock(&multicast_table); mutex_lock(&ctx->mutex); ret = rdma_join_multicast(ctx->cm_id, (struct sockaddr *)&mc->addr, join_state, mc); mutex_unlock(&ctx->mutex); if (ret) goto err_xa_erase; resp.id = mc->id; if (copy_to_user(u64_to_user_ptr(cmd->response), &resp, sizeof(resp))) { ret = -EFAULT; goto err_leave_multicast; } xa_store(&multicast_table, mc->id, mc, 0); ucma_put_ctx(ctx); return 0; err_leave_multicast: mutex_lock(&ctx->mutex); rdma_leave_multicast(ctx->cm_id, (struct sockaddr *) &mc->addr); mutex_unlock(&ctx->mutex); ucma_cleanup_mc_events(mc); err_xa_erase: xa_lock(&multicast_table); list_del(&mc->list); __xa_erase(&multicast_table, mc->id); err_free_mc: xa_unlock(&multicast_table); kfree(mc); err_put_ctx: ucma_put_ctx(ctx); return ret; } static ssize_t ucma_join_ip_multicast(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_join_ip_mcast cmd; struct rdma_ucm_join_mcast join_cmd; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; join_cmd.response = cmd.response; join_cmd.uid = cmd.uid; join_cmd.id = cmd.id; join_cmd.addr_size = rdma_addr_size_in6(&cmd.addr); if (!join_cmd.addr_size) return -EINVAL; join_cmd.join_flags = RDMA_MC_JOIN_FLAG_FULLMEMBER; memcpy(&join_cmd.addr, &cmd.addr, join_cmd.addr_size); return ucma_process_join(file, &join_cmd, out_len); } static ssize_t ucma_join_multicast(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_join_mcast cmd; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; if (!rdma_addr_size_kss(&cmd.addr)) return -EINVAL; return ucma_process_join(file, &cmd, out_len); } static ssize_t ucma_leave_multicast(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_destroy_id cmd; struct rdma_ucm_destroy_id_resp resp; struct ucma_multicast *mc; int ret = 0; if (out_len < sizeof(resp)) return -ENOSPC; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; xa_lock(&multicast_table); mc = xa_load(&multicast_table, cmd.id); if (!mc) mc = ERR_PTR(-ENOENT); else if (READ_ONCE(mc->ctx->file) != file) mc = ERR_PTR(-EINVAL); else if (!refcount_inc_not_zero(&mc->ctx->ref)) mc = ERR_PTR(-ENXIO); if (IS_ERR(mc)) { xa_unlock(&multicast_table); ret = PTR_ERR(mc); goto out; } list_del(&mc->list); __xa_erase(&multicast_table, mc->id); xa_unlock(&multicast_table); mutex_lock(&mc->ctx->mutex); rdma_leave_multicast(mc->ctx->cm_id, (struct sockaddr *) &mc->addr); mutex_unlock(&mc->ctx->mutex); ucma_cleanup_mc_events(mc); ucma_put_ctx(mc->ctx); resp.events_reported = mc->events_reported; kfree(mc); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; out: return ret; } static ssize_t ucma_migrate_id(struct ucma_file *new_file, const char __user *inbuf, int in_len, int out_len) { struct rdma_ucm_migrate_id cmd; struct rdma_ucm_migrate_resp resp; struct ucma_event *uevent, *tmp; struct ucma_context *ctx; LIST_HEAD(event_list); struct ucma_file *cur_file; int ret = 0; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; /* Get current fd to protect against it being closed */ CLASS(fd, f)(cmd.fd); if (fd_empty(f)) return -ENOENT; if (fd_file(f)->f_op != &ucma_fops) return -EINVAL; cur_file = fd_file(f)->private_data; /* Validate current fd and prevent destruction of id. */ ctx = ucma_get_ctx(cur_file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); rdma_lock_handler(ctx->cm_id); /* * ctx->file can only be changed under the handler & xa_lock. xa_load() * must be checked again to ensure the ctx hasn't begun destruction * since the ucma_get_ctx(). */ xa_lock(&ctx_table); if (_ucma_find_context(cmd.id, cur_file) != ctx) { xa_unlock(&ctx_table); ret = -ENOENT; goto err_unlock; } ctx->file = new_file; xa_unlock(&ctx_table); mutex_lock(&cur_file->mut); list_del(&ctx->list); /* * At this point lock_handler() prevents addition of new uevents for * this ctx. */ list_for_each_entry_safe(uevent, tmp, &cur_file->event_list, list) if (uevent->ctx == ctx) list_move_tail(&uevent->list, &event_list); resp.events_reported = ctx->events_reported; mutex_unlock(&cur_file->mut); mutex_lock(&new_file->mut); list_add_tail(&ctx->list, &new_file->ctx_list); list_splice_tail(&event_list, &new_file->event_list); mutex_unlock(&new_file->mut); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; err_unlock: rdma_unlock_handler(ctx->cm_id); ucma_put_ctx(ctx); return ret; } static ssize_t (*ucma_cmd_table[])(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) = { [RDMA_USER_CM_CMD_CREATE_ID] = ucma_create_id, [RDMA_USER_CM_CMD_DESTROY_ID] = ucma_destroy_id, [RDMA_USER_CM_CMD_BIND_IP] = ucma_bind_ip, [RDMA_USER_CM_CMD_RESOLVE_IP] = ucma_resolve_ip, [RDMA_USER_CM_CMD_RESOLVE_ROUTE] = ucma_resolve_route, [RDMA_USER_CM_CMD_QUERY_ROUTE] = ucma_query_route, [RDMA_USER_CM_CMD_CONNECT] = ucma_connect, [RDMA_USER_CM_CMD_LISTEN] = ucma_listen, [RDMA_USER_CM_CMD_ACCEPT] = ucma_accept, [RDMA_USER_CM_CMD_REJECT] = ucma_reject, [RDMA_USER_CM_CMD_DISCONNECT] = ucma_disconnect, [RDMA_USER_CM_CMD_INIT_QP_ATTR] = ucma_init_qp_attr, [RDMA_USER_CM_CMD_GET_EVENT] = ucma_get_event, [RDMA_USER_CM_CMD_GET_OPTION] = NULL, [RDMA_USER_CM_CMD_SET_OPTION] = ucma_set_option, [RDMA_USER_CM_CMD_NOTIFY] = ucma_notify, [RDMA_USER_CM_CMD_JOIN_IP_MCAST] = ucma_join_ip_multicast, [RDMA_USER_CM_CMD_LEAVE_MCAST] = ucma_leave_multicast, [RDMA_USER_CM_CMD_MIGRATE_ID] = ucma_migrate_id, [RDMA_USER_CM_CMD_QUERY] = ucma_query, [RDMA_USER_CM_CMD_BIND] = ucma_bind, [RDMA_USER_CM_CMD_RESOLVE_ADDR] = ucma_resolve_addr, [RDMA_USER_CM_CMD_JOIN_MCAST] = ucma_join_multicast }; static ssize_t ucma_write(struct file *filp, const char __user *buf, size_t len, loff_t *pos) { struct ucma_file *file = filp->private_data; struct rdma_ucm_cmd_hdr hdr; ssize_t ret; if (!ib_safe_file_access(filp)) { pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", __func__, task_tgid_vnr(current), current->comm); return -EACCES; } if (len < sizeof(hdr)) return -EINVAL; if (copy_from_user(&hdr, buf, sizeof(hdr))) return -EFAULT; if (hdr.cmd >= ARRAY_SIZE(ucma_cmd_table)) return -EINVAL; hdr.cmd = array_index_nospec(hdr.cmd, ARRAY_SIZE(ucma_cmd_table)); if (hdr.in + sizeof(hdr) > len) return -EINVAL; if (!ucma_cmd_table[hdr.cmd]) return -ENOSYS; ret = ucma_cmd_table[hdr.cmd](file, buf + sizeof(hdr), hdr.in, hdr.out); if (!ret) ret = len; return ret; } static __poll_t ucma_poll(struct file *filp, struct poll_table_struct *wait) { struct ucma_file *file = filp->private_data; __poll_t