| 273 292 276 277 260 260 387 387 386 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/interval_tree.c - interval tree for mapping->i_mmap * * Copyright (C) 2012, Michel Lespinasse <walken@google.com> */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/rmap.h> #include <linux/interval_tree_generic.h> static inline unsigned long vma_start_pgoff(struct vm_area_struct *v) { return v->vm_pgoff; } static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) { return v->vm_pgoff + vma_pages(v) - 1; } INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff, /* empty */, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root) { struct rb_node **link; struct vm_area_struct *parent; unsigned long last = vma_last_pgoff(node); VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); if (!prev->shared.rb.rb_right) { parent = prev; link = &prev->shared.rb.rb_right; } else { parent = rb_entry(prev->shared.rb.rb_right, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; while (parent->shared.rb.rb_left) { parent = rb_entry(parent->shared.rb.rb_left, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; } link = &parent->shared.rb.rb_left; } node->shared.rb_subtree_last = last; rb_link_node(&node->shared.rb, &parent->shared.rb, link); rb_insert_augmented(&node->shared.rb, &root->rb_root, &vma_interval_tree_augment); } static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc) { return vma_start_pgoff(avc->vma); } static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc) { return vma_last_pgoff(avc->vma); } INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last, avc_start_pgoff, avc_last_pgoff, static inline, __anon_vma_interval_tree) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root) { #ifdef CONFIG_DEBUG_VM_RB node->cached_vma_start = avc_start_pgoff(node); node->cached_vma_last = avc_last_pgoff(node); #endif __anon_vma_interval_tree_insert(node, root); } void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root) { __anon_vma_interval_tree_remove(node, root); } struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_first(root, first, last); } struct anon_vma_chain * anon_vma_interval_tree_iter_next(struct anon_vma_chain *node, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_next(node, first, last); } #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node) { WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node)); WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node)); } #endif |
| 37 112 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H /* * Define 'struct task_struct' and provide the main scheduler * APIs (schedule(), wakeup variants, etc.) */ #include <uapi/linux/sched.h> #include <asm/current.h> #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> #include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> #include <linux/smp_types.h> #include <linux/pid_types.h> #include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> #include <linux/mutex_types.h> #include <linux/plist_types.h> #include <linux/hrtimer_types.h> #include <linux/timer_types.h> #include <linux/seccomp_types.h> #include <linux/nodemask_types.h> #include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> #include <uapi/linux/rseq.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> #include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; struct robust_list_head; struct root_domain; struct rq; struct sched_attr; struct sched_dl_entity; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; struct task_struct; struct user_event_mm; #include <linux/sched/ext.h> /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). * * We have two separate sets of flags: task->__state * is about runnability, while task->exit_state are * about the task exiting. Confusing, but this way * modifying one set can't modify the other one by * mistake. */ /* Used in tsk->__state: */ #define TASK_RUNNING 0x00000000 #define TASK_INTERRUPTIBLE 0x00000001 #define TASK_UNINTERRUPTIBLE 0x00000002 #define __TASK_STOPPED 0x00000004 #define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ #define EXIT_DEAD 0x00000010 #define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->__state again: */ #define TASK_PARKED 0x00000040 #define TASK_DEAD 0x00000080 #define TASK_WAKEKILL 0x00000100 #define TASK_WAKING 0x00000200 #define TASK_NOLOAD 0x00000400 #define TASK_NEW 0x00000800 #define TASK_RTLOCK_WAIT 0x00001000 #define TASK_FREEZABLE 0x00002000 #define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) #define TASK_FROZEN 0x00008000 #define TASK_STATE_MAX 0x00010000 #define TASK_ANY (TASK_STATE_MAX-1) /* * DO NOT ADD ANY NEW USERS ! */ #define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) #define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) #define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) #define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_special_state_change(state_value) \ do { \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_set_state() \ do { \ current->saved_state_change = current->task_state_change;\ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_restore_state() \ do { \ current->task_state_change = current->saved_state_change;\ } while (0) #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) # define debug_rtlock_wait_set_state() do { } while (0) # define debug_rtlock_wait_restore_state() do { } while (0) #endif /* * set_current_state() includes a barrier so that the write of current->__state * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); * if (CONDITION) * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * where wake_up_state()/try_to_wake_up() executes a full memory barrier before * accessing p->__state. * * Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ smp_store_mb(current->__state, (state_value)); \ } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must * serialize against wakeups such that any possible in-flight TASK_RUNNING * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) /* * PREEMPT_RT specific variants for "sleeping" spin/rwlocks * * RT's spin/rwlock substitutions are state preserving. The state of the * task when blocking on the lock is saved in task_struct::saved_state and * restored after the lock has been acquired. These operations are * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT * lock related wakeups while the task is blocked on the lock are * redirected to operate on task_struct::saved_state to ensure that these * are not dropped. On restore task_struct::saved_state is set to * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. * * The lock operation looks like this: * * current_save_and_set_rtlock_wait_state(); * for (;;) { * if (try_lock()) * break; * raw_spin_unlock_irq(&lock->wait_lock); * schedule_rtlock(); * raw_spin_lock_irq(&lock->wait_lock); * set_current_state(TASK_RTLOCK_WAIT); * } * current_restore_rtlock_saved_state(); */ #define current_save_and_set_rtlock_wait_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define current_restore_rtlock_saved_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define get_current_state() READ_ONCE(current->__state) /* * Define the task command name length as enum, then it can be visible to * BPF programs. */ enum { TASK_COMM_LEN = 16, }; extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern long schedule_timeout(long timeout); extern long schedule_timeout_interruptible(long timeout); extern long schedule_timeout_killable(long timeout); extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); #ifdef CONFIG_PREEMPT_RT extern void schedule_rtlock(void); #endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields * * Stores previous user/system time values such that we can guarantee * monotonicity. */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE u64 utime; u64 stime; raw_spinlock_t lock; #endif }; enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, /* Task is idle */ VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, /* Task runs as guests in a CPU with VTIME active: */ VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; unsigned int cpu; u64 utime; u64 stime; u64 gtime; }; /* * Utilization clamp constraints. * @UCLAMP_MIN: Minimum utilization * @UCLAMP_MAX: Maximum utilization * @UCLAMP_CNT: Utilization clamp constraints count */ enum uclamp_id { UCLAMP_MIN = 0, UCLAMP_MAX, UCLAMP_CNT }; #ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif struct sched_param { int sched_priority; }; struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ /* # of times we have run on this CPU: */ unsigned long pcount; /* Time spent waiting on a runqueue: */ unsigned long long run_delay; /* Timestamps: */ /* When did we last run on a CPU? */ unsigned long long last_arrival; /* When were we last queued to run? */ unsigned long long last_queued; #endif /* CONFIG_SCHED_INFO */ }; /* * Integer metrics need fixed point arithmetic, e.g., sched/fair * has a few: load, load_avg, util_avg, freq, and capacity. * * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) /* Increase resolution of cpu_capacity calculations */ # define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT # define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) struct load_weight { unsigned long weight; u32 inv_weight; }; /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). * * [load_avg definition] * * load_avg = runnable% * scale_load_down(load) * * [runnable_avg definition] * * runnable_avg = runnable% * SCHED_CAPACITY_SCALE * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE * * where runnable% is the time ratio that a sched_entity is runnable and * running% the time ratio that a sched_entity is running. * * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * * N.B., the above ratios (runnable% and running%) themselves are in the * range of [0, 1]. To do fixed point arithmetics, we therefore scale them * to as large a range as necessary. This is for example reflected by * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities * with the highest load (=88761), always runnable on a single cfs_rq, * and should not overflow as the number already hits PID_MAX_LIMIT. * * For all other cases (including 32-bit kernels), struct load_weight's * weight will overflow first before we do, because: * * Max(load_avg) <= Max(load.weight) * * Then it is the load_weight's responsibility to consider overflow * issues. */ struct sched_avg { u64 last_update_time; u64 load_sum; u64 runnable_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; unsigned int util_est; } ____cacheline_aligned; /* * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg * updates. When a task is dequeued, its util_est should not be updated if its * util_avg has not been updated in the meantime. * This information is mapped into the MSB bit of util_est at dequeue time. * Since max value of util_est for a task is 1024 (PELT util_avg for a task) * it is safe to use MSB. */ #define UTIL_EST_WEIGHT_SHIFT 2 #define UTIL_AVG_UNCHANGED 0x80000000 struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; u64 iowait_count; u64 iowait_sum; u64 sleep_start; u64 sleep_max; s64 sum_sleep_runtime; u64 block_start; u64 block_max; s64 sum_block_runtime; s64 exec_max; u64 slice_max; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; u64 nr_wakeups_migrate; u64 nr_wakeups_local; u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; #ifdef CONFIG_SCHED_CORE u64 core_forceidle_sum; #endif #endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ struct load_weight load; struct rb_node run_node; u64 deadline; u64 min_vruntime; u64 min_slice; struct list_head group_node; unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; unsigned char custom_slice; /* hole */ u64 exec_start; u64 sum_exec_runtime; u64 prev_sum_exec_runtime; u64 vruntime; s64 vlag; u64 slice; u64 nr_migrations; #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; /* cached value of my_q->h_nr_running */ unsigned long runnable_weight; #endif #ifdef CONFIG_SMP /* * Per entity load average tracking. * * Put into separate cache line so it does not * collide with read-mostly values above. */ struct sched_avg avg; #endif }; struct sched_rt_entity { struct list_head run_list; unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; unsigned short on_rq; unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif } __randomize_layout; typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); struct sched_dl_entity { struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ u64 dl_bw; /* dl_runtime / dl_period */ u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ u64 deadline; /* Absolute deadline for this instance */ unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: * * @dl_throttled tells if we exhausted the runtime. If so, the * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * * @dl_non_contending tells if the task is inactive while still * contributing to the active utilization. In other words, it * indicates if the inactive timer has been armed and its handler * has not been executed yet. This flag is useful to avoid race * conditions between the inactive timer handler and the wakeup * code. * * @dl_overrun tells if the task asked to be informed about runtime * overruns. * * @dl_server tells if this is a server entity. * * @dl_defer tells if this is a deferred or regular server. For * now only defer server exists. * * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; /* * Inactive timer, responsible for decreasing the active utilization * at the "0-lag time". When a -deadline task blocks, it contributes * to GRUB's active utilization until the "0-lag time", hence a * timer is needed to decrease the active utilization at the correct * time. */ struct hrtimer inactive_timer; /* * Bits for DL-server functionality. Also see the comment near * dl_server_update(). * * @rq the runqueue this server is for * * @server_has_tasks() returns true if @server_pick return a * runnable task. */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* * Priority Inheritance. When a DEADLINE scheduling entity is boosted * pi_se points to the donor, otherwise points to the dl_se it belongs * to (the original one/itself). */ struct sched_dl_entity *pi_se; #endif }; #ifdef CONFIG_UCLAMP_TASK /* Number of utilization clamp buckets (shorter alias) */ #define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT /* * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. * * The active bit is set whenever a task has got an "effective" value assigned, * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. * * The user_defined bit is set whenever a task has got a task-specific clamp * value requested from userspace, i.e. the system defaults apply to this task * just as a restriction. This allows to relax default clamps when a less * restrictive task-specific value has been requested, thus allowing to * implement a "nice" semantic. For example, a task running with a 20% * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; enum perf_event_task_context { perf_invalid_context = -1, perf_hw_context = 0, perf_sw_context, perf_nr_task_contexts, }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 struct wake_q_node { struct wake_q_node *next; }; struct kmap_ctrl { #ifdef CONFIG_KMAP_LOCAL int idx; pte_t pteval[KM_MAX_IDX]; #endif }; struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ struct thread_info thread_info; #endif unsigned int __state; /* saved state for "spinlock sleepers" */ unsigned int saved_state; /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. */ randomized_struct_fields_start void *stack; refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; #ifdef CONFIG_MEM_ALLOC_PROFILING struct alloc_tag *alloc_tag; #endif #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; /* * recent_used_cpu is initially set as the last CPU used by a task * that wakes affine another task. Waker/wakee relationships can * push tasks around a CPU where each wakeup moves to the next one. * Tracking a recently used CPU allows a quick search for a recently * used CPU that may be idle. */ int recent_used_cpu; int wake_cpu; #endif int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; #ifdef CONFIG_SCHED_CLASS_EXT struct sched_ext_entity scx; #endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* * Effective clamp values used for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif struct sched_statistics stats; #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif unsigned int policy; unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP unsigned short migration_disabled; #endif unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; u8 rcu_tasks_holdout; u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; int rcu_tasks_exit_cpu; struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; struct list_head trc_holdout_list; struct list_head trc_blkd_node; int trc_blkd_cpu; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; struct list_head tasks; #ifdef CONFIG_SMP struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; #endif struct mm_struct *mm; struct mm_struct *active_mm; struct address_space *faults_disabled_mapping; int exit_state; int exit_code; int exit_signal; /* The signal sent when the parent dies: */ int pdeath_signal; /* JOBCTL_*, siglock protected: */ unsigned long jobctl; /* Used for emulating ABI behavior of previous Linux versions: */ unsigned int personality; /* Scheduler bits, serialized by scheduler locks: */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; /* Force alignment to the next boundary: */ unsigned :0; /* Unserialized, strictly 'current' */ /* * This field must not be in the scheduler word above due to wakelist * queueing no longer being serialized by p->on_cpu. However: * * p->XXX = X; ttwu() * schedule() if (p->on_rq && ..) // false * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true * deactivate_task() ttwu_queue_wakelist()) * p->on_rq = 0; p->sched_remote_wakeup = Y; * * guarantees all stores of 'current' are visible before * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; #ifdef CONFIG_RT_MUTEXES unsigned sched_rt_mutex:1; #endif /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN /* whether the LRU algorithm may apply to this access */ unsigned in_lru_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif #ifdef CONFIG_CGROUPS /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; /* task is frozen/stopped (used by the cgroup freezer) */ unsigned frozen:1; #endif #ifdef CONFIG_BLK_CGROUP unsigned use_memdelay:1; #endif #ifdef CONFIG_PSI /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif #ifdef CONFIG_PAGE_OWNER /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif #ifdef CONFIG_PREEMPT_RT struct netdev_xmit net_xmit; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; pid_t pid; pid_t tgid; #ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif /* * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ /* Real parent process: */ struct task_struct __rcu *real_parent; /* Recipient of SIGCHLD, wait4() reports: */ struct task_struct __rcu *parent; /* * Children/sibling form the list of natural children: */ struct list_head children; struct list_head sibling; struct task_struct *group_leader; /* * 'ptraced' is the list of tasks this task is using ptrace() on. * * This includes both natural children and PTRACE_ATTACH targets. * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ struct list_head ptraced; struct list_head ptrace_entry; /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_node; struct completion *vfork_done; /* CLONE_CHILD_SETTID: */ int __user *set_child_tid; /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; /* PF_KTHREAD | PF_IO_WORKER */ void *worker_private; u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME u64 utimescaled; u64 stimescaled; #endif u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif /* Context switch counts: */ unsigned long nvcsw; unsigned long nivcsw; /* Monotonic time in nsecs: */ u64 start_time; /* Boot based time in nsecs: */ u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; unsigned long maj_flt; /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK struct posix_cputimers_work posix_cputimers_work; #endif /* Process credentials: */ /* Tracer's credentials at attach: */ const struct cred __rcu *ptracer_cred; /* Objective and real subjective task credentials (COW): */ const struct cred __rcu *real_cred; /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; #ifdef CONFIG_KEYS /* Cached requested key. */ struct key *cached_requested_key; #endif /* * executable name, excluding path. * * - normally initialized begin_new_exec() * - set it with set_task_comm() * - strscpy_pad() to ensure it is always NUL-terminated and * zero-padded * - task_lock() to ensure the operation is atomic and the name is * fully updated. */ char comm[TASK_COMM_LEN]; struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC struct sysv_sem sysvsem; struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; /* Open file information: */ struct files_struct *files; #ifdef CONFIG_IO_URING struct io_uring_task *io_uring; #endif /* Namespaces: */ struct nsproxy *nsproxy; /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; struct callback_head *task_works; #ifdef CONFIG_AUDIT #ifdef CONFIG_AUDITSYSCALL struct audit_context *audit_context; #endif kuid_t loginuid; unsigned int sessionid; #endif struct seccomp seccomp; struct syscall_user_dispatch syscall_dispatch; /* Thread group tracking: */ u64 parent_exec_id; u64 self_exec_id; /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ spinlock_t alloc_lock; /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif #ifdef CONFIG_DEBUG_MUTEXES /* Mutex deadlock detection: */ struct mutex_waiter *blocked_on; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events irqtrace; unsigned int hardirq_threaded; u64 hardirq_chain_key; int softirqs_enabled; int softirq_context; int irq_config; #endif #ifdef CONFIG_PREEMPT_RT int softirq_disable_cnt; #endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif #if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif /* Journalling filesystem info: */ void *journal_info; /* Stacked block device info: */ struct bio_list *bio_list; /* Stack plugging: */ struct blk_plug *plug; /* VM state: */ struct reclaim_state *reclaim_state; struct io_context *io_context; #ifdef CONFIG_COMPACTION struct capture_control *capture_control; #endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_PSI /* Pressure stall state */ unsigned int psi_flags; #endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; /* Accumulated virtual memory usage: */ u64 acct_vm_mem1; /* stime + utime since last update: */ u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; unsigned long numa_migrate_retry; /* Migration stamp: */ u64 node_stamp; u64 last_task_numa_placement; u64 last_sum_exec_runtime; struct callback_head numa_work; /* * This pointer is only modified for current in syscall and * pagefault context (and for tasks being destroyed), so it can be read * from any of the following contexts: * - RCU read-side critical section * - current->numa_group from everywhere * - task's runqueue locked, task not running */ struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer * in this precise order. * * faults_memory: Exponential decaying average of faults on a per-node * basis. Scheduling placement decisions are made based on these * counts. The values remain static for the duration of a PTE scan. * faults_cpu: Track the nodes the process was running on when a NUMA * hinting fault was incurred. * faults_memory_buffer and faults_cpu_buffer: Record faults per node * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ unsigned long *numa_faults; unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local or failed to migrate. The task scan * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_RSEQ struct rseq __user *rseq; u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically * with respect to preemption. */ unsigned long rseq_event_mask; #endif #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ int last_mm_cid; /* Most recent cid in mm */ int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; struct page_frag task_frag; #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif #ifdef CONFIG_FAULT_INJECTION int make_it_fail; unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for a dirty throttling pause: */ int nr_dirtied; int nr_dirtied_pause; /* Start of a write-and-pause period: */ unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif /* * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ u64 timer_slack_ns; u64 default_timer_slack_ns; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) unsigned int kasan_depth; #endif #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif #ifdef CONFIG_KCSAN_WEAK_MEMORY int kcsan_stack_depth; #endif #endif #ifdef CONFIG_KMSAN struct kmsan_ctx kmsan_ctx; #endif #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; int curr_ret_depth; /* Stack of return addresses for return function tracing: */ unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced * because of depth overrun: */ atomic_t trace_overrun; /* Pause tracing: */ atomic_t tracing_graph_pause; #endif #ifdef CONFIG_TRACING /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV /* See kernel/kcov.c for more details. */ /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; /* Buffer for coverage collection: */ void *kcov_area; /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; /* KCOV common handle for remote coverage collection: */ u64 kcov_handle; /* KCOV sequence number: */ int kcov_sequence; /* Collect coverage from softirq context: */ unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; #endif #ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) unsigned int sequential_io; unsigned int sequential_io_avg; #endif struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; # ifdef CONFIG_PREEMPT_RT unsigned long saved_state_change; # endif #endif struct rcu_head rcu; refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; #endif #ifdef CONFIG_SECURITY /* Used by LSM modules for access restriction: */ void *security; #endif #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif /* Used by BPF for per-TASK xdp storage */ struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; unsigned long prev_lowest_stack; #endif #ifdef CONFIG_X86_MCE void __user *mce_vaddr; __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; int mce_count; #endif #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif #ifdef CONFIG_RETHOOK struct llist_head rethooks; #endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* * If L1D flush is supported on mm context switch * then we use this callback head to queue kill work * to kill tasks that are not running on SMT disabled * cores */ struct callback_head l1d_flush_kill; #endif #ifdef CONFIG_RV /* * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. * If we find justification for more monitors, we can think * about adding more or developing a dynamic method. So far, * none of these are justified. */ union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS struct user_event_mm *user_event_mm; #endif /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. */ randomized_struct_fields_end /* CPU-specific state of this task: */ struct thread_struct thread; /* * WARNING: on x86, 'thread_struct' contains a variable-sized * structure. It *MUST* be at the end of 'task_struct'. * * Do not put anything below here! */ }; #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) static inline unsigned int __task_state_index(unsigned int tsk_state, unsigned int tsk_exit_state) { unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if ((tsk_state & TASK_IDLE) == TASK_IDLE) state = TASK_REPORT_IDLE; /* * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. */ if (tsk_state & TASK_RTLOCK_WAIT) state = TASK_UNINTERRUPTIBLE; return fls(state); } static inline unsigned int task_state_index(struct task_struct *tsk) { return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); } static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } static inline char task_state_to_char(struct task_struct *tsk) { return task_index_to_char(task_state_index(tsk)); } extern struct pid *cad_pid; /* * Per process flags */ #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF__HOLE__00800000 0x00800000 #define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. * See memalloc_pin_save() */ #define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example * with tsk_used_math (like during threaded core dumping). * There is however an exception to this rule during ptrace * or during fork: the ptracer task is allowed to write to the * child->flags of its traced child (same goes for fork, the parent * can write to the child->flags), because we're guaranteed the * child is not running and in turn not changing child->flags * at the same time the parent does it. */ #define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) #define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) #define clear_used_math() clear_stopped_child_used_math(current) #define set_used_math() set_stopped_child_used_math(current) #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) #define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); #else return true; #endif } /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) TASK_PFA_TEST(SPREAD_PAGE, spread_page) TASK_PFA_SET(SPREAD_PAGE, spread_page) TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { current->flags &= ~flags; current->flags |= orig_flags & flags; } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP /* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task * @p: the task * @new_mask: CPU affinity mask * * Return: zero if successful, or a negative error code */ extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { if (src->user_cpus_ptr) return -EINVAL; return 0; } static inline void release_user_cpus_ptr(struct task_struct *p) { WARN_ON(p->user_cpus_ptr); } static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) { return 0; } #endif extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); /** * task_nice - return the nice value of a given task. * @p: the task in question. * * Return: The nice value [ -20 ... 0 ... 19 ]. */ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. * * Return: 1 if @p is an idle task. 0 otherwise. */ static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { struct task_struct task; #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; #ifndef CONFIG_THREAD_INFO_IN_TASK extern struct thread_info init_thread_info; #endif extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) #else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif /* * find a task by one of its numerical ids * * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid * * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); /* * find a task by its virtual pid and get the task struct */ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); static inline void set_task_comm(struct task_struct *tsk, const char *from) { __set_task_comm(tsk, from, false); } /* * - Why not use task_lock()? * User space can randomly change their names anyway, so locking for readers * doesn't make sense. For writers, locking is probably necessary, as a race * condition could lead to long-term mixed results. * The strscpy_pad() in __set_task_comm() can ensure that the task comm is * always NUL-terminated and zero-padded. Therefore the race condition between * reader and writer is not an issue. * * - BUILD_BUG_ON() can help prevent the buf from being truncated. * Since the callers don't perform any return value checks, this safeguard is * necessary. */ #define get_task_comm(buf, tsk) ({ \ BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ strscpy_pad(buf, (tsk)->comm); \ buf; \ }) #ifdef CONFIG_SMP static __always_inline void scheduler_ipi(void) { /* * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting * TIF_NEED_RESCHED remotely (for the first time) will also send * this IPI. */ preempt_fold_need_resched(); } #else static inline void scheduler_ipi(void) { } #endif extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(task_thread_info(tsk), flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, bool value) { update_ti_thread_flag(task_thread_info(tsk), flag, value); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(task_thread_info(tsk), flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) { return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) void sched_dynamic_klp_enable(void); void sched_dynamic_klp_disable(void); DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { return static_call_mod(cond_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) { return dynamic_cond_resched(); } #else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { klp_sched_try_switch(); return __cond_resched(); } #endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ #else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ static inline int _cond_resched(void) { klp_sched_try_switch(); return 0; } #endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); #define MIGHT_RESCHED_RCU_SHIFT 8 #define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) #ifndef CONFIG_PREEMPT_RT /* * Non RT kernels have an elevated preempt count due to the held lock, * but are not allowed to be inside a RCU read side critical section */ # define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET #else /* * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in * cond_resched*lock() has to take that into account because it checks for * preempt_count() and rcu_preempt_depth(). */ # define PREEMPT_LOCK_RESCHED_OFFSETS \ (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) #endif #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_read(lock); \ }) #define cond_resched_rwlock_write(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_write(lock); \ }) static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(const struct task_struct *p) { return READ_ONCE(task_thread_info(p)->cpu); } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else static inline unsigned int task_cpu(const struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ static inline bool task_is_runnable(struct task_struct *p) { return p->on_rq && !p->se.sched_delayed; } extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); #include <linux/spinlock.h> /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. * * This allows us to terminate optimistic spin loops and block, analogous to * the native optimistic spin heuristic of testing if the lock owner task is * running or not. */ #ifndef vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { return false; } #endif extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif #ifdef CONFIG_SMP static inline bool owner_on_cpu(struct task_struct *owner) { /* * As lock holder preemption issue, we both skip spinning if * task is not on cpu or its cpu is preempted */ return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); } /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, unsigned long uaddr); extern int sched_core_idle_cpu(int cpu); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } #endif extern void sched_set_stop_task(int cpu, struct task_struct *stop); #ifdef CONFIG_MEM_ALLOC_PROFILING static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) { swap(current->alloc_tag, tag); return tag; } static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) { #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); #endif current->alloc_tag = old; } #else #define alloc_tag_save(_tag) NULL #define alloc_tag_restore(_tag, _old) do {} while (0) #endif #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMENS_H #define _LINUX_TIMENS_H #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> #include <linux/time64.h> struct user_namespace; extern struct user_namespace init_user_ns; struct vm_area_struct; struct timens_offsets { struct timespec64 monotonic; struct timespec64 boottime; }; struct time_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; struct timens_offsets offsets; struct page *vvar_page; /* If set prevents changing offsets after any task joined namespace. */ bool frozen_offsets; } __randomize_layout; extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS extern int vdso_join_timens(struct task_struct *task, struct time_namespace *ns); extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { refcount_inc(&ns->ns.count); return ns; } struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) { if (refcount_dec_and_test(&ns->ns.count)) free_time_ns(ns); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m); struct proc_timens_offset { int clockid; struct timespec64 val; }; int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int n); static inline void timens_add_monotonic(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->monotonic); } static inline void timens_add_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->boottime); } static inline u64 timens_add_boottime_ns(u64 nsec) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; return nsec + timespec64_to_ns(&ns_offsets->boottime); } static inline void timens_sub_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_sub(*ts, ns_offsets->boottime); } ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *offsets); static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { struct time_namespace *ns = current->nsproxy->time_ns; if (likely(ns == &init_time_ns)) return tim; return do_timens_ktime_to_host(clockid, tim, &ns->offsets); } #else static inline int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { return 0; } static inline void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { } static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { return NULL; } static inline void put_time_ns(struct time_namespace *ns) { } static inline struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (flags & CLONE_NEWTIME) return ERR_PTR(-EINVAL); return old_ns; } static inline void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { return; } static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) { return NULL; } static inline void timens_add_monotonic(struct timespec64 *ts) { } static inline void timens_add_boottime(struct timespec64 *ts) { } static inline u64 timens_add_boottime_ns(u64 nsec) { return nsec; } static inline void timens_sub_boottime(struct timespec64 *ts) { } static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { return tim; } #endif struct vdso_data *arch_get_vdso_data(void *vvar_page); #endif /* _LINUX_TIMENS_H */ |
| 24 11 5 8 8 8 24 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 | // SPDX-License-Identifier: GPL-2.0-only /* * common LSM auditing functions * * Based on code written for SELinux by : * Stephen Smalley, <sds@tycho.nsa.gov> * 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/dccp.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_DCCP: { struct dccp_hdr *dh = dccp_hdr(skb); ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; 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_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } 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, char *name1, 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, char *name1, char *name2) { if (addr) audit_log_format(ab, " %s=%pI4", name1, &addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } /** * 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, struct common_audit_data *a) { char comm[sizeof(current->comm)]; /* * 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); audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current)); audit_log_untrustedstring(ab, get_task_comm(comm, current)); 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 comm[sizeof(tsk->comm)]; audit_log_format(ab, " opid=%d ocomm=", pid); audit_log_untrustedstring(ab, get_task_comm(comm, 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; } /* switch (a->type) */ } /** * 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); } |
| 185 186 186 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 | // SPDX-License-Identifier: GPL-2.0-only /* * Fixmap manipulation code */ #include <linux/bug.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/libfdt.h> #include <linux/memory.h> #include <linux/mm.h> #include <linux/sizes.h> #include <asm/fixmap.h> #include <asm/kernel-pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> /* ensure that the fixmap region does not grow down into the PCI I/O region */ static_assert(FIXADDR_TOT_START > PCI_IO_END); #define NR_BM_PTE_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT) #define NR_BM_PMD_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PUD_SHIFT) static_assert(NR_BM_PMD_TABLES == 1); #define __BM_TABLE_IDX(addr, shift) \ (((addr) >> (shift)) - (FIXADDR_TOT_START >> (shift))) #define BM_PTE_TABLE_IDX(addr) __BM_TABLE_IDX(addr, PMD_SHIFT) static pte_t bm_pte[NR_BM_PTE_TABLES][PTRS_PER_PTE] __page_aligned_bss; static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused; static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused; static inline pte_t *fixmap_pte(unsigned long addr) { return &bm_pte[BM_PTE_TABLE_IDX(addr)][pte_index(addr)]; } static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr) { pmd_t pmd = READ_ONCE(*pmdp); pte_t *ptep; if (pmd_none(pmd)) { ptep = bm_pte[BM_PTE_TABLE_IDX(addr)]; __pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE | PMD_TABLE_AF); } } static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr, unsigned long end) { unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; if (pud_none(pud)) __pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE | PUD_TABLE_AF); pmdp = pmd_offset_kimg(pudp, addr); do { next = pmd_addr_end(addr, end); early_fixmap_init_pte(pmdp, addr); } while (pmdp++, addr = next, addr != end); } static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end) { p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) && p4d_page_paddr(p4d) != __pa_symbol(bm_pud)) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); } if (p4d_none(p4d)) __p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE | P4D_TABLE_AF); pudp = pud_offset_kimg(p4dp, addr); early_fixmap_init_pmd(pudp, addr, end); } /* * The p*d_populate functions call virt_to_phys implicitly so they can't be used * directly on kernel symbols (bm_p*d). This function is called too early to use * lm_alias so __p*d_populate functions must be used to populate with the * physical address from __pa_symbol. */ void __init early_fixmap_init(void) { unsigned long addr = FIXADDR_TOT_START; unsigned long end = FIXADDR_TOP; pgd_t *pgdp = pgd_offset_k(addr); p4d_t *p4dp = p4d_offset_kimg(pgdp, addr); early_fixmap_init_pud(p4dp, addr, end); } /* * Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we * ever need to use IPIs for TLB broadcasting, then we're in trouble here. */ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); ptep = fixmap_pte(addr); if (pgprot_val(flags)) { __set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { __pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); phys_addr_t dt_phys_base; int offset; void *dt_virt; /* * Check whether the physical FDT address is set and meets the minimum * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be * at least 8 bytes so that we can always access the magic and size * fields of the FDT header after mapping the first chunk, double check * here if that is indeed the case. */ BUILD_BUG_ON(MIN_FDT_ALIGN < 8); if (!dt_phys || dt_phys % MIN_FDT_ALIGN) return NULL; dt_phys_base = round_down(dt_phys, PAGE_SIZE); offset = dt_phys % PAGE_SIZE; dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ create_mapping_noalloc(dt_phys_base, dt_virt_base, PAGE_SIZE, prot); if (fdt_magic(dt_virt) != FDT_MAGIC) return NULL; *size = fdt_totalsize(dt_virt); if (*size > MAX_FDT_SIZE) return NULL; if (offset + *size > PAGE_SIZE) { create_mapping_noalloc(dt_phys_base, dt_virt_base, offset + *size, prot); } return dt_virt; } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io */ /* Devmaps primary use is as a backend map for XDP BPF helper call * bpf_redirect_map(). Because XDP is mostly concerned with performance we * spent some effort to ensure the datapath with redirect maps does not use * any locking. This is a quick note on the details. * * We have three possible paths to get into the devmap control plane bpf * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall * will invoke an update, delete, or lookup operation. To ensure updates and * deletes appear atomic from the datapath side xchg() is used to modify the * netdev_map array. Then because the datapath does a lookup into the netdev_map * array (read-only) from an RCU critical section we use call_rcu() to wait for * an rcu grace period before free'ing the old data structures. This ensures the * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the * netdev_map consistent in this case. From the devmap side BPF programs * calling into these operations are the same as multiple user space threads * making system calls. * * Finally, any of the above may race with a netdev_unregister notifier. The * unregister notifier must search for net devices in the map structure that * contain a reference to the net device and remove them. This is a two step * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) * check to see if the ifindex is the same as the net_device being removed. * When removing the dev a cmpxchg() is used to ensure the correct dev is * removed, in the case of a concurrent update or delete operation it is * possible that the initially referenced dev is no longer in the map. As the * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. * * The devmap_hash type is a map type which interprets keys as ifindexes and * indexes these using a hashmap. This allows maps that use ifindex as key to be * densely packed instead of having holes in the lookup array for unused * ifindexes. The setup and packet enqueue/send code is shared between the two * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ struct hlist_head *dev_index_head; spinlock_t index_lock; unsigned int items; u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); static struct hlist_head *dev_map_create_hash(unsigned int entries, int numa_node) { int i; struct hlist_head *hash; hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, int idx) { return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } static int dev_map_alloc_check(union bpf_attr *attr) { u32 valsize = attr->value_size; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex * 8 bytes: ifindex + prog fd */ if (attr->max_entries == 0 || attr->key_size != 4 || (valsize != offsetofend(struct bpf_devmap_val, ifindex) && valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2; roundup_pow_of_two() * can overflow into UB on 32-bit arches */ if (attr->max_entries > 1UL << 31) return -EINVAL; } return 0; } static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2 */ dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) return -ENOMEM; } return 0; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { bpf_map_area_free(dtab); return ERR_PTR(err); } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. The following synchronize_rcu() guarantees * both rcu read critical sections complete and waits for * preempt-disable regions (NAPI being the relevant context here) so we * are certain there will be no further reads against the netdev_map and * all flush operations are complete. Flush operations can only be done * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() * during NAPI callback and cleared after the XDP redirect. There is no * explicit RCU read section which protects bpf_redirect_info->map but * local_bh_disable() also marks the beginning an RCU section. This * makes the complete softirq callback RCU protected. Thus after * following synchronize_rcu() there no bpf_redirect_info->map == map * assignment. */ synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } } bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } bpf_map_area_free(dtab->netdev_map); } bpf_map_area_free(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= dtab->map.max_entries) { *next = 0; return 0; } if (index == dtab->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; hlist_for_each_entry_rcu(dev, head, index_hlist, lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; return NULL; } static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 idx, *next = next_key; struct bpf_dtab_netdev *dev, *next_dev; struct hlist_head *head; int i = 0; if (!key) goto find_first; idx = *(u32 *)key; dev = __dev_map_hash_lookup_elem(map, idx); if (!dev) goto find_first; next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } i = idx & (dtab->n_buckets - 1); i++; find_first: for (; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } } return -ENOENT; } static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *tx_dev, struct net_device *rx_dev) { struct xdp_txq_info txq = { .dev = tx_dev }; struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; u32 act; int err; xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: err = xdp_update_frame_from_buff(&xdp, xdpf); if (unlikely(err < 0)) xdp_return_frame_rx_napi(xdpf); else frames[nframes++] = xdpf; break; default: bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); break; } } return nframes; /* sent frames count */ } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; unsigned int cnt = bq->count; int sent = 0, err = 0; int to_send = cnt; int i; if (unlikely(!cnt)) return; for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } if (bq->xdp_prog) { to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. */ err = sent; sent = 0; } /* If not all frames have been transmitted, it is our * responsibility to free them */ for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } /* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ void __dev_flush(struct list_head *flush_list) { struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); } } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; obj = rcu_dereference_check(dtab->netdev_map[key], rcu_read_lock_bh_held()); return obj; } /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. * * Do the same with xdp_prog and flush_list since these fields * are only ever modified together. */ if (!bq->dev_rx) { struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); } bq->q[bq->count++] = xdpf; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { int err; if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return -EOPNOTSUPP; if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); if (unlikely(err)) return err; bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { struct xdp_txq_info txq = { .dev = dst->dev }; struct xdp_buff xdp; u32 act; if (!dst->xdp_prog) return XDP_PASS; __skb_pull(skb, skb->mac_len); xdp.txq = &txq; act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: __skb_push(skb, skb->mac_len); break; default: bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); fallthrough; case XDP_DROP: kfree_skb(skb); break; } return act; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj) return false; if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return false; if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) return false; return true; } static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, struct net_device *dev_rx, struct xdp_frame *xdpf) { struct xdp_frame *nxdpf; nxdpf = xdpf_clone(xdpf); if (!nxdpf) return -ENOMEM; bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); return 0; } static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) { while (num_excluded--) { if (ifindex == excluded[num_excluded]) return true; } return false; } /* Get ifindex of each upper device. 'indexes' must be able to hold at * least MAX_NEST_DEV elements. * Returns the number of ifindexes added. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { indexes[n++] = upper->ifindex; } return n; } int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); excluded_devices[num_excluded++] = dev_rx->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } } /* consume the last copy of the frame */ if (last_dst) bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); else xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. */ if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) return 0; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; err = dev_map_generic_redirect(dst, nskb, xdp_prog); if (unlikely(err)) { consume_skb(nskb); return err; } return 0; } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices); excluded_devices[num_excluded++] = dev->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } } /* consume the first skb and return */ if (last_dst) return dev_map_generic_redirect(last_dst, skb, xdp_prog); /* dtab is empty */ consume_skb(skb); return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } return 0; } static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, k); if (old_dev) { dtab->items--; hlist_del_init_rcu(&old_dev->index_hlist); call_rcu(&old_dev->rcu, __dev_map_entry_free); ret = 0; } spin_unlock_irqrestore(&dtab->index_lock, flags); return ret; } static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, struct bpf_devmap_val *val, unsigned int idx) { struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), GFP_NOWAIT | __GFP_NOWARN, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); dev->dev = dev_get_by_index(net, val->ifindex); if (!dev->dev) goto err_out; if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; if (prog->expected_attach_type != BPF_XDP_DEVMAP || !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } dev->idx = idx; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; } else { dev->xdp_prog = NULL; dev->val.bpf_prog.id = 0; } dev->val.ifindex = val->ifindex; return dev; err_put_prog: bpf_prog_put(prog); err_put_dev: dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); } static long __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= dtab->map.max_entries)) return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); else atomic_inc((atomic_t *)&dtab->items); return 0; } static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) return -EINVAL; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, idx); if (old_dev && (map_flags & BPF_NOEXIST)) goto out_err; dev = __dev_map_alloc_node(net, dtab, &val, idx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_err; } if (old_dev) { hlist_del_rcu(&old_dev->index_hlist); } else { if (dtab->items >= dtab->map.max_entries) { spin_unlock_irqrestore(&dtab->index_lock, flags); call_rcu(&dev->rcu, __dev_map_entry_free); return -E2BIG; } dtab->items++; } hlist_add_head_rcu(&dev->index_hlist, dev_map_index_hash(dtab, idx)); spin_unlock_irqrestore(&dtab->index_lock, flags); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; out_err: spin_unlock_irqrestore(&dtab->index_lock, flags); return err; } static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } static u64 dev_map_mem_usage(const struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u64 usage = sizeof(struct bpf_dtab); if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); else usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); usage += atomic_read((atomic_t *)&dtab->items) * (u64)sizeof(struct bpf_dtab_netdev); return usage; } BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, .map_lookup_elem = dev_map_hash_lookup_elem, .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, struct net_device *netdev) { unsigned long flags; u32 i; spin_lock_irqsave(&dtab->index_lock, flags); for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev) continue; dtab->items--; hlist_del_rcu(&dev->index_hlist); call_rcu(&dev->rcu, __dev_map_entry_free); } } spin_unlock_irqrestore(&dtab->index_lock, flags); } static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; int i, cpu; switch (event) { case NETDEV_REGISTER: if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) break; /* will be freed in free_netdev() */ netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; for_each_possible_cpu(cpu) per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete * operation does not free a netdev_map entry while we * are comparing it against the netdev being unregistered. */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dev_map_hash_remove_netdev(dtab, netdev); continue; } for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } } } rcu_read_unlock(); break; default: break; } return NOTIFY_OK; } static struct notifier_block dev_map_notifier = { .notifier_call = dev_map_notification, }; static int __init dev_map_init(void) { /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } subsys_initcall(dev_map_init); |
| 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC port policer entry */ struct dsa_mall_policer_tc_entry { u32 burst; u64 rate_bytes_per_sec; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct dsa_mall_policer_tc_entry policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. * DEPRECATED: Do NOT set this field in new drivers. Instead look at * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. * Useful if the switch cannot preserve the VLAN tag as seen on the * wire for user port ingress, and chooses to send all frames as * VLAN-tagged to the CPU, including those which were originally * untagged. */ u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); int (*get_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, struct dsa_mall_policer_tc_entry *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct ifreq *ifr); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct ifreq *ifr); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); #endif |
| 64 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/nodemask_types.h> #include <linux/numa.h> #include <linux/random.h> extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mismatch error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) static __always_inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); } #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) static __always_inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); if (ret == MAX_NUMNODES) ret = __first_node(srcp); return ret; } static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static __always_inline int node_state(int node, enum node_states state) { return node == 0; } static __always_inline void node_set_state(int node, enum node_states state) { } static __always_inline void node_clear_state(int node, enum node_states state) { } static __always_inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int w, bit; w = nodes_weight(*maskp); switch (w) { case 0: bit = NUMA_NO_NODE; break; case 1: bit = first_node(*maskp); break; default: bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_u32_below(w)); break; } return bit; #else return 0; #endif } #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) /* * For nodemask scratch area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* Example structure for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */ |
| 287 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vmalloc #if !defined(_TRACE_VMALLOC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_VMALLOC_H #include <linux/tracepoint.h> /** * alloc_vmap_area - called when a new vmap allocation occurs * @addr: an allocated address * @size: a requested size * @align: a requested alignment * @vstart: a requested start range * @vend: a requested end range * @failed: an allocation failed or not * * This event is used for a debug purpose, it can give an extra * information for a developer about how often it occurs and which * parameters are passed for further validation. */ TRACE_EVENT(alloc_vmap_area, TP_PROTO(unsigned long addr, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int failed), TP_ARGS(addr, size, align, vstart, vend, failed), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, size) __field(unsigned long, align) __field(unsigned long, vstart) __field(unsigned long, vend) __field(int, failed) ), TP_fast_assign( __entry->addr = addr; __entry->size = size; __entry->align = align; __entry->vstart = vstart; __entry->vend = vend; __entry->failed = failed; ), TP_printk("va_start: %lu size=%lu align=%lu vstart=0x%lx vend=0x%lx failed=%d", __entry->addr, __entry->size, __entry->align, __entry->vstart, __entry->vend, __entry->failed) ); /** * purge_vmap_area_lazy - called when vmap areas were lazily freed * @start: purging start address * @end: purging end address * @npurged: numbed of purged vmap areas * * This event is used for a debug purpose. It gives some * indication about start:end range and how many objects * are released. */ TRACE_EVENT(purge_vmap_area_lazy, TP_PROTO(unsigned long start, unsigned long end, unsigned int npurged), TP_ARGS(start, end, npurged), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned int, npurged) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->npurged = npurged; ), TP_printk("start=0x%lx end=0x%lx num_purged=%u", __entry->start, __entry->end, __entry->npurged) ); /** * free_vmap_area_noflush - called when a vmap area is freed * @va_start: a start address of VA * @nr_lazy: number of current lazy pages * @nr_lazy_max: number of maximum lazy pages * * This event is used for a debug purpose. It gives some * indication about a VA that is released, number of current * outstanding areas and a maximum allowed threshold before * dropping all of them. */ TRACE_EVENT(free_vmap_area_noflush, TP_PROTO(unsigned long va_start, unsigned long nr_lazy, unsigned long nr_lazy_max), TP_ARGS(va_start, nr_lazy, nr_lazy_max), TP_STRUCT__entry( __field(unsigned long, va_start) __field(unsigned long, nr_lazy) __field(unsigned long, nr_lazy_max) ), TP_fast_assign( __entry->va_start = va_start; __entry->nr_lazy = nr_lazy; __entry->nr_lazy_max = nr_lazy_max; ), TP_printk("va_start=0x%lx nr_lazy=%lu nr_lazy_max=%lu", __entry->va_start, __entry->nr_lazy, __entry->nr_lazy_max) ); #endif /* _TRACE_VMALLOC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 2 3 3 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ratelimit.c - Do something with rate limit. * * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com> * * 2008-05-01 rewrite the function and use a ratelimit_state data struct as * parameter. Now every user can use their own standalone ratelimit_state. */ #include <linux/ratelimit.h> #include <linux/jiffies.h> #include <linux/export.h> /* * __ratelimit - rate limiting * @rs: ratelimit_state data * @func: name of calling function * * This enforces a rate limit: not more than @rs->burst callbacks * in every @rs->interval * * RETURNS: * 0 means callbacks will be suppressed. * 1 means go ahead and do it. */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { /* Paired with WRITE_ONCE() in .proc_handler(). * Changing two values seperately could be inconsistent * and some message could be lost. (See: net_ratelimit_state). */ int interval = READ_ONCE(rs->interval); int burst = READ_ONCE(rs->burst); unsigned long flags; int ret; if (!interval) return 1; /* * If we contend on this state's lock then almost * by definition we are too busy to print a message, * in addition to the one that will be printed by * the entity that is holding the lock already: */ if (!raw_spin_trylock_irqsave(&rs->lock, flags)) return 0; if (!rs->begin) rs->begin = jiffies; if (time_is_before_jiffies(rs->begin + interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { printk_deferred(KERN_WARNING "%s: %d callbacks suppressed\n", func, rs->missed); rs->missed = 0; } } rs->begin = jiffies; rs->printed = 0; } if (burst && burst > rs->printed) { rs->printed++; ret = 1; } else { rs->missed++; ret = 0; } raw_spin_unlock_irqrestore(&rs->lock, flags); return ret; } EXPORT_SYMBOL(___ratelimit); |
| 421 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/mmu_context.h * * Copyright (C) 1996 Russell King. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_MMU_CONTEXT_H #define __ASM_MMU_CONTEXT_H #ifndef __ASSEMBLY__ #include <linux/compiler.h> #include <linux/sched.h> #include <linux/sched/hotplug.h> #include <linux/mm_types.h> #include <linux/pgtable.h> #include <linux/pkeys.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/gcs.h> #include <asm/proc-fns.h> #include <asm/cputype.h> #include <asm/sysreg.h> #include <asm/tlbflush.h> extern bool rodata_full; static inline void contextidr_thread_switch(struct task_struct *next) { if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR)) return; write_sysreg(task_pid_nr(next), contextidr_el1); isb(); } /* * Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0. */ static inline void cpu_set_reserved_ttbr0_nosync(void) { unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); write_sysreg(ttbr, ttbr0_el1); } static inline void cpu_set_reserved_ttbr0(void) { cpu_set_reserved_ttbr0_nosync(); isb(); } void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm); static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) { BUG_ON(pgd == swapper_pg_dir); cpu_do_switch_mm(virt_to_phys(pgd),mm); } /* * TCR.T0SZ value to use when the ID map is active. */ #define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS) /* * Ensure TCR.T0SZ is set to the provided value. */ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) { unsigned long tcr = read_sysreg(tcr_el1); if ((tcr & TCR_T0SZ_MASK) == t0sz) return; tcr &= ~TCR_T0SZ_MASK; tcr |= t0sz; write_sysreg(tcr, tcr_el1); isb(); } #define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual)) #define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz) /* * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm. * * The idmap lives in the same VA range as userspace, but uses global entries * and may use a different TCR_EL1.T0SZ. To avoid issues resulting from * speculative TLB fetches, we must temporarily install the reserved page * tables while we invalidate the TLBs and set up the correct TCR_EL1.T0SZ. * * If current is a not a user task, the mm covers the TTBR1_EL1 page tables, * which should not be installed in TTBR0_EL1. In this case we can leave the * reserved page tables in place. */ static inline void cpu_uninstall_idmap(void) { struct mm_struct *mm = current->active_mm; cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); if (mm != &init_mm && !system_uses_ttbr0_pan()) cpu_switch_mm(mm->pgd, mm); } static inline void cpu_install_idmap(void) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* * Load our new page tables. A strict BBM approach requires that we ensure that * TLBs are free of any entries that may overlap with the global mappings we are * about to install. * * For a real hibernate/resume/kexec cycle TTBR0 currently points to a zero * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI runtime * services), while for a userspace-driven test_resume cycle it points to * userspace page tables (and we must point it at a zero page ourselves). * * We change T0SZ as part of installing the idmap. This is undone by * cpu_uninstall_idmap() in __cpu_suspend_exit(). */ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); __cpu_set_tcr_t0sz(t0sz); /* avoid cpu_switch_mm() and its SW-PAN and CNP interactions */ write_sysreg(ttbr0, ttbr0_el1); isb(); } void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp); static inline void cpu_enable_swapper_cnp(void) { __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true); } static inline void cpu_replace_ttbr1(pgd_t *pgdp) { /* * Only for early TTBR1 replacement before cpucaps are finalized and * before we've decided whether to use CNP. */ WARN_ON(system_capabilities_finalized()); __cpu_replace_ttbr1(pgdp, false); } /* * It would be nice to return ASIDs back to the allocator, but unfortunately * that introduces a race with a generation rollover where we could erroneously * free an ASID allocated in a future generation. We could workaround this by * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap), * but we'd then need to make sure that we didn't dirty any TLBs afterwards. * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you * take CPU migration into account. */ void check_and_switch_context(struct mm_struct *mm); #define init_new_context(tsk, mm) init_new_context(tsk, mm) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { atomic64_set(&mm->context.id, 0); refcount_set(&mm->context.pinned, 0); /* pkey 0 is the default, so always reserve it. */ mm->context.pkey_allocation_map = BIT(0); return 0; } static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); return 0; } static inline void arch_exit_mmap(struct mm_struct *mm) { } static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { u64 ttbr; if (!system_uses_ttbr0_pan()) return; if (mm == &init_mm) ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); else ttbr = phys_to_ttbr(virt_to_phys(mm->pgd)) | ASID(mm) << 48; WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr); } #else static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { } #endif #define enter_lazy_tlb enter_lazy_tlb static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { /* * We don't actually care about the ttbr0 mapping, so point it at the * zero page. */ update_saved_ttbr0(tsk, &init_mm); } static inline void __switch_mm(struct mm_struct *next) { /* * init_mm.pgd does not contain any user mappings and it is always * active for kernel addresses in TTBR1. Just set the reserved TTBR0. */ if (next == &init_mm) { cpu_set_reserved_ttbr0(); return; } check_and_switch_context(next); } static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { if (prev != next) __switch_mm(next); /* * Update the saved TTBR0_EL1 of the scheduled-in task as the previous * value may have not been initialised yet (activate_mm caller) or the * ASID has changed since the last run (following the context switch * of another thread of the same process). */ update_saved_ttbr0(tsk, next); } static inline const struct cpumask * task_cpu_possible_mask(struct task_struct *p) { if (!static_branch_unlikely(&arm64_mismatched_32bit_el0)) return cpu_possible_mask; if (!is_compat_thread(task_thread_info(p))) return cpu_possible_mask; return system_32bit_el0_cpumask(); } #define task_cpu_possible_mask task_cpu_possible_mask void verify_cpu_asid_bits(void); void post_ttbr_update_workaround(void); unsigned long arm64_mm_context_get(struct mm_struct *mm); void arm64_mm_context_put(struct mm_struct *mm); #define mm_untag_mask mm_untag_mask static inline unsigned long mm_untag_mask(struct mm_struct *mm) { return -1UL >> 8; } /* * Only enforce protection keys on the current process, because there is no * user context to access POR_EL0 for another address space. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { if (!system_supports_poe()) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return por_el0_allows_pkey(vma_pkey(vma), write, execute); } #define deactivate_mm deactivate_mm static inline void deactivate_mm(struct task_struct *tsk, struct mm_struct *mm) { gcs_free(tsk); } #include <asm-generic/mmu_context.h> #endif /* !__ASSEMBLY__ */ #endif /* !__ASM_MMU_CONTEXT_H */ |
| 461 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ |
| 9 1 4 1 1 1 1 94 95 9 8 71 71 63 9 9 63 71 71 71 317 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/reset.c * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/hw_breakpoint.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> #include <kvm/arm_arch_timer.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/fpsimd.h> #include <asm/ptrace.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/virt.h> /* Maximum phys_shift supported for any VM on this host */ static u32 __ro_after_init kvm_ipa_limit; unsigned int __ro_after_init kvm_host_sve_max_vl; /* * ARMv8 Reset Values */ #define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \ PSR_F_BIT | PSR_D_BIT) #define VCPU_RESET_PSTATE_EL2 (PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \ PSR_F_BIT | PSR_D_BIT) #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT) unsigned int __ro_after_init kvm_sve_max_vl; int __init kvm_arm_init_sve(void) { if (system_supports_sve()) { kvm_sve_max_vl = sve_max_virtualisable_vl(); kvm_host_sve_max_vl = sve_max_vl(); kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl; /* * The get_sve_reg()/set_sve_reg() ioctl interface will need * to be extended with multiple register slice support in * order to support vector lengths greater than * VL_ARCH_MAX: */ if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX)) kvm_sve_max_vl = VL_ARCH_MAX; /* * Don't even try to make use of vector lengths that * aren't available on all CPUs, for now: */ if (kvm_sve_max_vl < sve_max_vl()) pr_warn("KVM: SVE vector length for guests limited to %u bytes\n", kvm_sve_max_vl); } return 0; } static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) { vcpu->arch.sve_max_vl = kvm_sve_max_vl; /* * Userspace can still customize the vector lengths by writing * KVM_REG_ARM64_SVE_VLS. Allocation is deferred until * kvm_arm_vcpu_finalize(), which freezes the configuration. */ set_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &vcpu->kvm->arch.flags); } /* * Finalize vcpu's maximum SVE vector length, allocating * vcpu->arch.sve_state as necessary. */ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) { void *buf; unsigned int vl; size_t reg_sz; int ret; vl = vcpu->arch.sve_max_vl; /* * Responsibility for these properties is shared between * kvm_arm_init_sve(), kvm_vcpu_enable_sve() and * set_sve_vls(). Double-check here just to be sure: */ if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() || vl > VL_ARCH_MAX)) return -EIO; reg_sz = vcpu_sve_state_size(vcpu); buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT); if (!buf) return -ENOMEM; ret = kvm_share_hyp(buf, buf + reg_sz); if (ret) { kfree(buf); return ret; } vcpu->arch.sve_state = buf; vcpu_set_flag(vcpu, VCPU_SVE_FINALIZED); return 0; } int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature) { switch (feature) { case KVM_ARM_VCPU_SVE: if (!vcpu_has_sve(vcpu)) return -EINVAL; if (kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; return kvm_vcpu_finalize_sve(vcpu); } return -EINVAL; } bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) { if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu)) return false; return true; } void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) { void *sve_state = vcpu->arch.sve_state; kvm_unshare_hyp(vcpu, vcpu + 1); if (sve_state) kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); kfree(sve_state); kfree(vcpu->arch.ccsidr); } static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) { if (vcpu_has_sve(vcpu)) memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu)); } /** * kvm_reset_vcpu - sets core registers and sys_regs to reset value * @vcpu: The VCPU pointer * * This function sets the registers on the virtual CPU struct to their * architecturally defined reset values, except for registers whose reset is * deferred until kvm_arm_vcpu_finalize(). * * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT * ioctl or as part of handling a request issued by another VCPU in the PSCI * handling code. In the first case, the VCPU will not be loaded, and in the * second case the VCPU will be loaded. Because this function operates purely * on the memory-backed values of system registers, we want to do a full put if * we were loaded (handling a request) and load the values back at the end of * the function. Otherwise we leave the state alone. In both cases, we * disable preemption around the vcpu reset as we would otherwise race with * preempt notifiers which also call put/load. */ void kvm_reset_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_reset_state reset_state; bool loaded; u32 pstate; spin_lock(&vcpu->arch.mp_state_lock); reset_state = vcpu->arch.reset_state; vcpu->arch.reset_state.reset = false; spin_unlock(&vcpu->arch.mp_state_lock); /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); preempt_disable(); loaded = (vcpu->cpu != -1); if (loaded) kvm_arch_vcpu_put(vcpu); if (!kvm_arm_vcpu_sve_finalized(vcpu)) { if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) kvm_vcpu_enable_sve(vcpu); } else { kvm_vcpu_reset_sve(vcpu); } if (vcpu_el1_is_32bit(vcpu)) pstate = VCPU_RESET_PSTATE_SVC; else if (vcpu_has_nv(vcpu)) pstate = VCPU_RESET_PSTATE_EL2; else pstate = VCPU_RESET_PSTATE_EL1; /* Reset core registers */ memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu))); memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs)); vcpu->arch.ctxt.spsr_abt = 0; vcpu->arch.ctxt.spsr_und = 0; vcpu->arch.ctxt.spsr_irq = 0; vcpu->arch.ctxt.spsr_fiq = 0; vcpu_gp_regs(vcpu)->pstate = pstate; /* Reset system registers */ kvm_reset_sys_regs(vcpu); /* * Additional reset state handling that PSCI may have imposed on us. * Must be done after all the sys_reg reset. */ if (reset_state.reset) { unsigned long target_pc = reset_state.pc; /* Gracefully handle Thumb2 entry point */ if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { target_pc &= ~1UL; vcpu_set_thumb(vcpu); } /* Propagate caller endianness */ if (reset_state.be) kvm_vcpu_set_be(vcpu); *vcpu_pc(vcpu) = target_pc; vcpu_set_reg(vcpu, 0, reset_state.r0); } /* Reset timer */ kvm_timer_vcpu_reset(vcpu); if (loaded) kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); } u32 kvm_get_pa_bits(struct kvm *kvm) { /* Fixed limit until we can configure ID_AA64MMFR0.PARange */ return kvm_ipa_limit; } u32 get_kvm_ipa_limit(void) { return kvm_ipa_limit; } int __init kvm_set_ipa_limit(void) { unsigned int parange; u64 mmfr0; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); parange = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); /* * IPA size beyond 48 bits for 4K and 16K page size is only supported * when LPA2 is available. So if we have LPA2, enable it, else cap to 48 * bits, in case it's reported as larger on the system. */ if (!kvm_lpa2_is_enabled() && PAGE_SIZE != SZ_64K) parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48); /* * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at * Stage-2. If not, things will stop very quickly. */ switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_2_SHIFT)) { case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE: kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n"); return -EINVAL; case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT: kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n"); break; case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX: kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n"); break; default: kvm_err("Unsupported value for TGRAN_2, giving up\n"); return -EINVAL; } kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange); kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit, ((kvm_ipa_limit < KVM_PHYS_SHIFT) ? " (Reduced IPA size, limited VM/VMM compatibility)" : "")); return 0; } |
| 1 2 2 1 1 1 1 1 2 2 2 2 2 2 2 1 1 1 2 2 2 2 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 6 5 2 1 1 1 1 1 3 2 1 1 1 1 1 1 1 6 1 2 1 2 1 1 1 1 12 1 1 4 2 1 4 2 5 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * GICv3 ITS emulation * * Copyright (C) 2015,2016 ARM Ltd. * Author: Andre Przywara <andre.przywara@arm.com> */ #include <linux/cpu.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/uaccess.h> #include <linux/list_sort.h> #include <linux/irqchip/arm-gic-v3.h> #include <asm/kvm_emulate.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include "vgic.h" #include "vgic-mmio.h" static struct kvm_device_ops kvm_arm_vgic_its_ops; static int vgic_its_save_tables_v0(struct vgic_its *its); static int vgic_its_restore_tables_v0(struct vgic_its *its); static int vgic_its_commit_v0(struct vgic_its *its); static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, struct kvm_vcpu *filter_vcpu, bool needs_inv); #define vgic_its_read_entry_lock(i, g, valp, t) \ ({ \ int __sz = vgic_its_get_abi(i)->t##_esz; \ struct kvm *__k = (i)->dev->kvm; \ int __ret; \ \ BUILD_BUG_ON(NR_ITS_ABIS == 1 && \ sizeof(*(valp)) != ABI_0_ESZ); \ if (NR_ITS_ABIS > 1 && \ KVM_BUG_ON(__sz != sizeof(*(valp)), __k)) \ __ret = -EINVAL; \ else \ __ret = kvm_read_guest_lock(__k, (g), \ valp, __sz); \ __ret; \ }) #define vgic_its_write_entry_lock(i, g, val, t) \ ({ \ int __sz = vgic_its_get_abi(i)->t##_esz; \ struct kvm *__k = (i)->dev->kvm; \ typeof(val) __v = (val); \ int __ret; \ \ BUILD_BUG_ON(NR_ITS_ABIS == 1 && \ sizeof(__v) != ABI_0_ESZ); \ if (NR_ITS_ABIS > 1 && \ KVM_BUG_ON(__sz != sizeof(__v), __k)) \ __ret = -EINVAL; \ else \ __ret = vgic_write_guest_lock(__k, (g), \ &__v, __sz); \ __ret; \ }) /* * Creates a new (reference to a) struct vgic_irq for a given LPI. * If this LPI is already mapped on another ITS, we increase its refcount * and return a pointer to the existing structure. * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq. * This function returns a pointer to the _unlocked_ structure. */ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, struct kvm_vcpu *vcpu) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq; unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ if (irq) return irq; irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT); if (!irq) return ERR_PTR(-ENOMEM); ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); if (ret) { kfree(irq); return ERR_PTR(ret); } INIT_LIST_HEAD(&irq->ap_list); raw_spin_lock_init(&irq->irq_lock); irq->config = VGIC_CONFIG_EDGE; kref_init(&irq->refcount); irq->intid = intid; irq->target_vcpu = vcpu; irq->group = 1; xa_lock_irqsave(&dist->lpi_xa, flags); /* * There could be a race with another vgic_add_lpi(), so we need to * check that we don't add a second list entry with the same LPI. */ oldirq = xa_load(&dist->lpi_xa, intid); if (vgic_try_get_irq_kref(oldirq)) { /* Someone was faster with adding this LPI, lets use that. */ kfree(irq); irq = oldirq; goto out_unlock; } ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0)); if (ret) { xa_release(&dist->lpi_xa, intid); kfree(irq); } out_unlock: xa_unlock_irqrestore(&dist->lpi_xa, flags); if (ret) return ERR_PTR(ret); /* * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. * * Should any of these fail, behave as if we couldn't create the LPI * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); if (ret) { vgic_put_irq(kvm, irq); return ERR_PTR(ret); } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); if (ret) { vgic_put_irq(kvm, irq); return ERR_PTR(ret); } return irq; } struct its_device { struct list_head dev_list; /* the head for the list of ITTEs */ struct list_head itt_head; u32 num_eventid_bits; gpa_t itt_addr; u32 device_id; }; #define COLLECTION_NOT_MAPPED ((u32)~0) struct its_collection { struct list_head coll_list; u32 collection_id; u32 target_addr; }; #define its_is_collection_mapped(coll) ((coll) && \ ((coll)->target_addr != COLLECTION_NOT_MAPPED)) struct its_ite { struct list_head ite_list; struct vgic_irq *irq; struct its_collection *collection; u32 event_id; }; /** * struct vgic_its_abi - ITS abi ops and settings * @cte_esz: collection table entry size * @dte_esz: device table entry size * @ite_esz: interrupt translation table entry size * @save_tables: save the ITS tables into guest RAM * @restore_tables: restore the ITS internal structs from tables * stored in guest RAM * @commit: initialize the registers which expose the ABI settings, * especially the entry sizes */ struct vgic_its_abi { int cte_esz; int dte_esz; int ite_esz; int (*save_tables)(struct vgic_its *its); int (*restore_tables)(struct vgic_its *its); int (*commit)(struct vgic_its *its); }; #define ABI_0_ESZ 8 #define ESZ_MAX ABI_0_ESZ static const struct vgic_its_abi its_table_abi_versions[] = { [0] = { .cte_esz = ABI_0_ESZ, .dte_esz = ABI_0_ESZ, .ite_esz = ABI_0_ESZ, .save_tables = vgic_its_save_tables_v0, .restore_tables = vgic_its_restore_tables_v0, .commit = vgic_its_commit_v0, }, }; #define NR_ITS_ABIS ARRAY_SIZE(its_table_abi_versions) inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its) { return &its_table_abi_versions[its->abi_rev]; } static int vgic_its_set_abi(struct vgic_its *its, u32 rev) { const struct vgic_its_abi *abi; its->abi_rev = rev; abi = vgic_its_get_abi(its); return abi->commit(its); } /* * Find and returns a device in the device table for an ITS. * Must be called with the its_lock mutex held. */ static struct its_device *find_its_device(struct vgic_its *its, u32 device_id) { struct its_device *device; list_for_each_entry(device, &its->device_list, dev_list) if (device_id == device->device_id) return device; return NULL; } /* * Find and returns an interrupt translation table entry (ITTE) for a given * Device ID/Event ID pair on an ITS. * Must be called with the its_lock mutex held. */ static struct its_ite *find_ite(struct vgic_its *its, u32 device_id, u32 event_id) { struct its_device *device; struct its_ite *ite; device = find_its_device(its, device_id); if (device == NULL) return NULL; list_for_each_entry(ite, &device->itt_head, ite_list) if (ite->event_id == event_id) return ite; return NULL; } /* To be used as an iterator this macro misses the enclosing parentheses */ #define for_each_lpi_its(dev, ite, its) \ list_for_each_entry(dev, &(its)->device_list, dev_list) \ list_for_each_entry(ite, &(dev)->itt_head, ite_list) #define GIC_LPI_OFFSET 8192 #define VITS_TYPER_IDBITS 16 #define VITS_MAX_EVENTID (BIT(VITS_TYPER_IDBITS) - 1) #define VITS_TYPER_DEVBITS 16 #define VITS_MAX_DEVID (BIT(VITS_TYPER_DEVBITS) - 1) #define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1) #define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1) /* * Finds and returns a collection in the ITS collection table. * Must be called with the its_lock mutex held. */ static struct its_collection *find_collection(struct vgic_its *its, int coll_id) { struct its_collection *collection; list_for_each_entry(collection, &its->collection_list, coll_list) { if (coll_id == collection->collection_id) return collection; } return NULL; } #define LPI_PROP_ENABLE_BIT(p) ((p) & LPI_PROP_ENABLED) #define LPI_PROP_PRIORITY(p) ((p) & 0xfc) /* * Reads the configuration data for a given LPI from guest memory and * updates the fields in struct vgic_irq. * If filter_vcpu is not NULL, applies only if the IRQ is targeting this * VCPU. Unconditionally applies if filter_vcpu is NULL. */ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, struct kvm_vcpu *filter_vcpu, bool needs_inv) { u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser); u8 prop; int ret; unsigned long flags; ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, &prop, 1); if (ret) return ret; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!filter_vcpu || filter_vcpu == irq->target_vcpu) { irq->priority = LPI_PROP_PRIORITY(prop); irq->enabled = LPI_PROP_ENABLE_BIT(prop); if (!irq->hw) { vgic_queue_irq_unlock(kvm, irq, flags); return 0; } } raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) return its_prop_update_vlpi(irq->host_irq, prop, needs_inv); return 0; } static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int ret = 0; unsigned long flags; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; ret = its_get_vlpi(irq->host_irq, &map); if (ret) return ret; if (map.vpe) atomic_dec(&map.vpe->vlpi_count); map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; atomic_inc(&map.vpe->vlpi_count); ret = its_map_vlpi(irq->host_irq, &map); } return ret; } static struct kvm_vcpu *collection_to_vcpu(struct kvm *kvm, struct its_collection *col) { return kvm_get_vcpu_by_id(kvm, col->target_addr); } /* * Promotes the ITS view of affinity of an ITTE (which redistributor this LPI * is targeting) to the VGIC's view, which deals with target VCPUs. * Needs to be called whenever either the collection for a LPIs has * changed or the collection itself got retargeted. */ static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite) { struct kvm_vcpu *vcpu; if (!its_is_collection_mapped(ite->collection)) return; vcpu = collection_to_vcpu(kvm, ite->collection); update_affinity(ite->irq, vcpu); } /* * Updates the target VCPU for every LPI targeting this collection. * Must be called with the its_lock mutex held. */ static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its, struct its_collection *coll) { struct its_device *device; struct its_ite *ite; for_each_lpi_its(device, ite, its) { if (ite->collection != coll) continue; update_affinity_ite(kvm, ite); } } static u32 max_lpis_propbaser(u64 propbaser) { int nr_idbits = (propbaser & 0x1f) + 1; return 1U << min(nr_idbits, INTERRUPT_ID_BITS_ITS); } /* * Sync the pending table pending bit of LPIs targeting @vcpu * with our own data structures. This relies on the LPI being * mapped before. */ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) { gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); struct vgic_dist *dist = &vcpu->kvm->arch.vgic; unsigned long intid, flags; struct vgic_irq *irq; int last_byte_offset = -1; int ret = 0; u8 pendmask; xa_for_each(&dist->lpi_xa, intid, irq) { int byte_offset, bit_nr; byte_offset = intid / BITS_PER_BYTE; bit_nr = intid % BITS_PER_BYTE; /* * For contiguously allocated LPIs chances are we just read * this very same byte in the last iteration. Reuse that. */ if (byte_offset != last_byte_offset) { ret = kvm_read_guest_lock(vcpu->kvm, pendbase + byte_offset, &pendmask, 1); if (ret) return ret; last_byte_offset = byte_offset; } irq = vgic_get_irq(vcpu->kvm, intid); if (!irq) continue; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu == vcpu) irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } return ret; } static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 reg = GITS_TYPER_PLPIS; /* * We use linear CPU numbers for redistributor addressing, * so GITS_TYPER.PTA is 0. * Also we force all PROPBASER registers to be the same, so * CommonLPIAff is 0 as well. * To avoid memory waste in the guest, we keep the number of IDBits and * DevBits low - as least for the time being. */ reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT; reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT; reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT; return extract_bytes(reg, addr & 7, len); } static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { u32 val; val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK; val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM; return val; } static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u32 rev = GITS_IIDR_REV(val); if (rev >= NR_ITS_ABIS) return -EINVAL; return vgic_its_set_abi(its, rev); } static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { switch (addr & 0xffff) { case GITS_PIDR0: return 0x92; /* part number, bits[7:0] */ case GITS_PIDR1: return 0xb4; /* part number, bits[11:8] */ case GITS_PIDR2: return GIC_PIDR2_ARCH_GICv3 | 0x0b; case GITS_PIDR4: return 0x40; /* This is a 64K software visible page */ /* The following are the ID registers for (any) GIC. */ case GITS_CIDR0: return 0x0d; case GITS_CIDR1: return 0xf0; case GITS_CIDR2: return 0x05; case GITS_CIDR3: return 0xb1; } return 0; } static struct vgic_its *__vgic_doorbell_to_its(struct kvm *kvm, gpa_t db) { struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, db); if (!kvm_io_dev) return ERR_PTR(-EINVAL); if (kvm_io_dev->ops != &kvm_io_gic_ops) return ERR_PTR(-EINVAL); iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); if (iodev->iodev_type != IODEV_ITS) return ERR_PTR(-EINVAL); return iodev->its; } static unsigned long vgic_its_cache_key(u32 devid, u32 eventid) { return (((unsigned long)devid) << VITS_TYPER_IDBITS) | eventid; } static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, u32 devid, u32 eventid) { unsigned long cache_key = vgic_its_cache_key(devid, eventid); struct vgic_its *its; struct vgic_irq *irq; if (devid > VITS_MAX_DEVID || eventid > VITS_MAX_EVENTID) return NULL; its = __vgic_doorbell_to_its(kvm, db); if (IS_ERR(its)) return NULL; rcu_read_lock(); irq = xa_load(&its->translation_cache, cache_key); if (!vgic_try_get_irq_kref(irq)) irq = NULL; rcu_read_unlock(); return irq; } static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq *irq) { unsigned long cache_key = vgic_its_cache_key(devid, eventid); struct vgic_irq *old; /* Do not cache a directly injected interrupt */ if (irq->hw) return; /* * The irq refcount is guaranteed to be nonzero while holding the * its_lock, as the ITE (and the reference it holds) cannot be freed. */ lockdep_assert_held(&its->its_lock); vgic_get_irq_kref(irq); old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); /* * Put the reference taken on @irq if the store fails. Intentionally do * not return the error as the translation cache is best effort. */ if (xa_is_err(old)) { vgic_put_irq(kvm, irq); return; } /* * We could have raced with another CPU caching the same * translation behind our back, ensure we don't leak a * reference if that is the case. */ if (old) vgic_put_irq(kvm, old); } static void vgic_its_invalidate_cache(struct vgic_its *its) { struct kvm *kvm = its->dev->kvm; struct vgic_irq *irq; unsigned long idx; xa_for_each(&its->translation_cache, idx, irq) { xa_erase(&its->translation_cache, idx); vgic_put_irq(kvm, irq); } } void vgic_its_invalidate_all_caches(struct kvm *kvm) { struct kvm_device *dev; struct vgic_its *its; rcu_read_lock(); list_for_each_entry_rcu(dev, &kvm->devices, vm_node) { if (dev->ops != &kvm_arm_vgic_its_ops) continue; its = dev->private; vgic_its_invalidate_cache(its); } rcu_read_unlock(); } int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq) { struct kvm_vcpu *vcpu; struct its_ite *ite; if (!its->enabled) return -EBUSY; ite = find_ite(its, devid, eventid); if (!ite || !its_is_collection_mapped(ite->collection)) return E_ITS_INT_UNMAPPED_INTERRUPT; vcpu = collection_to_vcpu(kvm, ite->collection); if (!vcpu) return E_ITS_INT_UNMAPPED_INTERRUPT; if (!vgic_lpis_enabled(vcpu)) return -EBUSY; vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq); *irq = ite->irq; return 0; } struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi) { u64 address; if (!vgic_has_its(kvm)) return ERR_PTR(-ENODEV); if (!(msi->flags & KVM_MSI_VALID_DEVID)) return ERR_PTR(-EINVAL); address = (u64)msi->address_hi << 32 | msi->address_lo; return __vgic_doorbell_to_its(kvm, address); } /* * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. * Returns 0 on success, a positive error value for any ITS mapping * related errors and negative error values for generic errors. */ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid) { struct vgic_irq *irq = NULL; unsigned long flags; int err; err = vgic_its_resolve_lpi(kvm, its, devid, eventid, &irq); if (err) return err; if (irq->hw) return irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); return 0; } int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) { struct vgic_irq *irq; unsigned long flags; phys_addr_t db; db = (u64)msi->address_hi << 32 | msi->address_lo; irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data); if (!irq) return -EWOULDBLOCK; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); vgic_put_irq(kvm, irq); return 0; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { struct vgic_its *its; int ret; if (!vgic_its_inject_cached_translation(kvm, msi)) return 1; its = vgic_msi_to_its(kvm, msi); if (IS_ERR(its)) return PTR_ERR(its); mutex_lock(&its->its_lock); ret = vgic_its_trigger_msi(kvm, its, msi->devid, msi->data); mutex_unlock(&its->its_lock); if (ret < 0) return ret; /* * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 * if the guest has blocked the MSI. So we map any LPI mapping * related error to that. */ if (ret) return 0; else return 1; } /* Requires the its_lock to be held. */ static void its_free_ite(struct kvm *kvm, struct its_ite *ite) { list_del(&ite->ite_list); /* This put matches the get in vgic_add_lpi. */ if (ite->irq) { if (ite->irq->hw) WARN_ON(its_unmap_vlpi(ite->irq->host_irq)); vgic_put_irq(kvm, ite->irq); } kfree(ite); } static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size) { return (le64_to_cpu(its_cmd[word]) >> shift) & (BIT_ULL(size) - 1); } #define its_cmd_get_command(cmd) its_cmd_mask_field(cmd, 0, 0, 8) #define its_cmd_get_deviceid(cmd) its_cmd_mask_field(cmd, 0, 32, 32) #define its_cmd_get_size(cmd) (its_cmd_mask_field(cmd, 1, 0, 5) + 1) #define its_cmd_get_id(cmd) its_cmd_mask_field(cmd, 1, 0, 32) #define its_cmd_get_physical_id(cmd) its_cmd_mask_field(cmd, 1, 32, 32) #define its_cmd_get_collection(cmd) its_cmd_mask_field(cmd, 2, 0, 16) #define its_cmd_get_ittaddr(cmd) (its_cmd_mask_field(cmd, 2, 8, 44) << 8) #define its_cmd_get_target_addr(cmd) its_cmd_mask_field(cmd, 2, 16, 32) #define its_cmd_get_validbit(cmd) its_cmd_mask_field(cmd, 2, 63, 1) /* * The DISCARD command frees an Interrupt Translation Table Entry (ITTE). * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (ite && its_is_collection_mapped(ite->collection)) { struct its_device *device = find_its_device(its, device_id); int ite_esz = vgic_its_get_abi(its)->ite_esz; gpa_t gpa = device->itt_addr + ite->event_id * ite_esz; /* * Though the spec talks about removing the pending state, we * don't bother here since we clear the ITTE anyway and the * pending state is a property of the ITTE struct. */ vgic_its_invalidate_cache(its); its_free_ite(kvm, ite); return vgic_its_write_entry_lock(its, gpa, 0ULL, ite); } return E_ITS_DISCARD_UNMAPPED_INTERRUPT; } /* * The MOVI command moves an ITTE to a different collection. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); struct kvm_vcpu *vcpu; struct its_ite *ite; struct its_collection *collection; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_MOVI_UNMAPPED_INTERRUPT; if (!its_is_collection_mapped(ite->collection)) return E_ITS_MOVI_UNMAPPED_COLLECTION; collection = find_collection(its, coll_id); if (!its_is_collection_mapped(collection)) return E_ITS_MOVI_UNMAPPED_COLLECTION; ite->collection = collection; vcpu = collection_to_vcpu(kvm, collection); vgic_its_invalidate_cache(its); return update_affinity(ite->irq, vcpu); } static bool __is_visible_gfn_locked(struct vgic_its *its, gpa_t gpa) { gfn_t gfn = gpa >> PAGE_SHIFT; int idx; bool ret; idx = srcu_read_lock(&its->dev->kvm->srcu); ret = kvm_is_visible_gfn(its->dev->kvm, gfn); srcu_read_unlock(&its->dev->kvm->srcu, idx); return ret; } /* * Check whether an ID can be stored into the corresponding guest table. * For a direct table this is pretty easy, but gets a bit nasty for * indirect tables. We check whether the resulting guest physical address * is actually valid (covered by a memslot and guest accessible). * For this we have to read the respective first level entry. */ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, gpa_t *eaddr) { int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; u64 indirect_ptr, type = GITS_BASER_TYPE(baser); phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); int esz = GITS_BASER_ENTRY_SIZE(baser); int index; switch (type) { case GITS_BASER_TYPE_DEVICE: if (id > VITS_MAX_DEVID) return false; break; case GITS_BASER_TYPE_COLLECTION: /* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */ if (id >= BIT_ULL(16)) return false; break; default: return false; } if (!(baser & GITS_BASER_INDIRECT)) { phys_addr_t addr; if (id >= (l1_tbl_size / esz)) return false; addr = base + id * esz; if (eaddr) *eaddr = addr; return __is_visible_gfn_locked(its, addr); } /* calculate and check the index into the 1st level */ index = id / (SZ_64K / esz); if (index >= (l1_tbl_size / sizeof(u64))) return false; /* Each 1st level entry is represented by a 64-bit value. */ if (kvm_read_guest_lock(its->dev->kvm, base + index * sizeof(indirect_ptr), &indirect_ptr, sizeof(indirect_ptr))) return false; indirect_ptr = le64_to_cpu(indirect_ptr); /* check the valid bit of the first level entry */ if (!