mask = 0; poll_wait(filp, &file->poll_wait, wait); if (!list_empty(&file->event_list)) mask = EPOLLIN | EPOLLRDNORM; return mask; } /* * ucma_open() does not need the BKL: * * - no global state is referred to; * - there is no ioctl method to race against; * - no further module initialization is required for open to work * after the device is registered. */ static int ucma_open(struct inode *inode, struct file *filp) { struct ucma_file *file; file = kmalloc(sizeof *file, GFP_KERNEL); if (!file) return -ENOMEM; INIT_LIST_HEAD(&file->event_list); INIT_LIST_HEAD(&file->ctx_list); init_waitqueue_head(&file->poll_wait); mutex_init(&file->mut); filp->private_data = file; file->filp = filp; return stream_open(inode, filp); } static int ucma_close(struct inode *inode, struct file *filp) { struct ucma_file *file = filp->private_data; /* * All paths that touch ctx_list or ctx_list starting from write() are * prevented by this being a FD release function. The list_add_tail() in * ucma_connect_event_handler() can run concurrently, however it only * adds to the list *after* a listening ID. By only reading the first of * the list, and relying on ucma_destroy_private_ctx() to block * ucma_connect_event_handler(), no additional locking is needed. */ while (!list_empty(&file->ctx_list)) { struct ucma_context *ctx = list_first_entry( &file->ctx_list, struct ucma_context, list); WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY, GFP_KERNEL) != ctx); ucma_destroy_private_ctx(ctx); } kfree(file); return 0; } static const struct file_operations ucma_fops = { .owner = THIS_MODULE, .open = ucma_open, .release = ucma_close, .write = ucma_write, .poll = ucma_poll, }; static struct miscdevice ucma_misc = { .minor = MISC_DYNAMIC_MINOR, .name = "rdma_cm", .nodename = "infiniband/rdma_cm", .mode = 0666, .fops = &ucma_fops, }; static int ucma_get_global_nl_info(struct ib_client_nl_info *res) { res->abi = RDMA_USER_CM_ABI_VERSION; res->cdev = ucma_misc.this_device; return 0; } static struct ib_client rdma_cma_client = { .name = "rdma_cm", .get_global_nl_info = ucma_get_global_nl_info, }; MODULE_ALIAS_RDMA_CLIENT("rdma_cm"); static ssize_t abi_version_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", RDMA_USER_CM_ABI_VERSION); } static DEVICE_ATTR_RO(abi_version); static int __init ucma_init(void) { int ret; ret = misc_register(&ucma_misc); if (ret) return ret; ret = device_create_file(ucma_misc.this_device, &dev_attr_abi_version); if (ret) { pr_err("rdma_ucm: couldn't create abi_version attr\n"); goto err1; } ucma_ctl_table_hdr = register_net_sysctl(&init_net, "net/rdma_ucm", ucma_ctl_table); if (!ucma_ctl_table_hdr) { pr_err("rdma_ucm: couldn't register sysctl paths\n"); ret = -ENOMEM; goto err2; } ret = ib_register_client(&rdma_cma_client); if (ret) goto err3; return 0; err3: unregister_net_sysctl_table(ucma_ctl_table_hdr); err2: device_remove_file(ucma_misc.this_device, &dev_attr_abi_version); err1: misc_deregister(&ucma_misc); return ret; } static void __exit ucma_cleanup(void) { ib_unregister_client(&rdma_cma_client); unregister_net_sysctl_table(ucma_ctl_table_hdr); device_remove_file(ucma_misc.this_device, &dev_attr_abi_version); misc_deregister(&ucma_misc); } module_init(ucma_init); module_exit(ucma_cleanup); |