(indirect_ptr & BIT_ULL(63))) return false; /* Mask the guest physical address and calculate the frame number. */ indirect_ptr &= GENMASK_ULL(51, 16); /* Find the address of the actual entry */ index = id % (SZ_64K / esz); indirect_ptr += index * esz; if (eaddr) *eaddr = indirect_ptr; return __is_visible_gfn_locked(its, indirect_ptr); } /* * Check whether an event ID can be stored in the corresponding Interrupt * Translation Table, which starts at device->itt_addr. */ static bool vgic_its_check_event_id(struct vgic_its *its, struct its_device *device, u32 event_id) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int ite_esz = abi->ite_esz; gpa_t gpa; /* max table size is: BIT_ULL(device->num_eventid_bits) * ite_esz */ if (event_id >= BIT_ULL(device->num_eventid_bits)) return false; gpa = device->itt_addr + event_id * ite_esz; return __is_visible_gfn_locked(its, gpa); } /* * Add a new collection into the ITS collection table. * Returns 0 on success, and a negative error value for generic errors. */ static int vgic_its_alloc_collection(struct vgic_its *its, struct its_collection **colp, u32 coll_id) { struct its_collection *collection; collection = kzalloc(sizeof(*collection), GFP_KERNEL_ACCOUNT); if (!collection) return -ENOMEM; collection->collection_id = coll_id; collection->target_addr = COLLECTION_NOT_MAPPED; list_add_tail(&collection->coll_list, &its->collection_list); *colp = collection; return 0; } static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id) { struct its_collection *collection; struct its_device *device; struct its_ite *ite; /* * Clearing the mapping for that collection ID removes the * entry from the list. If there wasn't any before, we can * go home early. */ collection = find_collection(its, coll_id); if (!collection) return; for_each_lpi_its(device, ite, its) if (ite->collection && ite->collection->collection_id == coll_id) ite->collection = NULL; list_del(&collection->coll_list); kfree(collection); } /* Must be called with its_lock mutex held */ static struct its_ite *vgic_its_alloc_ite(struct its_device *device, struct its_collection *collection, u32 event_id) { struct its_ite *ite; ite = kzalloc(sizeof(*ite), GFP_KERNEL_ACCOUNT); if (!ite) return ERR_PTR(-ENOMEM); ite->event_id = event_id; ite->collection = collection; list_add_tail(&ite->ite_list, &device->itt_head); return ite; } /* * The MAPTI and MAPI commands map LPIs to ITTEs. * Must be called with its_lock mutex held. */ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); struct its_ite *ite; struct kvm_vcpu *vcpu = NULL; struct its_device *device; struct its_collection *collection, *new_coll = NULL; struct vgic_irq *irq; int lpi_nr; device = find_its_device(its, device_id); if (!device) return E_ITS_MAPTI_UNMAPPED_DEVICE; if (!vgic_its_check_event_id(its, device, event_id)) return E_ITS_MAPTI_ID_OOR; if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI) lpi_nr = its_cmd_get_physical_id(its_cmd); else lpi_nr = event_id; if (lpi_nr < GIC_LPI_OFFSET || lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) return E_ITS_MAPTI_PHYSICALID_OOR; /* If there is an existing mapping, behavior is UNPREDICTABLE. */ if (find_ite(its, device_id, event_id)) return 0; collection = find_collection(its, coll_id); if (!collection) { int ret; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return E_ITS_MAPC_COLLECTION_OOR; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; new_coll = collection; } ite = vgic_its_alloc_ite(device, collection, event_id); if (IS_ERR(ite)) { if (new_coll) vgic_its_free_collection(its, coll_id); return PTR_ERR(ite); } if (its_is_collection_mapped(collection)) vcpu = collection_to_vcpu(kvm, collection); irq = vgic_add_lpi(kvm, lpi_nr, vcpu); if (IS_ERR(irq)) { if (new_coll) vgic_its_free_collection(its, coll_id); its_free_ite(kvm, ite); return PTR_ERR(irq); } ite->irq = irq; return 0; } /* Requires the its_lock to be held. */ static void vgic_its_free_device(struct kvm *kvm, struct vgic_its *its, struct its_device *device) { struct its_ite *ite, *temp; /* * The spec says that unmapping a device with still valid * ITTEs associated is UNPREDICTABLE. We remove all ITTEs, * since we cannot leave the memory unreferenced. */ list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list) its_free_ite(kvm, ite); vgic_its_invalidate_cache(its); list_del(&device->dev_list); kfree(device); } /* its lock must be held */ static void vgic_its_free_device_list(struct kvm *kvm, struct vgic_its *its) { struct its_device *cur, *temp; list_for_each_entry_safe(cur, temp, &its->device_list, dev_list) vgic_its_free_device(kvm, its, cur); } /* its lock must be held */ static void vgic_its_free_collection_list(struct kvm *kvm, struct vgic_its *its) { struct its_collection *cur, *temp; list_for_each_entry_safe(cur, temp, &its->collection_list, coll_list) vgic_its_free_collection(its, cur->collection_id); } /* Must be called with its_lock mutex held */ static struct its_device *vgic_its_alloc_device(struct vgic_its *its, u32 device_id, gpa_t itt_addr, u8 num_eventid_bits) { struct its_device *device; device = kzalloc(sizeof(*device), GFP_KERNEL_ACCOUNT); if (!device) return ERR_PTR(-ENOMEM); device->device_id = device_id; device->itt_addr = itt_addr; device->num_eventid_bits = num_eventid_bits; INIT_LIST_HEAD(&device->itt_head); list_add_tail(&device->dev_list, &its->device_list); return device; } /* * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs). * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); bool valid = its_cmd_get_validbit(its_cmd); u8 num_eventid_bits = its_cmd_get_size(its_cmd); gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd); struct its_device *device; gpa_t gpa; if (!vgic_its_check_id(its, its->baser_device_table, device_id, &gpa)) return E_ITS_MAPD_DEVICE_OOR; if (valid && num_eventid_bits > VITS_TYPER_IDBITS) return E_ITS_MAPD_ITTSIZE_OOR; device = find_its_device(its, device_id); /* * The spec says that calling MAPD on an already mapped device * invalidates all cached data for this device. We implement this * by removing the mapping and re-establishing it. */ if (device) vgic_its_free_device(kvm, its, device); /* * The spec does not say whether unmapping a not-mapped device * is an error, so we are done in any case. */ if (!valid) return vgic_its_write_entry_lock(its, gpa, 0ULL, dte); device = vgic_its_alloc_device(its, device_id, itt_addr, num_eventid_bits); return PTR_ERR_OR_ZERO(device); } /* * The MAPC command maps collection IDs to redistributors. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u16 coll_id; struct its_collection *collection; bool valid; valid = its_cmd_get_validbit(its_cmd); coll_id = its_cmd_get_collection(its_cmd); if (!valid) { vgic_its_free_collection(its, coll_id); vgic_its_invalidate_cache(its); } else { struct kvm_vcpu *vcpu; vcpu = kvm_get_vcpu_by_id(kvm, its_cmd_get_target_addr(its_cmd)); if (!vcpu) return E_ITS_MAPC_PROCNUM_OOR; collection = find_collection(its, coll_id); if (!collection) { int ret; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return E_ITS_MAPC_COLLECTION_OOR; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; collection->target_addr = vcpu->vcpu_id; } else { collection->target_addr = vcpu->vcpu_id; update_affinity_collection(kvm, its, collection); } } return 0; } /* * The CLEAR command removes the pending state for a particular LPI. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_CLEAR_UNMAPPED_INTERRUPT; ite->irq->pending_latch = false; if (ite->irq->hw) return irq_set_irqchip_state(ite->irq->host_irq, IRQCHIP_STATE_PENDING, false); return 0; } int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq) { return update_lpi_config(kvm, irq, NULL, true); } /* * The INV command syncs the configuration bits from the memory table. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_INV_UNMAPPED_INTERRUPT; return vgic_its_inv_lpi(kvm, ite->irq); } /** * vgic_its_invall - invalidate all LPIs targeting a given vcpu * @vcpu: the vcpu for which the RD is targeted by an invalidation * * Contrary to the INVALL command, this targets a RD instead of a * collection, and we don't need to hold the its_lock, since no ITS is * involved here. */ int vgic_its_invall(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; xa_for_each(&dist->lpi_xa, intid, irq) { irq = vgic_get_irq(kvm, intid); if (!irq) continue; update_lpi_config(kvm, irq, vcpu, false); vgic_put_irq(kvm, irq); } if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm) its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe); return 0; } /* * The INVALL command requests flushing of all IRQ data in this collection. * Find the VCPU mapped to that collection, then iterate over the VM's list * of mapped LPIs and update the configuration for each IRQ which targets * the specified vcpu. The configuration will be read from the in-memory * configuration table. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 coll_id = its_cmd_get_collection(its_cmd); struct its_collection *collection; struct kvm_vcpu *vcpu; collection = find_collection(its, coll_id); if (!its_is_collection_mapped(collection)) return E_ITS_INVALL_UNMAPPED_COLLECTION; vcpu = collection_to_vcpu(kvm, collection); vgic_its_invall(vcpu); return 0; } /* * The MOVALL command moves the pending state of all IRQs targeting one * redistributor to another. We don't hold the pending state in the VCPUs, * but in the IRQs instead, so there is really not much to do for us here. * However the spec says that no IRQ must target the old redistributor * afterwards, so we make sure that no LPI is using the associated target_vcpu. * This command affects all LPIs in the system that target that redistributor. */ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu1, *vcpu2; struct vgic_irq *irq; unsigned long intid; /* We advertise GITS_TYPER.PTA==0, making the address the vcpu ID */ vcpu1 = kvm_get_vcpu_by_id(kvm, its_cmd_get_target_addr(its_cmd)); vcpu2 = kvm_get_vcpu_by_id(kvm, its_cmd_mask_field(its_cmd, 3, 16, 32)); if (!vcpu1 || !vcpu2) return E_ITS_MOVALL_PROCNUM_OOR; if (vcpu1 == vcpu2) return 0; xa_for_each(&dist->lpi_xa, intid, irq) { irq = vgic_get_irq(kvm, intid); if (!irq) continue; update_affinity(irq, vcpu2); vgic_put_irq(kvm, irq); } vgic_its_invalidate_cache(its); return 0; } /* * The INT command injects the LPI associated with that DevID/EvID pair. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* * This function is called with the its_cmd lock held, but the ITS data * structure lock dropped. */ static int vgic_its_handle_command(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { int ret = -ENODEV; mutex_lock(&its->its_lock); switch (its_cmd_get_command(its_cmd)) { case GITS_CMD_MAPD: ret = vgic_its_cmd_handle_mapd(kvm, its, its_cmd); break; case GITS_CMD_MAPC: ret = vgic_its_cmd_handle_mapc(kvm, its, its_cmd); break; case GITS_CMD_MAPI: ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); break; case GITS_CMD_MAPTI: ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); break; case GITS_CMD_MOVI: ret = vgic_its_cmd_handle_movi(kvm, its, its_cmd); break; case GITS_CMD_DISCARD: ret = vgic_its_cmd_handle_discard(kvm, its, its_cmd); break; case GITS_CMD_CLEAR: ret = vgic_its_cmd_handle_clear(kvm, its, its_cmd); break; case GITS_CMD_MOVALL: ret = vgic_its_cmd_handle_movall(kvm, its, its_cmd); break; case GITS_CMD_INT: ret = vgic_its_cmd_handle_int(kvm, its, its_cmd); break; case GITS_CMD_INV: ret = vgic_its_cmd_handle_inv(kvm, its, its_cmd); break; case GITS_CMD_INVALL: ret = vgic_its_cmd_handle_invall(kvm, its, its_cmd); break; case GITS_CMD_SYNC: /* we ignore this command: we are in sync all of the time */ ret = 0; break; } mutex_unlock(&its->its_lock); return ret; } static u64 vgic_sanitise_its_baser(u64 reg) { reg = vgic_sanitise_field(reg, GITS_BASER_SHAREABILITY_MASK, GITS_BASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GITS_BASER_INNER_CACHEABILITY_MASK, GITS_BASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GITS_BASER_OUTER_CACHEABILITY_MASK, GITS_BASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); /* We support only one (ITS) page size: 64K */ reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K; return reg; } static u64 vgic_sanitise_its_cbaser(u64 reg) { reg = vgic_sanitise_field(reg, GITS_CBASER_SHAREABILITY_MASK, GITS_CBASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GITS_CBASER_INNER_CACHEABILITY_MASK, GITS_CBASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GITS_CBASER_OUTER_CACHEABILITY_MASK, GITS_CBASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); /* Sanitise the physical address to be 64k aligned. */ reg &= ~GENMASK_ULL(15, 12); return reg; } static unsigned long vgic_mmio_read_its_cbaser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->cbaser, addr & 7, len); } static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { /* When GITS_CTLR.Enable is 1, this register is RO. */ if (its->enabled) return; mutex_lock(&its->cmd_lock); its->cbaser = update_64bit_reg(its->cbaser, addr & 7, len, val); its->cbaser = vgic_sanitise_its_cbaser(its->cbaser); its->creadr = 0; /* * CWRITER is architecturally UNKNOWN on reset, but we need to reset * it to CREADR to make sure we start with an empty command buffer. */ its->cwriter = its->creadr; mutex_unlock(&its->cmd_lock); } #define ITS_CMD_BUFFER_SIZE(baser) ((((baser) & 0xff) + 1) << 12) #define ITS_CMD_SIZE 32 #define ITS_CMD_OFFSET(reg) ((reg) & GENMASK(19, 5)) /* Must be called with the cmd_lock held. */ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) { gpa_t cbaser; u64 cmd_buf[4]; /* Commands are only processed when the ITS is enabled. */ if (!its->enabled) return; cbaser = GITS_CBASER_ADDRESS(its->cbaser); while (its->cwriter != its->creadr) { int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, cmd_buf, ITS_CMD_SIZE); /* * If kvm_read_guest() fails, this could be due to the guest * programming a bogus value in CBASER or something else going * wrong from which we cannot easily recover. * According to section 6.3.2 in the GICv3 spec we can just * ignore that command then. */ if (!ret) vgic_its_handle_command(kvm, its, cmd_buf); its->creadr += ITS_CMD_SIZE; if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser)) its->creadr = 0; } } /* * By writing to CWRITER the guest announces new commands to be processed. * To avoid any races in the first place, we take the its_cmd lock, which * protects our ring buffer variables, so that there is only one user * per ITS handling commands at a given time. */ static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u64 reg; if (!its) return; mutex_lock(&its->cmd_lock); reg = update_64bit_reg(its->cwriter, addr & 7, len, val); reg = ITS_CMD_OFFSET(reg); if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { mutex_unlock(&its->cmd_lock); return; } its->cwriter = reg; vgic_its_process_commands(kvm, its); mutex_unlock(&its->cmd_lock); } static unsigned long vgic_mmio_read_its_cwriter(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->cwriter, addr & 0x7, len); } static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->creadr, addr & 0x7, len); } static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u32 cmd_offset; int ret = 0; mutex_lock(&its->cmd_lock); if (its->enabled) { ret = -EBUSY; goto out; } cmd_offset = ITS_CMD_OFFSET(val); if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { ret = -EINVAL; goto out; } its->creadr = cmd_offset; out: mutex_unlock(&its->cmd_lock); return ret; } #define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7) static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { u64 reg; switch (BASER_INDEX(addr)) { case 0: reg = its->baser_device_table; break; case 1: reg = its->baser_coll_table; break; default: reg = 0; break; } return extract_bytes(reg, addr & 7, len); } #define GITS_BASER_RO_MASK (GENMASK_ULL(52, 48) | GENMASK_ULL(58, 56)) static void vgic_mmio_write_its_baser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 entry_size, table_type; u64 reg, *regptr, clearbits = 0; /* When GITS_CTLR.Enable is 1, we ignore write accesses. */ if (its->enabled) return; switch (BASER_INDEX(addr)) { case 0: regptr = &its->baser_device_table; entry_size = abi->dte_esz; table_type = GITS_BASER_TYPE_DEVICE; break; case 1: regptr = &its->baser_coll_table; entry_size = abi->cte_esz; table_type = GITS_BASER_TYPE_COLLECTION; clearbits = GITS_BASER_INDIRECT; break; default: return; } reg = update_64bit_reg(*regptr, addr & 7, len, val); reg &= ~GITS_BASER_RO_MASK; reg &= ~clearbits; reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT; reg |= table_type << GITS_BASER_TYPE_SHIFT; reg = vgic_sanitise_its_baser(reg); *regptr = reg; if (!(reg & GITS_BASER_VALID)) { /* Take the its_lock to prevent a race with a save/restore */ mutex_lock(&its->its_lock); switch (table_type) { case GITS_BASER_TYPE_DEVICE: vgic_its_free_device_list(kvm, its); break; case GITS_BASER_TYPE_COLLECTION: vgic_its_free_collection_list(kvm, its); break; } mutex_unlock(&its->its_lock); } } static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu, struct vgic_its *its, gpa_t addr, unsigned int len) { u32 reg = 0; mutex_lock(&its->cmd_lock); if (its->creadr == its->cwriter) reg |= GITS_CTLR_QUIESCENT; if (its->enabled) reg |= GITS_CTLR_ENABLE; mutex_unlock(&its->cmd_lock); return reg; } static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { mutex_lock(&its->cmd_lock); /* * It is UNPREDICTABLE to enable the ITS if any of the CBASER or * device/collection BASER are invalid */ if (!its->enabled && (val & GITS_CTLR_ENABLE) && (!(its->baser_device_table & GITS_BASER_VALID) || !(its->baser_coll_table & GITS_BASER_VALID) || !(its->cbaser & GITS_CBASER_VALID))) goto out; its->enabled = !!(val & GITS_CTLR_ENABLE); if (!its->enabled) vgic_its_invalidate_cache(its); /* * Try to process any pending commands. This function bails out early * if the ITS is disabled or no commands have been queued. */ vgic_its_process_commands(kvm, its); out: mutex_unlock(&its->cmd_lock); } #define REGISTER_ITS_DESC(off, rd, wr, length, acc) \ { \ .reg_offset = off, \ .len = length, \ .access_flags = acc, \ .its_read = rd, \ .its_write = wr, \ } #define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\ { \ .reg_offset = off, \ .len = length, \ .access_flags = acc, \ .its_read = rd, \ .its_write = wr, \ .uaccess_its_write = uwr, \ } static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ } static struct vgic_register_region its_registers[] = { REGISTER_ITS_DESC(GITS_CTLR, vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4, VGIC_ACCESS_32bit), REGISTER_ITS_DESC_UACCESS(GITS_IIDR, vgic_mmio_read_its_iidr, its_mmio_write_wi, vgic_mmio_uaccess_write_its_iidr, 4, VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_TYPER, vgic_mmio_read_its_typer, its_mmio_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_CBASER, vgic_mmio_read_its_cbaser, vgic_mmio_write_its_cbaser, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_CWRITER, vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC_UACCESS(GITS_CREADR, vgic_mmio_read_its_creadr, its_mmio_write_wi, vgic_mmio_uaccess_write_its_creadr, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_BASER, vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_IDREGS_BASE, vgic_mmio_read_its_idregs, its_mmio_write_wi, 0x30, VGIC_ACCESS_32bit), }; /* This is called on setting the LPI enable bit in the redistributor. */ void vgic_enable_lpis(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ)) its_sync_lpi_pending_table(vcpu); } static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its, u64 addr) { struct vgic_io_device *iodev = &its->iodev; int ret; mutex_lock(&kvm->slots_lock); if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -EBUSY; goto out; } its->vgic_its_base = addr; iodev->regions = its_registers; iodev->nr_regions = ARRAY_SIZE(its_registers); kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops); iodev->base_addr = its->vgic_its_base; iodev->iodev_type = IODEV_ITS; iodev->its = its; ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr, KVM_VGIC_V3_ITS_SIZE, &iodev->dev); out: mutex_unlock(&kvm->slots_lock); return ret; } #define INITIAL_BASER_VALUE \ (GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) | \ GITS_BASER_PAGE_SIZE_64K) #define INITIAL_PROPBASER_VALUE \ (GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)) static int vgic_its_create(struct kvm_device *dev, u32 type) { int ret; struct vgic_its *its; if (type != KVM_DEV_TYPE_ARM_VGIC_ITS) return -ENODEV; its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL_ACCOUNT); if (!its) return -ENOMEM; mutex_lock(&dev->kvm->arch.config_lock); if (vgic_initialized(dev->kvm)) { ret = vgic_v4_init(dev->kvm); if (ret < 0) { mutex_unlock(&dev->kvm->arch.config_lock); kfree(its); return ret; } } mutex_init(&its->its_lock); mutex_init(&its->cmd_lock); /* Yep, even more trickery for lock ordering... */ #ifdef CONFIG_LOCKDEP mutex_lock(&its->cmd_lock); mutex_lock(&its->its_lock); mutex_unlock(&its->its_lock); mutex_unlock(&its->cmd_lock); #endif its->vgic_its_base = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&its->device_list); INIT_LIST_HEAD(&its->collection_list); xa_init(&its->translation_cache); dev->kvm->arch.vgic.msis_require_devid = true; dev->kvm->arch.vgic.has_its = true; its->enabled = false; its->dev = dev; its->baser_device_table = INITIAL_BASER_VALUE | ((u64)GITS_BASER_TYPE_DEVICE << GITS_BASER_TYPE_SHIFT); its->baser_coll_table = INITIAL_BASER_VALUE | ((u64)GITS_BASER_TYPE_COLLECTION << GITS_BASER_TYPE_SHIFT); dev->kvm->arch.vgic.propbaser = INITIAL_PROPBASER_VALUE; dev->private = its; ret = vgic_its_set_abi(its, NR_ITS_ABIS - 1); mutex_unlock(&dev->kvm->arch.config_lock); return ret; } static void vgic_its_destroy(struct kvm_device *kvm_dev) { struct kvm *kvm = kvm_dev->kvm; struct vgic_its *its = kvm_dev->private; mutex_lock(&its->its_lock); vgic_its_free_device_list(kvm, its); vgic_its_free_collection_list(kvm, its); vgic_its_invalidate_cache(its); xa_destroy(&its->translation_cache); mutex_unlock(&its->its_lock); kfree(its); kfree(kvm_dev);/* alloc by kvm_ioctl_create_device, free by .destroy */ } static int vgic_its_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) { const struct vgic_register_region *region; gpa_t offset = attr->attr; int align; align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7; if (offset & align) return -EINVAL; region = vgic_find_mmio_region(its_registers, ARRAY_SIZE(its_registers), offset); if (!region) return -ENXIO; return 0; } static int vgic_its_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, u64 *reg, bool is_write) { const struct vgic_register_region *region; struct vgic_its *its; gpa_t addr, offset; unsigned int len; int align, ret = 0; its = dev->private; offset = attr->attr; /* * Although the spec supports upper/lower 32-bit accesses to * 64-bit ITS registers, the userspace ABI requires 64-bit * accesses to all 64-bit wide registers. We therefore only * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID * registers */ if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4)) align = 0x3; else align = 0x7; if (offset & align) return -EINVAL; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -ENXIO; goto out; } region = vgic_find_mmio_region(its_registers, ARRAY_SIZE(its_registers), offset); if (!region) { ret = -ENXIO; goto out; } addr = its->vgic_its_base + offset; len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4; if (is_write) { if (region->uaccess_its_write) ret = region->uaccess_its_write(dev->kvm, its, addr, len, *reg); else region->its_write(dev->kvm, its, addr, len, *reg); } else { *reg = region->its_read(dev->kvm, its, addr, len); } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return ret; } static u32 compute_next_devid_offset(struct list_head *h, struct its_device *dev) { struct its_device *next; u32 next_offset; if (list_is_last(&dev->dev_list, h)) return 0; next = list_next_entry(dev, dev_list); next_offset = next->device_id - dev->device_id; return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET); } static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite) { struct its_ite *next; u32 next_offset; if (list_is_last(&ite->ite_list, h)) return 0; next = list_next_entry(ite, ite_list); next_offset = next->event_id - ite->event_id; return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET); } /** * typedef entry_fn_t - Callback called on a table entry restore path * @its: its handle * @id: id of the entry * @entry: pointer to the entry * @opaque: pointer to an opaque data * * Return: < 0 on error, 0 if last element was identified, id offset to next * element otherwise */ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry, void *opaque); /** * scan_its_table - Scan a contiguous table in guest RAM and applies a function * to each entry * * @its: its handle * @base: base gpa of the table * @size: size of the table in bytes * @esz: entry size in bytes * @start_id: the ID of the first entry in the table * (non zero for 2d level tables) * @fn: function to apply on each entry * @opaque: pointer to opaque data * * Return: < 0 on error, 0 if last element was identified, 1 otherwise * (the last element may not be found on second level tables) */ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, int start_id, entry_fn_t fn, void *opaque) { struct kvm *kvm = its->dev->kvm; unsigned long len = size; int id = start_id; gpa_t gpa = base; char entry[ESZ_MAX]; int ret; memset(entry, 0, esz); while (true) { int next_offset; size_t byte_offset; ret = kvm_read_guest_lock(kvm, gpa, entry, esz); if (ret) return ret; next_offset = fn(its, id, entry, opaque); if (next_offset <= 0) return next_offset; byte_offset = next_offset * esz; if (byte_offset >= len) break; id += next_offset; gpa += byte_offset; len -= byte_offset; } return 1; } /* * vgic_its_save_ite - Save an interrupt translation entry at @gpa */ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, struct its_ite *ite, gpa_t gpa) { u32 next_offset; u64 val; next_offset = compute_next_eventid_offset(&dev->itt_head, ite); val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) | ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); return vgic_its_write_entry_lock(its, gpa, val, ite); } /** * vgic_its_restore_ite - restore an interrupt translation entry * * @its: its handle * @event_id: id used for indexing * @ptr: pointer to the ITE entry * @opaque: pointer to the its_device */ static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, void *ptr, void *opaque) { struct its_device *dev = opaque; struct its_collection *collection; struct kvm *kvm = its->dev->kvm; struct kvm_vcpu *vcpu = NULL; u64 val; u64 *p = (u64 *)ptr; struct vgic_irq *irq; u32 coll_id, lpi_id; struct its_ite *ite; u32 offset; val = *p; val = le64_to_cpu(val); coll_id = val & KVM_ITS_ITE_ICID_MASK; lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT; if (!lpi_id) return 1; /* invalid entry, no choice but to scan next entry */ if (lpi_id < VGIC_MIN_LPI) return -EINVAL; offset = val >> KVM_ITS_ITE_NEXT_SHIFT; if (event_id + offset >= BIT_ULL(dev->num_eventid_bits)) return -EINVAL; collection = find_collection(its, coll_id); if (!collection) return -EINVAL; if (!vgic_its_check_event_id(its, dev, event_id)) return -EINVAL; ite = vgic_its_alloc_ite(dev, collection, event_id); if (IS_ERR(ite)) return PTR_ERR(ite); if (its_is_collection_mapped(collection)) vcpu = kvm_get_vcpu_by_id(kvm, collection->target_addr); irq = vgic_add_lpi(kvm, lpi_id, vcpu); if (IS_ERR(irq)) { its_free_ite(kvm, ite); return PTR_ERR(irq); } ite->irq = irq; return offset; } static int vgic_its_ite_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct its_ite *itea = container_of(a, struct its_ite, ite_list); struct its_ite *iteb = container_of(b, struct its_ite, ite_list); if (itea->event_id < iteb->event_id) return -1; else return 1; } static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); gpa_t base = device->itt_addr; struct its_ite *ite; int ret; int ite_esz = abi->ite_esz; list_sort(NULL, &device->itt_head, vgic_its_ite_cmp); list_for_each_entry(ite, &device->itt_head, ite_list) { gpa_t gpa = base + ite->event_id * ite_esz; /* * If an LPI carries the HW bit, this means that this * interrupt is controlled by GICv4, and we do not * have direct access to that state without GICv4.1. * Let's simply fail the save operation... */ if (ite->irq->hw && !kvm_vgic_global_state.has_gicv4_1) return -EACCES; ret = vgic_its_save_ite(its, device, ite, gpa); if (ret) return ret; } return 0; } /** * vgic_its_restore_itt - restore the ITT of a device * * @its: its handle * @dev: device handle * * Return 0 on success, < 0 on error */ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); gpa_t base = dev->itt_addr; int ret; int ite_esz = abi->ite_esz; size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz; ret = scan_its_table(its, base, max_size, ite_esz, 0, vgic_its_restore_ite, dev); /* scan_its_table returns +1 if all ITEs are invalid */ if (ret > 0) ret = 0; return ret; } /** * vgic_its_save_dte - Save a device table entry at a given GPA * * @its: ITS handle * @dev: ITS device * @ptr: GPA */ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, gpa_t ptr) { u64 val, itt_addr_field; u32 next_offset; itt_addr_field = dev->itt_addr >> 8; next_offset = compute_next_devid_offset(&its->device_list, dev); val = (1ULL << KVM_ITS_DTE_VALID_SHIFT | ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) | (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); return vgic_its_write_entry_lock(its, ptr, val, dte); } /** * vgic_its_restore_dte - restore a device table entry * * @its: its handle * @id: device id the DTE corresponds to * @ptr: kernel VA where the 8 byte DTE is located * @opaque: unused * * Return: < 0 on error, 0 if the dte is the last one, id offset to the * next dte otherwise */ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, void *ptr, void *opaque) { struct its_device *dev; u64 baser = its->baser_device_table; gpa_t itt_addr; u8 num_eventid_bits; u64 entry = *(u64 *)ptr; bool valid; u32 offset; int ret; entry = le64_to_cpu(entry); valid = entry >> KVM_ITS_DTE_VALID_SHIFT; num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1; itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK) >> KVM_ITS_DTE_ITTADDR_SHIFT) << 8; if (!valid) return 1; /* dte entry is valid */ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; if (!vgic_its_check_id(its, baser, id, NULL)) return -EINVAL; dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits); if (IS_ERR(dev)) return PTR_ERR(dev); ret = vgic_its_restore_itt(its, dev); if (ret) { vgic_its_free_device(its->dev->kvm, its, dev); return ret; } return offset; } static int vgic_its_device_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct its_device *deva = container_of(a, struct its_device, dev_list); struct its_device *devb = container_of(b, struct its_device, dev_list); if (deva->device_id < devb->device_id) return -1; else return 1; } /* * vgic_its_save_device_tables - Save the device table and all ITT * into guest RAM * * L1/L2 handling is hidden by vgic_its_check_id() helper which directly * returns the GPA of the device entry */ static int vgic_its_save_device_tables(struct vgic_its *its) { u64 baser = its->baser_device_table; struct its_device *dev; if (!(baser & GITS_BASER_VALID)) return 0; list_sort(NULL, &its->device_list, vgic_its_device_cmp); list_for_each_entry(dev, &its->device_list, dev_list) { int ret; gpa_t eaddr; if (!vgic_its_check_id(its, baser, dev->device_id, &eaddr)) return -EINVAL; ret = vgic_its_save_itt(its, dev); if (ret) return ret; ret = vgic_its_save_dte(its, dev, eaddr); if (ret) return ret; } return 0; } /** * handle_l1_dte - callback used for L1 device table entries (2 stage case) * * @its: its handle * @id: index of the entry in the L1 table * @addr: kernel VA * @opaque: unused * * L1 table entries are scanned by steps of 1 entry * Return < 0 if error, 0 if last dte was found when scanning the L2 * table, +1 otherwise (meaning next L1 entry must be scanned) */ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr, void *opaque) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int l2_start_id = id * (SZ_64K / abi->dte_esz); u64 entry = *(u64 *)addr; int dte_esz = abi->dte_esz; gpa_t gpa; int ret; entry = le64_to_cpu(entry); if (!(entry & KVM_ITS_L1E_VALID_MASK)) return 1; gpa = entry & KVM_ITS_L1E_ADDR_MASK; ret = scan_its_table(its, gpa, SZ_64K, dte_esz, l2_start_id, vgic_its_restore_dte, NULL); return ret; } /* * vgic_its_restore_device_tables - Restore the device table and all ITT * from guest RAM to internal data structs */ static int vgic_its_restore_device_tables(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_device_table; int l1_esz, ret; int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; gpa_t l1_gpa; if (!(baser & GITS_BASER_VALID)) return 0; l1_gpa = GITS_BASER_ADDR_48_to_52(baser); if (baser & GITS_BASER_INDIRECT) { l1_esz = GITS_LVL1_ENTRY_SIZE; ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, handle_l1_dte, NULL); } else { l1_esz = abi->dte_esz; ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, vgic_its_restore_dte, NULL); } /* scan_its_table returns +1 if all entries are invalid */ if (ret > 0) ret = 0; if (ret < 0) vgic_its_free_device_list(its->dev->kvm, its); return ret; } static int vgic_its_save_cte(struct vgic_its *its, struct its_collection *collection, gpa_t gpa) { u64 val; val = (1ULL << KVM_ITS_CTE_VALID_SHIFT | ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); return vgic_its_write_entry_lock(its, gpa, val, cte); } /* * Restore a collection entry into the ITS collection table. * Return +1 on success, 0 if the entry was invalid (which should be * interpreted as end-of-table), and a negative error value for generic errors. */ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa) { struct its_collection *collection; struct kvm *kvm = its->dev->kvm; u32 target_addr, coll_id; u64 val; int ret; ret = vgic_its_read_entry_lock(its, gpa, &val, cte); if (ret) return ret; val = le64_to_cpu(val); if (!(val & KVM_ITS_CTE_VALID_MASK)) return 0; target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT); coll_id = val & KVM_ITS_CTE_ICID_MASK; if (target_addr != COLLECTION_NOT_MAPPED && !kvm_get_vcpu_by_id(kvm, target_addr)) return -EINVAL; collection = find_collection(its, coll_id); if (collection) return -EEXIST; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return -EINVAL; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; collection->target_addr = target_addr; return 1; } /* * vgic_its_save_collection_table - Save the collection table into * guest RAM */ static int vgic_its_save_collection_table(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_coll_table; gpa_t gpa = GITS_BASER_ADDR_48_to_52(baser); struct its_collection *collection; size_t max_size, filled = 0; int ret, cte_esz = abi->cte_esz; if (!(baser & GITS_BASER_VALID)) return 0; max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; list_for_each_entry(collection, &its->collection_list, coll_list) { ret = vgic_its_save_cte(its, collection, gpa); if (ret) return ret; gpa += cte_esz; filled += cte_esz; } if (filled == max_size) return 0; /* * table is not fully filled, add a last dummy element * with valid bit unset */ return vgic_its_write_entry_lock(its, gpa, 0ULL, cte); } /* * vgic_its_restore_collection_table - reads the collection table * in guest memory and restores the ITS internal state. Requires the * BASER registers to be restored before. */ static int vgic_its_restore_collection_table(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_coll_table; int cte_esz = abi->cte_esz; size_t max_size, read = 0; gpa_t gpa; int ret; if (!(baser & GITS_BASER_VALID)) return 0; gpa = GITS_BASER_ADDR_48_to_52(baser); max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; while (read < max_size) { ret = vgic_its_restore_cte(its, gpa); if (ret <= 0) break; gpa += cte_esz; read += cte_esz; } if (ret > 0) return 0; if (ret < 0) vgic_its_free_collection_list(its->dev->kvm, its); return ret; } /* * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM * according to v0 ABI */ static int vgic_its_save_tables_v0(struct vgic_its *its) { int ret; ret = vgic_its_save_device_tables(its); if (ret) return ret; return vgic_its_save_collection_table(its); } /* * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM * to internal data structs according to V0 ABI * */ static int vgic_its_restore_tables_v0(struct vgic_its *its) { int ret; ret = vgic_its_restore_collection_table(its); if (ret) return ret; ret = vgic_its_restore_device_tables(its); if (ret) vgic_its_free_collection_list(its->dev->kvm, its); return ret; } static int vgic_its_commit_v0(struct vgic_its *its) { const struct vgic_its_abi *abi; abi = vgic_its_get_abi(its); its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK; its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK; its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5) << GITS_BASER_ENTRY_SIZE_SHIFT); its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5) << GITS_BASER_ENTRY_SIZE_SHIFT); return 0; } static void vgic_its_reset(struct kvm *kvm, struct vgic_its *its) { /* We need to keep the ABI specific field values */ its->baser_coll_table &= ~GITS_BASER_VALID; its->baser_device_table &= ~GITS_BASER_VALID; its->cbaser = 0; its->creadr = 0; its->cwriter = 0; its->enabled = 0; vgic_its_free_device_list(kvm, its); vgic_its_free_collection_list(kvm, its); } static int vgic_its_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_ITS_ADDR_TYPE: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; case KVM_DEV_ARM_ITS_CTRL_RESET: return 0; case KVM_DEV_ARM_ITS_SAVE_TABLES: return 0; case KVM_DEV_ARM_ITS_RESTORE_TABLES: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: return vgic_its_has_attr_regs(dev, attr); } return -ENXIO; } static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ return 0; mutex_lock(&kvm->lock); if (!lock_all_vcpus(kvm)) { mutex_unlock(&kvm->lock); return -EBUSY; } mutex_lock(&kvm->arch.config_lock); mutex_lock(&its->its_lock); switch (attr) { case KVM_DEV_ARM_ITS_CTRL_RESET: vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: ret = abi->save_tables(its); break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); break; } mutex_unlock(&its->its_lock); mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); mutex_unlock(&kvm->lock); return ret; } /* * kvm_arch_allow_write_without_running_vcpu - allow writing guest memory * without the running VCPU when dirty ring is enabled. * * The running VCPU is required to track dirty guest pages when dirty ring * is enabled. Otherwise, the backup bitmap should be used to track the * dirty guest pages. When vgic/its tables are being saved, the backup * bitmap is used to track the dirty guest pages due to the missed running * VCPU in the period. */ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; return dist->table_write_in_progress; } static int vgic_its_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { struct vgic_its *its = dev->private; int ret; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; unsigned long type = (unsigned long)attr->attr; u64 addr; if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; if (copy_from_user(&addr, uaddr, sizeof(addr))) return -EFAULT; ret = vgic_check_iorange(dev->kvm, its->vgic_its_base, addr, SZ_64K, KVM_VGIC_V3_ITS_SIZE); if (ret) return ret; return vgic_register_its_iodev(dev->kvm, its, addr); } case KVM_DEV_ARM_VGIC_GRP_CTRL: return vgic_its_ctrl(dev->kvm, its, attr->attr); case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; u64 reg; if (get_user(reg, uaddr)) return -EFAULT; return vgic_its_attr_regs_access(dev, attr, ®, true); } } return -ENXIO; } static int vgic_its_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: { struct vgic_its *its = dev->private; u64 addr = its->vgic_its_base; u64 __user *uaddr = (u64 __user *)(long)attr->addr; unsigned long type = (unsigned long)attr->attr; if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; if (copy_to_user(uaddr, &addr, sizeof(addr))) return -EFAULT; break; } case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; u64 reg; int ret; ret = vgic_its_attr_regs_access(dev, attr, ®, false); if (ret) return ret; return put_user(reg, uaddr); } default: return -ENXIO; } return 0; } static struct kvm_device_ops kvm_arm_vgic_its_ops = { .name = "kvm-arm-vgic-its", .create = vgic_its_create, .destroy = vgic_its_destroy, .set_attr = vgic_its_set_attr, .get_attr = vgic_its_get_attr, .has_attr = vgic_its_has_attr, }; int kvm_vgic_register_its_device(void) { return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } |
| 196 196 196 1 195 35 160 1 199 1 198 66 66 66 66 66 66 199 198 198 199 199 199 66 199 199 198 66 66 199 199 199 199 198 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * hugetlbpage-backed filesystem. Based on ramfs. * * Nadia Yvette Chambers, 2002 * * Copyright (C) 2002 Linus Torvalds. * License: GPL */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/thread_info.h> #include <asm/current.h> #include <linux/falloc.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/kernel.h> #include <linux/writeback.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/string.h> #include <linux/capability.h> #include <linux/ctype.h> #include <linux/backing-dev.h> #include <linux/hugetlb.h> #include <linux/pagevec.h> #include <linux/fs_parser.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/dnotify.h> #include <linux/statfs.h> #include <linux/security.h> #include <linux/magic.h> #include <linux/migrate.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <linux/sched/mm.h> #define CREATE_TRACE_POINTS #include <trace/events/hugetlbfs.h> static const struct address_space_operations hugetlbfs_aops; static const struct file_operations hugetlbfs_file_operations; static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT }; struct hugetlbfs_fs_context { struct hstate *hstate; unsigned long long max_size_opt; unsigned long long min_size_opt; long max_hpages; long nr_inodes; long min_hpages; enum hugetlbfs_size_type max_val_type; enum hugetlbfs_size_type min_val_type; kuid_t uid; kgid_t gid; umode_t mode; }; int sysctl_hugetlb_shm_group; enum hugetlb_param { Opt_gid, Opt_min_size, Opt_mode, Opt_nr_inodes, Opt_pagesize, Opt_size, Opt_uid, }; static const struct fs_parameter_spec hugetlb_fs_parameters[] = { fsparam_gid ("gid", Opt_gid), fsparam_string("min_size", Opt_min_size), fsparam_u32oct("mode", Opt_mode), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("pagesize", Opt_pagesize), fsparam_string("size", Opt_size), fsparam_uid ("uid", Opt_uid), {} }; /* * Mask used when checking the page offset value passed in via system * calls. This value will be converted to a loff_t which is signed. * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the * value. The extra bit (- 1 in the shift value) is to take the sign * bit into account. */ #define PGOFF_LOFFT_MAX \ (((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1))) static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has * already been checked by prepare_hugepage_range. If you add * any error returns here, do so after setting VM_HUGETLB, so * is_vm_hugetlb_page tests below unmap_region go the right * way when do_mmap unwinds (may be important on powerpc * and ia64). */ vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND); vma->vm_ops = &hugetlb_vm_ops; ret = seal_check_write(info->seals, vma); if (ret) return ret; /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can * only happen on architectures where sizeof(loff_t) == * sizeof(unsigned long). So, only check in those instances. */ if (sizeof(unsigned long) == sizeof(loff_t)) { if (vma->vm_pgoff & PGOFF_LOFFT_MAX) return -EINVAL; } /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* check for overflow */ if (len < vma_len) return -EINVAL; inode_lock(inode); file_accessed(file); ret = -ENOMEM; vm_flags = vma->vm_flags; /* * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip * reserving here. Note: only for SHM hugetlbfs file, the inode * flag S_PRIVATE is set. */ if (inode->i_flags & S_PRIVATE) vm_flags |= VM_NORESERVE; if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, vm_flags)) goto out; ret = 0; if (vma->vm_flags & VM_WRITE && inode->i_size < len) i_size_write(inode, len); out: inode_unlock(inode); return ret; } /* * Called under mmap_write_lock(mm). */ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long addr0 = 0; struct hstate *h = hstate_file(file); if (len & ~huge_page_mask(h)) return -EINVAL; if (flags & MAP_FIXED) { if (addr & ~huge_page_mask(h)) return -EINVAL; if (prepare_hugepage_range(file, addr, len)) return -EINVAL; } if (addr) addr0 = ALIGN(addr, huge_page_size(h)); return mm_get_unmapped_area_vmflags(current->mm, file, addr0, len, pgoff, flags, 0); } /* * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset. * Returns the maximum number of bytes one can read without touching the 1st raw * HWPOISON subpage. * * The implementation borrows the iteration logic from copy_page_to_iter*. */ static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t bytes) { size_t n = 0; size_t res = 0; /* First subpage to start the loop. */ page = nth_page(page, offset / PAGE_SIZE); offset %= PAGE_SIZE; while (1) { if (is_raw_hwpoison_page_in_hugepage(page)) break; /* Safe to read n bytes without touching HWPOISON subpage. */ n = min(bytes, (size_t)PAGE_SIZE - offset); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page = nth_page(page, 1); offset = 0; } } return res; } /* * Support for read() - Find the page attached to f_mapping and copy out the * data. This provides functionality similar to filemap_read(). */ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct hstate *h = hstate_file(file); struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; unsigned long index = iocb->ki_pos >> huge_page_shift(h); unsigned long offset = iocb->ki_pos & ~huge_page_mask(h); unsigned long end_index; loff_t isize; ssize_t retval = 0; while (iov_iter_count(to)) { struct folio *folio; size_t nr, copied, want; /* nr is the maximum number of bytes to copy from this page */ nr = huge_page_size(h); isize = i_size_read(inode); if (!isize) break; end_index = (isize - 1) >> huge_page_shift(h); if (index > end_index) break; if (index == end_index) { nr = ((isize - 1) & ~huge_page_mask(h)) + 1; if (nr <= offset) break; } nr = nr - offset; /* Find the folio */ folio = filemap_lock_hugetlb_folio(h, mapping, index); if (IS_ERR(folio)) { /* * We have a HOLE, zero out the user-buffer for the * length of the hole or request. */ copied = iov_iter_zero(nr, to); } else { folio_unlock(folio); if (!folio_test_hwpoison(folio)) want = nr; else { /* * Adjust how many bytes safe to read without * touching the 1st raw HWPOISON subpage after * offset. */ want = adjust_range_hwpoison(&folio->page, offset, nr); if (want == 0) { folio_put(folio); retval = -EIO; break; } } /* * We have the folio, copy it to user space buffer. */ copied = copy_folio_to_iter(folio, offset, want, to); folio_put(folio); } offset += copied; retval += copied; if (copied != nr && iov_iter_count(to)) { if (!retval) retval = -EFAULT; break; } index += offset >> huge_page_shift(h); offset &= ~huge_page_mask(h); } iocb->ki_pos = ((loff_t)index << huge_page_shift(h)) + offset; return retval; } static int hugetlbfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { return -EINVAL; } static int hugetlbfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { BUG(); return -EINVAL; } static void hugetlb_delete_from_page_cache(struct folio *folio) { folio_clear_dirty(folio); folio_clear_uptodate(folio); filemap_remove_folio(folio); } /* * Called with i_mmap_rwsem held for inode based vma maps. This makes * sure vma (and vm_mm) will not go away. We also hold the hugetlb fault * mutex for the page in the mapping. So, we can not race with page being * faulted into the vma. */ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { pte_t *ptep, pte; ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma))); if (!ptep) return false; pte = huge_ptep_get(vma->vm_mm, addr, ptep); if (huge_pte_none(pte) || !pte_present(pte)) return false; if (pte_page(pte) == page) return true; return false; } /* * Can vma_offset_start/vma_offset_end overflow on 32-bit arches? * No, because the interval tree returns us only those vmas * which overlap the truncated area starting at pgoff, * and no vma on a 32-bit arch can span beyond the 4GB. */ static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start) { unsigned long offset = 0; if (vma->vm_pgoff < start) offset = (start - vma->vm_pgoff) << PAGE_SHIFT; return vma->vm_start + offset; } static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end) { unsigned long t_end; if (!end) return vma->vm_end; t_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + vma->vm_start; if (t_end > vma->vm_end) t_end = vma->vm_end; return t_end; } /* * Called with hugetlb fault mutex held. Therefore, no more mappings to * this folio can be created while executing the routine. */ static void hugetlb_unmap_file_folio(struct hstate *h, struct address_space *mapping, struct folio *folio, pgoff_t index) { struct rb_root_cached *root = &mapping->i_mmap; struct hugetlb_vma_lock *vma_lock; struct page *page = &folio->page; struct vm_area_struct *vma; unsigned long v_start; unsigned long v_end; pgoff_t start, end; start = index * pages_per_huge_page(h); end = (index + 1) * pages_per_huge_page(h); i_mmap_lock_write(mapping); retry: vma_lock = NULL; vma_interval_tree_foreach(vma, root, start, end - 1) { v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); if (!hugetlb_vma_maps_page(vma, v_start, page)) continue; if (!hugetlb_vma_trylock_write(vma)) { vma_lock = vma->vm_private_data; /* * If we can not get vma lock, we need to drop * immap_sema and take locks in order. First, * take a ref on the vma_lock structure so that * we can be guaranteed it will not go away when * dropping immap_sema. */ kref_get(&vma_lock->refs); break; } unmap_hugepage_range(vma, v_start, v_end, NULL, ZAP_FLAG_DROP_MARKER); hugetlb_vma_unlock_write(vma); } i_mmap_unlock_write(mapping); if (vma_lock) { /* * Wait on vma_lock. We know it is still valid as we have * a reference. We must 'open code' vma locking as we do * not know if vma_lock is still attached to vma. */ down_write(&vma_lock->rw_sema); i_mmap_lock_write(mapping); vma = vma_lock->vma; if (!vma) { /* * If lock is no longer attached to vma, then just * unlock, drop our reference and retry looking for * other vmas. */ up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); goto retry; } /* * vma_lock is still attached to vma. Check to see if vma * still maps page and if so, unmap. */ v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); if (hugetlb_vma_maps_page(vma, v_start, page)) unmap_hugepage_range(vma, v_start, v_end, NULL, ZAP_FLAG_DROP_MARKER); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); hugetlb_vma_unlock_write(vma); goto retry; } } static void hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, zap_flags_t zap_flags) { struct vm_area_struct *vma; /* * end == 0 indicates that the entire range after start should be * unmapped. Note, end is exclusive, whereas the interval tree takes * an inclusive "last". */ vma_interval_tree_foreach(vma, root, start, end ? end - 1 : ULONG_MAX) { unsigned long v_start; unsigned long v_end; if (!hugetlb_vma_trylock_write(vma)) continue; v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags); /* * Note that vma lock only exists for shared/non-private * vmas. Therefore, lock is not held when calling * unmap_hugepage_range for private vmas. */ hugetlb_vma_unlock_write(vma); } } /* * Called with hugetlb fault mutex held. * Returns true if page was actually removed, false otherwise. */ static bool remove_inode_single_folio(struct hstate *h, struct inode *inode, struct address_space *mapping, struct folio *folio, pgoff_t index, bool truncate_op) { bool ret = false; /* * If folio is mapped, it was faulted in after being * unmapped in caller. Unmap (again) while holding * the fault mutex. The mutex will prevent faults * until we finish removing the folio. */ if (unlikely(folio_mapped(folio))) hugetlb_unmap_file_folio(h, mapping, folio, index); folio_lock(folio); /* * We must remove the folio from page cache before removing * the region/ reserve map (hugetlb_unreserve_pages). In * rare out of memory conditions, removal of the region/reserve * map could fail. Correspondingly, the subpool and global * reserve usage count can need to be adjusted. */ VM_BUG_ON_FOLIO(folio_test_hugetlb_restore_reserve(folio), folio); hugetlb_delete_from_page_cache(folio); ret = true; if (!truncate_op) { if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1))) hugetlb_fix_reserve_counts(inode); } folio_unlock(folio); return ret; } /* * remove_inode_hugepages handles two distinct cases: truncation and hole * punch. There are subtle differences in operation for each case. * * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserve * maps and global counts. Page faults can race with truncation. * During faults, hugetlb_no_page() checks i_size before page allocation, * and again after obtaining page table lock. It will 'back out' * allocations in the truncated range. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserve map * deleted. The region/reserve map for ranges without associated * pages are not modified. Page faults can race with hole punch. * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, loff_t lend) { struct hstate *h = hstate_inode(inode); struct address_space *mapping = &inode->i_data; const pgoff_t end = lend >> PAGE_SHIFT; struct folio_batch fbatch; pgoff_t next, index; int i, freed = 0; bool truncate_op = (lend == LLONG_MAX); folio_batch_init(&fbatch); next = lstart >> PAGE_SHIFT; while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) { for (i = 0; i < folio_batch_count(&fbatch); ++i) { struct folio *folio = fbatch.folios[i]; u32 hash = 0; index = folio->index >> huge_page_order(h); hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Remove folio that was part of folio_batch. */ if (remove_inode_single_folio(h, inode, mapping, folio, index, truncate_op)) freed++; mutex_unlock(&hugetlb_fault_mutex_table[hash]); } folio_batch_release(&fbatch); cond_resched(); } if (truncate_op) (void)hugetlb_unreserve_pages(inode, lstart >> huge_page_shift(h), LONG_MAX, freed); } static void hugetlbfs_evict_inode(struct inode *inode) { struct resv_map *resv_map; trace_hugetlbfs_evict_inode(inode); remove_inode_hugepages(inode, 0, LLONG_MAX); /* * Get the resv_map from the address space embedded in the inode. * This is the address space which points to any resv_map allocated * at inode creation time. If this is a device special inode, * i_mapping may not point to the original address space. */ resv_map = (struct resv_map *)(&inode->i_data)->i_private_data; /* Only regular and link inodes have associated reserve maps */ if (resv_map) resv_map_release(&resv_map->refs); clear_inode(inode); } static void hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); BUG_ON(offset & ~huge_page_mask(h)); pgoff = offset >> PAGE_SHIFT; i_size_write(inode, offset); i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0, ZAP_FLAG_DROP_MARKER); i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); } static void hugetlbfs_zero_partial_page(struct hstate *h, struct address_space *mapping, loff_t start, loff_t end) { pgoff_t idx = start >> huge_page_shift(h); struct folio *folio; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) return; start = start & ~huge_page_mask(h); end = end & ~huge_page_mask(h); if (!end) end = huge_page_size(h); folio_zero_segment(folio, (size_t)start, (size_t)end); folio_unlock(folio); folio_put(folio); } static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) { struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); loff_t hpage_size = huge_page_size(h); loff_t hole_start, hole_end; /* * hole_start and hole_end indicate the full pages within the hole. */ hole_start = round_up(offset, hpage_size); hole_end = round_down(offset + len, hpage_size); inode_lock(inode); /* protected by i_rwsem */ if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { inode_unlock(inode); return -EPERM; } i_mmap_lock_write(mapping); /* If range starts before first full page, zero partial page. */ if (offset < hole_start) hugetlbfs_zero_partial_page(h, mapping, offset, min(offset + len, hole_start)); /* Unmap users of full pages in the hole. */ if (hole_end > hole_start) { if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT, 0); } /* If range extends beyond last full page, zero partial page. */ if ((offset + len) > hole_end && (offset + len) > hole_start) hugetlbfs_zero_partial_page(h, mapping, hole_end, offset + len); i_mmap_unlock_write(mapping); /* Remove full pages from the file. */ if (hole_end > hole_start) remove_inode_hugepages(inode, hole_start, hole_end); inode_unlock(inode); return 0; } static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); struct vm_area_struct pseudo_vma; struct mm_struct *mm = current->mm; loff_t hpage_size = huge_page_size(h); unsigned long hpage_shift = huge_page_shift(h); pgoff_t start, index, end; int error; u32 hash; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) { error = hugetlbfs_punch_hole(inode, offset, len); goto out_nolock; } /* * Default preallocate case. * For this range, start is rounded down and end is rounded up * as well as being converted to page offsets. */ start = offset >> hpage_shift; end = (offset + len + hpage_size - 1) >> hpage_shift; inode_lock(inode); /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ error = inode_newsize_ok(inode, offset + len); if (error) goto out; if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { error = -EPERM; goto out; } /* * Initialize a pseudo vma as this is required by the huge page * allocation routines. */ vma_init(&pseudo_vma, mm); vm_flags_init(&pseudo_vma, VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; for (index = start; index < end; index++) { /* * This is supposed to be the vaddr where the page is being * faulted in, but we have no vaddr here. */ struct folio *folio; unsigned long addr; cond_resched(); /* * fallocate(2) manpage permits EINTR; we may have been * interrupted because we are using up too much memory. */ if (signal_pending(current)) { error = -EINTR; break; } /* addr is the offset within the file (zero based) */ addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ folio = filemap_get_folio(mapping, index << huge_page_order(h)); if (!IS_ERR(folio)) { folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); continue; } /* * Allocate folio without setting the avoid_reserve argument. * There certainly are no reserves associated with the * pseudo_vma. However, there could be shared mappings with * reserves for the file at the inode level. If we fallocate * folios in these areas, we need to consume the reserves * to keep reservation accounting consistent. */ folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0); if (IS_ERR(folio)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); error = PTR_ERR(folio); goto out; } folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size)); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { restore_reserve_on_error(h, &pseudo_vma, addr, folio); folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; } mutex_unlock(&hugetlb_fault_mutex_table[hash]); folio_set_hugetlb_migratable(folio); /* * folio_unlock because locked by hugetlb_add_to_page_cache() * folio_put() due to reference from alloc_hugetlb_folio() */ folio_unlock(folio); folio_put(folio); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode_set_ctime_current(inode); out: inode_unlock(inode); out_nolock: trace_hugetlbfs_fallocate(inode, mode, offset, len, error); return error; } static int hugetlbfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct hstate *h = hstate_inode(inode); int error; unsigned int ia_valid = attr->ia_valid; struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); error = setattr_prepare(idmap, dentry, attr); if (error) return error; trace_hugetlbfs_setattr(inode, dentry, attr); if (ia_valid & ATTR_SIZE) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; if (newsize & ~huge_page_mask(h)) return -EINVAL; /* protected by i_rwsem */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; hugetlb_vmtruncate(inode, newsize); } setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); return 0; } static struct inode *hugetlbfs_get_root(struct super_block *sb, struct hugetlbfs_fs_context *ctx) { struct inode *inode; inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = S_IFDIR | ctx->mode; inode->i_uid = ctx->uid; inode->i_gid = ctx->gid; simple_inode_init_ts(inode); inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); lockdep_annotate_inode_mutex_key(inode); } return inode; } /* * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never * be taken from reclaim -- unlike regular filesystems. This needs an * annotation because huge_pmd_share() does an allocation under hugetlb's * i_mmap_rwsem. */ static struct lock_class_key hugetlbfs_i_mmap_rwsem_key; static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct mnt_idmap *idmap, struct inode *dir, umode_t mode, dev_t dev) { struct inode *inode; struct resv_map *resv_map = NULL; /* * Reserve maps are only needed for inodes that can have associated * page allocations. */ if (S_ISREG(mode) || S_ISLNK(mode)) { resv_map = resv_map_alloc(); if (!resv_map) return NULL; } inode = new_inode(sb); if (inode) { struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); inode->i_ino = get_next_ino(); inode_init_owner(idmap, inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; simple_inode_init_ts(inode); inode->i_mapping->i_private_data = resv_map; info->seals = F_SEAL_SEAL; switch (mode & S_IFMT) { default: init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_op = &hugetlbfs_inode_operations; inode->i_fop = &hugetlbfs_file_operations; break; case S_IFDIR: inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); break; } lockdep_annotate_inode_mutex_key(inode); trace_hugetlbfs_alloc_inode(inode, dir, mode); } else { if (resv_map) kref_put(&resv_map->refs, resv_map_release); } return inode; } /* * File creation. Allocate an inode, and we're done.. */ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_instantiate(dentry, inode); dget(dentry);/* Extra count - pin the dentry in core */ return 0; } static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int retval = hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } static int hugetlbfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0); } static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_tmpfile(file, inode); return finish_open_simple(file, 0); } static int hugetlbfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { const umode_t mode = S_IFLNK|S_IRWXUGO; struct inode *inode; int error = -ENOSPC; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0); if (inode) { int l = strlen(symname)+1; error = page_symlink(inode, symname, l); if (!error) { d_instantiate(dentry, inode); dget(dentry); } else iput(inode); } inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return error; } #ifdef CONFIG_MIGRATION static int hugetlbfs_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { int rc; rc = migrate_huge_page_move_mapping(mapping, dst, src); if (rc != MIGRATEPAGE_SUCCESS) return rc; if (hugetlb_folio_subpool(src)) { hugetlb_set_folio_subpool(dst, hugetlb_folio_subpool(src)); hugetlb_set_folio_subpool(src, NULL); } folio_migrate_flags(dst, src); return MIGRATEPAGE_SUCCESS; } #else #define hugetlbfs_migrate_folio NULL #endif static int hugetlbfs_error_remove_folio(struct address_space *mapping, struct folio *folio) { return 0; } /* * Display the mount options in /proc/mounts. */ static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb); struct hugepage_subpool *spool = sbinfo->spool; unsigned long hpage_size = huge_page_size(sbinfo->hstate); unsigned hpage_shift = huge_page_shift(sbinfo->hstate); char mod; if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, sbinfo->uid)); if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, sbinfo->gid)); if (sbinfo->mode != 0755) seq_printf(m, ",mode=%o", sbinfo->mode); if (sbinfo->max_inodes != -1) seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes); hpage_size /= 1024; mod = 'K'; if (hpage_size >= 1024) { hpage_size /= 1024; mod = 'M'; } seq_printf(m, ",pagesize=%lu%c", hpage_size, mod); if (spool) { if (spool->max_hpages != -1) seq_printf(m, ",size=%llu", (unsigned long long)spool->max_hpages << hpage_shift); if (spool->min_hpages != -1) seq_printf(m, ",min_size=%llu", (unsigned long long)spool->min_hpages << hpage_shift); } return 0; } static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); struct hstate *h = hstate_inode(d_inode(dentry)); u64 id = huge_encode_dev(dentry->d_sb->s_dev); buf->f_fsid = u64_to_fsid(id); buf->f_type = HUGETLBFS_MAGIC; buf->f_bsize = huge_page_size(h); if (sbinfo) { spin_lock(&sbinfo->stat_lock); /* If no limits set, just report 0 or -1 for max/free/used * blocks, like simple_statfs() */ if (sbinfo->spool) { long free_pages; spin_lock_irq(&sbinfo->spool->lock); buf->f_blocks = sbinfo->spool->max_hpages; free_pages = sbinfo->spool->max_hpages - sbinfo->spool->used_hpages; buf->f_bavail = buf->f_bfree = free_pages; spin_unlock_irq(&sbinfo->spool->lock); buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } spin_unlock(&sbinfo->stat_lock); } buf->f_namelen = NAME_MAX; return 0; } static void hugetlbfs_put_super(struct super_block *sb) { struct hugetlbfs_sb_info *sbi = HUGETLBFS_SB(sb); if (sbi) { sb->s_fs_info = NULL; if (sbi->spool) hugepage_put_subpool(sbi->spool); kfree(sbi); } } static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo) { if (sbinfo->free_inodes >= 0) { spin_lock(&sbinfo->stat_lock); if (unlikely(!sbinfo->free_inodes)) { spin_unlock(&sbinfo->stat_lock); return 0; } sbinfo->free_inodes--; spin_unlock(&sbinfo->stat_lock); } return 1; } static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo) { if (sbinfo->free_inodes >= 0) { spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; spin_unlock(&sbinfo->stat_lock); } } static struct kmem_cache *hugetlbfs_inode_cachep; static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb); struct hugetlbfs_inode_info *p; if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo))) return NULL; p = alloc_inode_sb(sb, hugetlbfs_inode_cachep, GFP_KERNEL); if (unlikely(!p)) { hugetlbfs_inc_free_inodes(sbinfo); return NULL; } return &p->vfs_inode; } static void hugetlbfs_free_inode(struct inode *inode) { trace_hugetlbfs_free_inode(inode); kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode)); } static void hugetlbfs_destroy_inode(struct inode *inode) { hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb)); } static const struct address_space_operations hugetlbfs_aops = { .write_begin = hugetlbfs_write_begin, .write_end = hugetlbfs_write_end, .dirty_folio = noop_dirty_folio, .migrate_folio = hugetlbfs_migrate_folio, .error_remove_folio = hugetlbfs_error_remove_folio, }; static void init_once(void *foo) { struct hugetlbfs_inode_info *ei = foo; inode_init_once(&ei->vfs_inode); } static const struct file_operations hugetlbfs_file_operations = { .read_iter = hugetlbfs_read_iter, .mmap = hugetlbfs_file_mmap, .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, .llseek = default_llseek, .fallocate = hugetlbfs_fallocate, .fop_flags = FOP_HUGE_PAGES, }; static const struct inode_operations hugetlbfs_dir_inode_operations = { .create = hugetlbfs_create, .lookup = simple_lookup, .link = simple_link, .unlink = simple_unlink, .symlink = hugetlbfs_symlink, .mkdir = hugetlbfs_mkdir, .rmdir = simple_rmdir, .mknod = hugetlbfs_mknod, .rename = simple_rename, .setattr = hugetlbfs_setattr, .tmpfile = hugetlbfs_tmpfile, }; static const struct inode_operations hugetlbfs_inode_operations = { .setattr = hugetlbfs_setattr, }; static const struct super_operations hugetlbfs_ops = { .alloc_inode = hugetlbfs_alloc_inode, .free_inode = hugetlbfs_free_inode, .destroy_inode = hugetlbfs_destroy_inode, .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, .put_super = hugetlbfs_put_super, .show_options = hugetlbfs_show_options, }; /* * Convert size option passed from command line to number of huge pages * in the pool specified by hstate. Size option could be in bytes * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). */ static long hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, enum hugetlbfs_size_type val_type) { if (val_type == NO_SIZE) return -1; if (val_type == SIZE_PERCENT) { size_opt <<= huge_page_shift(h); size_opt *= h->max_huge_pages; do_div(size_opt, 100); } size_opt >>= huge_page_shift(h); return size_opt; } /* * Parse one mount parameter. */ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; struct hstate *h; char *rest; unsigned long ps; int opt; opt = fs_parse(fc, hugetlb_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_uid: ctx->uid = result.uid; return 0; case Opt_gid: ctx->gid = result.gid; return 0; case Opt_mode: ctx->mode = result.uint_32 & 01777U; return 0; case Opt_size: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->max_size_opt = memparse(param->string, &rest); ctx->max_val_type = SIZE_STD; if (*rest == '%') ctx->max_val_type = SIZE_PERCENT; return 0; case Opt_nr_inodes: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->nr_inodes = memparse(param->string, &rest); return 0; case Opt_pagesize: ps = memparse(param->string, &rest); h = size_to_hstate(ps); if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } ctx->hstate = h; return 0; case Opt_min_size: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->min_size_opt = memparse(param->string, &rest); ctx->min_val_type = SIZE_STD; if (*rest == '%') ctx->min_val_type = SIZE_PERCENT; return 0; default: return -EINVAL; } bad_val: return invalfc(fc, "Bad value '%s' for mount option '%s'\n", param->string, param->key); } /* * Validate the parsed options. */ static int hugetlbfs_validate(struct fs_context *fc) { struct hugetlbfs_fs_context *ctx = fc->fs_private; /* * Use huge page pool size (in hstate) to convert the size * options to number of huge pages. If NO_SIZE, -1 is returned. */ ctx->max_hpages = hugetlbfs_size_to_hpages(ctx->hstate, ctx->max_size_opt, ctx->max_val_type); ctx->min_hpages = hugetlbfs_size_to_hpages(ctx->hstate, ctx->min_size_opt, ctx->min_val_type); /* * If max_size was specified, then min_size must be smaller */ if (ctx->max_val_type > NO_SIZE && ctx->min_hpages > ctx->max_hpages) { pr_err("Minimum size can not be greater than maximum size\n"); return -EINVAL; } return 0; } static int hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct hugetlbfs_sb_info *sbinfo; sbinfo = kmalloc(sizeof(struct hugetlbfs_sb_info), GFP_KERNEL); if (!sbinfo) return -ENOMEM; sb->s_fs_info = sbinfo; spin_lock_init(&sbinfo->stat_lock); sbinfo->hstate = ctx->hstate; sbinfo->max_inodes = ctx->nr_inodes; sbinfo->free_inodes = ctx->nr_inodes; sbinfo->spool = NULL; sbinfo->uid = ctx->uid; sbinfo->gid = ctx->gid; sbinfo->mode = ctx->mode; /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimum size) are taken * when the subpool is created. */ if (ctx->max_hpages != -1 || ctx->min_hpages != -1) { sbinfo->spool = hugepage_new_subpool(ctx->hstate, ctx->max_hpages, ctx->min_hpages); if (!sbinfo->spool) goto out_free; } sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = huge_page_size(ctx->hstate); sb->s_blocksize_bits = huge_page_shift(ctx->hstate); sb->s_magic = HUGETLBFS_MAGIC; sb->s_op = &hugetlbfs_ops; sb->s_time_gran = 1; /* * Due to the special and limited functionality of hugetlbfs, it does * not work well as a stacking filesystem. */ sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx)); if (!sb->s_root) goto out_free; return 0; out_free: kfree(sbinfo->spool); kfree(sbinfo); return -ENOMEM; } static int hugetlbfs_get_tree(struct fs_context *fc) { int err = hugetlbfs_validate(fc); if (err) return err; return get_tree_nodev(fc, hugetlbfs_fill_super); } static void hugetlbfs_fs_context_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations hugetlbfs_fs_context_ops = { .free = hugetlbfs_fs_context_free, .parse_param = hugetlbfs_parse_param, .get_tree = hugetlbfs_get_tree, }; static int hugetlbfs_init_fs_context(struct fs_context *fc) { struct hugetlbfs_fs_context *ctx; ctx = kzalloc(sizeof(struct hugetlbfs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->max_hpages = -1; /* No limit on size by default */ ctx->nr_inodes = -1; /* No limit on number of inodes by default */ ctx->uid = current_fsuid(); ctx->gid = current_fsgid(); ctx->mode = 0755; ctx->hstate = &default_hstate; ctx->min_hpages = -1; /* No default minimum size */ ctx->max_val_type = NO_SIZE; ctx->min_val_type = NO_SIZE; fc->fs_private = ctx; fc->ops = &hugetlbfs_fs_context_ops; return 0; } static struct file_system_type hugetlbfs_fs_type = { .name = "hugetlbfs", .init_fs_context = hugetlbfs_init_fs_context, .parameters = hugetlb_fs_parameters, .kill_sb = kill_litter_super, .fs_flags = FS_ALLOW_IDMAP, }; static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE]; static int can_do_hugetlb_shm(void) { kgid_t shm_group; shm_group = make_kgid(&init_user_ns, sysctl_hugetlb_shm_group); return capable(CAP_IPC_LOCK) || in_group_p(shm_group); } static int get_hstate_idx(int page_size_log) { struct hstate *h = hstate_sizelog(page_size_log); if (!h) return -1; return hstate_index(h); } /* * Note that size should be aligned to proper hugepage size in caller side, * otherwise hugetlb_reserve_pages reserves one less hugepages than intended. */ struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { struct inode *inode; struct vfsmount *mnt; int hstate_idx; struct file *file; hstate_idx = get_hstate_idx(page_size_log); if (hstate_idx < 0) return ERR_PTR(-ENODEV); mnt = hugetlbfs_vfsmount[hstate_idx]; if (!mnt) return ERR_PTR(-ENOENT); if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) { struct ucounts *ucounts = current_ucounts(); if (user_shm_lock(size, ucounts)) { pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is obsolete\n", current->comm, current->pid); user_shm_unlock(size, ucounts); } return ERR_PTR(-EPERM); } file = ERR_PTR(-ENOSPC); /* hugetlbfs_vfsmount[] mounts do not use idmapped mounts. */ inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL, S_IFREG | S_IRWXUGO, 0); if (!inode) goto out; if (creat_flags == HUGETLB_SHMFS_INODE) inode->i_flags |= S_PRIVATE; inode->i_size = size; clear_nlink(inode); if (!hugetlb_reserve_pages(inode, 0, size >> huge_page_shift(hstate_inode(inode)), NULL, acctflag)) file = ERR_PTR(-ENOMEM); else file = alloc_file_pseudo(inode, mnt, name, O_RDWR, &hugetlbfs_file_operations); if (!IS_ERR(file)) return file; iput(inode); out: return file; } static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h) { struct fs_context *fc; struct vfsmount *mnt; fc = fs_context_for_mount(&hugetlbfs_fs_type, SB_KERNMOUNT); if (IS_ERR(fc)) { mnt = ERR_CAST(fc); } else { struct hugetlbfs_fs_context *ctx = fc->fs_private; ctx->hstate = h; mnt = fc_mount(fc); put_fs_context(fc); } if (IS_ERR(mnt)) pr_err("Cannot mount internal hugetlbfs for page size %luK", huge_page_size(h) / SZ_1K); return mnt; } static int __init init_hugetlbfs_fs(void) { struct vfsmount *mnt; struct hstate *h; int error; int i; if (!hugepages_supported()) { pr_info("disabling because there are no supported hugepage sizes\n"); return -ENOTSUPP; } error = -ENOMEM; hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache", sizeof(struct hugetlbfs_inode_info), 0, SLAB_ACCOUNT, init_once); if (hugetlbfs_inode_cachep == NULL) goto out; error = register_filesystem(&hugetlbfs_fs_type); if (error) goto out_free; /* default hstate mount is required */ mnt = mount_one_hugetlbfs(&default_hstate); if (IS_ERR(mnt)) { error = PTR_ERR(mnt); goto out_unreg; } hugetlbfs_vfsmount[default_hstate_idx] = mnt; /* other hstates are optional */ i = 0; for_each_hstate(h) { if (i == default_hstate_idx) { i++; continue; } mnt = mount_one_hugetlbfs(h); if (IS_ERR(mnt)) hugetlbfs_vfsmount[i] = NULL; else hugetlbfs_vfsmount[i] = mnt; i++; } return 0; out_unreg: (void)unregister_filesystem(&hugetlbfs_fs_type); out_free: kmem_cache_destroy(hugetlbfs_inode_cachep); out: return error; } fs_initcall(init_hugetlbfs_fs) |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 | // SPDX-License-Identifier: GPL-2.0 /* * HugeTLB Vmemmap Optimization (HVO) * * Copyright (c) 2020, ByteDance. All rights reserved. * * Author: Muchun Song <songmuchun@bytedance.com> */ #ifndef _LINUX_HUGETLB_VMEMMAP_H #define _LINUX_HUGETLB_VMEMMAP_H #include <linux/hugetlb.h> /* * Reserve one vmemmap page, all vmemmap addresses are mapped to it. See * Documentation/mm/vmemmap_dedup.rst. */ #define HUGETLB_VMEMMAP_RESERVE_SIZE PAGE_SIZE #define HUGETLB_VMEMMAP_RESERVE_PAGES (HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page)) #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio); long hugetlb_vmemmap_restore_folios(const struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios); void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio); void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list); static inline unsigned int hugetlb_vmemmap_size(const struct hstate *h) { return pages_per_huge_page(h) * sizeof(struct page); } /* * Return how many vmemmap size associated with a HugeTLB page that can be * optimized and can be freed to the buddy allocator. */ static inline unsigned int hugetlb_vmemmap_optimizable_size(const struct hstate *h) { int size = hugetlb_vmemmap_size(h) - HUGETLB_VMEMMAP_RESERVE_SIZE; if (!is_power_of_2(sizeof(struct page))) return 0; return size > 0 ? size : 0; } #else static inline int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio) { return 0; } static long hugetlb_vmemmap_restore_folios(const struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { list_splice_init(folio_list, non_hvo_folios); return 0; } static inline void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio) { } static inline void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list) { } static inline unsigned int hugetlb_vmemmap_optimizable_size(const struct hstate *h) { return 0; } #endif /* CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP */ static inline bool hugetlb_vmemmap_optimizable(const struct hstate *h) { return hugetlb_vmemmap_optimizable_size(h) != 0; } #endif /* _LINUX_HUGETLB_VMEMMAP_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master, int extra) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; int len; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; len = sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload); /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header. * RedBox might use @extra more bytes. */ skb = dev_alloc_skb(len + extra + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; skb_reset_network_header(skb); skb_reset_transport_header(skb); if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; int extra = 0; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } if (hsr->redbox) extra = sizeof(struct hsr_sup_tlv) + sizeof(struct hsr_sup_payload); skb = hsr_init_skb(port, extra); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master, 0); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (!interlink) goto done; list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } done: rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { bool is_slave_a_added = false; bool is_slave_b_added = false; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; ret = vlan_vid_add(port->dev, proto, vid); switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { /* clean up Slave-B */ netdev_err(dev, "add vid failed for Slave-A\n"); if (is_slave_b_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_a_added = true; break; case HSR_PT_SLAVE_B: if (ret) { /* clean up Slave-A */ netdev_err(dev, "add vid failed for Slave-B\n"); if (is_slave_a_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_b_added = true; break; default: break; } } return 0; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: vlan_vid_del(port->dev, proto, vid); break; default: break; } } return 0; } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; /* Prevent recursive tx locking */ dev->lltx = true; /* Not sure about this. Taken from bridge code. netdevice.h says * it means "Does not change network namespaces". */ dev->netns_local = true; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_FILTER; dev->features = dev->hw_features; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 144 144 243 243 343 146 164 78 164 77 180 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 | // SPDX-License-Identifier: GPL-2.0-only /* * Integrity Measurement Architecture * * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Reiner Sailer <sailer@watson.ibm.com> * Serge Hallyn <serue@us.ibm.com> * Kylene Hall <kylene@us.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_main.c * implements the IMA hooks: ima_bprm_check, ima_file_mmap, * and ima_file_check. */ #include <linux/module.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/kernel_read_file.h> #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/ima.h> #include <linux/fs.h> #include <linux/iversion.h> #include <linux/evm.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE int ima_appraise = IMA_APPRAISE_ENFORCE; #else int ima_appraise; #endif int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static struct notifier_block ima_lsm_policy_notifier = { .notifier_call = ima_lsm_policy_change, }; static int __init hash_setup(char *str) { struct ima_template_desc *template_desc = ima_template_desc_current(); int i; if (hash_setup_done) return 1; if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) { if (strncmp(str, "sha1", 4) == 0) { ima_hash_algo = HASH_ALGO_SHA1; } else if (strncmp(str, "md5", 3) == 0) { ima_hash_algo = HASH_ALGO_MD5; } else { pr_err("invalid hash algorithm \"%s\" for template \"%s\"", str, IMA_TEMPLATE_IMA_NAME); return 1; } goto out; } i = match_string(hash_algo_name, HASH_ALGO__LAST, str); if (i < 0) { pr_err("invalid hash algorithm \"%s\"", str); return 1; } ima_hash_algo = i; out: hash_setup_done = 1; return 1; } __setup("ima_hash=", hash_setup); enum hash_algo ima_get_current_hash_algo(void) { return ima_hash_algo; } /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, char *filename) { struct inode *inode; int rc = 0; if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && mapping_writably_mapped(file->f_mapping)) { rc = -ETXTBSY; inode = file_inode(file); if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */ *pathname = ima_d_path(&file->f_path, pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname, "mmap_file", "mmapped_writers", rc, 0); } return rc; } /* * ima_rdwr_violation_check * * Only invalidate the PCR for measured files: * - Opening a file for write when already open for read, * results in a time of measure, time of use (ToMToU) error. * - Opening a file for read when already open for write, * could result in a file measurement error. * */ static void ima_rdwr_violation_check(struct file *file, struct ima_iint_cache *iint, int must_measure, char **pathbuf, const char **pathname, char *filename) { struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; bool send_tomtou = false, send_writers = false; if (mode & FMODE_WRITE) { if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = ima_iint_find(inode); /* IMA_MEASURE is set from reader side */ if (iint && test_bit(IMA_MUST_MEASURE, &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) set_bit(IMA_MUST_MEASURE, &iint->atomic_flags); if (inode_is_open_for_write(inode) && must_measure) send_writers = true; } if (!send_tomtou && !send_writers) return; *pathname = ima_d_path(&file->f_path, pathbuf, filename); if (send_tomtou) ima_add_violation(file, *pathname, iint, "invalid_pcr", "ToMToU"); if (send_writers) ima_add_violation(file, *pathname, iint, "invalid_pcr", "open_writers"); } static void ima_check_last_writer(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { fmode_t mode = file->f_mode; bool update; if (!(mode & FMODE_WRITE)) return; mutex_lock(&iint->mutex); if (atomic_read(&inode->i_writecount) == 1) { struct kstat stat; update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if ((iint->flags & IMA_NEW_FILE) || vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT) || !(stat.result_mask & STATX_CHANGE_COOKIE) || stat.change_cookie != iint->real_inode.version) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; if (update) ima_update_xattr(iint, file); } } mutex_unlock(&iint->mutex); } /** * ima_file_free - called on __fput() * @file: pointer to file structure being freed * * Flag files that changed, based on i_version */ static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct ima_iint_cache *iint; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; ima_check_last_writer(iint, inode, file); } static int process_measurement(struct file *file, const struct cred *cred, struct lsm_prop *prop, char *buf, loff_t size, int mask, enum ima_hooks func) { struct inode *real_inode, *inode = file_inode(file); struct ima_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; struct inode *metadata_inode; char *pathbuf = NULL; char filename[NAME_MAX]; const char *pathname = NULL; int rc = 0, action, must_appraise = 0; int pcr = CONFIG_IMA_MEASURE_PCR_IDX; struct evm_ima_xattr_data *xattr_value = NULL; struct modsig *modsig = NULL; int xattr_len = 0; bool violation_check; enum hash_algo hash_algo; unsigned int allowed_algos = 0; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return 0; /* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ action = ima_get_action(file_mnt_idmap(file), inode, cred, prop, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && (ima_policy_flag & IMA_MEASURE)); if (!action && !violation_check) return 0; must_appraise = action & IMA_APPRAISE; /* Is the appraise rule hook specific? */ if (action & IMA_FILE_APPRAISE) func = FILE_CHECK; inode_lock(inode); if (action) { iint = ima_inode_get(inode); if (!iint) rc = -ENOMEM; } if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE, &pathbuf, &pathname, filename); inode_unlock(inode); if (rc) goto out; if (!action) goto out; mutex_lock(&iint->mutex); if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags)) /* reset appraisal flags if ima_inode_post_setattr was called */ iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED | IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK | IMA_NONACTION_FLAGS); /* * Re-evaulate the file if either the xattr has changed or the * kernel has no way of detecting file change on the filesystem. * (Limited to privileged mounted filesystems.) */ if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) && !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * On stacked filesystems, detect and re-evaluate file data and * metadata changes. */ real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) || integrity_inode_attrs_changed(&iint->real_inode, real_inode)) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * Reset the EVM status when metadata changed. */ metadata_inode = d_inode(d_real(file_dentry(file), D_REAL_METADATA)); if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED | IMA_APPRAISED_SUBMASK); } /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) */ iint->flags |= action; action &= IMA_DO_MASK; action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1); /* If target pcr is already measured, unset IMA_MEASURE action */ if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr))) action ^= IMA_MEASURE; /* HASH sets the digital signature and update flags, nothing else */ if ((action & IMA_HASH) && !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) { xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); if ((xattr_value && xattr_len > 2) && (xattr_value->type == EVM_IMA_XATTR_DIGSIG)) set_bit(IMA_DIGSIG, &iint->atomic_flags); iint->flags |= IMA_HASHED; action ^= IMA_HASH; set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } /* Nothing to do, just return existing appraised status */ if (!action) { if (must_appraise) { rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); if (!rc) rc = ima_get_cache_status(iint, func); } goto out_locked; } if ((action & IMA_APPRAISE_SUBMASK) || strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) { /* read 'security.ima' */ xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); /* * Read the appended modsig if allowed by the policy, and allow * an additional measurement list entry, if needed, based on the * template format and whether the file was already measured. */ if (iint->flags & IMA_MODSIG_ALLOWED) { rc = ima_read_modsig(func, buf, size, &modsig); if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED) action |= IMA_MEASURE; } } hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); if (rc != 0 && rc != -EBADF && rc != -EINVAL) goto out_locked; if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname, xattr_value, xattr_len, modsig, pcr, template_desc); if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { rc = ima_check_blacklist(iint, modsig, pcr); if (rc != -EPERM) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, xattr_value, xattr_len, modsig); inode_unlock(inode); } if (!rc) rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); } if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO)) rc = 0; /* Ensure the digest was generated using an allowed algorithm */ if (rc == 0 && must_appraise && allowed_algos != 0 && (allowed_algos & (1U << hash_algo)) == 0) { rc = -EACCES; integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file), pathname, "collect_data", "denied-hash-algorithm", rc, 0); } out_locked: if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE)) rc = -EACCES; mutex_unlock(&iint->mutex); kfree(xattr_value); ima_free_modsig(modsig); out: if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE)) return -EACCES; if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } return 0; } /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { struct lsm_prop prop; int ret; if (!file) return 0; security_current_getlsmprop_subj(&prop); if (reqprot & PROT_EXEC) { ret = process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT); if (ret) return ret; } if (prot & PROT_EXEC) return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK); return 0; } /** * ima_file_mprotect - based on policy, limit mprotect change * @vma: vm_area_struct protection is set to * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * * Files can be mmap'ed read/write and later changed to execute to circumvent * IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore * would be taken before i_mutex), files can not be measured or appraised at * this point. Eliminate this integrity gap by denying the mprotect * PROT_EXECUTE change, if an mmap appraise policy rule exists. * * On mprotect change success, return 0. On failure, return -EACESS. */ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; struct lsm_prop prop; int result = 0; int action; int pcr; /* Is mprotect making an mmap'ed file executable? */ if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file || !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; security_current_getlsmprop_subj(&prop); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) return 0; if (action & IMA_APPRAISE_SUBMASK) result = -EPERM; file = vma->vm_file; pathname = ima_d_path(&file->f_path, &pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname, "collect_data", "failed-mprotect", result, 0); if (pathbuf) __putname(pathbuf); return result; } /** * ima_bprm_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_check(struct linux_binprm *bprm) { int ret; struct lsm_prop prop; security_current_getlsmprop_subj(&prop); ret = process_measurement(bprm->file, current_cred(), &prop, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) return ret; security_cred_getlsmprop(bprm->cred, &prop); return process_measurement(bprm->file, bprm->cred, &prop, NULL, 0, MAY_EXEC, CREDS_CHECK); } /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND * * Measure files based on the ima_must_measure() policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_check(struct file *file, int mask) { struct lsm_prop prop; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { struct ima_iint_cache *iint = NULL, tmp_iint; int rc, hash_algo; if (ima_policy_flag) { iint = ima_iint_find(inode); if (iint) mutex_lock(&iint->mutex); } if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) { if (iint) mutex_unlock(&iint->mutex); memset(&tmp_iint, 0, sizeof(tmp_iint)); mutex_init(&tmp_iint.mutex); rc = ima_collect_measurement(&tmp_iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) { /* ima_hash could be allocated in case of failure. */ if (rc != -ENOMEM) kfree(tmp_iint.ima_hash); return -EOPNOTSUPP; } iint = &tmp_iint; mutex_lock(&iint->mutex); } if (!iint) return -EOPNOTSUPP; /* * ima_file_hash can be called when ima_collect_measurement has still * not been called, we might not always have a hash. */ if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) { mutex_unlock(&iint->mutex); return -EOPNOTSUPP; } if (buf) { size_t copied_size; copied_size = min_t(size_t, iint->ima_hash->length, buf_size); memcpy(buf, iint->ima_hash->digest, copied_size); } hash_algo = iint->ima_hash->algo; mutex_unlock(&iint->mutex); if (iint == &tmp_iint) kfree(iint->ima_hash); return hash_algo; } /** * ima_file_hash - return a measurement of the file * @file: pointer to the file * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The file hash returned is based on the entire file, including the appended * signature. * * If the measurement cannot be performed, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_file_hash(struct file *file, char *buf, size_t buf_size) { if (!file) return -EINVAL; return __ima_inode_hash(file_inode(file), file, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_file_hash); /** * ima_inode_hash - return the stored measurement if the inode has been hashed * and is in the iint cache. * @inode: pointer to the inode * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The hash returned is based on the entire contents, including the appended * signature. * * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { if (!inode) return -EINVAL; return __ima_inode_hash(inode, NULL, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ static void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct ima_iint_cache *iint; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for writing the security xattrs */ set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); iint->ima_file_status = INTEGRITY_PASS; } /** * ima_post_path_mknod - mark as a new inode * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct ima_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for re-opening empty files */ iint->flags |= IMA_NEW_FILE; } /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit * @read_id: caller identifier * @contents: whether a subsequent call will be made to ima_post_read_file() * * Permit reading a file based on policy. The policy rules are written * in terms of the policy identifier. Appraising the integrity of * a file requires a file descriptor. * * For permission return 0, otherwise return -EACCES. */ static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; struct lsm_prop prop; /* * Do devices using pre-allocated memory run the risk of the * firmware being accessible to the device prior to the completion * of IMA's signature verification any more than when using two * buffers? It may be desirable to include the buffer address * in this API and walk all the dma_map_single() mappings to check. */ /* * There will be a call made to ima_post_read_file() with * a filled buffer, so we don't need to perform an extra * read early here. */ if (contents) return 0; /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_READ, func); } const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, [READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK, [READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK, [READING_POLICY] = POLICY_CHECK }; /** * ima_post_read_file - in memory collect/appraise/audit measurement * @file: pointer to the file to be measured/appraised/audit * @buf: pointer to in memory file contents * @size: size of in memory file contents * @read_id: caller identifier * * Measure/appraise/audit in memory file based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; struct lsm_prop prop; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) return 0; if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; return 0; } func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, buf, size, MAY_READ, func); } /** * ima_load_data - appraise decision based on policy * @id: kernel load data caller identifier * @contents: whether the full contents will be available in a later * call to ima_post_load_data(). * * Callers of this LSM hook can not measure, appraise, or audit the * data provided by userspace. Enforce policy rules requiring a file * signature (eg. kexec'ed kernel image). * * For permission return 0, otherwise return -EACCES. */ static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; ima_enforce = (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_ima_get_secureboot()) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; } if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); if (ima_enforce && (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; default: break; } return 0; } /** * ima_post_load_data - appraise decision based on policy * @buf: pointer to in memory file contents * @size: size of in memory file contents * @load_id: kernel load data caller identifier * @description: @load_id-specific description of contents * * Measure/appraise/audit in memory buffer based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id load_id, char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && (ima_appraise & IMA_APPRAISE_ENFORCE)) { pr_err("Prevent firmware loading_store.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } return 0; } /* * Measure the init_module syscall buffer containing the ELF image. */ if (load_id == LOADING_MODULE) ima_measure_critical_data("modules", "init_module", buf, size, true, NULL, 0); return 0; } /** * process_buffer_measurement - Measure the buffer or the buffer data hash * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). * @eventname: event name to be used for the buffer entry. * @func: IMA hook * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; struct ima_template_entry *entry = NULL; struct ima_iint_cache iint = {}; struct ima_event_data event_data = {.iint = &iint, .filename = eventname, .buf = buf, .buf_len = size}; struct ima_template_desc *template; struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); char digest_hash[IMA_MAX_DIGEST_SIZE]; int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; struct lsm_prop prop; if (digest && digest_len < digest_hash_len) return -EINVAL; if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); if (!template) { ret = -EINVAL; audit_cause = "ima_template_desc_buf"; goto out; } /* * Both LSM hooks and auxilary based buffer measurements are * based on policy. To avoid code duplication, differentiate * between the LSM hooks and auxilary buffer measurements, * retrieving the policy rule information only for the LSM hook * buffer measurements. */ if (func) { security_current_getlsmprop_subj(&prop); action = ima_get_action(idmap, inode, current_cred(), &prop, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } if (!pcr) pcr = CONFIG_IMA_MEASURE_PCR_IDX; iint.ima_hash = hash_hdr; iint.ima_hash->algo = ima_hash_algo; iint.ima_hash->length = hash_digest_size[ima_hash_algo]; ret = ima_calc_buffer_hash(buf, size, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } if (buf_hash) { memcpy(digest_hash, hash_hdr->digest, digest_hash_len); ret = ima_calc_buffer_hash(digest_hash, digest_hash_len, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } event_data.buf = digest_hash; event_data.buf_len = digest_hash_len; } if (digest) memcpy(digest, iint.ima_hash->digest, digest_hash_len); if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) return 1; ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; goto out; } ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr); if (ret < 0) { audit_cause = "store_entry"; ima_free_template_entry(entry); } out: if (ret < 0) integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname, func_measure_str(func), audit_cause, ret, 0, ret); return ret; } /** * ima_kexec_cmdline - measure kexec cmdline boot args * @kernel_fd: file descriptor of the kexec kernel being loaded * @buf: pointer to buffer * @size: size of buffer * * Buffers can only be measured, not appraised. */ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { if (!buf || !size) return; CLASS(fd, f)(kernel_fd); if (fd_empty(f)) return; process_buffer_measurement(file_mnt_idmap(fd_file(f)), file_inode(fd_file(f)), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); } /** * ima_measure_critical_data - measure kernel integrity critical data * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); } EXPORT_SYMBOL_GPL(ima_measure_critical_data); #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS /** * ima_kernel_module_request - Prevent crypto-pkcs1(rsa,*) requests * @kmod_name: kernel module name * * Avoid a verification loop where verifying the signature of the modprobe * binary requires executing modprobe itself. Since the modprobe iint->mutex * is already held when the signature verification is performed, a deadlock * occurs as soon as modprobe is executed within the critical region, since * the same lock cannot be taken again. * * This happens when public_key_verify_signature(), in case of RSA algorithm, * use alg_name to store internal information in order to construct an * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name * in order to load a kernel module with same name. * * Since we don't have any real "crypto-pkcs1(rsa,*)" kernel modules, * we are safe to fail such module request from crypto_larval_lookup(), and * avoid the verification loop. * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1(rsa,", 17) == 0) return -EINVAL; return 0; } #endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ static int __init init_ima(void) { int error; ima_appraise_parse_cmdline(); ima_init_template_list(); hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); if (error && strcmp(hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH) != 0) { pr_info("Allocating %s failed, going to use default hash algorithm %s\n", hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH); hash_setup_done = 0; hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); } if (error) return error; error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier); if (error) pr_warn("Couldn't register LSM notifier, error %d\n", error); if (!error) ima_update_policy_flags(); return error; } static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu), }; static const struct lsm_id ima_lsmid = { .name = "ima", .id = LSM_ID_IMA, }; static int __init init_ima_lsm(void) { ima_iintcache_init(); security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); init_ima_appraise_lsm(&ima_lsmid); return 0; } struct lsm_blob_sizes ima_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct ima_iint_cache *), }; DEFINE_LSM(ima) = { .name = "ima", .init = init_ima_lsm, .order = LSM_ORDER_LAST, .blobs = &ima_blob_sizes, }; late_initcall(init_ima); /* Start IMA after the TPM is available */ |
| 794 795 174 794 11 11 9 11 11 11 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 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 | // 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); |
| 965 966 966 965 43 968 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/domain.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/rculist.h> /* Variables definitions.*/ /* The initial domain. */ struct tomoyo_domain_info tomoyo_kernel_domain; /** * tomoyo_update_policy - Update an entry for exception policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)) { int error = param->is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_head *entry; struct list_head *list = param->list; if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) continue; entry->is_deleted = param->is_delete; error = 0; break; } if (error && !param->is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); return error; } /** * tomoyo_same_acl_head - Check for duplicated "struct tomoyo_acl_info" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_acl_head(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { return a->type == b->type && a->cond == b->cond; } /** * tomoyo_update_domain - Update an entry for domain policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * @merge_duplicate: Callback function to merge duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate)(struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)) { const bool is_delete = param->is_delete; int error = is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_info *entry; struct list_head * const list = param->list; if (param->data[0]) { new_entry->cond = tomoyo_get_condition(param); if (!new_entry->cond) return -EINVAL; /* * Domain transition preference is allowed for only * "file execute" entries. */ if (new_entry->cond->transit && !(new_entry->type == TOMOYO_TYPE_PATH_ACL && container_of(new_entry, struct tomoyo_path_acl, head) ->perm == 1 << TOMOYO_TYPE_EXECUTE)) goto out; } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || !check_duplicate(entry, new_entry)) continue; if (merge_duplicate) entry->is_deleted = merge_duplicate(entry, new_entry, is_delete); else entry->is_deleted = is_delete; error = 0; break; } if (error && !is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_condition(new_entry->cond); return error; } /** * tomoyo_check_acl - Do permission check. * * @r: Pointer to "struct tomoyo_request_info". * @check_entry: Callback function to check type specific parameters. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)) { const struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; const struct list_head *list = &domain->acl_info_list; u16 i = 0; retry: list_for_each_entry_rcu(ptr, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) continue; if (!tomoyo_condition(r, ptr->cond)) continue; r->matched_acl = ptr; r->granted = true; return; } for (; i < TOMOYO_MAX_ACL_GROUPS; i++) { if (!test_bit(i, domain->group)) continue; list = &domain->ns->acl_group[i++]; goto retry; } r->granted = false; } /* The list for "struct tomoyo_domain_info". */ LIST_HEAD(tomoyo_domain_list); /** * tomoyo_last_word - Get last component of a domainname. * * @name: Domainname to check. * * Returns the last word of @domainname. */ static const char *tomoyo_last_word(const char *name) { const char *cp = strrchr(name, ' '); if (cp) return cp + 1; return name; } /** * tomoyo_same_transition_control - Check for duplicated "struct tomoyo_transition_control" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_transition_control(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_transition_control *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_transition_control *p2 = container_of(b, typeof(*p2), head); return p1->type == p2->type && p1->is_last_name == p2->is_last_name && p1->domainname == p2->domainname && p1->program == p2->program; } /** * tomoyo_write_transition_control - Write "struct tomoyo_transition_control" list. * * @param: Pointer to "struct tomoyo_acl_param". * @type: Type of this entry. * * Returns 0 on success, negative value otherwise. */ int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type) { struct tomoyo_transition_control e = { .type = type }; int error = param->is_delete ? -ENOENT : -ENOMEM; char *program = param->data; char *domainname = strstr(program, " from "); if (domainname) { *domainname = '\0'; domainname += 6; } else if (type == TOMOYO_TRANSITION_CONTROL_NO_KEEP || type == TOMOYO_TRANSITION_CONTROL_KEEP) { domainname = program; program = NULL; } if (program && strcmp(program, "any")) { if (!tomoyo_correct_path(program)) return -EINVAL; e.program = tomoyo_get_name(program); if (!e.program) goto out; } if (domainname && strcmp(domainname, "any")) { if (!tomoyo_correct_domain(domainname)) { if (!tomoyo_correct_path(domainname)) goto out; e.is_last_name = true; } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) goto out; } param->list = ¶m->ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_transition_control); out: tomoyo_put_name(e.domainname); tomoyo_put_name(e.program); return error; } /** * tomoyo_scan_transition - Try to find specific domain transition type. * * @list: Pointer to "struct list_head". * @domainname: The name of current domain. * @program: The name of requested program. * @last_name: The last component of @domainname. * @type: One of values in "enum tomoyo_transition_type". * * Returns true if found one, false otherwise. * * Caller holds tomoyo_read_lock(). */ static inline bool tomoyo_scan_transition (const struct list_head *list, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program, const char *last_name, const enum tomoyo_transition_type type) { const struct tomoyo_transition_control *ptr; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { if (!ptr->is_last_name) { if (ptr->domainname != domainname) continue; } else { /* * Use direct strcmp() since this is * unlikely used. */ if (strcmp(ptr->domainname->name, last_name)) continue; } } if (ptr->program && tomoyo_pathcmp(ptr->program, program)) continue; return true; } return false; } /** * tomoyo_transition_type - Get domain transition type. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @domainname: The name of current domain. * @program: The name of requested program. * * Returns TOMOYO_TRANSITION_CONTROL_TRANSIT if executing @program causes * domain transition across namespaces, TOMOYO_TRANSITION_CONTROL_INITIALIZE if * executing @program reinitializes domain transition within that namespace, * TOMOYO_TRANSITION_CONTROL_KEEP if executing @program stays at @domainname , * others otherwise. * * Caller holds tomoyo_read_lock(). */ static enum tomoyo_transition_type tomoyo_transition_type (const struct tomoyo_policy_namespace *ns, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program) { const char *last_name = tomoyo_last_word(domainname->name); enum tomoyo_transition_type type = TOMOYO_TRANSITION_CONTROL_NO_RESET; while (type < TOMOYO_MAX_TRANSITION_TYPE) { const struct list_head * const list = &ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; if (!tomoyo_scan_transition(list, domainname, program, last_name, type)) { type++; continue; } if (type != TOMOYO_TRANSITION_CONTROL_NO_RESET && type != TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE) break; /* * Do not check for reset_domain if no_reset_domain matched. * Do not check for initialize_domain if no_initialize_domain * matched. */ type++; type++; } return type; } /** * tomoyo_same_aggregator - Check for duplicated "struct tomoyo_aggregator" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_aggregator(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_aggregator *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_aggregator *p2 = container_of(b, typeof(*p2), head); return p1->original_name == p2->original_name && p1->aggregated_name == p2->aggregated_name; } /** * tomoyo_write_aggregator - Write "struct tomoyo_aggregator" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_aggregator(struct tomoyo_acl_param *param) { struct tomoyo_aggregator e = { }; int error = param->is_delete ? -ENOENT : -ENOMEM; const char *original_name = tomoyo_read_token(param); const char *aggregated_name = tomoyo_read_token(param); if (!tomoyo_correct_word(original_name) || !tomoyo_correct_path(aggregated_name)) return -EINVAL; e.original_name = tomoyo_get_name(original_name); e.aggregated_name = tomoyo_get_name(aggregated_name); if (!e.original_name || !e.aggregated_name || e.aggregated_name->is_patterned) /* No patterns allowed. */ goto out; param->list = ¶m->ns->policy_list[TOMOYO_ID_AGGREGATOR]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_aggregator); out: tomoyo_put_name(e.original_name); tomoyo_put_name(e.aggregated_name); return error; } /** * tomoyo_find_namespace - Find specified namespace. * * @name: Name of namespace to find. * @len: Length of @name. * * Returns pointer to "struct tomoyo_policy_namespace" if found, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ static struct tomoyo_policy_namespace *tomoyo_find_namespace (const char *name, const unsigned int len) { struct tomoyo_policy_namespace *ns; list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { if (strncmp(name, ns->name, len) || (name[len] && name[len] != ' ')) continue; return ns; } return NULL; } /** * tomoyo_assign_namespace - Create a new namespace. * * @domainname: Name of namespace to create. * * Returns pointer to "struct tomoyo_policy_namespace" on success, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_policy_namespace *tomoyo_assign_namespace(const char *domainname) { struct tomoyo_policy_namespace *ptr; struct tomoyo_policy_namespace *entry; const char *cp = domainname; unsigned int len = 0; while (*cp && *cp++ != ' ') len++; ptr = tomoyo_find_namespace(domainname, len); if (ptr) return ptr; if (len >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_domain_def(domainname)) return NULL; entry = kzalloc(sizeof(*entry) + len + 1, GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = tomoyo_find_namespace(domainname, len); if (!ptr && tomoyo_memory_ok(entry)) { char *name = (char *) (entry + 1); ptr = entry; memmove(name, domainname, len); name[len] = '\0'; entry->name = name; tomoyo_init_policy_namespace(entry); entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_namespace_jump - Check for namespace jump. * * @domainname: Name of domain. * * Returns true if namespace differs, false otherwise. */ static bool tomoyo_namespace_jump(const char *domainname) { const char *namespace = tomoyo_current_namespace()->name; const int len = strlen(namespace); return strncmp(domainname, namespace, len) || (domainname[len] && domainname[len] != ' '); } /** * tomoyo_assign_domain - Create a domain or a namespace. * * @domainname: The name of domain. * @transit: True if transit to domain found or created. * * Returns pointer to "struct tomoyo_domain_info" on success, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit) { struct tomoyo_domain_info e = { }; struct tomoyo_domain_info *entry = tomoyo_find_domain(domainname); bool created = false; if (entry) { if (transit) { /* * Since namespace is created at runtime, profiles may * not be created by the moment the process transits to * that domain. Do not perform domain transition if * profile for that domain is not yet created. */ if (tomoyo_policy_loaded && !entry->ns->profile_ptr[entry->profile]) return NULL; } return entry; } /* Requested domain does not exist. */ /* Don't create requested domain if domainname is invalid. */ if (strlen(domainname) >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_correct_domain(domainname)) return NULL; /* * Since definition of profiles and acl_groups may differ across * namespaces, do not inherit "use_profile" and "use_group" settings * by automatically creating requested domain upon domain transition. */ if (transit && tomoyo_namespace_jump(domainname)) return NULL; e.ns = tomoyo_assign_namespace(domainname); if (!e.ns) return NULL; /* * "use_profile" and "use_group" settings for automatically created * domains are inherited from current domain. These are 0 for manually * created domains. */ if (transit) { const struct tomoyo_domain_info *domain = tomoyo_domain(); e.profile = domain->profile; memcpy(e.group, domain->group, sizeof(e.group)); } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) return NULL; if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; entry = tomoyo_find_domain(domainname); if (!entry) { entry = tomoyo_commit_ok(&e, sizeof(e)); if (entry) { INIT_LIST_HEAD(&entry->acl_info_list); list_add_tail_rcu(&entry->list, &tomoyo_domain_list); created = true; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_name(e.domainname); if (entry && transit) { if (created) { struct tomoyo_request_info r; int i; tomoyo_init_request_info(&r, entry, TOMOYO_MAC_FILE_EXECUTE); r.granted = false; tomoyo_write_log(&r, "use_profile %u\n", entry->profile); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) if (test_bit(i, entry->group)) tomoyo_write_log(&r, "use_group %u\n", i); tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); } } return entry; } /** * tomoyo_environ - Check permission for environment variable names. * * @ee: Pointer to "struct tomoyo_execve". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_environ(struct tomoyo_execve *ee) { struct tomoyo_request_info *r = &ee->r; struct linux_binprm *bprm = ee->bprm; /* env_page.data is allocated by tomoyo_dump_page(). */ struct tomoyo_page_dump env_page = { }; char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ int arg_len = 0; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; int error = -ENOMEM; ee->r.type = TOMOYO_MAC_ENVIRON; ee->r.profile = r->domain->profile; ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile, TOMOYO_MAC_ENVIRON); if (!r->mode || !envp_count) return 0; arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!arg_ptr) goto out; while (error == -ENOMEM) { if (!tomoyo_dump_page(bprm, pos, &env_page)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (argv_count && offset < PAGE_SIZE) { if (!env_page.data[offset++]) argv_count--; } if (argv_count) { offset = 0; continue; } while (offset < PAGE_SIZE) { const unsigned char c = env_page.data[offset++]; if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { if (c == '=') { arg_ptr[arg_len++] = '\0'; } else if (c == '\\') { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = '\\'; } else if (c > ' ' && c < 127) { arg_ptr[arg_len++] = c; } else { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = (c >> 6) + '0'; arg_ptr[arg_len++] = ((c >> 3) & 7) + '0'; arg_ptr[arg_len++] = (c & 7) + '0'; } } else { arg_ptr[arg_len] = '\0'; } if (c) continue; if (tomoyo_env_perm(r, arg_ptr)) { error = -EPERM; break; } if (!--envp_count) { error = 0; break; } arg_len = 0; } offset = 0; } out: if (r->mode != TOMOYO_CONFIG_ENFORCING) error = 0; kfree(env_page.data); kfree(arg_ptr); return error; } /** * tomoyo_find_next_domain - Find a domain. * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_find_next_domain(struct linux_binprm *bprm) { struct tomoyo_domain_info *old_domain = tomoyo_domain(); struct tomoyo_domain_info *domain = NULL; const char *original_name = bprm->filename; int retval = -ENOMEM; bool reject_on_transition_failure = false; const struct tomoyo_path_info *candidate; struct tomoyo_path_info exename; struct tomoyo_execve *ee = kzalloc(sizeof(*ee), GFP_NOFS); if (!ee) return -ENOMEM; ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!ee->tmp) { kfree(ee); return -ENOMEM; } /* ee->dump->data is allocated by tomoyo_dump_page(). */ tomoyo_init_request_info(&ee->r, NULL, TOMOYO_MAC_FILE_EXECUTE); ee->r.ee = ee; ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* Get symlink's pathname of program. */ exename.name = tomoyo_realpath_nofollow(original_name); if (!exename.name) { /* Fallback to realpath if symlink's pathname does not exist. */ exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); if (!exename.name) goto out; } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ { struct tomoyo_aggregator *ptr; struct list_head *list = &old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR]; /* Check 'aggregator' directive. */ candidate = &exename; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) continue; candidate = ptr->aggregated_name; break; } } /* Check execute permission. */ retval = tomoyo_execute_permission(&ee->r, candidate); if (retval == TOMOYO_RETRY_REQUEST) goto retry; if (retval < 0) goto out; /* * To be able to specify domainnames with wildcards, use the * pathname specified in the policy (which may contain * wildcard) rather than the pathname passed to execve() * (which never contains wildcard). */ if (ee->r.param.path.matched_path) candidate = ee->r.param.path.matched_path; /* * Check for domain transition preference if "file execute" matched. * If preference is given, make execve() fail if domain transition * has failed, for domain transition preference should be used with * destination domain defined. */ if (ee->transition) { const char *domainname = ee->transition->name; reject_on_transition_failure = true; if (!strcmp(domainname, "keep")) goto force_keep_domain; if (!strcmp(domainname, "child")) goto force_child_domain; if (!strcmp(domainname, "reset")) goto force_reset_domain; if (!strcmp(domainname, "initialize")) goto force_initialize_domain; if (!strcmp(domainname, "parent")) { char *cp; strscpy(ee->tmp, old_domain->domainname->name, TOMOYO_EXEC_TMPSIZE); cp = strrchr(ee->tmp, ' '); if (cp) *cp = '\0'; } else if (*domainname == '<') strscpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE); else snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, domainname); goto force_jump_domain; } /* * No domain transition preference specified. * Calculate domain to transit to. */ switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname, candidate)) { case TOMOYO_TRANSITION_CONTROL_RESET: force_reset_domain: /* Transit to the root of specified namespace. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", candidate->name); /* * Make execve() fail if domain transition across namespaces * has failed. */ reject_on_transition_failure = true; break; case TOMOYO_TRANSITION_CONTROL_INITIALIZE: force_initialize_domain: /* Transit to the child of current namespace's root. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->ns->name, candidate->name); break; case TOMOYO_TRANSITION_CONTROL_KEEP: force_keep_domain: /* Keep current domain. */ domain = old_domain; break; default: if (old_domain == &tomoyo_kernel_domain && !tomoyo_policy_loaded) { /* * Needn't to transit from kernel domain before * starting /sbin/init. But transit from kernel domain * if executing initializers because they might start * before /sbin/init. */ domain = old_domain; break; } force_child_domain: /* Normal domain transition. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, candidate->name); break; } force_jump_domain: if (!domain) domain = tomoyo_assign_domain(ee->tmp, true); if (domain) retval = 0; else if (reject_on_transition_failure) { pr_warn("ERROR: Domain '%s' not ready.\n", ee->tmp); retval = -ENOMEM; } else if (ee->r.mode == TOMOYO_CONFIG_ENFORCING) retval = -ENOMEM; else { retval = 0; if (!old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED]) { old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED] = true; ee->r.granted = false; tomoyo_write_log(&ee->r, "%s", tomoyo_dif [TOMOYO_DIF_TRANSITION_FAILED]); pr_warn("ERROR: Domain '%s' not defined.\n", ee->tmp); } } out: if (!domain) domain = old_domain; /* Update reference count on "struct tomoyo_domain_info". */ { struct tomoyo_task *s = tomoyo_task(current); s->old_domain_info = s->domain_info; s->domain_info = domain; atomic_inc(&domain->users); } kfree(exename.name); if (!retval) { ee->r.domain = domain; retval = tomoyo_environ(ee); } kfree(ee->tmp); kfree(ee->dump.data); kfree(ee); return retval; } /** * tomoyo_dump_page - Dump a page to buffer. * * @bprm: Pointer to "struct linux_binprm". * @pos: Location to dump. * @dump: Pointer to "struct tomoyo_page_dump". * * Returns true on success, false otherwise. */ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump) { struct page *page; #ifdef CONFIG_MMU int ret; #endif /* dump->data is released by tomoyo_find_next_domain(). */ if (!dump->data) { dump->data = kzalloc(PAGE_SIZE, GFP_NOFS); if (!dump->data) return false; } /* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */ #ifdef CONFIG_MMU /* * This is called at execve() time in order to dig around * in the argv/environment of the new proceess * (represented by bprm). */ mmap_read_lock(bprm->mm); ret = get_user_pages_remote(bprm->mm, pos, 1, FOLL_FORCE, &page, NULL); mmap_read_unlock(bprm->mm); if (ret <= 0) return false; #else page = bprm->page[pos / PAGE_SIZE]; #endif if (page != dump->page) { const unsigned int offset = pos % PAGE_SIZE; /* * Maybe kmap()/kunmap() should be used here. * But remove_arg_zero() uses kmap_atomic()/kunmap_atomic(). * So do I. */ char *kaddr = kmap_atomic(page); dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); kunmap_atomic(kaddr); } /* Same with put_arg_page(page) in fs/exec.c */ #ifdef CONFIG_MMU put_page(page); #endif return true; } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Pieter Beyens <pieter.beyens@eia.be> // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2018 Protonic, // Robin van der Gracht <robin@protonic.nl> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> /* Core of can-j1939 that links j1939 to CAN. */ #include <linux/can/can-ml.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/if_arp.h> #include <linux/module.h> #include "j1939-priv.h" MODULE_DESCRIPTION("PF_CAN SAE J1939"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("EIA Electronics (Kurt Van Dijck & Pieter Beyens)"); MODULE_ALIAS("can-proto-" __stringify(CAN_J1939)); /* LOWLEVEL CAN interface */ /* CAN_HDR: #bytes before can_frame data part */ #define J1939_CAN_HDR (offsetof(struct can_frame, data)) /* lowest layer */ static void j1939_can_recv(struct sk_buff *iskb, void *data) { struct j1939_priv *priv = data; struct sk_buff *skb; struct j1939_sk_buff_cb *skcb, *iskcb; struct can_frame *cf; /* make sure we only get Classical CAN frames */ if (!can_is_can_skb(iskb)) return; /* create a copy of the skb * j1939 only delivers the real data bytes, * the header goes into sockaddr. * j1939 may not touch the incoming skb in such way */ skb = skb_clone(iskb, GFP_ATOMIC); if (!skb) return; j1939_priv_get(priv); can_skb_set_owner(skb, iskb->sk); /* get a pointer to the header of the skb * the skb payload (pointer) is moved, so that the next skb_data * returns the actual payload */ cf = (void *)skb->data; skb_pull(skb, J1939_CAN_HDR); /* fix length, set to dlc, with 8 maximum */ skb_trim(skb, min_t(uint8_t, cf->len, 8)); /* set addr */ skcb = j1939_skb_to_cb(skb); memset(skcb, 0, sizeof(*skcb)); iskcb = j1939_skb_to_cb(iskb); skcb->tskey = iskcb->tskey; skcb->priority = (cf->can_id >> 26) & 0x7; skcb->addr.sa = cf->can_id; skcb->addr.pgn = (cf->can_id >> 8) & J1939_PGN_MAX; /* set default message type */ skcb->addr.type = J1939_TP; if (!j1939_address_is_valid(skcb->addr.sa)) { netdev_err_once(priv->ndev, "%s: sa is broadcast address, ignoring!\n", __func__); goto done; } if (j1939_pgn_is_pdu1(skcb->addr.pgn)) { /* Type 1: with destination address */ skcb->addr.da = skcb->addr.pgn; /* normalize pgn: strip dst address */ skcb->addr.pgn &= 0x3ff00; } else { /* set broadcast address */ skcb->addr.da = J1939_NO_ADDR; } /* update localflags */ read_lock_bh(&priv->lock); if (j1939_address_is_unicast(skcb->addr.sa) && priv->ents[skcb->addr.sa].nusers) skcb->flags |= J1939_ECU_LOCAL_SRC; if (j1939_address_is_unicast(skcb->addr.da) && priv->ents[skcb->addr.da].nusers) skcb->flags |= J1939_ECU_LOCAL_DST; read_unlock_bh(&priv->lock); /* deliver into the j1939 stack ... */ j1939_ac_recv(priv, skb); if (j1939_tp_recv(priv, skb)) /* this means the transport layer processed the message */ goto done; j1939_simple_recv(priv, skb); j1939_sk_recv(priv, skb); done: j1939_priv_put(priv); kfree_skb(skb); } /* NETDEV MANAGEMENT */ /* values for can_rx_(un)register */ #define J1939_CAN_ID CAN_EFF_FLAG #define J1939_CAN_MASK (CAN_EFF_FLAG | CAN_RTR_FLAG) static DEFINE_MUTEX(j1939_netdev_lock); static struct j1939_priv *j1939_priv_create(struct net_device *ndev) { struct j1939_priv *priv; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return NULL; rwlock_init(&priv->lock); INIT_LIST_HEAD(&priv->ecus); priv->ndev = ndev; kref_init(&priv->kref); kref_init(&priv->rx_kref); dev_hold(ndev); netdev_dbg(priv->ndev, "%s : 0x%p\n", __func__, priv); return priv; } static inline void j1939_priv_set(struct net_device *ndev, struct j1939_priv *priv) { struct can_ml_priv *can_ml = can_get_ml_priv(ndev); can_ml->j1939_priv = priv; } static void __j1939_priv_release(struct kref *kref) { struct j1939_priv *priv = container_of(kref, struct j1939_priv, kref); struct net_device *ndev = priv->ndev; netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv); WARN_ON_ONCE(!list_empty(&priv->active_session_list)); WARN_ON_ONCE(!list_empty(&priv->ecus)); WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); dev_put(ndev); kfree(priv); } void j1939_priv_put(struct j1939_priv *priv) { kref_put(&priv->kref, __j1939_priv_release); } void j1939_priv_get(struct j1939_priv *priv) { kref_get(&priv->kref); } static int j1939_can_rx_register(struct j1939_priv *priv) { struct net_device *ndev = priv->ndev; int ret; j1939_priv_get(priv); ret = can_rx_register(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv, "j1939", NULL); if (ret < 0) { j1939_priv_put(priv); return ret; } return 0; } static void j1939_can_rx_unregister(struct j1939_priv *priv) { struct net_device *ndev = priv->ndev; can_rx_unregister(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv); /* The last reference of priv is dropped by the RCU deferred * j1939_sk_sock_destruct() of the last socket, so we can * safely drop this reference here. */ j1939_priv_put(priv); } static void __j1939_rx_release(struct kref *kref) __releases(&j1939_netdev_lock) { struct j1939_priv *priv = container_of(kref, struct j1939_priv, rx_kref); j1939_can_rx_unregister(priv); j1939_ecu_unmap_all(priv); j1939_priv_set(priv->ndev, NULL); mutex_unlock(&j1939_netdev_lock); } /* get pointer to priv without increasing ref counter */ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { struct can_ml_priv *can_ml = can_get_ml_priv(ndev); return can_ml->j1939_priv; } static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) { struct j1939_priv *priv; lockdep_assert_held(&j1939_netdev_lock); priv = j1939_ndev_to_priv(ndev); if (priv) j1939_priv_get(priv); return priv; } static struct j1939_priv *j1939_priv_get_by_ndev(struct net_device *ndev) { struct j1939_priv *priv; mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); mutex_unlock(&j1939_netdev_lock); return priv; } struct j1939_priv *j1939_netdev_start(struct net_device *ndev) { struct j1939_priv *priv, *priv_new; int ret; mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); if (priv) { kref_get(&priv->rx_kref); mutex_unlock(&j1939_netdev_lock); return priv; } mutex_unlock(&j1939_netdev_lock); priv = j1939_priv_create(ndev); if (!priv) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); priv_new = j1939_priv_get_by_ndev_locked(ndev); if (priv_new) { /* Someone was faster than us, use their priv and roll * back our's. */ kref_get(&priv_new->rx_kref); mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return priv_new; } j1939_priv_set(ndev, priv); ret = j1939_can_rx_register(priv); if (ret < 0) goto out_priv_put; mutex_unlock(&j1939_netdev_lock); return priv; out_priv_put: j1939_priv_set(ndev, NULL); mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return ERR_PTR(ret); } void j1939_netdev_stop(struct j1939_priv *priv) { kref_put_mutex(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); j1939_priv_put(priv); } int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) { int ret, dlc; canid_t canid; struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); struct can_frame *cf; /* apply sanity checks */ if (j1939_pgn_is_pdu1(skcb->addr.pgn)) skcb->addr.pgn &= J1939_PGN_PDU1_MAX; else skcb->addr.pgn &= J1939_PGN_MAX; if (skcb->priority > 7) skcb->priority = 6; ret = j1939_ac_fixup(priv, skb); if (unlikely(ret)) goto failed; dlc = skb->len; /* re-claim the CAN_HDR from the SKB */ cf = skb_push(skb, J1939_CAN_HDR); /* initialize header structure */ memset(cf, 0, J1939_CAN_HDR); /* make it a full can frame again */ skb_put_zero(skb, 8 - dlc); canid = CAN_EFF_FLAG | (skcb->priority << 26) | (skcb->addr.pgn << 8) | skcb->addr.sa; if (j1939_pgn_is_pdu1(skcb->addr.pgn)) canid |= skcb->addr.da << 8; cf->can_id = canid; cf->len = dlc; return can_send(skb, 1); failed: kfree_skb(skb); return ret; } static int j1939_netdev_notify(struct notifier_block *nb, unsigned long msg, void *data) { struct net_device *ndev = netdev_notifier_info_to_dev(data); struct can_ml_priv *can_ml = can_get_ml_priv(ndev); struct j1939_priv *priv; if (!can_ml) goto notify_done; priv = j1939_priv_get_by_ndev(ndev); if (!priv) goto notify_done; switch (msg) { case NETDEV_DOWN: j1939_cancel_active_session(priv, NULL); j1939_sk_netdev_event_netdown(priv); j1939_ecu_unmap_all(priv); break; } j1939_priv_put(priv); notify_done: return NOTIFY_DONE; } static struct notifier_block j1939_netdev_notifier = { .notifier_call = j1939_netdev_notify, }; /* MODULE interface */ static __init int j1939_module_init(void) { int ret; pr_info("can: SAE J1939\n"); ret = register_netdevice_notifier(&j1939_netdev_notifier); if (ret) goto fail_notifier; ret = can_proto_register(&j1939_can_proto); if (ret < 0) { pr_err("can: registration of j1939 protocol failed\n"); goto fail_sk; } return 0; fail_sk: unregister_netdevice_notifier(&j1939_netdev_notifier); fail_notifier: return ret; } static __exit void j1939_module_exit(void) { can_proto_unregister(&j1939_can_proto); unregister_netdevice_notifier(&j1939_netdev_notifier); } module_init(j1939_module_init); module_exit(j1939_module_exit); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the IP protocol. * * Version: @(#)ip.h 1.0.2 04/28/93 * * Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_IP_H #define _LINUX_IP_H #include <linux/skbuff.h> #include <uapi/linux/ip.h> static inline struct iphdr *ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_network_header(skb); } static inline struct iphdr *inner_ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_inner_network_header(skb); } static inline struct iphdr *ipip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_transport_header(skb); } static inline unsigned int ip_transport_len(const struct sk_buff *skb) { return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb); } static inline unsigned int iph_totlen(const struct sk_buff *skb, const struct iphdr *iph) { u32 len = ntohs(iph->tot_len); return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? len : skb->len - skb_network_offset(skb); } static inline unsigned int skb_ip_totlen(const struct sk_buff *skb) { return iph_totlen(skb, ip_hdr(skb)); } /* IPv4 datagram length is stored into 16bit field (tot_len) */ #define IP_MAX_MTU 0xFFFFU static inline void iph_set_totlen(struct iphdr *iph, unsigned int len) { iph->tot_len = len <= IP_MAX_MTU ? htons(len) : 0; } #endif /* _LINUX_IP_H */ |
| 248 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 145 263 263 10 1 10 10 10 7 6 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/xarray.h> /** * idr_alloc_u32() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @nextid: Pointer to an ID. * @max: The maximum ID to allocate (inclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @nextid and @max. * Note that @max is inclusive whereas the @end parameter to idr_alloc() * is exclusive. The new ID is assigned to @nextid before the pointer * is inserted into the IDR, so if @nextid points into the object pointed * to by @ptr, a concurrent lookup will not find an uninitialised ID. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. If an error occurred, * @nextid is unchanged. */ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, unsigned long max, gfp_t gfp) { struct radix_tree_iter iter; void __rcu **slot; unsigned int base = idr->idr_base; unsigned int id = *nextid; if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base); if (IS_ERR(slot)) return PTR_ERR(slot); *nextid = iter.index + base; /* there is a memory barrier inside radix_tree_iter_replace() */ radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr); radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE); return 0; } EXPORT_SYMBOL_GPL(idr_alloc_u32); /** * idr_alloc() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = start; int ret; if (WARN_ON_ONCE(start < 0)) return -EINVAL; ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp); if (ret) return ret; return id; } EXPORT_SYMBOL_GPL(idr_alloc); /** * idr_alloc_cyclic() - Allocate an ID cyclically. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * The search for an unused ID will start at the last ID allocated and will * wrap around to @start if no free IDs are found before reaching @end. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = idr->idr_next; int err, max = end > 0 ? end - 1 : INT_MAX; if ((int)id < start) id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); if ((err == -ENOSPC) && (id > start)) { id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); } if (err) return err; idr->idr_next = id + 1; return id; } EXPORT_SYMBOL(idr_alloc_cyclic); /** * idr_remove() - Remove an ID from the IDR. * @idr: IDR handle. * @id: Pointer ID. * * Removes this ID from the IDR. If the ID was not previously in the IDR, * this function returns %NULL. * * Since this function modifies the IDR, the caller should provide their * own locking to ensure that concurrent modification of the same IDR is * not possible. * * Return: The pointer formerly associated with this ID. */ void *idr_remove(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL); } EXPORT_SYMBOL_GPL(idr_remove); /** * idr_find() - Return pointer for given ID. * @idr: IDR handle. * @id: Pointer ID. * * Looks up the pointer associated with this ID. A %NULL pointer may * indicate that @id is not allocated or that the %NULL pointer was * associated with this ID. * * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. * * Return: The pointer associated with this ID. */ void *idr_find(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base); } EXPORT_SYMBOL_GPL(idr_find); /** * idr_for_each() - Iterate through all stored pointers. * @idr: IDR handle. * @fn: Function to be called for each pointer. * @data: Data passed to callback function. * * The callback function will be called for each entry in @idr, passing * the ID, the entry and @data. * * If @fn returns anything other than %0, the iteration stops and that * value is returned from this function. * * idr_for_each() can be called concurrently with idr_alloc() and * idr_remove() if protected by RCU. Newly added entries may not be * seen and deleted entries may be seen, but adding and removing entries * will not cause other entries to be skipped, nor spurious ones to be seen. */ int idr_for_each(const struct idr *idr, int (*fn)(int id, void *p, void *data), void *data) { struct radix_tree_iter iter; void __rcu **slot; int base = idr->idr_base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { int ret; unsigned long id = iter.index + base; if (WARN_ON_ONCE(id > INT_MAX)) break; ret = fn(id, rcu_dereference_raw(*slot), data); if (ret) return ret; } return 0; } EXPORT_SYMBOL(idr_for_each); /** * idr_get_next_ul() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; void *entry = NULL; unsigned long base = idr->idr_base; unsigned long id = *nextid; id = (id < base) ? 0 : id - base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) { entry = rcu_dereference_raw(*slot); if (!entry) continue; if (!xa_is_internal(entry)) break; if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry)) break; slot = radix_tree_iter_retry(&iter); } if (!slot) return NULL; *nextid = iter.index + base; return entry; } EXPORT_SYMBOL(idr_get_next_ul); /** * idr_get_next() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next(struct idr *idr, int *nextid) { unsigned long id = *nextid; void *entry = idr_get_next_ul(idr, &id); if (WARN_ON_ONCE(id > INT_MAX)) return NULL; *nextid = id; return entry; } EXPORT_SYMBOL(idr_get_next); /** * idr_replace() - replace pointer for given ID. * @idr: IDR handle. * @ptr: New pointer to associate with the ID. * @id: ID to change. * * Replace the pointer registered with an ID and return the old value. * This function can be called under the RCU read lock concurrently with * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * * Returns: the old value on success. %-ENOENT indicates that @id was not * found. %-EINVAL indicates that @ptr was not valid. */ void *idr_replace(struct idr *idr, void *ptr, unsigned long id) { struct radix_tree_node *node; void __rcu **slot = NULL; void *entry; id -= idr->idr_base; entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot); if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) return ERR_PTR(-ENOENT); __radix_tree_replace(&idr->idr_rt, node, slot, ptr); return entry; } EXPORT_SYMBOL(idr_replace); /** * DOC: IDA description * * The IDA is an ID allocator which does not provide the ability to * associate an ID with a pointer. As such, it only needs to store one * bit per ID, and so is more space efficient than an IDR. To use an IDA, * define it using DEFINE_IDA() (or embed a &struct ida in a data structure, * then initialise it using ida_init()). To allocate a new ID, call * ida_alloc(), ida_alloc_min(), ida_alloc_max() or ida_alloc_range(). * To free an ID, call ida_free(). * * ida_destroy() can be used to dispose of an IDA without needing to * free the individual IDs in it. You can use ida_is_empty() to find * out whether the IDA has any IDs currently allocated. * * The IDA handles its own locking. It is safe to call any of the IDA * functions without synchronisation in your code. * * IDs are currently limited to the range [0-INT_MAX]. If this is an awkward * limitation, it should be quite straightforward to raise the maximum. */ /* * Developer's notes: * * The IDA uses the functionality provided by the XArray to store bitmaps in * each entry. The XA_FREE_MARK is only cleared when all bits in the bitmap * have been set. * * I considered telling the XArray that each slot is an order-10 node * and indexing by bit number, but the XArray can't allow a single multi-index * entry in the head, which would significantly increase memory consumption * for the IDA. So instead we divide the index by the number of bits in the * leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given * leaf, instead of allocating a 128-byte bitmap, we store the bits * as a value entry. Value entries never have the XA_FREE_MARK cleared * because we can always convert them into a bitmap entry. * * It would be possible to optimise further; once we've run out of a * single 128-byte bitmap, we currently switch to a 576-byte node, put * the 128-byte bitmap in the first entry and then start allocating extra * 128-byte entries. We could instead use the 512 bytes of the node's * data as a bitmap before moving to that scheme. I do not believe this * is a worthwhile optimisation; Rasmus Villemoes surveyed the current * users of the IDA and almost none of them use more than 1024 entries. * Those that do use more than the 8192 IDs that the 512 bytes would * provide. * * The IDA always uses a lock to alloc/free. If we add a 'test_bit' * equivalent, it will still need locking. Going to RCU lookup would require * using RCU to free bitmaps, and that's not trivial without embedding an * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte * bitmap, which is excessive. */ /** * ida_alloc_range() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and @max, inclusive. The allocated ID will * not exceed %INT_MAX, even if @max is larger. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max, gfp_t gfp) { XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS); unsigned bit = min % IDA_BITMAP_BITS; unsigned long flags; struct ida_bitmap *bitmap, *alloc = NULL; if ((int)min < 0) return -ENOSPC; if ((int)max < 0) max = INT_MAX; retry: xas_lock_irqsave(&xas, flags); next: bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK); if (xas.xa_index > min / IDA_BITMAP_BITS) bit = 0; if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (xa_is_value(bitmap)) { unsigned long tmp = xa_to_value(bitmap); if (bit < BITS_PER_XA_VALUE) { bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit < BITS_PER_XA_VALUE) { tmp |= 1UL << bit; xas_store(&xas, xa_mk_value(tmp)); goto out; } } bitmap = alloc; if (!bitmap) bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); if (!bitmap) goto alloc; bitmap->bitmap[0] = tmp; xas_store(&xas, bitmap); if (xas_error(&xas)) { bitmap->bitmap[0] = 0; goto out; } } if (bitmap) { bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit == IDA_BITMAP_BITS) goto next; __set_bit(bit, bitmap->bitmap); if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) xas_clear_mark(&xas, XA_FREE_MARK); } else { if (bit < BITS_PER_XA_VALUE) { bitmap = xa_mk_value(1UL << bit); } else { bitmap = alloc; if (!bitmap) bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); if (!bitmap) goto alloc; __set_bit(bit, bitmap->bitmap); } xas_store(&xas, bitmap); } out: xas_unlock_irqrestore(&xas, flags); if (xas_nomem(&xas, gfp)) { xas.xa_index = min / IDA_BITMAP_BITS; bit = min % IDA_BITMAP_BITS; goto retry; } if (bitmap != alloc) kfree(alloc); if (xas_error(&xas)) return xas_error(&xas); return xas.xa_index * IDA_BITMAP_BITS + bit; alloc: xas_unlock_irqrestore(&xas, flags); alloc = kzalloc(sizeof(*bitmap), gfp); if (!alloc) return -ENOMEM; xas_set(&xas, min / IDA_BITMAP_BITS); bit = min % IDA_BITMAP_BITS; goto retry; nospc: xas_unlock_irqrestore(&xas, flags); kfree(alloc); return -ENOSPC; } EXPORT_SYMBOL(ida_alloc_range); /** * ida_free() - Release an allocated ID. * @ida: IDA handle. * @id: Previously allocated ID. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_free(struct ida *ida, unsigned int id) { XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS); unsigned bit = id % IDA_BITMAP_BITS; struct ida_bitmap *bitmap; unsigned long flags; if ((int)id < 0) return; xas_lock_irqsave(&xas, flags); bitmap = xas_load(&xas); if (xa_is_value(bitmap)) { unsigned long v = xa_to_value(bitmap); if (bit >= BITS_PER_XA_VALUE) goto err; if (!(v & (1UL << bit))) goto err; v &= ~(1UL << bit); if (!v) goto delete; xas_store(&xas, xa_mk_value(v)); } else { if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) { kfree(bitmap); delete: xas_store(&xas, NULL); } } xas_unlock_irqrestore(&xas, flags); return; err: xas_unlock_irqrestore(&xas, flags); WARN(1, "ida_free called for id=%d which is not allocated.\n", id); } EXPORT_SYMBOL(ida_free); /** * ida_destroy() - Free all IDs. * @ida: IDA handle. * * Calling this function frees all IDs and releases all resources used * by an IDA. When this call returns, the IDA is empty and can be reused * or freed. If the IDA is already empty, there is no need to call this * function. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_destroy(struct ida *ida) { XA_STATE(xas, &ida->xa, 0); struct ida_bitmap *bitmap; unsigned long flags; xas_lock_irqsave(&xas, flags); xas_for_each(&xas, bitmap, ULONG_MAX) { if (!xa_is_value(bitmap)) kfree(bitmap); xas_store(&xas, NULL); } xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(ida_destroy); #ifndef __KERNEL__ extern void xa_dump_index(unsigned long index, unsigned int shift); #define IDA_CHUNK_SHIFT ilog2(IDA_BITMAP_BITS) static void ida_dump_entry(void *entry, unsigned long index) { unsigned long i; if (!entry) return; if (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); unsigned int shift = node->shift + IDA_CHUNK_SHIFT + XA_CHUNK_SHIFT; xa_dump_index(index * IDA_BITMAP_BITS, shift); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) ida_dump_entry(node->slots[i], index | (i << node->shift)); } else if (xa_is_value(entry)) { xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG)); pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry); } else { struct ida_bitmap *bitmap = entry; xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT); pr_cont("bitmap: %p data", bitmap); for (i = 0; i < IDA_BITMAP_LONGS; i++) pr_cont(" %lx", bitmap->bitmap[i]); pr_cont("\n"); } } static void ida_dump(struct ida *ida) { struct xarray *xa = &ida->xa; pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head, xa->xa_flags >> ROOT_TAG_SHIFT); ida_dump_entry(xa->xa_head, 0); } #endif |
| 875 875 186 875 875 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/cleanup.h> #include <linux/kernel.h> #include <linux/bitmap.h> #include <linux/cpumask_types.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/gfp_types.h> #include <linux/numa.h> /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) #define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); #else nr_cpu_ids = nr; #endif } /* * We have several different "preferred sizes" for the cpumask * operations, depending on operation. * * For example, the bitmap scanning and operating operations have * optimized routines that work for the single-word case, but only when * the size is constant. So if NR_CPUS fits in one single word, we are * better off using that small constant, in order to trigger the * optimized bit finding. That is 'small_cpumask_size'. * * The clearing and copying operations will similarly perform better * with a constant size, but we limit that size arbitrarily to four * words. We call this 'large_cpumask_size'. * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask * allocations are at least that size (see cpumask_size()). The * optimization comes from being able to potentially use a compile-time * constant instead of a run-time generated exact number of CPUs. */ #if NR_CPUS <= BITS_PER_LONG #define small_cpumask_bits ((unsigned int)NR_CPUS) #define large_cpumask_bits ((unsigned int)NR_CPUS) #elif NR_CPUS <= 4*BITS_PER_LONG #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits ((unsigned int)NR_CPUS) #else #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits nr_cpu_ids #endif #define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if all cpus are set. */ static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 * @srcp1: the first input * @srcp2: the second input * @srcp3: the third input * * Return: >= nr_cpu_ids if no cpus set in all. */ static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set. */ static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus unset. */ static __always_inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static __always_inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static __always_inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } static __always_inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } #else unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); unsigned int cpumask_any_distribute(const struct cpumask *srcp); #endif /* NR_CPUS */ /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); if (n != -1) cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, * since there is only one valid option. */ if (wrap && n >= 0) return nr_cpumask_bits; return cpumask_first(mask); } #else unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); #endif /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding * those present in another. * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_andnot(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_or - iterate over every cpu present in either mask * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_or(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_or(cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_from(cpu, mask) \ for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } /** * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) { unsigned int i; cpumask_check(cpu); i = cpumask_first_and(mask1, mask2); if (i != cpu) return i; return cpumask_next_and(cpu, mask1, mask2); } /** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_assign_cpu - assign a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer * @bool: the value to assign */ static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { __assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_set_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_clear_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); return; } bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input * * Return: true if the cpumasks are equal, false if not */ static __always_inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input * * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ static __always_inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input * * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ static __always_inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Return: true if *@src1p is a subset of *@src2p, else returns false */ static __always_inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. * * Return: true if srcp is empty (has no bits set), else false */ static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. * * Return: true if srcp is full (has all bits set), else false */ static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in *srcp */ static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static __always_inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** * cpumask_any - pick a "random" cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes * * Return: size to allocate for a &struct cpumask in bytes */ static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } #ifdef CONFIG_CPUMASK_OFFSTACK #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. * * Return: %true if allocation succeeded, %false if not */ static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static __always_inline void free_cpumask_var(cpumask_var_t mask) { } static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #if NR_CPUS == 1 /* Uniprocessor: the possible/online/present masks are always "1" */ #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. * * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_dying(unsigned int cpu) { return false; } #endif /* NR_CPUS > 1 */ #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } /** * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as * hex values of cpumask * * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * The function prints the cpumask into the buffer as hex values of * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } /* * Provide a valid theoretical max size for cpumap and cpulist sysfs files * to avoid breaking userspace which may allocate a buffer based on the size * reported by e.g. fstat. * * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. * * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up * to 2 orders of magnitude larger than 8192. And then we divide by 2 to * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * * Use PAGE_SIZE as a minimum for smaller configurations while avoiding * unsigned comparison to -1. */ #define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) #endif /* __LINUX_CPUMASK_H */ |