| 194 119 78 6 69 8 125 94 81 132 73 89 41 46 10 22 226 180 147 230 10 408 2 200 188 4 2 3 3 76 168 406 378 399 95 361 1 8 11 56 152 143 61 61 58 8 3 330 291 76 291 77 31 13 13 13 31 568 81 39 25 30 145 54 44 95 46 199 150 95 55 77 27 31 40 24 48 96 97 88 34 31 31 197 93 193 195 145 37 143 45 96 41 39 194 104 127 124 199 212 3 5 111 199 6 199 199 245 245 164 11 372 9 339 5 41 1 6 36 6 63 63 9 58 58 58 21 58 1 29 6 38 62 33 20 42 29 18 4 63 61 3 25 4 22 23 62 62 11 9 7 12 16 24 2 62 1 49 45 13 61 62 61 61 39 39 39 33 36 2 39 6 38 4 39 39 15 39 39 43 3 1 3 63 10 4 1 51 15 40 41 21 1 24 2 19 5 1 6 11 32 10 6 63 63 44 61 5 1 63 39 63 63 1 62 36 62 62 57 31 62 62 62 41 2 12 66 66 58 50 65 6 64 64 6 4 34 63 20 34 47 59 63 62 34 59 15 57 42 42 40 21 62 61 62 64 64 64 64 64 66 65 66 65 4 4 4 4 4 820 55 9 49 13 55 52 47 47 46 9 21 55 3 3 2 2 2 1 37 37 37 37 2 32 5 37 68 68 2 2 240 39 36 35 5 35 34 18 17 2 24 24 194 17 192 51 43 18 52 52 52 51 1 9 50 55 55 55 2 55 55 2 2 2 2 2 2 2 2 2 2 61 33 3 3 3 32 20 66 16 70 21 70 68 61 70 69 1 13 69 46 62 6 9 7 36 36 68 56 33 57 57 57 2 2 2 2 2 2 69 9 66 69 69 2 55 58 375 345 399 10 192 44 376 378 377 172 440 301 317 146 315 110 332 7 35 399 1 2 369 369 242 35 19 43 46 353 47 4 369 47 369 47 204 241 35 370 370 32 370 367 82 351 302 242 203 83 55 308 401 62 373 4 368 4 202 60 50 360 401 400 400 243 300 299 300 51 17 9 64 33 39 339 172 373 373 187 53 406 408 303 408 302 200 150 86 89 148 53 1 11 14 48 26 35 25 25 25 62 62 162 349 8 4 4 1 2 2 2 1 398 13 400 59 2 398 1 409 1 247 372 407 107 376 25 365 223 408 404 65 408 2 408 62 408 401 400 400 8 401 68 39 202 373 202 377 399 401 401 75 73 2 75 75 2 2 2 4 5 94 4 2 7 563 562 562 23 302 1 5 5 170 244 1 171 244 2 3 231 255 171 247 2 3 66 95 13 7 13 81 3 4 282 42 243 258 16 232 217 210 4 3 4 10 2 13 2 7 1 3 3 2 1 1 21 2 238 221 221 183 38 176 7 37 220 70 15 54 70 6 48 48 16 33 42 17 18 43 168 17 2 111 1 49 159 37 24 13 13 13 29 29 15 9 19 4 12 13 23 45 10 43 36 29 30 18 18 3 32 29 33 18 18 190 33 188 138 127 126 7 31 225 44 35 53 1 55 50 26 45 10 286 190 181 44 41 66 15 50 26 27 45 25 27 9 17 1 21 44 26 45 28 65 66 66 299 242 172 123 265 265 53 1 41 14 3 44 17 246 245 370 370 168 317 317 224 4 223 2 2 58 173 172 61 197 55 35 40 218 43 226 193 101 6 220 151 151 156 1 17 17 66 31 26 28 677 666 30 9 31 12 28 9 7 2 28 26 28 28 27 28 2 28 28 27 27 28 24 31 26 23 26 21 26 19 4 14 2 15 15 15 44 13 31 31 28 15 18 1 114 115 103 115 450 416 115 106 57 194 395 305 289 132 294 251 129 62 64 29 218 297 80 80 1 80 78 8 391 356 80 358 70 56 407 408 365 3 2 3 7 30 2 36 43 286 7 165 20 6 286 285 195 116 252 35 87 84 2 29 30 70 13 38 6 44 42 12 44 260 2 260 232 233 233 333 333 333 333 333 168 91 76 166 2 76 92 27 26 27 27 27 75 1 241 328 87 9 9 245 176 76 76 76 76 76 49 27 76 13 13 62 1 165 8 3 165 168 556 555 9 18 1 2 100 406 62 204 27 196 1 165 1 163 165 165 1 164 165 163 1 56 56 53 7 189 48 6 2 188 189 72 59 16 3 97 97 96 97 97 13 13 2 13 69 96 97 13 97 97 34 67 7 8 69 73 69 8 1 7 73 69 69 8 69 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 152 |