| 143 246 246 173 163 246 162 173 173 1 246 1 1 1 1 23 23 15 17 23 17 15 15 23 23 186 186 186 186 186 186 186 186 186 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 | // SPDX-License-Identifier: GPL-2.0-only /* * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> #include <asm/sections.h> /* mutex to protect coming/going of the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); void jump_label_lock(void) { mutex_lock(&jump_label_mutex); } void jump_label_unlock(void) { mutex_unlock(&jump_label_mutex); } static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; const struct jump_entry *jeb = b; /* * Entrires are sorted by key. */ if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; /* * In the batching mode, entries should also be sorted by the code * inside the already sorted list of entries, enabling a bsearch in * the vector. */ if (jump_entry_code(jea) < jump_entry_code(jeb)) return -1; if (jump_entry_code(jea) > jump_entry_code(jeb)) return 1; return 0; } static void jump_label_swap(void *a, void *b, int size) { long delta = (unsigned long)a - (unsigned long)b; struct jump_entry *jea = a; struct jump_entry *jeb = b; struct jump_entry tmp = *jea; jea->code = jeb->code - delta; jea->target = jeb->target - delta; jea->key = jeb->key - delta; jeb->code = tmp.code + delta; jeb->target = tmp.target + delta; jeb->key = tmp.key + delta; } static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; void *swapfn = NULL; if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); /* * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h. * The use of 'atomic_read()' requires atomic.h and its problematic for some * kernel headers such as kernel.h and others. Since static_key_count() is not * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok * to have it be a function here. Similarly, for 'static_key_enable()' and * 'static_key_disable()', which require bug.h. This should allow jump_label.h * to be included from most/all places for CONFIG_JUMP_LABEL. */ int static_key_count(struct static_key *key) { /* * -1 means the first static_key_slow_inc() is in progress. * static_key_enabled() must return true, so return 1 here. */ int n = atomic_read(&key->enabled); return n >= 0 ? n : 1; } EXPORT_SYMBOL_GPL(static_key_count); /* * static_key_fast_inc_not_disabled - adds a user for a static key * @key: static key that must be already enabled * * The caller must make sure that the static key can't get disabled while * in this function. It doesn't patch jump labels, only adds a user to * an already enabled static key. * * Returns true if the increment was done. Unlike refcount_t the ref counter * is not saturated, but will fail to increment on overflow. */ bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Negative key->enabled has a special meaning: it sends * static_key_slow_inc/dec() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). * * The INT_MAX overflow condition is either used by the networking * code to reset or detected in the slow path of * static_key_slow_inc_cpuslocked(). */ v = atomic_read(&key->enabled); do { if (v <= 0 || v == INT_MAX) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); bool static_key_slow_inc_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc/dec() calls; * later calls must wait for the first one to _finish_ the * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. */ if (static_key_fast_inc_not_disabled(key)) return true; guard(mutex)(&jump_label_mutex); /* Try to mark it as 'enabling in progress. */ if (!atomic_cmpxchg(&key->enabled, 0, -1)) { jump_label_update(key); /* * Ensure that when static_key_fast_inc_not_disabled() or * static_key_dec_not_one() observe the positive value, * they must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { /* * While holding the mutex this should never observe * anything else than a value >= 1 and succeed */ if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) return false; } return true; } bool static_key_slow_inc(struct static_key *key) { bool ret; cpus_read_lock(); ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * See static_key_slow_inc(). */ atomic_set_release(&key->enabled, 1); } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked); void static_key_enable(struct static_key *key) { cpus_read_lock(); static_key_enable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } jump_label_lock(); if (atomic_cmpxchg(&key->enabled, 1, 0) == 1) jump_label_update(key); jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked); void static_key_disable(struct static_key *key) { cpus_read_lock(); static_key_disable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable); static bool static_key_dec_not_one(struct static_key *key) { int v; /* * Go into the slow path if key::enabled is less than or equal than * one. One is valid to shut down the key, anything less than one * is an imbalance, which is handled at the call site. * * That includes the special case of '-1' which is set in * static_key_slow_inc_cpuslocked(), but that's harmless as it is * fully serialized in the slow path below. By the time this task * acquires the jump label lock the value is back to one and the * retry under the lock must succeed. */ v = atomic_read(&key->enabled); do { /* * Warn about the '-1' case though; since that means a * decrement is concurrent with a first (0->1) increment. IOW * people are trying to disable something that wasn't yet fully * enabled. This suggests an ordering problem on the user side. */ WARN_ON_ONCE(v < 0); /* * Warn about underflow, and lie about success in an attempt to * not make things worse. */ if (WARN_ON_ONCE(v == 0)) return true; if (v <= 1) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1))); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); int val; if (static_key_dec_not_one(key)) return; guard(mutex)(&jump_label_mutex); val = atomic_read(&key->enabled); /* * It should be impossible to observe -1 with jump_label_mutex held, * see static_key_slow_inc_cpuslocked(). */ if (WARN_ON_ONCE(val == -1)) return; /* * Cannot already be 0, something went sideways. */ if (WARN_ON_ONCE(val == 0)) return; if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); } static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key); } EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec_cpuslocked(key); } void __static_key_slow_dec_deferred(struct static_key *key, struct delayed_work *work, unsigned long timeout) { STATIC_KEY_CHECK_USE(key); if (static_key_dec_not_one(key)) return; schedule_delayed_work(work, timeout); } EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); flush_delayed_work(work); } EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { if (jump_entry_code(entry) <= (unsigned long)end && jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start) return 1; return 0; } static int __jump_label_text_reserved(struct jump_entry *iter_start, struct jump_entry *iter_stop, void *start, void *end, bool init) { struct jump_entry *iter; iter = iter_start; while (iter < iter_stop) { if (init || !jump_entry_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifndef arch_jump_label_transform_static static void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { /* nothing to do on most architectures */ } #endif static inline struct jump_entry *static_key_entries(struct static_key *key) { WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK); } static inline bool static_key_type(struct static_key *key) { return key->type & JUMP_TYPE_TRUE; } static inline bool static_key_linked(struct static_key *key) { return key->type & JUMP_TYPE_LINKED; } static inline void static_key_clear_linked(struct static_key *key) { key->type &= ~JUMP_TYPE_LINKED; } static inline void static_key_set_linked(struct static_key *key) { key->type |= JUMP_TYPE_LINKED; } /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in * turn point to 'struct jump_entry' tables. * * The two lower bits of the pointer are used to keep track of which pointer * type is in use and to store the initial branch direction, we use an access * function which preserves these bits. */ static void static_key_set_entries(struct static_key *key, struct jump_entry *entries) { unsigned long type; WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->entries = entries; key->type |= type; } static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; } static bool jump_label_can_update(struct jump_entry *entry, bool init) { /* * Cannot update code that was in an init text area. */ if (!init && jump_entry_is_init(entry)) return false; if (!kernel_text_address(jump_entry_code(entry))) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); return false; } return true; } #ifndef HAVE_JUMP_LABEL_BATCH static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (jump_label_can_update(entry, init)) arch_jump_label_transform(entry, jump_label_type(entry)); } } #else static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init)) continue; if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) { /* * Queue is full: Apply the current queue and try again. */ arch_jump_label_transform_apply(); BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry))); } } arch_jump_label_transform_apply(); } #endif void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct static_key *key = NULL; struct jump_entry *iter; /* * Since we are initializing the static_key.enabled field with * with the 'raw' int values (to avoid pulling in atomic.h) in * jump_label.h, let's make sure that is safe. There are only two * cases to check since we initialize to 0 or 1. */ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); if (static_key_initialized) return; cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); in_init = init_section_contains((void *)jump_entry_code(iter), 1); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; static_key_set_entries(key, iter); } static_key_initialized = true; jump_label_unlock(); cpus_read_unlock(); } static inline bool static_key_sealed(struct static_key *key) { return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); } static inline void static_key_seal(struct static_key *key) { unsigned long type = key->type & JUMP_TYPE_TRUE; key->type = JUMP_TYPE_LINKED | type; } void jump_label_init_ro(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct jump_entry *iter; if (WARN_ON_ONCE(!static_key_initialized)) return; cpus_read_lock(); jump_label_lock(); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk = jump_entry_key(iter); if (!is_kernel_ro_after_init((unsigned long)iterk)) continue; if (static_key_sealed(iterk)) continue; static_key_seal(iterk); } jump_label_unlock(); cpus_read_unlock(); } #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; } struct static_key_mod { struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; static inline struct static_key_mod *static_key_mod(struct static_key *key) { WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } /*** * key->type and key->next are the same via union. * This sets key->next and preserves the type bits. * * See additional comments above static_key_set_entries(). */ static void static_key_set_mod(struct static_key *key, struct static_key_mod *mod) { unsigned long type; WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->next = mod; key->type |= type; } static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; preempt_disable(); mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; preempt_enable(); if (!mod) return 0; ret = __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static void __jump_label_mod_update(struct static_key *key) { struct static_key_mod *mod; for (mod = static_key_mod(key); mod; mod = mod->next) { struct jump_entry *stop; struct module *m; /* * NULL if the static_key is defined in a module * that does not use it */ if (!mod->entries) continue; m = mod->mod; if (!m) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; __jump_label_update(key, mod->entries, stop, m && m->state == MODULE_STATE_COMING); } } static int jump_label_add_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, *jlm2; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return 0; jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; in_init = within_module_init(jump_entry_code(iter), mod); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } /* * If the key was sealed at init, then there's no need to keep a * reference to its module entries - just patch them now and be * done with it. */ if (static_key_sealed(key)) goto do_poke; jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { jlm2 = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm2) { kfree(jlm); return -ENOMEM; } preempt_disable(); jlm2->mod = __module_address((unsigned long)key); preempt_enable(); jlm2->entries = static_key_entries(key); jlm2->next = NULL; static_key_set_mod(key, jlm2); static_key_set_linked(key); } jlm->mod = mod; jlm->entries = iter; jlm->next = static_key_mod(key); static_key_set_mod(key, jlm); static_key_set_linked(key); /* Only update if we've changed from our initial state */ do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } return 0; } static void jump_label_del_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (jump_entry_key(iter) == key) continue; key = jump_entry_key(iter); if (within_module((unsigned long)key, mod)) continue; /* No @jlm allocated because key was sealed at init. */ if (static_key_sealed(key)) continue; /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; prev = &key->next; jlm = static_key_mod(key); while (jlm && jlm->mod != mod) { prev = &jlm->next; jlm = jlm->next; } /* No memory during module load */ if (WARN_ON(!jlm)) continue; if (prev == &key->next) static_key_set_mod(key, jlm->next); else *prev = jlm->next; kfree(jlm); jlm = static_key_mod(key); /* if only one etry is left, fold it back into the static_key */ if (jlm->next == NULL) { static_key_set_entries(key, jlm->entries); static_key_clear_linked(key); kfree(jlm); } } } static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); jump_label_lock(); switch (val) { case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; case MODULE_STATE_GOING: jump_label_del_module(mod); break; } jump_label_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, .priority = 1, /* higher than tracepoints */ }; static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ /*** * jump_label_text_reserved - check if addr range is reserved * @start: start text addr * @end: end text addr * * checks if the text addr located between @start and @end * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ int jump_label_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __jump_label_text_reserved(__start___jump_table, __stop___jump_table, start, end, init); if (ret) return ret; #ifdef CONFIG_MODULES ret = __jump_label_mod_text_reserved(start, end); #endif return ret; } static void jump_label_update(struct static_key *key) { struct jump_entry *stop = __stop___jump_table; bool init = system_state < SYSTEM_RUNNING; struct jump_entry *entry; #ifdef CONFIG_MODULES struct module *mod; if (static_key_linked(key)) { __jump_label_mod_update(key); return; } preempt_disable(); mod = __module_address((unsigned long)key); if (mod) { stop = mod->jump_entries + mod->num_jump_entries; init = mod->state == MODULE_STATE_COMING; } preempt_enable(); #endif entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) __jump_label_update(key, entry, stop, init); } #ifdef CONFIG_STATIC_KEYS_SELFTEST static DEFINE_STATIC_KEY_TRUE(sk_true); static DEFINE_STATIC_KEY_FALSE(sk_false); static __init int jump_label_test(void) { int i; for (i = 0; i < 2; i++) { WARN_ON(static_key_enabled(&sk_true.key) != true); WARN_ON(static_key_enabled(&sk_false.key) != false); WARN_ON(!static_branch_likely(&sk_true)); WARN_ON(!static_branch_unlikely(&sk_true)); WARN_ON(static_branch_likely(&sk_false)); WARN_ON(static_branch_unlikely(&sk_false)); static_branch_disable(&sk_true); static_branch_enable(&sk_false); WARN_ON(static_key_enabled(&sk_true.key) == true); WARN_ON(static_key_enabled(&sk_false.key) == false); WARN_ON(static_branch_likely(&sk_true)); WARN_ON(static_branch_unlikely(&sk_true)); WARN_ON(!static_branch_likely(&sk_false)); WARN_ON(!static_branch_unlikely(&sk_false)); static_branch_enable(&sk_true); static_branch_disable(&sk_false); } return 0; } early_initcall(jump_label_test); #endif /* STATIC_KEYS_SELFTEST */ |
| 372 194 194 387 387 40 97 12 572 125 125 125 118 573 373 404 379 381 380 3 378 781 777 406 99 118 782 776 386 52 779 34 778 404 404 593 782 390 105 10 125 10 386 387 3 387 125 387 571 571 573 571 379 378 378 17 125 379 3 1 3 381 380 380 381 379 380 126 369 3 381 122 777 403 782 777 377 369 742 672 387 387 387 387 375 375 105 376 376 376 376 362 376 375 376 6 6 6 393 62 141 373 373 6 125 125 3 125 125 125 125 369 370 369 369 125 125 3 125 125 125 13 2 112 2 35 60 2 4 59 60 60 2 125 125 15 14 125 125 123 125 125 125 121 379 2 125 125 25 125 35 125 125 125 62 125 125 11 59 94 9 40 100 38 3 39 1 33 10 4 118 3 112 15 3 120 120 116 404 403 170 404 402 3 3 3 3 45 17 36 45 45 125 45 35 25 25 2 45 3 125 10 10 45 10 10 10 10 125 125 1 125 125 125 29 125 125 3 125 125 125 125 10 125 125 125 125 125 125 125 125 125 125 125 25 35 45 45 2 35 25 37 12 45 767 769 766 743 574 573 770 769 765 766 3 45 45 3 10 45 45 45 45 45 45 45 45 45 10 36 36 36 36 26 18 36 43 14 14 118 118 118 118 118 3 118 117 9 118 118 3 118 118 118 118 118 118 118 118 118 117 118 51 13 13 88 13 88 96 88 13 51 51 118 118 13 88 121 14 118 104 105 105 9 105 105 341 36 381 24 26 403 404 404 404 403 36 36 36 36 36 26 3 24 3 28 3 1 12 17 331 88 87 88 88 88 88 35 36 36 8 29 36 36 343 304 62 370 62 377 377 330 1 377 7 119 374 377 62 11 11 11 43 87 4 4 122 7 158 391 3 39 40 121 399 121 376 251 82 40 11 377 36 121 374 24 400 103 342 105 369 119 14 379 404 376 404 403 398 129 401 395 67 119 40 378 388 387 389 374 122 9 31 21 21 21 21 21 21 387 387 38 38 38 36 11 38 38 387 394 394 48 388 387 395 38 395 395 394 62 571 386 571 3 572 573 572 572 573 573 572 386 641 639 636 578 578 52 641 571 640 572 641 641 642 570 573 21 21 21 21 21 21 21 270 331 643 330 328 21 21 21 21 21 21 21 21 3 3 3 3 3 3 3 3 97 97 3 3 96 10 97 369 369 368 371 372 8 372 372 372 381 381 381 368 369 369 403 404 402 149 149 384 368 129 367 368 95 47 47 395 394 16 16 394 395 109 109 573 572 342 573 572 1 328 573 573 388 88 86 88 87 87 10 10 9 9 4 21 21 385 385 349 97 23 516 513 515 516 56 147 184 514 56 511 387 387 387 387 387 387 387 387 387 387 387 386 385 387 386 386 387 386 386 385 387 387 387 386 387 387 387 387 387 386 387 387 387 387 386 386 387 387 387 386 387 387 385 387 387 387 387 387 384 387 387 387 387 387 387 387 387 387 387 387 386 387 387 387 387 387 387 387 387 387 387 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 | // SPDX-License-Identifier: GPL-2.0+ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* * DOC: Interesting implementation details of the Maple Tree * * Each node type has a number of slots for entries and a number of slots for * pivots. In the case of dense nodes, the pivots are implied by the position * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges. Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * * * The following illustrates the layout of a range64 nodes slots and pivots. * * * Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 | * ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ * │ │ │ │ │ │ │ │ └─ Implied maximum * │ │ │ │ │ │ │ └─ Pivot 14 * │ │ │ │ │ │ └─ Pivot 13 * │ │ │ │ │ └─ Pivot 12 * │ │ │ │ └─ Pivot 11 * │ │ │ └─ Pivot 2 * │ │ └─ Pivot 1 * │ └─ Pivot 0 * └─ Implied minimum * * Slot contents: * Internal (non-leaf) nodes contain pointers to other nodes. * Leaf nodes contain entries. * * The location of interest is often referred to as an offset. All offsets have * a slot, but the last offset has an implied pivot from the node above (or * UINT_MAX for the root node. * * Ranges complicate certain write activities. When modifying any of * the B-tree variants, it is known that one entry will either be added or * deleted. When modifying the Maple Tree, one store operation may overwrite * the entire data set, or one half of the tree, or the middle half of the tree. * */ #include <linux/maple_tree.h> #include <linux/xarray.h> #include <linux/types.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/limits.h> #include <asm/barrier.h> #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. * * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is * permissible to bypass this. Otherwise remain cautious and retain the hashing. * * Userland doesn't know about %px so also use %p there. */ #if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) #define PTR_FMT "%px" #else #define PTR_FMT "%p" #endif #define MA_ROOT_PARENT 1 /* * Maple state flags * * MA_STATE_BULK - Bulk insert mode * * MA_STATE_REBALANCE - Indicate a rebalance during bulk insert * * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation */ #define MA_STATE_BULK 1 #define MA_STATE_REBALANCE 2 #define MA_STATE_PREALLOC 4 #define ma_parent_ptr(x) ((struct maple_pnode *)(x)) #define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT) #define ma_mnode_ptr(x) ((struct maple_node *)(x)) #define ma_enode_ptr(x) ((struct maple_enode *)(x)) static struct kmem_cache *maple_node_cache; #ifdef CONFIG_DEBUG_MAPLE_TREE static const unsigned long mt_max[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = ULONG_MAX, [maple_range_64] = ULONG_MAX, [maple_arange_64] = ULONG_MAX, }; #define mt_node_max(x) mt_max[mte_node_type(x)] #endif static const unsigned char mt_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = MAPLE_RANGE64_SLOTS, [maple_range_64] = MAPLE_RANGE64_SLOTS, [maple_arange_64] = MAPLE_ARANGE64_SLOTS, }; #define mt_slot_count(x) mt_slots[mte_node_type(x)] static const unsigned char mt_pivots[] = { [maple_dense] = 0, [maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1, [maple_range_64] = MAPLE_RANGE64_SLOTS - 1, [maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1, }; #define mt_pivot_count(x) mt_pivots[mte_node_type(x)] static const unsigned char mt_min_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS / 2, [maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1, }; #define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)] #define MAPLE_BIG_NODE_SLOTS (MAPLE_RANGE64_SLOTS * 2 + 2) #define MAPLE_BIG_NODE_GAPS (MAPLE_ARANGE64_SLOTS * 2 + 1) struct maple_big_node { unsigned long pivot[MAPLE_BIG_NODE_SLOTS - 1]; union { struct maple_enode *slot[MAPLE_BIG_NODE_SLOTS]; struct { unsigned long padding[MAPLE_BIG_NODE_GAPS]; unsigned long gap[MAPLE_BIG_NODE_GAPS]; }; }; unsigned char b_end; enum maple_type type; }; /* * The maple_subtree_state is used to build a tree to replace a segment of an * existing tree in a more atomic way. Any walkers of the older tree will hit a * dead node and restart on updates. */ struct maple_subtree_state { struct ma_state *orig_l; /* Original left side of subtree */ struct ma_state *orig_r; /* Original right side of subtree */ struct ma_state *l; /* New left side of subtree */ struct ma_state *m; /* New middle of subtree (rare) */ struct ma_state *r; /* New right side of subtree */ struct ma_topiary *free; /* nodes to be freed */ struct ma_topiary *destroy; /* Nodes to be destroyed (walked and freed) */ struct maple_big_node *bn; }; #ifdef CONFIG_KASAN_STACK /* Prevent mas_wr_bnode() from exceeding the stack frame limit */ #define noinline_for_kasan noinline_for_stack #else #define noinline_for_kasan inline #endif /* Functions */ static inline struct maple_node *mt_alloc_one(gfp_t gfp) { return kmem_cache_alloc(maple_node_cache, gfp); } static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes) { return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes); } static inline void mt_free_one(struct maple_node *node) { kmem_cache_free(maple_node_cache, node); } static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); } static void mt_free_rcu(struct rcu_head *head) { struct maple_node *node = container_of(head, struct maple_node, rcu); kmem_cache_free(maple_node_cache, node); } /* * ma_free_rcu() - Use rcu callback to free a maple node * @node: The node to free * * The maple tree uses the parent pointer to indicate this node is no longer in * use and will be freed. */ static void ma_free_rcu(struct maple_node *node) { WARN_ON(node->parent != ma_parent_ptr(node)); call_rcu(&node->rcu, mt_free_rcu); } static void mas_set_height(struct ma_state *mas) { unsigned int new_flags = mas->tree->ma_flags; new_flags &= ~MT_FLAGS_HEIGHT_MASK; MAS_BUG_ON(mas, mas->depth > MAPLE_HEIGHT_MAX); new_flags |= mas->depth << MT_FLAGS_HEIGHT_OFFSET; mas->tree->ma_flags = new_flags; } static unsigned int mas_mt_height(struct ma_state *mas) { return mt_height(mas->tree); } static inline unsigned int mt_attr(struct maple_tree *mt) { return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; } static __always_inline enum maple_type mte_node_type( const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } /* * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); mas->status = ma_error; } static __always_inline bool mas_is_ptr(const struct ma_state *mas) { return mas->status == ma_root; } static __always_inline bool mas_is_start(const struct ma_state *mas) { return mas->status == ma_start; } static __always_inline bool mas_is_none(const struct ma_state *mas) { return mas->status == ma_none; } static __always_inline bool mas_is_paused(const struct ma_state *mas) { return mas->status == ma_pause; } static __always_inline bool mas_is_overflow(struct ma_state *mas) { return mas->status == ma_overflow; } static inline bool mas_is_underflow(struct ma_state *mas) { return mas->status == ma_underflow; } static __always_inline struct maple_node *mte_to_node( const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mte_to_mat() - Convert a maple encoded node to a maple topiary node. * @entry: The maple encoded node * * Return: a maple topiary pointer */ static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry) { return (struct maple_topiary *) ((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mas_mn() - Get the maple state node. * @mas: The maple state * * Return: the maple node (not encoded - bare pointer). */ static inline struct maple_node *mas_mn(const struct ma_state *mas) { return mte_to_node(mas->node); } /* * mte_set_node_dead() - Set a maple encoded node as dead. * @mn: The maple encoded node. */ static inline void mte_set_node_dead(struct maple_enode *mn) { mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn)); smp_wmb(); /* Needed for RCU */ } /* Bit 1 indicates the root is a node */ #define MAPLE_ROOT_NODE 0x02 /* maple_type stored bit 3-6 */ #define MAPLE_ENODE_TYPE_SHIFT 0x03 /* Bit 2 means a NULL somewhere below */ #define MAPLE_ENODE_NULL 0x04 static inline struct maple_enode *mt_mk_node(const struct maple_node *node, enum maple_type type) { return (void *)((unsigned long)node | (type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL); } static inline void *mte_mk_root(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ROOT_NODE); } static inline void *mte_safe_root(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } static inline void __maybe_unused *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } static inline bool __maybe_unused mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } static inline bool mas_is_root_limits(const struct ma_state *mas) { return !mas->min && mas->max == ULONG_MAX; } static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } /* * The Parent Pointer * Excluding root, the parent pointer is 256B aligned like all other tree nodes. * When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16 * bit values need an extra bit to store the offset. This extra bit comes from * a reuse of the last bit in the node type. This is possible by using bit 1 to * indicate if bit 2 is part of the type or the slot. * * Note types: * 0x??1 = Root * 0x?00 = 16 bit nodes * 0x010 = 32 bit nodes * 0x110 = 64 bit nodes * * Slot size and alignment * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-7 * 0b010 : 32 bit values, type in 0-2, slot in 3-7 * 0b110 : 64 bit values, type in 0-2, slot in 3-7 */ #define MAPLE_PARENT_ROOT 0x01 #define MAPLE_PARENT_SLOT_SHIFT 0x03 #define MAPLE_PARENT_SLOT_MASK 0xF8 #define MAPLE_PARENT_16B_SLOT_SHIFT 0x02 #define MAPLE_PARENT_16B_SLOT_MASK 0xFC #define MAPLE_PARENT_RANGE64 0x06 #define MAPLE_PARENT_RANGE32 0x04 #define MAPLE_PARENT_NOT_RANGE16 0x02 /* * mte_parent_shift() - Get the parent shift for the slot storage. * @parent: The parent pointer cast as an unsigned long * Return: The shift into that pointer to the star to of the slot */ static inline unsigned long mte_parent_shift(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_SHIFT; return MAPLE_PARENT_16B_SLOT_SHIFT; } /* * mte_parent_slot_mask() - Get the slot mask for the parent. * @parent: The parent pointer cast as an unsigned long. * Return: The slot mask for that parent. */ static inline unsigned long mte_parent_slot_mask(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_MASK; return MAPLE_PARENT_16B_SLOT_MASK; } /* * mas_parent_type() - Return the maple_type of the parent from the stored * parent type. * @mas: The maple state * @enode: The maple_enode to extract the parent's enum * Return: The node->parent maple_type */ static inline enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) { unsigned long p_type; p_type = (unsigned long)mte_to_node(enode)->parent; if (WARN_ON(p_type & MAPLE_PARENT_ROOT)) return 0; p_type &= MAPLE_NODE_MASK; p_type &= ~mte_parent_slot_mask(p_type); switch (p_type) { case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */ if (mt_is_alloc(mas->tree)) return maple_arange_64; return maple_range_64; } return 0; } /* * mas_set_parent() - Set the parent node and encode the slot * @mas: The maple state * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. * * Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the * parent type. */ static inline void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64); switch (p_type) { case maple_range_64: case maple_arange_64: shift = MAPLE_PARENT_SLOT_SHIFT; type = MAPLE_PARENT_RANGE64; break; default: case maple_dense: case maple_leaf_64: shift = type = 0; break; } val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */ val |= (slot << shift) | type; mte_to_node(enode)->parent = ma_parent_ptr(val); } /* * mte_parent_slot() - get the parent slot of @enode. * @enode: The encoded maple node. * * Return: The slot in the parent node where @enode resides. */ static __always_inline unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; if (unlikely(val & MA_ROOT_PARENT)) return 0; /* * Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost * by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT */ return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val); } /* * mte_parent() - Get the parent of @node. * @enode: The encoded maple node. * * Return: The parent maple node. */ static __always_inline struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); } /* * ma_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *parent, *node; node = mte_to_node(enode); /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = mte_parent(enode); return (parent == node); } /* * mas_allocated() - Get the number of nodes allocated in a maple state. * @mas: The maple state * * The ma_state alloc member is overloaded to hold a pointer to the first * allocated node or to the number of requested nodes to allocate. If bit 0 is * set, then the alloc contains the number of requested nodes. If there is an * allocated node, then the total allocated nodes is in that node. * * Return: The total number of nodes allocated */ static inline unsigned long mas_allocated(const struct ma_state *mas) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) return 0; return mas->alloc->total; } /* * mas_set_alloc_req() - Set the requested number of allocations. * @mas: the maple state * @count: the number of allocations. * * The requested number of allocations is either in the first allocated node, * located in @mas->alloc->request_count, or directly in @mas->alloc if there is * no allocated node. Set the request either in the node or do the necessary * encoding to store in @mas->alloc directly. */ static inline void mas_set_alloc_req(struct ma_state *mas, unsigned long count) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) { if (!count) mas->alloc = NULL; else mas->alloc = (struct maple_alloc *)(((count) << 1U) | 1U); return; } mas->alloc->request_count = count; } /* * mas_alloc_req() - get the requested number of allocations. * @mas: The maple state * * The alloc count is either stored directly in @mas, or in * @mas->alloc->request_count if there is at least one node allocated. Decode * the request count if it's stored directly in @mas->alloc. * * Return: The allocation request count. */ static inline unsigned int mas_alloc_req(const struct ma_state *mas) { if ((unsigned long)mas->alloc & 0x1) return (unsigned long)(mas->alloc) >> 1; else if (mas->alloc) return mas->alloc->request_count; return 0; } /* * ma_pivots() - Get a pointer to the maple node pivots. * @node: the maple node * @type: the node type * * In the event of a dead node, this array may be %NULL * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.pivot; case maple_range_64: case maple_leaf_64: return node->mr64.pivot; case maple_dense: return NULL; } return NULL; } /* * ma_gaps() - Get a pointer to the maple node gaps. * @node: the maple node * @type: the node type * * Return: A pointer to the maple node gaps */ static inline unsigned long *ma_gaps(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.gap; case maple_range_64: case maple_leaf_64: case maple_dense: return NULL; } return NULL; } /* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @piv: The pivot to fetch * @type: The maple node type * * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { if (piv >= mt_pivots[type]) return mas->max; return pivots[piv]; } /* * mas_safe_min() - Return the minimum for a given offset. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @offset: The offset into the pivot array * * Return: The minimum range value that is contained in @offset. */ static inline unsigned long mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset) { if (likely(offset)) return pivots[offset - 1] + 1; return mas->min; } /* * mte_set_pivot() - Set a pivot to a value in an encoded maple node. * @mn: The encoded maple node * @piv: The pivot offset * @val: The value of the pivot */ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, unsigned long val) { struct maple_node *node = mte_to_node(mn); enum maple_type type = mte_node_type(mn); BUG_ON(piv >= mt_pivots[type]); switch (type) { case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; break; case maple_arange_64: node->ma64.pivot[piv] = val; break; case maple_dense: break; } } /* * ma_slots() - Get a pointer to the maple node slots. * @mn: The maple node * @mt: The maple node type * * Return: A pointer to the maple node slots */ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return mn->ma64.slot; case maple_range_64: case maple_leaf_64: return mn->mr64.slot; case maple_dense: return mn->slot; } return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_write_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } static __always_inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset. */ static __always_inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } /* * mas_slot() - Get the slot value when not holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset */ static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot(mas->tree, slots, offset); } /* * mas_root() - Get the maple tree root. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } static inline void *mt_root_locked(struct maple_tree *mt) { return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt)); } /* * mas_root_locked() - Get the maple tree root when holding the maple tree lock. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static inline void *mas_root_locked(struct ma_state *mas) { return mt_root_locked(mas->tree); } static inline struct maple_metadata *ma_meta(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return &mn->ma64.meta; default: return &mn->mr64.meta; } } /* * ma_set_meta() - Set the metadata information of a node. * @mn: The maple node * @mt: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, unsigned char offset, unsigned char end) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; meta->end = end; } /* * mt_clear_meta() - clear the metadata information of a node, if it exists * @mt: The maple tree * @mn: The maple node * @type: The maple node type */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) { struct maple_metadata *meta; unsigned long *pivots; void __rcu **slots; void *next; switch (type) { case maple_range_64: pivots = mn->mr64.pivot; if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { slots = mn->mr64.slot; next = mt_slot_locked(mt, slots, MAPLE_RANGE64_SLOTS - 1); if (unlikely((mte_to_node(next) && mte_node_type(next)))) return; /* no metadata, could be node */ } fallthrough; case maple_arange_64: meta = ma_meta(mn, type); break; default: return; } meta->gap = 0; meta->end = 0; } /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type */ static inline unsigned char ma_meta_end(struct maple_node *mn, enum maple_type mt) { struct maple_metadata *meta = ma_meta(mn, mt); return meta->end; } /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node */ static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node * @mt: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, unsigned char offset) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; } /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. * @mat: the ma_topiary, a linked list of dead nodes. * @dead_enode: the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ static inline void mat_add(struct ma_topiary *mat, struct maple_enode *dead_enode) { mte_set_node_dead(dead_enode); mte_to_mat(dead_enode)->next = NULL; if (!mat->tail) { mat->tail = mat->head = dead_enode; return; } mte_to_mat(mat->tail)->next = dead_enode; mat->tail = dead_enode; } static void mt_free_walk(struct rcu_head *head); static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. * @mas: the maple state * @mat: the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) { struct maple_enode *next; struct maple_node *node; bool in_rcu = mt_in_rcu(mas->tree); while (mat->head) { next = mte_to_mat(mat->head)->next; node = mte_to_node(mat->head); mt_destroy_walk(mat->head, mas->tree, !in_rcu); if (in_rcu) call_rcu(&node->rcu, mt_free_walk); mat->head = next; } } /* * mas_descend() - Descend into the slot stored in the ma_state. * @mas: the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ static inline void mas_descend(struct ma_state *mas) { enum maple_type type; unsigned long *pivots; struct maple_node *node; void __rcu **slots; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1; mas->max = mas_safe_pivot(mas, pivots, mas->offset, type); mas->node = mas_slot(mas, slots, mas->offset); } /* * mte_set_gap() - Set a maple node gap. * @mn: The encoded maple node * @gap: The offset of the gap to set * @val: The gap value */ static inline void mte_set_gap(const struct maple_enode *mn, unsigned char gap, unsigned long val) { switch (mte_node_type(mn)) { default: break; case maple_arange_64: mte_to_node(mn)->ma64.gap[gap] = val; break; } } /* * mas_ascend() - Walk up a level of the tree. * @mas: The maple state * * Sets the @mas->max and @mas->min to the correct values when walking up. This * may cause several levels of walking up to find the correct min and max. * May find a dead node which will cause a premature return. * Return: 1 on dead node, 0 otherwise */ static int mas_ascend(struct ma_state *mas) { struct maple_enode *p_enode; /* parent enode. */ struct maple_enode *a_enode; /* ancestor enode. */ struct maple_node *a_node; /* ancestor node. */ struct maple_node *p_node; /* parent node. */ unsigned char a_slot; enum maple_type a_type; unsigned long min, max; unsigned long *pivots; bool set_max = false, set_min = false; a_node = mas_mn(mas); if (ma_is_root(a_node)) { mas->offset = 0; return 0; } p_node = mte_parent(mas->node); if (unlikely(a_node == p_node)) return 1; a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node); a_enode = mt_mk_node(p_node, a_type); /* Check to make sure all parent information is still accurate */ if (p_node != mte_parent(mas->node)) return 1; mas->node = a_enode; if (mte_is_root(a_enode)) { mas->max = ULONG_MAX; mas->min = 0; return 0; } min = 0; max = ULONG_MAX; if (!mas->offset) { min = mas->min; set_min = true; } if (mas->max == ULONG_MAX) set_max = true; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); a_enode = mt_mk_node(a_node, a_type); pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node))) return 1; if (!set_min && a_slot) { set_min = true; min = pivots[a_slot - 1] + 1; } if (!set_max && a_slot < mt_pivots[a_type]) { set_max = true; max = pivots[a_slot]; } if (unlikely(ma_dead_node(a_node))) return 1; if (unlikely(ma_is_root(a_node))) break; } while (!set_min || !set_max); mas->max = max; mas->min = min; return 0; } /* * mas_pop_node() - Get a previously allocated maple node from the maple state. * @mas: The maple state * * Return: A pointer to a maple node. */ static inline struct maple_node *mas_pop_node(struct ma_state *mas) { struct maple_alloc *ret, *node = mas->alloc; unsigned long total = mas_allocated(mas); unsigned int req = mas_alloc_req(mas); /* nothing or a request pending. */ if (WARN_ON(!total)) return NULL; if (total == 1) { /* single allocation in this ma_state */ mas->alloc = NULL; ret = node; goto single_node; } if (node->node_count == 1) { /* Single allocation in this node. */ mas->alloc = node->slot[0]; mas->alloc->total = node->total - 1; ret = node; goto new_head; } node->total--; ret = node->slot[--node->node_count]; node->slot[node->node_count] = NULL; single_node: new_head: if (req) { req++; mas_set_alloc_req(mas, req); } memset(ret, 0, sizeof(*ret)); return (struct maple_node *)ret; } /* * mas_push_node() - Push a node back on the maple state allocation. * @mas: The maple state * @used: The used maple node * * Stores the maple node back into @mas->alloc for reuse. Updates allocated and * requested node count as necessary. */ static inline void mas_push_node(struct ma_state *mas, struct maple_node *used) { struct maple_alloc *reuse = (struct maple_alloc *)used; struct maple_alloc *head = mas->alloc; unsigned long count; unsigned int requested = mas_alloc_req(mas); count = mas_allocated(mas); reuse->request_count = 0; reuse->node_count = 0; if (count) { if (head->node_count < MAPLE_ALLOC_SLOTS) { head->slot[head->node_count++] = reuse; head->total++; goto done; } reuse->slot[0] = head; reuse->node_count = 1; } reuse->total = count + 1; mas->alloc = reuse; done: if (requested > 1) mas_set_alloc_req(mas, requested - 1); } /* * mas_alloc_nodes() - Allocate nodes into a maple state * @mas: The maple state * @gfp: The GFP Flags */ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) { struct maple_alloc *node; unsigned long allocated = mas_allocated(mas); unsigned int requested = mas_alloc_req(mas); unsigned int count; void **slots = NULL; unsigned int max_req = 0; if (!requested) return; mas_set_alloc_req(mas, 0); if (mas->mas_flags & MA_STATE_PREALLOC) { if (allocated) return; BUG_ON(!allocated); WARN_ON(!allocated); } if (!allocated || mas->alloc->node_count == MAPLE_ALLOC_SLOTS) { node = (struct maple_alloc *)mt_alloc_one(gfp); if (!node) goto nomem_one; if (allocated) { node->slot[0] = mas->alloc; node->node_count = 1; } else { node->node_count = 0; } mas->alloc = node; node->total = ++allocated; node->request_count = 0; requested--; } node = mas->alloc; while (requested) { max_req = MAPLE_ALLOC_SLOTS - node->node_count; slots = (void **)&node->slot[node->node_count]; max_req = min(requested, max_req); count = mt_alloc_bulk(gfp, max_req, slots); if (!count) goto nomem_bulk; if (node->node_count == 0) { node->slot[0]->node_count = 0; node->slot[0]->request_count = 0; } node->node_count += count; allocated += count; /* find a non-full node*/ do { node = node->slot[0]; } while (unlikely(node->node_count == MAPLE_ALLOC_SLOTS)); requested -= count; } mas->alloc->total = allocated; return; nomem_bulk: /* Clean up potential freed allocations on bulk failure */ memset(slots, 0, max_req * sizeof(unsigned long)); mas->alloc->total = allocated; nomem_one: mas_set_alloc_req(mas, requested); mas_set_err(mas, -ENOMEM); } /* * mas_free() - Free an encoded maple node * @mas: The maple state * @used: The encoded maple node to free. * * Uses rcu free if necessary, pushes @used back on the maple state allocations * otherwise. */ static inline void mas_free(struct ma_state *mas, struct maple_enode *used) { struct maple_node *tmp = mte_to_node(used); if (mt_in_rcu(mas->tree)) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_node_count_gfp() - Check if enough nodes are allocated and request more * if there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * @gfp: the gfp flags */ static void mas_node_count_gfp(struct ma_state *mas, int count, gfp_t gfp) { unsigned long allocated = mas_allocated(mas); if (allocated < count) { mas_set_alloc_req(mas, count - allocated); mas_alloc_nodes(mas, gfp); } } /* * mas_node_count() - Check if enough nodes are allocated and request more if * there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * * Note: Uses GFP_NOWAIT | __GFP_NOWARN for gfp flags. */ static void mas_node_count(struct ma_state *mas, int count) { return mas_node_count_gfp(mas, count, GFP_NOWAIT | __GFP_NOWARN); } /* * mas_start() - Sets up maple state for operations. * @mas: The maple state. * * If mas->status == mas_start, then set the min, max and depth to * defaults. * * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none * - If it's a single entry: The entry & mas->status == ma_root * - If it's a tree: NULL & mas->status == ma_active */ static inline struct maple_enode *mas_start(struct ma_state *mas) { if (likely(mas_is_start(mas))) { struct maple_enode *root; mas->min = 0; mas->max = ULONG_MAX; retry: mas->depth = 0; root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) goto retry; return NULL; } mas->node = NULL; /* empty tree */ if (unlikely(!root)) { mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ if (mas->index > 0) return NULL; return root; } return NULL; } /* * ma_data_end() - Find the end of the data in a node. * @node: The maple node * @type: The maple node type * @pivots: The array of pivots in the node * @max: The maximum value in the node * * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ static __always_inline unsigned char ma_data_end(struct maple_node *node, enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; if (!pivots) return 0; if (type == maple_arange_64) return ma_meta_end(node, type); offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == max)) return offset; return mt_pivots[type]; } /* * mas_data_end() - Find the end of the data (slot). * @mas: the maple state * * This method is optimized to check the metadata of a node if the node type * supports data end metadata. * * Return: The zero indexed last slot with data (may be null). */ static inline unsigned char mas_data_end(struct ma_state *mas) { enum maple_type type; struct maple_node *node; unsigned char offset; unsigned long *pivots; type = mte_node_type(mas->node); node = mas_mn(mas); if (type == maple_arange_64) return ma_meta_end(node, type); pivots = ma_pivots(node, type); if (unlikely(ma_dead_node(node))) return 0; offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max)) return offset; return mt_pivots[type]; } /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node * @mas: the maple state * * Return: The maximum gap in the leaf. */ static unsigned long mas_leaf_max_gap(struct ma_state *mas) { enum maple_type mt; unsigned long pstart, gap, max_gap; struct maple_node *mn; unsigned long *pivots; void __rcu **slots; unsigned char i; unsigned char max_piv; mt = mte_node_type(mas->node); mn = mas_mn(mas); slots = ma_slots(mn, mt); max_gap = 0; if (unlikely(ma_is_dense(mt))) { gap = 0; for (i = 0; i < mt_slots[mt]; i++) { if (slots[i]) { if (gap > max_gap) max_gap = gap; gap = 0; } else { gap++; } } if (gap > max_gap) max_gap = gap; return max_gap; } /* * Check the first implied pivot optimizes the loop below and slot 1 may * be skipped if there is a gap in slot 0. */ pivots = ma_pivots(mn, mt); if (likely(!slots[0])) { max_gap = pivots[0] - mas->min + 1; i = 2; } else { i = 1; } /* reduce max_piv as the special case is checked before the loop */ max_piv = ma_data_end(mn, mt, pivots, mas->max) - 1; /* * Check end implied pivot which can only be a gap on the right most * node. */ if (unlikely(mas->max == ULONG_MAX) && !slots[max_piv + 1]) { gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; if (max_gap > pivots[max_piv] - mas->min) return max_gap; } for (; i <= max_piv; i++) { /* data == no gap. */ if (likely(slots[i])) continue; pstart = pivots[i - 1]; gap = pivots[i] - pstart; if (gap > max_gap) max_gap = gap; /* There cannot be two gaps in a row. */ i++; } return max_gap; } /* * ma_max_gap() - Get the maximum gap in a maple node (non-leaf) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type * @off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * * Return: The maximum gap value */ static inline unsigned long ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt, unsigned char *off) { unsigned char offset, i; unsigned long max_gap = 0; i = offset = ma_meta_end(node, mt); do { if (gaps[i] > max_gap) { max_gap = gaps[i]; offset = i; } } while (i--); *off = offset; return max_gap; } /* * mas_max_gap() - find the largest gap in a non-leaf node and set the slot. * @mas: The maple state. * * Return: The gap value. */ static inline unsigned long mas_max_gap(struct ma_state *mas) { unsigned long *gaps; unsigned char offset; enum maple_type mt; struct maple_node *node; mt = mte_node_type(mas->node); if (ma_is_leaf(mt)) return mas_leaf_max_gap(mas); node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } /* * mas_parent_gap() - Set the parent gap and any gaps above, as needed * @mas: The maple state * @offset: The gap offset in the parent to set * @new: The new gap value. * * Set the parent gap then continue to set the gap upwards, using the metadata * of the parent to see if it is necessary to check the node above. */ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, unsigned long new) { unsigned long meta_gap = 0; struct maple_node *pnode; struct maple_enode *penode; unsigned long *pgaps; unsigned char meta_offset; enum maple_type pmt; pnode = mte_parent(mas->node); pmt = mas_parent_type(mas, mas->node); penode = mt_mk_node(pnode, pmt); pgaps = ma_gaps(pnode, pmt); ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; if (meta_gap == new) return; if (offset != meta_offset) { if (meta_gap > new) return; ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset); ma_set_meta_gap(pnode, pmt, meta_offset); } if (ma_is_root(pnode)) return; /* Go to the parent node. */ pnode = mte_parent(penode); pmt = mas_parent_type(mas, penode); pgaps = ma_gaps(pnode, pmt); offset = mte_parent_slot(penode); penode = mt_mk_node(pnode, pmt); goto ascend; } /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. * @mas: the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { unsigned char pslot; unsigned long p_gap; unsigned long max_gap; if (!mt_is_alloc(mas->tree)) return; if (mte_is_root(mas->node)) return; max_gap = mas_max_gap(mas); pslot = mte_parent_slot(mas->node); p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap); } /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. * @mas: the maple state (for the tree) * @parent: the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) { enum maple_type type = mte_node_type(parent); struct maple_node *node = mte_to_node(parent); void __rcu **slots = ma_slots(node, type); unsigned long *pivots = ma_pivots(node, type); struct maple_enode *child; unsigned char offset; offset = ma_data_end(node, type, pivots, mas->max); do { child = mas_slot_locked(mas, slots, offset); mas_set_parent(mas, child, parent, offset); } while (offset--); } /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. * @mas: the maple state with the new node * @old_enode: The old maple encoded node to replace. */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { unsigned char offset; void __rcu **slots; if (mte_is_root(mas->node)) { mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas)); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); mas_set_height(mas); } else { offset = mte_parent_slot(mas->node); slots = ma_slots(mte_parent(mas->node), mas_parent_type(mas, mas->node)); rcu_assign_pointer(slots[offset], mas->node); } mte_set_node_dead(old_enode); } /* * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. * @mas: the ma_state with @mas->node pointing to the new node. * @old_enode: The old maple encoded node. */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { mas_put_in_tree(mas, old_enode); mas_free(mas, old_enode); } /* * mas_find_child() - Find a child who has the parent @mas->node. * @mas: the maple state with the parent. * @child: the maple state to store the child. */ static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child) __must_hold(mas->tree->ma_lock) { enum maple_type mt; unsigned char offset; unsigned char end; unsigned long *pivots; struct maple_enode *entry; struct maple_node *node; void __rcu **slots; mt = mte_node_type(mas->node); node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset); if (mte_parent(entry) == node) { *child = *mas; mas->offset = offset + 1; child->offset = offset; mas_descend(child); child->offset = 0; return true; } } return false; } /* * mab_shift_right() - Shift the data in mab right. Note, does not clean out the * old data or set b_node->b_end. * @b_node: the maple_big_node * @shift: the shift count */ static inline void mab_shift_right(struct maple_big_node *b_node, unsigned char shift) { unsigned long size = b_node->b_end * sizeof(unsigned long); memmove(b_node->pivot + shift, b_node->pivot, size); memmove(b_node->slot + shift, b_node->slot, size); if (b_node->type == maple_arange_64) memmove(b_node->gap + shift, b_node->gap, size); } /* * mab_middle_node() - Check if a middle node is needed (unlikely) * @b_node: the maple_big_node that contains the data. * @split: the potential split location * @slot_count: the size that can be stored in a single node being considered. * * Return: true if a middle node is required. */ static inline bool mab_middle_node(struct maple_big_node *b_node, int split, unsigned char slot_count) { unsigned char size = b_node->b_end; if (size >= 2 * slot_count) return true; if (!b_node->slot[split] && (size >= 2 * slot_count - 1)) return true; return false; } /* * mab_no_null_split() - ensure the split doesn't fall on a NULL * @b_node: the maple_big_node with the data * @split: the suggested split location * @slot_count: the number of slots in the node being considered. * * Return: the split location. */ static inline int mab_no_null_split(struct maple_big_node *b_node, unsigned char split, unsigned char slot_count) { if (!b_node->slot[split]) { /* * If the split is less than the max slot && the right side will * still be sufficient, then increment the split on NULL. */ if ((split < slot_count - 1) && (b_node->b_end - split) > (mt_min_slots[b_node->type])) split++; else split--; } return split; } /* * mab_calc_split() - Calculate the split location and if there needs to be two * splits. * @mas: The maple state * @bn: The maple_big_node with the data * @mid_split: The second split, if required. 0 otherwise. * * Return: The first split location. The middle split is set in @mid_split. */ static inline int mab_calc_split(struct ma_state *mas, struct maple_big_node *bn, unsigned char *mid_split, unsigned long min) { unsigned char b_end = bn->b_end; int split = b_end / 2; /* Assume equal split. */ unsigned char slot_min, slot_count = mt_slots[bn->type]; /* * To support gap tracking, all NULL entries are kept together and a node cannot * end on a NULL entry, with the exception of the left-most leaf. The * limitation means that the split of a node must be checked for this condition * and be able to put more data in one direction or the other. */ if (unlikely((mas->mas_flags & MA_STATE_BULK))) { *mid_split = 0; split = b_end - mt_min_slots[bn->type]; if (!ma_is_leaf(bn->type)) return split; mas->mas_flags |= MA_STATE_REBALANCE; if (!bn->slot[split]) split--; return split; } /* * Although extremely rare, it is possible to enter what is known as the 3-way * split scenario. The 3-way split comes about by means of a store of a range * that overwrites the end and beginning of two full nodes. The result is a set * of entries that cannot be stored in 2 nodes. Sometimes, these two nodes can * also be located in different parent nodes which are also full. This can * carry upwards all the way to the root in the worst case. */ if (unlikely(mab_middle_node(bn, split, slot_count))) { split = b_end / 3; *mid_split = split * 2; } else { slot_min = mt_min_slots[bn->type]; *mid_split = 0; /* * Avoid having a range less than the slot count unless it * causes one node to be deficient. * NOTE: mt_min_slots is 1 based, b_end and split are zero. */ while ((split < slot_count - 1) && ((bn->pivot[split] - min) < slot_count - 1) && (b_end - split > slot_min)) split++; } /* Avoid ending a node on a NULL entry */ split = mab_no_null_split(bn, split, slot_count); if (unlikely(*mid_split)) *mid_split = mab_no_null_split(bn, *mid_split, slot_count); return split; } /* * mas_mab_cp() - Copy data from a maple state inclusively to a maple_big_node * and set @b_node->b_end to the next free slot. * @mas: The maple state * @mas_start: The starting slot to copy * @mas_end: The end slot to copy (inclusively) * @b_node: The maple_big_node to place the data * @mab_start: The starting location in maple_big_node to store the data. */ static inline void mas_mab_cp(struct ma_state *mas, unsigned char mas_start, unsigned char mas_end, struct maple_big_node *b_node, unsigned char mab_start) { enum maple_type mt; struct maple_node *node; void __rcu **slots; unsigned long *pivots, *gaps; int i = mas_start, j = mab_start; unsigned char piv_end; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); if (!i) { b_node->pivot[j] = pivots[i++]; if (unlikely(i > mas_end)) goto complete; j++; } piv_end = min(mas_end, mt_pivots[mt]); for (; i < piv_end; i++, j++) { b_node->pivot[j] = pivots[i]; if (unlikely(!b_node->pivot[j])) goto complete; if (unlikely(mas->max == b_node->pivot[j])) goto complete; } b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); complete: b_node->b_end = ++j; j -= mab_start; slots = ma_slots(node, mt); memcpy(b_node->slot + mab_start, slots + mas_start, sizeof(void *) * j); if (!ma_is_leaf(mt) && mt_is_alloc(mas->tree)) { gaps = ma_gaps(node, mt); memcpy(b_node->gap + mab_start, gaps + mas_start, sizeof(unsigned long) * j); } } /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. * @node: The maple node * @mt: The maple type * @end: The node end */ static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } /* * mab_mas_cp() - Copy data from maple_big_node to a maple encoded node. * @b_node: the maple_big_node that has the data * @mab_start: the start location in @b_node. * @mab_end: The end location in @b_node (inclusively) * @mas: The maple state with the maple encoded node. */ static inline void mab_mas_cp(struct maple_big_node *b_node, unsigned char mab_start, unsigned char mab_end, struct ma_state *mas, bool new_max) { int i, j = 0; enum maple_type mt = mte_node_type(mas->node); struct maple_node *node = mte_to_node(mas->node); void __rcu **slots = ma_slots(node, mt); unsigned long *pivots = ma_pivots(node, mt); unsigned long *gaps = NULL; unsigned char end; if (mab_end - mab_start > mt_pivots[mt]) mab_end--; if (!pivots[mt_pivots[mt] - 1]) slots[mt_pivots[mt]] = NULL; i = mab_start; do { pivots[j++] = b_node->pivot[i++]; } while (i <= mab_end && likely(b_node->pivot[i])); memcpy(slots, b_node->slot + mab_start, sizeof(void *) * (i - mab_start)); if (new_max) mas->max = b_node->pivot[i - 1]; end = j - 1; if (likely(!ma_is_leaf(mt) && mt_is_alloc(mas->tree))) { unsigned long max_gap = 0; unsigned char offset = 0; gaps = ma_gaps(node, mt); do { gaps[--j] = b_node->gap[--i]; if (gaps[j] > max_gap) { offset = j; max_gap = gaps[j]; } } while (j); ma_set_meta(node, mt, offset, end); } else { mas_leaf_set_meta(node, mt, end); } } /* * mas_bulk_rebalance() - Rebalance the end of a tree after a bulk insert. * @mas: The maple state * @end: The maple node end * @mt: The maple node type */ static inline void mas_bulk_rebalance(struct ma_state *mas, unsigned char end, enum maple_type mt) { if (!(mas->mas_flags & MA_STATE_BULK)) return; if (mte_is_root(mas->node)) return; if (end > mt_min_slots[mt]) { mas->mas_flags &= ~MA_STATE_REBALANCE; return; } } /* * mas_store_b_node() - Store an @entry into the b_node while also copying the * data from a maple encoded node. * @wr_mas: the maple write state * @b_node: the maple_big_node to fill with data * @offset_end: the offset to end copying * * Return: The actual end of the data stored in @b_node */ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node, unsigned char offset_end) { unsigned char slot; unsigned char b_end; /* Possible underflow of piv will wrap back to 0 before use. */ unsigned long piv; struct ma_state *mas = wr_mas->mas; b_node->type = wr_mas->type; b_end = 0; slot = mas->offset; if (slot) { /* Copy start data up to insert. */ mas_mab_cp(mas, 0, slot - 1, b_node, 0); b_end = b_node->b_end; piv = b_node->pivot[b_end - 1]; } else piv = mas->min - 1; if (piv + 1 < mas->index) { /* Handle range starting after old range */ b_node->slot[b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = mas->index - 1 - piv; b_node->pivot[b_end++] = mas->index - 1; } /* Store the new entry. */ mas->offset = b_end; b_node->slot[b_end] = wr_mas->entry; b_node->pivot[b_end] = mas->last; /* Appended. */ if (mas->last >= mas->max) goto b_end; /* Handle new range ending before old range ends */ piv = mas_safe_pivot(mas, wr_mas->pivots, offset_end, wr_mas->type); if (piv > mas->last) { if (piv == ULONG_MAX) mas_bulk_rebalance(mas, b_node->b_end, wr_mas->type); if (offset_end != slot) wr_mas->content = mas_slot_locked(mas, wr_mas->slots, offset_end); b_node->slot[++b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = piv - mas->last + 1; b_node->pivot[b_end] = piv; } slot = offset_end + 1; if (slot > mas->end) goto b_end; /* Copy end data to the end of the node. */ mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end); b_node->b_end--; return; b_end: b_node->b_end = b_end; } /* * mas_prev_sibling() - Find the previous node with the same parent. * @mas: the maple state * * Return: True if there is a previous sibling, false otherwise. */ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; mas_ascend(mas); mas->offset = p_slot - 1; mas_descend(mas); return true; } /* * mas_next_sibling() - Find the next node with the same parent. * @mas: the maple state * * Return: true if there is a next sibling, false otherwise. */ static inline bool mas_next_sibling(struct ma_state *mas) { MA_STATE(parent, mas->tree, mas->index, mas->last); if (mte_is_root(mas->node)) return false; parent = *mas; mas_ascend(&parent); parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent)) return false; *mas = parent; mas_descend(mas); return true; } /* * mas_node_or_none() - Set the enode and state. * @mas: the maple state * @enode: The encoded maple node. * * Set the node to the enode and the status. */ static inline void mas_node_or_none(struct ma_state *mas, struct maple_enode *enode) { if (enode) { mas->node = enode; mas->status = ma_active; } else { mas->node = NULL; mas->status = ma_none; } } /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. * If @mas->index cannot be found within the containing * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. */ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; mas->offset = mas->index = mas->min; return; } wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) offset++; wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } /* * mast_rebalance_next() - Rebalance against the next node * @mast: The maple subtree state */ static inline void mast_rebalance_next(struct maple_subtree_state *mast) { unsigned char b_end = mast->bn->b_end; mas_mab_cp(mast->orig_r, 0, mt_slot_count(mast->orig_r->node), mast->bn, b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_rebalance_prev() - Rebalance against the previous node * @mast: The maple subtree state */ static inline void mast_rebalance_prev(struct maple_subtree_state *mast) { unsigned char end = mas_data_end(mast->orig_l) + 1; unsigned char b_end = mast->bn->b_end; mab_shift_right(mast->bn, end); mas_mab_cp(mast->orig_l, 0, end - 1, mast->bn, 0); mast->l->min = mast->orig_l->min; mast->orig_l->index = mast->orig_l->min; mast->bn->b_end = end + b_end; mast->l->offset += end; } /* * mast_spanning_rebalance() - Rebalance nodes with nearest neighbour favouring * the node to the right. Checking the nodes to the right then the left at each * level upwards until root is reached. * Data is copied into the @mast->bn. * @mast: The maple_subtree_state. */ static inline bool mast_spanning_rebalance(struct maple_subtree_state *mast) { struct ma_state r_tmp = *mast->orig_r; struct ma_state l_tmp = *mast->orig_l; unsigned char depth = 0; do { mas_ascend(mast->orig_r); mas_ascend(mast->orig_l); depth++; if (mast->orig_r->offset < mas_data_end(mast->orig_r)) { mast->orig_r->offset++; do { mas_descend(mast->orig_r); mast->orig_r->offset = 0; } while (--depth); mast_rebalance_next(mast); *mast->orig_l = l_tmp; return true; } else if (mast->orig_l->offset != 0) { mast->orig_l->offset--; do { mas_descend(mast->orig_l); mast->orig_l->offset = mas_data_end(mast->orig_l); } while (--depth); mast_rebalance_prev(mast); *mast->orig_r = r_tmp; return true; } } while (!mte_is_root(mast->orig_r->node)); *mast->orig_r = r_tmp; *mast->orig_l = l_tmp; return false; } /* * mast_ascend() - Ascend the original left and right maple states. * @mast: the maple subtree state. * * Ascend the original left and right sides. Set the offsets to point to the * data already in the new tree (@mast->l and @mast->r). */ static inline void mast_ascend(struct maple_subtree_state *mast) { MA_WR_STATE(wr_mas, mast->orig_r, NULL); mas_ascend(mast->orig_l); mas_ascend(mast->orig_r); mast->orig_r->offset = 0; mast->orig_r->index = mast->r->max; /* last should be larger than or equal to index */ if (mast->orig_r->last < mast->orig_r->index) mast->orig_r->last = mast->orig_r->index; wr_mas.type = mte_node_type(mast->orig_r->node); mas_wr_node_walk(&wr_mas); /* Set up the left side of things */ mast->orig_l->offset = 0; mast->orig_l->index = mast->l->min; wr_mas.mas = mast->orig_l; wr_mas.type = mte_node_type(mast->orig_l->node); mas_wr_node_walk(&wr_mas); mast->bn->type = wr_mas.type; } /* * mas_new_ma_node() - Create and return a new maple node. Helper function. * @mas: the maple state with the allocations. * @b_node: the maple_big_node with the type encoding. * * Use the node type from the maple_big_node to allocate a new node from the * ma_state. This function exists mainly for code readability. * * Return: A new maple encoded node */ static inline struct maple_enode *mas_new_ma_node(struct ma_state *mas, struct maple_big_node *b_node) { return mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), b_node->type); } /* * mas_mab_to_node() - Set up right and middle nodes * * @mas: the maple state that contains the allocations. * @b_node: the node which contains the data. * @left: The pointer which will have the left node * @right: The pointer which may have the right node * @middle: the pointer which may have the middle node (rare) * @mid_split: the split location for the middle node * * Return: the split of left. */ static inline unsigned char mas_mab_to_node(struct ma_state *mas, struct maple_big_node *b_node, struct maple_enode **left, struct maple_enode **right, struct maple_enode **middle, unsigned char *mid_split, unsigned long min) { unsigned char split = 0; unsigned char slot_count = mt_slots[b_node->type]; *left = mas_new_ma_node(mas, b_node); *right = NULL; *middle = NULL; *mid_split = 0; if (b_node->b_end < slot_count) { split = b_node->b_end; } else { split = mab_calc_split(mas, b_node, mid_split, min); *right = mas_new_ma_node(mas, b_node); } if (*mid_split) *middle = mas_new_ma_node(mas, b_node); return split; } /* * mab_set_b_end() - Add entry to b_node at b_node->b_end and increment the end * pointer. * @b_node: the big node to add the entry * @mas: the maple state to get the pivot (mas->max) * @entry: the entry to add, if NULL nothing happens. */ static inline void mab_set_b_end(struct maple_big_node *b_node, struct ma_state *mas, void *entry) { if (!entry) return; b_node->slot[b_node->b_end] = entry; if (mt_is_alloc(mas->tree)) b_node->gap[b_node->b_end] = mas_max_gap(mas); b_node->pivot[b_node->b_end++] = mas->max; } /* * mas_set_split_parent() - combine_then_separate helper function. Sets the parent * of @mas->node to either @left or @right, depending on @slot and @split * * @mas: the maple state with the node that needs a parent * @left: possible parent 1 * @right: possible parent 2 * @slot: the slot the mas->node was placed * @split: the split location between @left and @right */ static inline void mas_set_split_parent(struct ma_state *mas, struct maple_enode *left, struct maple_enode *right, unsigned char *slot, unsigned char split) { if (mas_is_none(mas)) return; if ((*slot) <= split) mas_set_parent(mas, mas->node, left, *slot); else if (right) mas_set_parent(mas, mas->node, right, (*slot) - split - 1); (*slot)++; } /* * mte_mid_split_check() - Check if the next node passes the mid-split * @l: Pointer to left encoded maple node. * @m: Pointer to middle encoded maple node. * @r: Pointer to right encoded maple node. * @slot: The offset * @split: The split location. * @mid_split: The middle split. */ static inline void mte_mid_split_check(struct maple_enode **l, struct maple_enode **r, struct maple_enode *right, unsigned char slot, unsigned char *split, unsigned char mid_split) { if (*r == right) return; if (slot < mid_split) return; *l = *r; *r = right; *split = mid_split; } /* * mast_set_split_parents() - Helper function to set three nodes parents. Slot * is taken from @mast->l. * @mast: the maple subtree state * @left: the left node * @right: the right node * @split: the split location. */ static inline void mast_set_split_parents(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { unsigned char slot; struct maple_enode *l = left; struct maple_enode *r = right; if (mas_is_none(mast->l)) return; if (middle) r = middle; slot = mast->l->offset; mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->l, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->m, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->r, l, r, &slot, split); } /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; struct maple_enode *enode; if (mas_is_none(tmp_mas)) return; enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); if (in_rcu) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_topiary_replace() - Replace the data with new data, then repair the * parent links within the new tree. Iterate over the dead sub-tree and collect * the dead subtrees and topiary the nodes that are no longer of use. * * The new tree will have up to three children with the correct parent. Keep * track of the new entries as they need to be followed to find the next level * of new entries. * * The old tree will have up to three children with the old parent. Keep track * of the old entries as they may have more nodes below replaced. Nodes within * [index, last] are dead subtrees, others need to be freed and followed. * * @mas: The maple state pointing at the new data * @old_enode: The maple encoded node being replaced * */ static inline void mas_topiary_replace(struct ma_state *mas, struct maple_enode *old_enode) { struct ma_state tmp[3], tmp_next[3]; MA_TOPIARY(subtrees, mas->tree); bool in_rcu; int i, n; /* Place data in tree & then mark node as old */ mas_put_in_tree(mas, old_enode); /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; tmp[1].status = ma_none; tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; n++; } mas_adopt_children(&tmp[i], tmp[i].node); } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; } /* Collect the old nodes that need to be discarded */ if (mte_is_leaf(old_enode)) return mas_free(mas, old_enode); tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; tmp[1].status = ma_none; tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); tmp_next[n].status = ma_none; } else { n++; } } } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state * @old_enode: The old maple encoded node that is being replaced. * * Updates gap as necessary. */ static inline void mas_wmb_replace(struct ma_state *mas, struct maple_enode *old_enode) { /* Insert the new data in the tree */ mas_topiary_replace(mas, old_enode); if (mte_is_leaf(mas->node)) return; mas_update_gap(mas); } /* * mast_cp_to_nodes() - Copy data out to nodes. * @mast: The maple subtree state * @left: The left encoded maple node * @middle: The middle encoded maple node * @right: The right encoded maple node * @split: The location to split between left and (middle ? middle : right) * @mid_split: The location to split between middle and right. */ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { bool new_lmax = true; mas_node_or_none(mast->l, left); mas_node_or_none(mast->m, middle); mas_node_or_none(mast->r, right); mast->l->min = mast->orig_l->min; if (split == mast->bn->b_end) { mast->l->max = mast->orig_r->max; new_lmax = false; } mab_mas_cp(mast->bn, 0, split, mast->l, new_lmax); if (middle) { mab_mas_cp(mast->bn, 1 + split, mid_split, mast->m, true); mast->m->min = mast->bn->pivot[split] + 1; split = mid_split; } mast->r->max = mast->orig_r->max; if (right) { mab_mas_cp(mast->bn, 1 + split, mast->bn->b_end, mast->r, false); mast->r->min = mast->bn->pivot[split] + 1; } } /* * mast_combine_cp_left - Copy in the original left side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_left(struct maple_subtree_state *mast) { unsigned char l_slot = mast->orig_l->offset; if (!l_slot) return; mas_mab_cp(mast->orig_l, 0, l_slot - 1, mast->bn, 0); } /* * mast_combine_cp_right: Copy in the original right side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_right(struct maple_subtree_state *mast) { if (mast->bn->pivot[mast->bn->b_end - 1] >= mast->orig_r->max) return; mas_mab_cp(mast->orig_r, mast->orig_r->offset + 1, mt_slot_count(mast->orig_r->node), mast->bn, mast->bn->b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_sufficient: Check if the maple subtree state has enough data in the big * node to create at least one sufficient node * @mast: the maple subtree state */ static inline bool mast_sufficient(struct maple_subtree_state *mast) { if (mast->bn->b_end > mt_min_slot_count(mast->orig_l->node)) return true; return false; } /* * mast_overflow: Check if there is too much data in the subtree state for a * single node. * @mast: The maple subtree state */ static inline bool mast_overflow(struct maple_subtree_state *mast) { if (mast->bn->b_end >= mt_slot_count(mast->orig_l->node)) return true; return false; } static inline void *mtree_range_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next, *last; enum maple_type type; void __rcu **slots; unsigned char end; unsigned long max, min; unsigned long prev_max, prev_min; next = mas->node; min = mas->min; max = mas->max; do { last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); prev_min = min; prev_max = max; if (pivots[0] >= mas->index) { offset = 0; max = pivots[0]; goto next; } offset = 1; while (offset < end) { if (pivots[offset] >= mas->index) { max = pivots[offset]; break; } offset++; } min = pivots[offset - 1] + 1; next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; mas->min = prev_min; mas->max = prev_max; mas->node = last; return (void *)next; dead_node: mas_reset(mas); return NULL; } /* * mas_spanning_rebalance() - Rebalance across two nodes which may not be peers. * @mas: The starting maple state * @mast: The maple_subtree_state, keeps track of 4 maple states. * @count: The estimated count of iterations needed. * * Follow the tree upwards from @l_mas and @r_mas for @count, or until the root * is hit. First @b_node is split into two entries which are inserted into the * next iteration of the loop. @b_node is returned populated with the final * iteration. @mas is used to obtain allocations. orig_l_mas keeps track of the * nodes that will remain active by using orig_l_mas->index and orig_l_mas->last * to account of what has been copied into the new sub-tree. The update of * orig_l_mas->last is used in mas_consume to find the slots that will need to * be either freed or destroyed. orig_l_mas->depth keeps track of the height of * the new sub-tree in case the sub-tree becomes the full tree. */ static void mas_spanning_rebalance(struct ma_state *mas, struct maple_subtree_state *mast, unsigned char count) { unsigned char split, mid_split; unsigned char slot = 0; struct maple_enode *left = NULL, *middle = NULL, *right = NULL; struct maple_enode *old_enode; MA_STATE(l_mas, mas->tree, mas->index, mas->index); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(m_mas, mas->tree, mas->index, mas->index); /* * The tree needs to be rebalanced and leaves need to be kept at the same level. * Rebalancing is done by use of the ``struct maple_topiary``. */ mast->l = &l_mas; mast->m = &m_mas; mast->r = &r_mas; l_mas.status = r_mas.status = m_mas.status = ma_none; /* Check if this is not root and has sufficient data. */ if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) && unlikely(mast->bn->b_end <= mt_min_slots[mast->bn->type])) mast_spanning_rebalance(mast); l_mas.depth = 0; /* * Each level of the tree is examined and balanced, pushing data to the left or * right, or rebalancing against left or right nodes is employed to avoid * rippling up the tree to limit the amount of churn. Once a new sub-section of * the tree is created, there may be a mix of new and old nodes. The old nodes * will have the incorrect parent pointers and currently be in two trees: the * original tree and the partially new tree. To remedy the parent pointers in * the old tree, the new data is swapped into the active tree and a walk down * the tree is performed and the parent pointers are updated. * See mas_topiary_replace() for more information. */ while (count--) { mast->bn->b_end--; mast->bn->type = mte_node_type(mast->orig_l->node); split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle, &mid_split, mast->orig_l->min); mast_set_split_parents(mast, left, middle, right, split, mid_split); mast_cp_to_nodes(mast, left, middle, right, split, mid_split); /* * Copy data from next level in the tree to mast->bn from next * iteration */ memset(mast->bn, 0, sizeof(struct maple_big_node)); mast->bn->type = mte_node_type(left); l_mas.depth++; /* Root already stored in l->node. */ if (mas_is_root_limits(mast->l)) goto new_root; mast_ascend(mast); mast_combine_cp_left(mast); l_mas.offset = mast->bn->b_end; mab_set_b_end(mast->bn, &l_mas, left); mab_set_b_end(mast->bn, &m_mas, middle); mab_set_b_end(mast->bn, &r_mas, right); /* Copy anything necessary out of the right node. */ mast_combine_cp_right(mast); mast->orig_l->last = mast->orig_l->max; if (mast_sufficient(mast)) continue; if (mast_overflow(mast)) continue; /* May be a new root stored in mast->bn */ if (mas_is_root_limits(mast->orig_l)) break; mast_spanning_rebalance(mast); /* rebalancing from other nodes may require another loop. */ if (!count) count++; } l_mas.node = mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), mte_node_type(mast->orig_l->node)); l_mas.depth++; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, &l_mas, true); mas_set_parent(mas, left, l_mas.node, slot); if (middle) mas_set_parent(mas, middle, l_mas.node, ++slot); if (right) mas_set_parent(mas, right, l_mas.node, ++slot); if (mas_is_root_limits(mast->l)) { new_root: mas_mn(mast->l)->parent = ma_parent_ptr(mas_tree_parent(mas)); while (!mte_is_root(mast->orig_l->node)) mast_ascend(mast); } else { mas_mn(&l_mas)->parent = mas_mn(mast->orig_l)->parent; } old_enode = mast->orig_l->node; mas->depth = l_mas.depth; mas->node = l_mas.node; mas->min = l_mas.min; mas->max = l_mas.max; mas->offset = l_mas.offset; mas_wmb_replace(mas, old_enode); mtree_range_walk(mas); return; } /* * mas_rebalance() - Rebalance a given node. * @mas: The maple state * @b_node: The big maple node. * * Rebalance two nodes into a single node or two new nodes that are sufficient. * Continue upwards until tree is sufficient. */ static inline void mas_rebalance(struct ma_state *mas, struct maple_big_node *b_node) { char empty_count = mas_mt_height(mas); struct maple_subtree_state mast; unsigned char shift, b_end = ++b_node->b_end; MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); /* * Rebalancing occurs if a node is insufficient. Data is rebalanced * against the node to the right if it exists, otherwise the node to the * left of this node is rebalanced against this node. If rebalancing * causes just one node to be produced instead of two, then the parent * is also examined and rebalanced if it is insufficient. Every level * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ mast.orig_l = &l_mas; mast.orig_r = &r_mas; mast.bn = b_node; mast.bn->type = mte_node_type(mas->node); l_mas = r_mas = *mas; if (mas_next_sibling(&r_mas)) { mas_mab_cp(&r_mas, 0, mt_slot_count(r_mas.node), b_node, b_end); r_mas.last = r_mas.index = r_mas.max; } else { mas_prev_sibling(&l_mas); shift = mas_data_end(&l_mas) + 1; mab_shift_right(b_node, shift); mas->offset += shift; mas_mab_cp(&l_mas, 0, shift - 1, b_node, 0); b_node->b_end = shift + b_end; l_mas.index = l_mas.last = l_mas.min; } return mas_spanning_rebalance(mas, &mast, empty_count); } /* * mas_destroy_rebalance() - Rebalance left-most node while destroying the maple * state. * @mas: The maple state * @end: The end of the left-most node. * * During a mass-insert event (such as forking), it may be necessary to * rebalance the left-most node when it is not sufficient. */ static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end) { enum maple_type mt = mte_node_type(mas->node); struct maple_node reuse, *newnode, *parent, *new_left, *left, *node; struct maple_enode *eparent, *old_eparent; unsigned char offset, tmp, split = mt_slots[mt] / 2; void __rcu **l_slots, **slots; unsigned long *l_pivs, *pivs, gap; bool in_rcu = mt_in_rcu(mas->tree); MA_STATE(l_mas, mas->tree, mas->index, mas->last); l_mas = *mas; mas_prev_sibling(&l_mas); /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { newnode = &reuse; } node = mas_mn(mas); newnode->parent = node->parent; slots = ma_slots(newnode, mt); pivs = ma_pivots(newnode, mt); left = mas_mn(&l_mas); l_slots = ma_slots(left, mt); l_pivs = ma_pivots(left, mt); if (!l_slots[split]) split++; tmp = mas_data_end(&l_mas) - split; memcpy(slots, l_slots + split + 1, sizeof(void *) * tmp); memcpy(pivs, l_pivs + split + 1, sizeof(unsigned long) * tmp); pivs[tmp] = l_mas.max; memcpy(slots + tmp, ma_slots(node, mt), sizeof(void *) * end); memcpy(pivs + tmp, ma_pivots(node, mt), sizeof(unsigned long) * end); l_mas.max = l_pivs[split]; mas->min = l_mas.max + 1; old_eparent = mt_mk_node(mte_parent(l_mas.node), mas_parent_type(&l_mas, l_mas.node)); tmp += end; if (!in_rcu) { unsigned char max_p = mt_pivots[mt]; unsigned char max_s = mt_slots[mt]; if (tmp < max_p) memset(pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); if (tmp < mt_slots[mt]) memset(slots + tmp, 0, sizeof(void *) * (max_s - tmp)); memcpy(node, newnode, sizeof(struct maple_node)); ma_set_meta(node, mt, 0, tmp - 1); mte_set_pivot(old_eparent, mte_parent_slot(l_mas.node), l_pivs[split]); /* Remove data from l_pivs. */ tmp = split + 1; memset(l_pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); memset(l_slots + tmp, 0, sizeof(void *) * (max_s - tmp)); ma_set_meta(left, mt, 0, split); eparent = old_eparent; goto done; } /* RCU requires replacing both l_mas, mas, and parent. */ mas->node = mt_mk_node(newnode, mt); ma_set_meta(newnode, mt, 0, tmp); new_left = mas_pop_node(mas); new_left->parent = left->parent; mt = mte_node_type(l_mas.node); slots = ma_slots(new_left, mt); pivs = ma_pivots(new_left, mt); memcpy(slots, l_slots, sizeof(void *) * split); memcpy(pivs, l_pivs, sizeof(unsigned long) * split); ma_set_meta(new_left, mt, 0, split); l_mas.node = mt_mk_node(new_left, mt); /* replace parent. */ offset = mte_parent_slot(mas->node); mt = mas_parent_type(&l_mas, l_mas.node); parent = mas_pop_node(mas); slots = ma_slots(parent, mt); pivs = ma_pivots(parent, mt); memcpy(parent, mte_to_node(old_eparent), sizeof(struct maple_node)); rcu_assign_pointer(slots[offset], mas->node); rcu_assign_pointer(slots[offset - 1], l_mas.node); pivs[offset - 1] = l_mas.max; eparent = mt_mk_node(parent, mt); done: gap = mas_leaf_max_gap(mas); mte_set_gap(eparent, mte_parent_slot(mas->node), gap); gap = mas_leaf_max_gap(&l_mas); mte_set_gap(eparent, mte_parent_slot(l_mas.node), gap); mas_ascend(mas); if (in_rcu) { mas_replace_node(mas, old_eparent); mas_adopt_children(mas, mas->node); } mas_update_gap(mas); } /* * mas_split_final_node() - Split the final node in a subtree operation. * @mast: the maple subtree state * @mas: The maple state * @height: The height of the tree in case it's a new root. */ static inline void mas_split_final_node(struct maple_subtree_state *mast, struct ma_state *mas, int height) { struct maple_enode *ancestor; if (mte_is_root(mas->node)) { if (mt_is_alloc(mas->tree)) mast->bn->type = maple_arange_64; else mast->bn->type = maple_range_64; mas->depth = height; } /* * Only a single node is used here, could be root. * The Big_node data should just fit in a single node. */ ancestor = mas_new_ma_node(mas, mast->bn); mas_set_parent(mas, mast->l->node, ancestor, mast->l->offset); mas_set_parent(mas, mast->r->node, ancestor, mast->r->offset); mte_to_node(ancestor)->parent = mas_mn(mas)->parent; mast->l->node = ancestor; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true); mas->offset = mast->bn->b_end - 1; } /* * mast_fill_bnode() - Copy data into the big node in the subtree state * @mast: The maple subtree state * @mas: the maple state * @skip: The number of entries to skip for new nodes insertion. */ static inline void mast_fill_bnode(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char skip) { bool cp = true; unsigned char split; memset(mast->bn, 0, sizeof(struct maple_big_node)); if (mte_is_root(mas->node)) { cp = false; } else { mas_ascend(mas); mas->offset = mte_parent_slot(mas->node); } if (cp && mast->l->offset) mas_mab_cp(mas, 0, mast->l->offset - 1, mast->bn, 0); split = mast->bn->b_end; mab_set_b_end(mast->bn, mast->l, mast->l->node); mast->r->offset = mast->bn->b_end; mab_set_b_end(mast->bn, mast->r, mast->r->node); if (mast->bn->pivot[mast->bn->b_end - 1] == mas->max) cp = false; if (cp) mas_mab_cp(mas, split + skip, mt_slot_count(mas->node) - 1, mast->bn, mast->bn->b_end); mast->bn->b_end--; mast->bn->type = mte_node_type(mas->node); } /* * mast_split_data() - Split the data in the subtree state big node into regular * nodes. * @mast: The maple subtree state * @mas: The maple state * @split: The location to split the big node */ static inline void mast_split_data(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char split) { unsigned char p_slot; mab_mas_cp(mast->bn, 0, split, mast->l, true); mte_set_pivot(mast->r->node, 0, mast->r->max); mab_mas_cp(mast->bn, split + 1, mast->bn->b_end, mast->r, false); mast->l->offset = mte_parent_slot(mas->node); mast->l->max = mast->bn->pivot[split]; mast->r->min = mast->l->max + 1; if (mte_is_leaf(mas->node)) return; p_slot = mast->orig_l->offset; mas_set_split_parent(mast->orig_l, mast->l->node, mast->r->node, &p_slot, split); mas_set_split_parent(mast->orig_r, mast->l->node, mast->r->node, &p_slot, split); } /* * mas_push_data() - Instead of splitting a node, it is beneficial to push the * data to the right or left node if there is room. * @mas: The maple state * @height: The current height of the maple state * @mast: The maple subtree state * @left: Push left or not. * * Keeping the height of the tree low means faster lookups. * * Return: True if pushed, false otherwise. */ static inline bool mas_push_data(struct ma_state *mas, int height, struct maple_subtree_state *mast, bool left) { unsigned char slot_total = mast->bn->b_end; unsigned char end, space, split; MA_STATE(tmp_mas, mas->tree, mas->index, mas->last); tmp_mas = *mas; tmp_mas.depth = mast->l->depth; if (left && !mas_prev_sibling(&tmp_mas)) return false; else if (!left && !mas_next_sibling(&tmp_mas)) return false; end = mas_data_end(&tmp_mas); slot_total += end; space = 2 * mt_slot_count(mas->node) - 2; /* -2 instead of -1 to ensure there isn't a triple split */ if (ma_is_leaf(mast->bn->type)) space--; if (mas->max == ULONG_MAX) space--; if (slot_total >= space) return false; /* Get the data; Fill mast->bn */ mast->bn->b_end++; if (left) { mab_shift_right(mast->bn, end + 1); mas_mab_cp(&tmp_mas, 0, end, mast->bn, 0); mast->bn->b_end = slot_total + 1; } else { mas_mab_cp(&tmp_mas, 0, end, mast->bn, mast->bn->b_end); } /* Configure mast for splitting of mast->bn */ split = mt_slots[mast->bn->type] - 2; if (left) { /* Switch mas to prev node */ *mas = tmp_mas; /* Start using mast->l for the left side. */ tmp_mas.node = mast->l->node; *mast->l = tmp_mas; } else { tmp_mas.node = mast->r->node; *mast->r = tmp_mas; split = slot_total - split; } split = mab_no_null_split(mast->bn, split, mt_slots[mast->bn->type]); /* Update parent slot for split calculation. */ if (left) mast->orig_l->offset += end + 1; mast_split_data(mast, mas, split); mast_fill_bnode(mast, mas, 2); mas_split_final_node(mast, mas, height + 1); return true; } /* * mas_split() - Split data that is too big for one node into two. * @mas: The maple state * @b_node: The maple big node */ static void mas_split(struct ma_state *mas, struct maple_big_node *b_node) { struct maple_subtree_state mast; int height = 0; unsigned char mid_split, split = 0; struct maple_enode *old; /* * Splitting is handled differently from any other B-tree; the Maple * Tree splits upwards. Splitting up means that the split operation * occurs when the walk of the tree hits the leaves and not on the way * down. The reason for splitting up is that it is impossible to know * how much space will be needed until the leaf is (or leaves are) * reached. Since overwriting data is allowed and a range could * overwrite more than one range or result in changing one entry into 3 * entries, it is impossible to know if a split is required until the * data is examined. * * Splitting is a balancing act between keeping allocations to a minimum * and avoiding a 'jitter' event where a tree is expanded to make room * for an entry followed by a contraction when the entry is removed. To * accomplish the balance, there are empty slots remaining in both left * and right nodes after a split. */ MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); mas->depth = mas_mt_height(mas); mast.l = &l_mas; mast.r = &r_mas; mast.orig_l = &prev_l_mas; mast.orig_r = &prev_r_mas; mast.bn = b_node; while (height++ <= mas->depth) { if (mt_slots[b_node->type] > b_node->b_end) { mas_split_final_node(&mast, mas, height); break; } l_mas = r_mas = *mas; l_mas.node = mas_new_ma_node(mas, b_node); r_mas.node = mas_new_ma_node(mas, b_node); /* * Another way that 'jitter' is avoided is to terminate a split up early if the * left or right node has space to spare. This is referred to as "pushing left" * or "pushing right" and is similar to the B* tree, except the nodes left or * right can rarely be reused due to RCU, but the ripple upwards is halted which * is a significant savings. */ /* Try to push left. */ if (mas_push_data(mas, height, &mast, true)) break; /* Try to push right. */ if (mas_push_data(mas, height, &mast, false)) break; split = mab_calc_split(mas, b_node, &mid_split, prev_l_mas.min); mast_split_data(&mast, mas, split); /* * Usually correct, mab_mas_cp in the above call overwrites * r->max. */ mast.r->max = mas->max; mast_fill_bnode(&mast, mas, 1); prev_l_mas = *mast.l; prev_r_mas = *mast.r; } /* Set the original node as dead */ old = mas->node; mas->node = l_mas.node; mas_wmb_replace(mas, old); mtree_range_walk(mas); return; } /* * mas_commit_b_node() - Commit the big node into the tree. * @wr_mas: The maple write state * @b_node: The maple big node */ static noinline_for_kasan void mas_commit_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node) { enum store_type type = wr_mas->mas->store_type; WARN_ON_ONCE(type != wr_rebalance && type != wr_split_store); if (type == wr_rebalance) return mas_rebalance(wr_mas->mas, b_node); return mas_split(wr_mas->mas, b_node); } /* * mas_root_expand() - Expand a root to a node * @mas: The maple state * @entry: The entry to store into the tree */ static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; int slot = 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents); if (likely(mas->index > 1)) slot++; } pivots[slot++] = mas->index - 1; } rcu_assign_pointer(slots[slot], entry); mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX; mas->depth = 1; mas_set_height(mas); ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); return; } /* * mas_store_root() - Storing value into root. * @mas: The maple state * @entry: The entry to store. * * There is no root node now and we are storing a value into the root - this * function either assigns the pointer or expands into a node. */ static inline void mas_store_root(struct ma_state *mas, void *entry) { if (!entry) { if (!mas->index) rcu_assign_pointer(mas->tree->ma_root, NULL); } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; } } /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. * @wr_mas: The maple write state * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. * * Return: True if this is a spanning write, false otherwise. */ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) { unsigned long max = wr_mas->r_max; unsigned long last = wr_mas->mas->last; enum maple_type type = wr_mas->type; void *entry = wr_mas->entry; /* Contained in this pivot, fast path */ if (last < max) return false; if (ma_is_leaf(type)) { max = wr_mas->mas->max; if (last < max) return false; } if (last == max) { /* * The last entry of leaf node cannot be NULL unless it is the * rightmost node (writing ULONG_MAX), otherwise it spans slots. */ if (entry || last == ULONG_MAX) return false; } trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry); return true; } static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas) { wr_mas->type = mte_node_type(wr_mas->mas->node); mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); } static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas) { wr_mas->mas->max = wr_mas->r_max; wr_mas->mas->min = wr_mas->r_min; wr_mas->mas->node = wr_mas->content; wr_mas->mas->offset = 0; wr_mas->mas->depth++; } /* * mas_wr_walk() - Walk the tree for a write. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. * * Return: True if it's contained in a node, false on spanning write. */ static bool mas_wr_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); if (unlikely(mas_is_span_wr(wr_mas))) return false; wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; mas_wr_walk_traverse(wr_mas); } return true; } static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return; mas_wr_walk_traverse(wr_mas); } } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state */ static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { struct ma_state *r_mas = r_wr_mas->mas; struct ma_state *l_mas = l_wr_mas->mas; unsigned char l_slot; l_slot = l_mas->offset; if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) { if (l_slot > 1) l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1; else l_mas->index = l_mas->min; l_mas->offset = l_slot - 1; } if (!r_wr_mas->content) { if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max; r_mas->offset++; } else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots, r_wr_mas->type, r_mas->offset + 1); r_mas->offset++; } } static inline void *mas_state_walk(struct ma_state *mas) { void *entry; entry = mas_start(mas); if (mas_is_none(mas)) return NULL; if (mas_is_ptr(mas)) return entry; return mtree_range_walk(mas); } /* * mtree_lookup_walk() - Internal quick lookup that does not keep maple state up * to date. * * @mas: The maple state. * * Note: Leaves mas in undesirable state. * Return: The entry for @mas->index or %NULL on dead node. */ static inline void *mtree_lookup_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next; enum maple_type type; void __rcu **slots; unsigned char end; next = mas->node; do { node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = mt_pivots[type]; offset = 0; do { if (pivots[offset] >= mas->index) break; } while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); return (void *)next; dead_node: mas_reset(mas); return NULL; } static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); /* * mas_new_root() - Create a new root node that only contains the entry passed * in. * @mas: The maple state * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX */ static inline void mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); if (!entry) { mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; goto done; } node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mas->depth = 1; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); return; } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed * and new nodes where necessary, then place the sub-tree in the actual tree. * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state */ static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_subtree_state mast; struct maple_big_node b_node; struct ma_state *mas; unsigned char height; /* Left and Right side of spanning store */ MA_STATE(l_mas, NULL, 0, 0); MA_STATE(r_mas, NULL, 0, 0); MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry); MA_WR_STATE(l_wr_mas, &l_mas, wr_mas->entry); /* * A store operation that spans multiple nodes is called a spanning * store and is handled early in the store call stack by the function * mas_is_span_wr(). When a spanning store is identified, the maple * state is duplicated. The first maple state walks the left tree path * to ``index``, the duplicate walks the right tree path to ``last``. * The data in the two nodes are combined into a single node, two nodes, * or possibly three nodes (see the 3-way split above). A ``NULL`` * written to the last entry of a node is considered a spanning store as * a rebalance is required for the operation to complete and an overflow * of data may happen. */ mas = wr_mas->mas; trace_ma_op(__func__, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); /* * Node rebalancing may occur due to this store, so there may be three new * entries per level plus a new root. */ height = mas_mt_height(mas); /* * Set up right side. Need to get to the next offset after the spanning * store to ensure it's not NULL and to combine both the next node and * the node with the start together. */ r_mas = *mas; /* Avoid overflow, walk to next slot in the tree. */ if (r_mas.last + 1) r_mas.last++; r_mas.index = r_mas.last; mas_wr_walk_index(&r_wr_mas); r_mas.last = r_mas.index = mas->last; /* Set up left side. */ l_mas = *mas; mas_wr_walk_index(&l_wr_mas); if (!wr_mas->entry) { mas_extend_spanning_null(&l_wr_mas, &r_wr_mas); mas->offset = l_mas.offset; mas->index = l_mas.index; mas->last = l_mas.last = r_mas.last; } /* expanding NULLs may make this cover the entire range */ if (!l_mas.index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX); return mas_new_root(mas, wr_mas->entry); } memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); /* Copy r_mas into b_node if there is anything to copy. */ if (r_mas.max > r_mas.last) mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else b_node.b_end++; /* Stop spanning searches by searching for just index. */ l_mas.index = l_mas.last = mas->index; mast.bn = &b_node; mast.orig_l = &l_mas; mast.orig_r = &r_mas; /* Combine l_mas and r_mas and split them up evenly again. */ return mas_spanning_rebalance(mas, &mast, height + 1); } /* * mas_wr_node_store() - Attempt to store the value in a node * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. */ static inline void mas_wr_node_store(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; void __rcu **dst_slots; unsigned long *dst_pivots; unsigned char dst_offset, offset_end = wr_mas->offset_end; struct maple_node reuse, *newnode; unsigned char copy_size, node_pivots = mt_pivots[wr_mas->type]; bool in_rcu = mt_in_rcu(mas->tree); if (mas->last == wr_mas->end_piv) offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) mas_bulk_rebalance(mas, mas->end, wr_mas->type); /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); newnode = &reuse; } newnode->parent = mas_mn(mas)->parent; dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type); /* Copy from start to insert point */ memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset); memcpy(dst_slots, wr_mas->slots, sizeof(void *) * mas->offset); /* Handle insert of new range starting after old range */ if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content); dst_pivots[mas->offset++] = mas->index - 1; } /* Store the new entry and range end. */ if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last; rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry); /* * this range wrote to the end of the node or it overwrote the rest of * the data */ if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, sizeof(unsigned long) * (copy_size - 1)); if (new_end < node_pivots) dst_pivots[new_end] = mas->max; done: mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace_node(mas, old_enode); } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } trace_ma_write(__func__, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; return; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state */ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; void __rcu **slots = wr_mas->slots; bool gap = false; gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1); if (wr_mas->offset_end - offset == 1) { if (mas->index == wr_mas->r_min) { /* Overwriting the range and a part of the next one */ rcu_assign_pointer(slots[offset], wr_mas->entry); wr_mas->pivots[offset] = mas->last; } else { /* Overwriting a part of the range and the next one */ rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } } else { WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges */ gap |= !mt_slot_locked(mas->tree, slots, offset + 2); rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ } trace_ma_write(__func__, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. */ if (!wr_mas->entry || gap) mas_update_gap(mas); return; } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!wr_mas->slots[wr_mas->offset_end]) { /* If this one is null, the next and prev are not */ mas->last = wr_mas->end_piv; } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; wr_mas->end_piv = mas->last; } } if (!wr_mas->content) { /* If this one is null, the next and prev are not */ mas->index = wr_mas->r_min; } else { /* Check prev slot if we are overwriting the start */ if (mas->index == wr_mas->r_min && mas->offset && !wr_mas->slots[mas->offset - 1]) { mas->offset--; wr_mas->r_min = mas->index = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = wr_mas->pivots[mas->offset]; } } } static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) new_end--; if (wr_mas->end_piv == mas->last) new_end--; return new_end; } /* * mas_wr_append: Attempt to append * @wr_mas: the maple write state * @new_end: The end of the node after the modification * * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. */ static inline void mas_wr_append(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; void __rcu **slots; unsigned char end = mas->end; if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end); } slots = wr_mas->slots; if (new_end == end + 1) { if (mas->last == wr_mas->r_max) { /* Append to end of range */ rcu_assign_pointer(slots[new_end], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = new_end; } else { /* Append to start of range */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end] = mas->last; rcu_assign_pointer(slots[end], wr_mas->entry); } } else { /* Append to the range without touching any boundaries. */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end + 1] = mas->last; rcu_assign_pointer(slots[end + 1], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = end + 1; } if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); mas->end = new_end; trace_ma_write(__func__, mas, new_end, wr_mas->entry); return; } /* * mas_wr_bnode() - Slow path for a modification. * @wr_mas: The write maple state * * This is where split, rebalance end up. */ static void mas_wr_bnode(struct ma_wr_state *wr_mas) { struct maple_big_node b_node; trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); mas_commit_b_node(wr_mas, &b_node); } /* * mas_wr_store_entry() - Internal call to store a value * @wr_mas: The maple write state */ static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas_wr_new_end(wr_mas); switch (mas->store_type) { case wr_invalid: MT_BUG_ON(mas->tree, 1); return; case wr_new_root: mas_new_root(mas, wr_mas->entry); break; case wr_store_root: mas_store_root(mas, wr_mas->entry); break; case wr_exact_fit: rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); break; case wr_append: mas_wr_append(wr_mas, new_end); break; case wr_slot_store: mas_wr_slot_store(wr_mas); break; case wr_node_store: mas_wr_node_store(wr_mas, new_end); break; case wr_spanning_store: mas_wr_spanning_store(wr_mas); break; case wr_split_store: case wr_rebalance: mas_wr_bnode(wr_mas); break; } return; } static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!mas_is_active(mas)) { if (mas_is_start(mas)) goto set_content; if (unlikely(mas_is_paused(mas))) goto reset; if (unlikely(mas_is_none(mas))) goto reset; if (unlikely(mas_is_overflow(mas))) goto reset; if (unlikely(mas_is_underflow(mas))) goto reset; } /* * A less strict version of mas_is_span_wr() where we allow spanning * writes within this node. This is to stop partial walks in * mas_prealloc() from being reset. */ if (mas->last > mas->max) goto reset; if (wr_mas->entry) goto set_content; if (mte_is_leaf(mas->node) && mas->last == mas->max) goto reset; goto set_content; reset: mas_reset(mas); set_content: wr_mas->content = mas_start(mas); } /** * mas_prealloc_calc() - Calculate number of nodes needed for a * given store oepration * @mas: The maple state * @entry: The entry to store into the tree * * Return: Number of nodes required for preallocation. */ static inline int mas_prealloc_calc(struct ma_state *mas, void *entry) { int ret = mas_mt_height(mas) * 3 + 1; switch (mas->store_type) { case wr_invalid: WARN_ON_ONCE(1); break; case wr_new_root: ret = 1; break; case wr_store_root: if (likely((mas->last != 0) || (mas->index != 0))) ret = 1; else if (((unsigned long) (entry) & 3) == 2) ret = 1; else ret = 0; break; case wr_spanning_store: ret = mas_mt_height(mas) * 3 + 1; break; case wr_split_store: ret = mas_mt_height(mas) * 2 + 1; break; case wr_rebalance: ret = mas_mt_height(mas) * 2 - 1; break; case wr_node_store: ret = mt_in_rcu(mas->tree) ? 1 : 0; break; case wr_append: case wr_exact_fit: case wr_slot_store: ret = 0; } return ret; } /* * mas_wr_store_type() - Determine the store type for a given * store operation. * @wr_mas: The maple write state * * Return: the type of store needed for the operation */ static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return wr_store_root; if (unlikely(!mas_wr_walk(wr_mas))) return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) return wr_exact_fit; if (unlikely(!mas->index && mas->last == ULONG_MAX)) return wr_new_root; new_end = mas_wr_new_end(wr_mas); /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK)) return wr_rebalance; return wr_node_store; } if (new_end >= mt_slots[wr_mas->type]) return wr_split_store; if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) return wr_append; if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || (wr_mas->offset_end - mas->offset == 1))) return wr_slot_store; return wr_node_store; } /** * mas_wr_preallocate() - Preallocate enough nodes for a store operation * @wr_mas: The maple write state * @entry: The entry that will be stored * */ static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; int request; mas_wr_prealloc_setup(wr_mas); mas->store_type = mas_wr_store_type(wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return; mas_node_count(mas, request); } /** * mas_insert() - Internal call to insert a value * @mas: The maple state * @entry: The entry to store * * Return: %NULL or the contents that already exists at the requested index * otherwise. The maple state needs to be checked for error conditions. */ static inline void *mas_insert(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); /* * Inserting a new range inserts either 0, 1, or 2 pivots within the * tree. If the insert fits exactly into an existing gap with a value * of NULL, then the slot only needs to be written with the new value. * If the range being inserted is adjacent to another range, then only a * single pivot needs to be inserted (as well as writing the entry). If * the new range is within a gap but does not touch any other ranges, * then two pivots need to be inserted: the start - 1, and the end. As * usual, the entry must be written. Most operations require a new node * to be allocated and replace an existing node to ensure RCU safety, * when in RCU mode. The exception to requiring a newly allocated node * is when inserting at the end of a node (appending). When done * carefully, appending can reuse the node in place. */ wr_mas.content = mas_start(mas); if (wr_mas.content) goto exists; mas_wr_preallocate(&wr_mas, entry); if (mas_is_err(mas)) return NULL; /* spanning writes always overwrite something */ if (mas->store_type == wr_spanning_store) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) { wr_mas.offset_end = mas->offset; wr_mas.end_piv = wr_mas.r_max; if (wr_mas.content || (mas->last > wr_mas.r_max)) goto exists; } mas_wr_store_entry(&wr_mas); return wr_mas.content; exists: mas_set_err(mas, -EEXIST); return wr_mas.content; } /** * mas_alloc_cyclic() - Internal call to find somewhere to store an entry * @mas: The maple state. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, or -EBUSY if there are no * free entries. */ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { unsigned long min = range_lo; int ret = 0; range_lo = max(min, *next); ret = mas_empty_area(mas, range_lo, range_hi, 1); if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && range_lo > min) { ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; } if (ret < 0) return ret; do { mas_insert(mas, entry); } while (mas_nomem(mas, gfp)); if (mas_is_err(mas)) return xa_err(mas->node); *startp = mas->index; *next = *startp + 1; if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; mas_destroy(mas); return ret; } EXPORT_SYMBOL(mas_alloc_cyclic); static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); mas_state_walk(mas); if (mas_is_start(mas)) goto retry; } static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { mas_rewalk(mas, index); return true; } return false; } /* * mas_prev_node() - Find the prev non-null entry at the same level in the * tree. The prev value will be mas->node[mas->offset] or the status will be * ma_none. * @mas: The maple state * @min: The lower limit to search * * The prev node value will be mas->node[mas->offset] or the status will be * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; void __rcu **slots; struct maple_node *node; unsigned long *pivots; unsigned long max; node = mas_mn(mas); if (!mas->min) goto no_entry; max = mas->min - 1; if (max < min) goto no_entry; level = 0; do { if (ma_is_root(node)) goto no_entry; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; offset = mas->offset; level++; node = mas_mn(mas); } while (!offset); offset--; mt = mte_node_type(mas->node); while (level > 1) { level--; slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node))) return 1; mt = mte_node_type(mas->node); node = mas_mn(mas); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node))) return 1; } slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node))) return 1; if (likely(offset)) mas->min = pivots[offset - 1] + 1; mas->max = max; mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node))) return 1; mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_underflow; return 0; } /* * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state * @min: The minimum starting range * @empty: Can be empty * * Return: The entry in the previous slot which is possibly NULL */ static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; unsigned long pivot; enum maple_type type; unsigned long *pivots; struct maple_node *node; unsigned long save_point = mas->index; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot <= min) goto underflow; } again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { if (mas->index <= min) goto underflow; if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_underflow(mas))) return NULL; mas->last = mas->max; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->index = pivots[mas->offset - 1] + 1; } slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (likely(entry)) return entry; if (!empty) { if (mas->index <= min) { mas->status = ma_underflow; return NULL; } goto again; } return entry; underflow: mas->status = ma_underflow; return NULL; } /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state * @node: The maple node * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have * overflowed. * Return: 1 on dead node, 0 otherwise. */ static int mas_next_node(struct ma_state *mas, struct maple_node *node, unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; level++; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; } while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt); mas->offset++; enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node))) return 1; if (level > 1) mas->offset = 0; while (unlikely(level > 1)) { level--; mas->node = enode; node = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node))) return 1; } if (!mas->offset) pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); tmp = mte_to_node(enode); mt = mte_node_type(enode); pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; mas->node = enode; mas->min = min; return 0; overflow: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_overflow; return 0; } /* * mas_next_slot() - Get the entry in the next slot * * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty * * Return: The entry in the next slot which is possibly NULL */ static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; unsigned long save_point = mas->last; void *entry; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow; return NULL; } } if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; mas->offset = 0; mas->index = mas->min; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->last = pivots[0]; } slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (entry) return entry; if (!empty) { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } mas->index = mas->last + 1; goto again; } return entry; } /* * mas_next_entry() - Internal function to get the next entry. * @mas: The maple state * @limit: The maximum range start. * * Set the @mas->node to the next entry and the range_start to * the beginning value for the entry. Does not check beyond @limit. * Sets @mas->index and @mas->last to the range, Does not update @mas->index and * @mas->last on overflow. * Restarts on dead nodes. * * Return: the next entry or %NULL. */ static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { if (mas->last >= limit) { mas->status = ma_overflow; return NULL; } return mas_next_slot(mas, limit, false); } /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state * @size: The needed size. * * Return: True if found in a leaf, false otherwise. * */ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) return true; if (ma_is_dense(type)) { /* dense nodes. */ mas->offset = (unsigned char)(mas->index - mas->min); return true; } pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); /* Skip out of bounds. */ while (mas->last < min) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = max - min + 1; if (gap) { if ((size <= gap) && (size <= mas->last - min + 1)) break; if (!gaps) { /* Skip the next slot, it cannot be a gap. */ if (offset < 2) goto ascend; offset -= 2; max = pivots[offset]; min = mas_safe_min(mas, pivots, offset); continue; } } if (!offset) goto ascend; offset--; max = min - 1; min = mas_safe_min(mas, pivots, offset); } if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; *gap_min = min; *gap_max = min + gap - 1; return true; } /* descend, only happens under lock. */ mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = max; mas->offset = mas_data_end(mas); return false; ascend: if (!mte_is_root(mas->node)) return false; no_space: mas_set_err(mas, -EBUSY); return false; } static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; unsigned char offset, data_end; unsigned long *gaps, *pivots; void __rcu **slots; struct maple_node *node; bool found = false; if (ma_is_dense(type)) { mas->offset = (unsigned char)(mas->index - mas->min); return true; } node = mas_mn(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) { pivot = mas_safe_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) goto next_slot; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = min(pivot, mas->last) - max(mas->index, min) + 1; else goto next_slot; if (gap >= size) { if (ma_is_leaf(type)) { found = true; goto done; } if (mas->index <= pivot) { mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = pivot; offset = 0; break; } } next_slot: min = pivot + 1; if (mas->last <= pivot) { mas_set_err(mas, -EBUSY); return true; } } if (mte_is_root(mas->node)) found = true; done: mas->offset = offset; return found; } /** * mas_walk() - Search for @mas->index in the tree. * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ void *mas_walk(struct ma_state *mas) { void *entry; if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { goto retry; } else if (mas_is_none(mas)) { mas->index = 0; mas->last = ULONG_MAX; } else if (mas_is_ptr(mas)) { if (!mas->index) { mas->last = 0; return entry; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return NULL; } return entry; } EXPORT_SYMBOL_GPL(mas_walk); static inline bool mas_rewind_node(struct ma_state *mas) { unsigned char slot; do { if (mte_is_root(mas->node)) { slot = mas->offset; if (!slot) return false; } else { mas_ascend(mas); slot = mas->offset; } } while (!slot); mas->offset = --slot; return true; } /* * mas_skip_node() - Internal function. Skip over a node. * @mas: The maple state. * * Return: true if there is another node, false otherwise. */ static inline bool mas_skip_node(struct ma_state *mas) { if (mas_is_err(mas)) return false; do { if (mte_is_root(mas->node)) { if (mas->offset >= mas_data_end(mas)) { mas_set_err(mas, -EBUSY); return false; } } else { mas_ascend(mas); } } while (mas->offset >= mas_data_end(mas)); mas->offset++; return true; } /* * mas_awalk() - Allocation walk. Search from low address to high, for a gap of * @size * @mas: The maple state * @size: The size of the gap required * * Search between @mas->index and @mas->last for a gap of @size. */ static inline void mas_awalk(struct ma_state *mas, unsigned long size) { struct maple_enode *last = NULL; /* * There are 4 options: * go to child (descend) * go back to parent (ascend) * no gap found. (return, slot == MAPLE_NODE_SLOTS) * found the gap. (return, slot != MAPLE_NODE_SLOTS) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas); else last = mas->node; } } /* * mas_sparse_area() - Internal function. Return upper or lower limit when * searching for a gap in an empty tree. * @mas: The maple state * @min: the minimum range * @max: The maximum range * @size: The size of the gap * @fwd: Searching forward or back */ static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { if (!unlikely(mas_is_none(mas)) && min == 0) { min++; /* * At this time, min is increased, we need to recheck whether * the size is satisfied. */ if (min > max || max - min + 1 < size) return -EBUSY; } /* mas_is_ptr */ if (fwd) { mas->index = min; mas->last = min + size - 1; } else { mas->last = max; mas->index = max - size + 1; } return 0; } /* * mas_empty_area() - Get the lowest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { unsigned char offset; unsigned long *pivots; enum maple_type mt; struct maple_node *node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) mas->offset -= 2; else if (!mas_skip_node(mas)) return -EBUSY; /* Empty set */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; mas->last = max; mas_awalk(mas, size); if (unlikely(mas_is_err(mas))) return xa_err(mas->node); offset = mas->offset; if (unlikely(offset == MAPLE_NODE_SLOTS)) return -EBUSY; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); /* * mas_empty_area_rev() - Get the highest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { struct maple_enode *last = mas->node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); else if (mas->offset >= 2) mas->offset -= 2; else mas->offset = mas_data_end(mas); /* The start of the window can only be within these values. */ mas->index = min; mas->last = max; while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; } else { last = mas->node; } } if (mas_is_err(mas)) return xa_err(mas->node); if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; /* Trim the upper limit to the max. */ if (max < mas->last) mas->last = max; mas->index = mas->last - size + 1; mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. * @enode: the encoded node * @mt: the maple tree * @slots: Pointer to the slot array * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ if (!node || !type) break; mte_set_node_dead(entry); node->type = type; rcu_assign_pointer(slots[offset], node); } return offset; } /** * mte_dead_walk() - Walk down a dead tree to just before the leaves * @enode: The maple encoded node * @offset: The starting offset * * Note: This can only be used from the RCU callback context. */ static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; next = mte_to_node(*enode); do { *enode = ma_enode_ptr(next); node = mte_to_node(*enode); slots = ma_slots(node, node->type); next = rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } /** * mt_free_walk() - Walk & free a tree in the RCU callback context * @head: The RCU head that's within the node. * * Note: This can only be used from the RCU callback context. */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; struct maple_enode *enode; unsigned char offset; enum maple_type type; node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; start = node; enode = mt_mk_node(node, node->type); slots = mte_dead_walk(&enode, 0); node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if ((offset < mt_slots[type]) && rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map))) slots = mte_dead_walk(&enode, offset); node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); free_leaf: mt_free_rcu(&node->rcu); } static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; struct maple_enode *next = *enode; void __rcu **slots = NULL; enum maple_type type; unsigned char next_offset = 0; do { *enode = next; node = mte_to_node(*enode); type = mte_node_type(*enode); slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset); mte_set_node_dead(*enode); node->type = type; node->piv_parent = prev; node->parent_slot = offset; offset = next_offset; next_offset = 0; prev = *enode; } while (!mte_is_leaf(next)); return slots; } static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; if (mte_is_leaf(enode)) { node->type = mte_node_type(enode); goto free_leaf; } start = enode; slots = mte_destroy_descend(&enode, mt, start, 0); node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { parent = enode; enode = tmp; slots = mte_destroy_descend(&enode, mt, parent, offset); } next: node = mte_to_node(enode); } while (start != enode); node = mte_to_node(enode); node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); free_leaf: if (free) mt_free_rcu(&node->rcu); else mt_clear_meta(mt, node, node->type); } /* * mte_destroy_walk() - Free a tree or sub-tree. * @enode: the encoded maple node (maple_enode) to start * @mt: the tree to free - needed for node types. * * Must hold the write lock. */ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_tree *mt) { struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { mt_destroy_walk(enode, mt, true); } } /* Interface */ /** * mas_store() - Store an @entry. * @mas: The maple state. * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { int request; MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(__func__, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); return NULL; } #endif /* * Storing is the same operation as insert with the added caveat that it * can overwrite entries. Although this seems simple enough, one may * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); if (mas->mas_flags & MA_STATE_PREALLOC) { mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); return wr_mas.content; } request = mas_prealloc_calc(mas, entry); if (!request) goto store; mas_node_count(mas, request); if (mas_is_err(mas)) return NULL; store: mas_wr_store_entry(&wr_mas); mas_destroy(mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); /** * mas_store_gfp() - Store a value into the tree. * @mas: The maple state * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations if necessary. * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { unsigned long index = mas->index; unsigned long last = mas->last; MA_WR_STATE(wr_mas, mas, entry); int ret = 0; retry: mas_wr_preallocate(&wr_mas, entry); if (unlikely(mas_nomem(mas, gfp))) { if (!entry) __mas_set_range(mas, index, last); goto retry; } if (mas_is_err(mas)) { ret = xa_err(mas->node); goto out; } mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_store_gfp); /** * mas_store_prealloc() - Store a value into the tree using memory * preallocated in the maple state. * @mas: The maple state * @entry: The entry to store. */ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); if (mas->store_type == wr_store_root) { mas_wr_prealloc_setup(&wr_mas); goto store; } mas_wr_walk_descend(&wr_mas); if (mas->store_type != wr_spanning_store) { /* set wr_mas->content to current slot */ wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); mas_wr_end_piv(&wr_mas); } store: trace_ma_write(__func__, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); } EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); int ret = 0; int request; mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return ret; mas_node_count_gfp(mas, request, gfp); if (mas_is_err(mas)) { mas_set_alloc_req(mas, 0); ret = xa_err(mas->node); mas_destroy(mas); mas_reset(mas); return ret; } mas->mas_flags |= MA_STATE_PREALLOC; return ret; } EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. * @mas: The maple state * * Upon completion, check the left-most node and rebalance against the node to * the right if necessary. Frees any allocated nodes associated with this maple * state. */ void mas_destroy(struct ma_state *mas) { struct maple_alloc *node; unsigned long total; /* * When using mas_for_each() to insert an expected number of elements, * it is possible that the number inserted is less than the expected * number. To fix an invalid final node, a check is performed here to * rebalance the previous node with the final node. */ if (mas->mas_flags & MA_STATE_REBALANCE) { unsigned char end; if (mas_is_err(mas)) mas_reset(mas); mas_start(mas); mtree_range_walk(mas); end = mas->end + 1; if (end < mt_min_slot_count(mas->node) - 1) mas_destroy_rebalance(mas, end); mas->mas_flags &= ~MA_STATE_REBALANCE; } mas->mas_flags &= ~(MA_STATE_BULK|MA_STATE_PREALLOC); total = mas_allocated(mas); while (total) { node = mas->alloc; mas->alloc = node->slot[0]; if (node->node_count > 1) { size_t count = node->node_count - 1; mt_free_bulk(count, (void __rcu **)&node->slot[1]); total -= count; } mt_free_one(ma_mnode_ptr(node)); total--; } mas->alloc = NULL; } EXPORT_SYMBOL_GPL(mas_destroy); /* * mas_expected_entries() - Set the expected number of entries that will be inserted. * @mas: The maple state * @nr_entries: The number of expected entries. * * This will attempt to pre-allocate enough nodes to store the expected number * of entries. The allocations will occur using the bulk allocator interface * for speed. Please call mas_destroy() on the @mas after inserting the entries * to ensure any unused nodes are freed. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries) { int nonleaf_cap = MAPLE_ARANGE64_SLOTS - 2; struct maple_enode *enode = mas->node; int nr_nodes; int ret; /* * Sometimes it is necessary to duplicate a tree to a new tree, such as * forking a process and duplicating the VMAs from one tree to a new * tree. When such a situation arises, it is known that the new tree is * not going to be used until the entire tree is populated. For * performance reasons, it is best to use a bulk load with RCU disabled. * This allows for optimistic splitting that favours the left and reuse * of nodes during the operation. */ /* Optimize splitting for bulk insert in-order */ mas->mas_flags |= MA_STATE_BULK; /* * Avoid overflow, assume a gap between each entry and a trailing null. * If this is wrong, it just means allocation can happen during * insertion of entries. */ nr_nodes = max(nr_entries, nr_entries * 2 + 1); if (!mt_is_alloc(mas->tree)) nonleaf_cap = MAPLE_RANGE64_SLOTS - 2; /* Leaves; reduce slots to keep space for expansion */ nr_nodes = DIV_ROUND_UP(nr_nodes, MAPLE_RANGE64_SLOTS - 2); /* Internal nodes */ nr_nodes += DIV_ROUND_UP(nr_nodes, nonleaf_cap); /* Add working room for split (2 nodes) + new parents */ mas_node_count_gfp(mas, nr_nodes + 3, GFP_KERNEL); /* Detect if allocations run out */ mas->mas_flags |= MA_STATE_PREALLOC; if (!mas_is_err(mas)) return 0; ret = xa_err(mas->node); mas->node = enode; mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_expected_entries); static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { mas->status = ma_overflow; return true; } switch (mas->status) { case ma_active: return false; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; fallthrough; case ma_start: mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ break; case ma_overflow: /* Overflowed before, but the max changed */ mas->status = ma_active; break; case ma_underflow: /* The user expects the mas to be one before where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (likely(mas_is_active(mas))) /* Fast path */ return false; if (mas_is_ptr(mas)) { *entry = NULL; if (was_none && mas->index == 0) { mas->index = mas->last = 0; return true; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return true; } if (mas_is_none(mas)) return true; return false; } /** * mas_next() - Get the next entry. * @mas: The maple state * @max: The maximum index to check. * * Returns the next entry after @mas->index. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); /** * mas_next_range() - Advance the maple state to the next range * @mas: The maple state * @max: The maximum index to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); /** * mt_next() - get the next value in the maple tree * @mt: The maple tree * @index: The start index * @max: The maximum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry higher than @index or %NULL if nothing is found. */ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_next(&mas, max); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_next); static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } switch (mas->status) { case ma_active: return false; case ma_start: break; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; break; case ma_underflow: /* underflowed before but the min changed */ mas->status = ma_active; break; case ma_overflow: /* User expects mas to be one after where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { if (!mas->index) { mas->status = ma_none; return true; } mas->index = mas->last = 0; *entry = mas_root(mas); return true; } if (mas_is_none(mas)) { if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } return true; } return false; } /** * mas_prev() - Get the previous entry * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); /** * mas_prev_range() - Advance to the previous range * @mas: The maple state * @min: The minimum value to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev_range(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); /** * mt_prev() - get the previous value in the maple tree * @mt: The maple tree * @index: The start index * @min: The minimum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry before @index or %NULL if nothing is found. */ void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_prev(&mas, min); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_prev); /** * mas_pause() - Pause a mas_find/mas_for_each to drop the lock. * @mas: The maple state to pause * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @mas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call mas_pause(), the mt_for_each() * iterator may be more appropriate. * */ void mas_pause(struct ma_state *mas) { mas->status = ma_pause; mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); /** * mas_find_setup() - Internal function to set up mas_find*(). * @mas: The maple state * @max: The maximum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { switch (mas->status) { case ma_active: if (mas->last < max) return false; return true; case ma_start: break; case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; mas->status = ma_start; break; case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; mas->status = ma_start; break; case ma_underflow: /* mas is pointing at entry before unable to go lower */ if (unlikely(mas->index >= max)) { mas->status = ma_overflow; return true; } mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_overflow: if (unlikely(mas->last >= max)) return true; mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto ptr_out_of_range; if (unlikely(mas_is_none(mas))) return true; if (mas->index == max) return true; return false; ptr_out_of_range: mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; } /** * mas_find() - On the first call, find the entry at or after mas->index up to * %max. Otherwise, find the entry after mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ entry = mas_next_slot(mas, max, false); /* Ignore overflow */ mas->status = ma_active; return entry; } EXPORT_SYMBOL_GPL(mas_find); /** * mas_find_range() - On the first call, find the entry at or after * mas->index up to %max. Otherwise, advance to the next slot mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); /** * mas_find_rev_setup() - Internal function to set up mas_find_*_rev() * @mas: The maple state * @min: The minimum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { switch (mas->status) { case ma_active: goto active; case ma_start: break; case ma_pause: if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->last = --mas->index; mas->status = ma_start; break; case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; mas->status = ma_start; break; case ma_overflow: /* user expects the mas to be one after where it is */ if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->status = ma_active; break; case ma_underflow: /* user expects the mas to be one before where it is */ if (unlikely(mas->index <= min)) return true; mas->status = ma_active; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto none; if (unlikely(mas_is_none(mas))) { /* * Walked to the location, and there was nothing so the previous * location is 0. */ mas->last = mas->index = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } active: if (mas->index < min) return true; return false; none: mas->status = ma_none; return true; } /** * mas_find_rev: On the first call, find the first non-null entry at or below * mas->index down to %min. Otherwise find the first non-null entry below * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); /** * mas_find_range_rev: On the first call, find the first non-null entry at or * below mas->index down to %min. Otherwise advance to the previous slot after * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); /** * mas_erase() - Find the range in which index resides and erase the entire * range. * @mas: The maple state * * Must hold the write lock. * Searches for @mas->index, sets @mas->index and @mas->last to the range and * erases that range. * * Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated. */ void *mas_erase(struct ma_state *mas) { void *entry; unsigned long index = mas->index; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; write_retry: entry = mas_state_walk(mas); if (!entry) return NULL; /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); mas_wr_preallocate(&wr_mas, NULL); if (mas_nomem(mas, GFP_KERNEL)) { /* in case the range of entry changed when unlocked */ mas->index = mas->last = index; goto write_retry; } if (mas_is_err(mas)) goto out; mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return entry; } EXPORT_SYMBOL_GPL(mas_erase); /** * mas_nomem() - Check if there was an error allocating and do the allocation * if necessary If there are allocations, then free them. * @mas: The maple state * @gfp: The GFP_FLAGS to use for allocations * Return: true on allocation, false otherwise. */ bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { if (likely(mas->node != MA_ERROR(-ENOMEM))) return false; if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); mas_alloc_nodes(mas, gfp); mtree_lock(mas->tree); } else { mas_alloc_nodes(mas, gfp); } if (!mas_allocated(mas)) return false; mas->status = ma_start; return true; } void __init maple_tree_init(void) { maple_node_cache = kmem_cache_create("maple_node", sizeof(struct maple_node), sizeof(struct maple_node), SLAB_PANIC, NULL); } /** * mtree_load() - Load a value stored in a maple tree * @mt: The maple tree * @index: The index to load * * Return: the entry or %NULL */ void *mtree_load(struct maple_tree *mt, unsigned long index) { MA_STATE(mas, mt, index, index); void *entry; trace_ma_read(__func__, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); if (unlikely(mas_is_none(&mas))) goto unlock; if (unlikely(mas_is_ptr(&mas))) { if (index) entry = NULL; goto unlock; } entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas))) goto retry; unlock: rcu_read_unlock(); if (xa_is_zero(entry)) return NULL; return entry; } EXPORT_SYMBOL(mtree_load); /** * mtree_store_range() - Store an entry at a given range. * @mt: The maple tree * @index: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); int ret = 0; trace_ma_write(__func__, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (index > last) return -EINVAL; mtree_lock(mt); ret = mas_store_gfp(&mas, entry, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_store_range); /** * mtree_store() - Store an entry at a given index. * @mt: The maple tree * @index: The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_store_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_store); /** * mtree_insert_range() - Insert an entry at a given range if there is no value. * @mt: The maple tree * @first: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); int ret = 0; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (first > last) return -EINVAL; mtree_lock(mt); retry: mas_insert(&ms, entry); if (mas_nomem(&ms, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&ms)) ret = xa_err(ms.node); mas_destroy(&ms); return ret; } EXPORT_SYMBOL(mtree_insert_range); /** * mtree_insert() - Insert an entry at a given index if there is no value. * @mt: The maple tree * @index : The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_insert_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_insert); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_range); /** * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. * @mt: The maple tree. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Finds an empty entry in @mt after @next, stores the new index into * the @id pointer, stores the entry at that index, then updates @next. * * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. * * Context: Any context. Takes and releases the mt.lock. May sleep if * the @gfp flags permit. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no * free entries. */ int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { int ret; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, next, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_cyclic); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area_rev(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); /** * mtree_erase() - Find an index and erase the entire range. * @mt: The maple tree * @index: The index to erase * * Erasing is the same as a walk to an entry then a store of a NULL to that * ENTIRE range. In fact, it is implemented as such using the advanced API. * * Return: The entry stored at the @index or %NULL */ void *mtree_erase(struct maple_tree *mt, unsigned long index) { void *entry = NULL; MA_STATE(mas, mt, index, index); trace_ma_op(__func__, &mas); mtree_lock(mt); entry = mas_erase(&mas); mtree_unlock(mt); return entry; } EXPORT_SYMBOL(mtree_erase); /* * mas_dup_free() - Free an incomplete duplication of a tree. * @mas: The maple state of a incomplete tree. * * The parameter @mas->node passed in indicates that the allocation failed on * this node. This function frees all nodes starting from @mas->node in the * reverse order of mas_dup_build(). There is no need to hold the source tree * lock at this time. */ static void mas_dup_free(struct ma_state *mas) { struct maple_node *node; enum maple_type type; void __rcu **slots; unsigned char count, i; /* Maybe the first node allocation failed. */ if (mas_is_none(mas)) return; while (!mte_is_root(mas->node)) { mas_ascend(mas); if (mas->offset) { mas->offset--; do { mas_descend(mas); mas->offset = mas_data_end(mas); } while (!mte_is_leaf(mas->node)); mas_ascend(mas); } node = mte_to_node(mas->node); type = mte_node_type(mas->node); slots = ma_slots(node, type); count = mas_data_end(mas) + 1; for (i = 0; i < count; i++) ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; mt_free_bulk(count, slots); } node = mte_to_node(mas->node); mt_free_one(node); } /* * mas_copy_node() - Copy a maple node and replace the parent. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @parent: The parent of the new node. * * Copy @mas->node to @new_mas->node, set @parent to be the parent of * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, struct maple_pnode *parent) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); unsigned long val; /* Copy the node completely. */ memcpy(new_node, node, sizeof(struct maple_node)); /* Update the parent node pointer. */ val = (unsigned long)node->parent & MAPLE_NODE_MASK; new_node->parent = ma_parent_ptr(val | (unsigned long)parent); } /* * mas_dup_alloc() - Allocate child nodes for a maple node. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @gfp: The GFP_FLAGS to use for allocations. * * This function allocates child nodes for @new_mas->node during the duplication * process. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); enum maple_type type; unsigned char request, count, i; void __rcu **slots; void __rcu **new_slots; unsigned long val; /* Allocate memory for child nodes. */ type = mte_node_type(mas->node); new_slots = ma_slots(new_node, type); request = mas_data_end(mas) + 1; count = mt_alloc_bulk(gfp, request, (void **)new_slots); if (unlikely(count < request)) { memset(new_slots, 0, request * sizeof(void *)); mas_set_err(mas, -ENOMEM); return; } /* Restore node type information in slots. */ slots = ma_slots(node, type); for (i = 0; i < count; i++) { val = (unsigned long)mt_slot_locked(mas->tree, slots, i); val &= MAPLE_NODE_MASK; ((unsigned long *)new_slots)[i] |= val; } } /* * mas_dup_build() - Build a new maple tree from a source tree * @mas: The maple state of source tree, need to be in MAS_START state. * @new_mas: The maple state of new tree, need to be in MAS_START state. * @gfp: The GFP_FLAGS to use for allocations. * * This function builds a new tree in DFS preorder. If the memory allocation * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the * last node. mas_dup_free() will free the incomplete duplication of a tree. * * Note that the attributes of the two trees need to be exactly the same, and the * new tree needs to be empty, otherwise -EINVAL will be set in @mas. */ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node; struct maple_pnode *parent = NULL; struct maple_enode *root; enum maple_type type; if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || unlikely(!mtree_empty(new_mas->tree))) { mas_set_err(mas, -EINVAL); return; } root = mas_start(mas); if (mas_is_ptr(mas) || mas_is_none(mas)) goto set_new_tree; node = mt_alloc_one(gfp); if (!node) { new_mas->status = ma_none; mas_set_err(mas, -ENOMEM); return; } type = mte_node_type(mas->node); root = mt_mk_node(node, type); new_mas->node = root; new_mas->min = 0; new_mas->max = ULONG_MAX; root = mte_mk_root(root); while (1) { mas_copy_node(mas, new_mas, parent); if (!mte_is_leaf(mas->node)) { /* Only allocate child nodes for non-leaf nodes. */ mas_dup_alloc(mas, new_mas, gfp); if (unlikely(mas_is_err(mas))) return; } else { /* * This is the last leaf node and duplication is * completed. */ if (mas->max == ULONG_MAX) goto done; /* This is not the last leaf node and needs to go up. */ do { mas_ascend(mas); mas_ascend(new_mas); } while (mas->offset == mas_data_end(mas)); /* Move to the next subtree. */ mas->offset++; new_mas->offset++; } mas_descend(mas); parent = ma_parent_ptr(mte_to_node(new_mas->node)); mas_descend(new_mas); mas->offset = 0; new_mas->offset = 0; } done: /* Specially handle the parent of the root node. */ mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); set_new_tree: /* Make them the same height */ new_mas->tree->ma_flags = mas->tree->ma_flags; rcu_assign_pointer(new_mas->tree->ma_root, root); } /** * __mt_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * Note that the user needs to manually lock the source tree and the new tree. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_dup_build(&mas, &new_mas, gfp); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } return ret; } EXPORT_SYMBOL(__mt_dup); /** * mtree_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_lock(&new_mas); mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); mas_dup_build(&mas, &new_mas, gfp); mas_unlock(&mas); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } mas_unlock(&new_mas); return ret; } EXPORT_SYMBOL(mtree_dup); /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree * * Note: Does not handle locking. */ void __mt_destroy(struct maple_tree *mt) { void *root = mt_root_locked(mt); rcu_assign_pointer(mt->ma_root, NULL); if (xa_is_node(root)) mte_destroy_walk(root, mt); mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); /** * mtree_destroy() - Destroy a maple tree * @mt: The maple tree * * Frees all resources used by the tree. Handles locking. */ void mtree_destroy(struct maple_tree *mt) { mtree_lock(mt); __mt_destroy(mt); mtree_unlock(mt); } EXPORT_SYMBOL(mtree_destroy); /** * mt_find() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value of the search range * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * In case that an entry is found @index is updated to point to the next * possible entry independent whether the found entry is occupying a * single index or a range if indices. * * Return: The entry at or after the @index or %NULL */ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) { MA_STATE(mas, mt, *index, *index); void *entry; #ifdef CONFIG_DEBUG_MAPLE_TREE unsigned long copy = *index; #endif trace_ma_read(__func__, &mas); if ((*index) > max) return NULL; rcu_read_lock(); retry: entry = mas_state_walk(&mas); if (mas_is_start(&mas)) goto retry; if (unlikely(xa_is_zero(entry))) entry = NULL; if (entry) goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_entry(&mas, max); if (likely(entry && !xa_is_zero(entry))) break; } if (unlikely(xa_is_zero(entry))) entry = NULL; unlock: rcu_read_unlock(); if (likely(entry)) { *index = mas.last + 1; #ifdef CONFIG_DEBUG_MAPLE_TREE if (MT_WARN_ON(mt, (*index) && ((*index) <= copy))) pr_err("index not increased! %lx <= %lx\n", *index, copy); #endif } return entry; } EXPORT_SYMBOL(mt_find); /** * mt_find_after() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value to check * * Same as mt_find() except that it checks @index for 0 before * searching. If @index == 0, the search is aborted. This covers a wrap * around of @index to 0 in an iterator loop. * * Return: The entry at or after the @index or %NULL */ void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max) { if (!(*index)) return NULL; return mt_find(mt, index, max); } EXPORT_SYMBOL(mt_find_after); #ifdef CONFIG_DEBUG_MAPLE_TREE atomic_t maple_tree_tests_run; EXPORT_SYMBOL_GPL(maple_tree_tests_run); atomic_t maple_tree_tests_passed; EXPORT_SYMBOL_GPL(maple_tree_tests_passed); #ifndef __KERNEL__ extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int); void mt_set_non_kernel(unsigned int val) { kmem_cache_set_non_kernel(maple_node_cache, val); } extern void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *)); void mt_set_callback(void (*callback)(void *)) { kmem_cache_set_callback(maple_node_cache, callback); } extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private); void mt_set_private(void *private) { kmem_cache_set_private(maple_node_cache, private); } extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { return kmem_cache_get_alloc(maple_node_cache); } extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *); void mt_zero_nr_tallocated(void) { kmem_cache_zero_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *); unsigned int mt_nr_tallocated(void) { return kmem_cache_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *); unsigned int mt_nr_allocated(void) { return kmem_cache_nr_allocated(maple_node_cache); } void mt_cache_shrink(void) { } #else /* * mt_cache_shrink() - For testing, don't use this. * * Certain testcases can trigger an OOM when combined with other memory * debugging configuration options. This function is used to reduce the * possibility of an out of memory even due to kmem_cache objects remaining * around for longer than usual. */ void mt_cache_shrink(void) { kmem_cache_shrink(maple_node_cache); } EXPORT_SYMBOL_GPL(mt_cache_shrink); #endif /* not defined __KERNEL__ */ /* * mas_get_slot() - Get the entry in the maple state node stored at @offset. * @mas: The maple state * @offset: The offset into the slot array to fetch. * * Return: The entry stored at @offset. */ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, unsigned char offset) { return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)), offset); } /* Depth first search, post-order */ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) return; mas->node = mn; mas_ascend(mas); do { p = mas->node; p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; mas->min = p_min; } /* Tree validations */ static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format); static void mt_dump_range(unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { static const char spaces[] = " "; switch(format) { case mt_dump_hex: if (min == max) pr_info("%.*s%lx: ", depth * 2, spaces, min); else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); else pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max); } } static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_range_64 *node = &mte_to_node(entry)->mr64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_RANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i] && max != mt_node_max(entry)) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_arange64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { switch (format) { case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } } pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap); for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_ARANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i]) break; if (last == 0 && i > 0) break; if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_node *node = mte_to_node(entry); unsigned int type = mte_node_type(entry); unsigned int i; mt_dump_range(min, max, depth, format); pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); for (i = 0; i < MAPLE_NODE_SLOTS; i++) { if (min + i > max) pr_cont("OUT OF RANGE: "); mt_dump_entry(mt_slot(mt, node->slot, i), min + i, min + i, depth, format); } break; case maple_leaf_64: case maple_range_64: mt_dump_range64(mt, entry, min, max, depth, format); break; case maple_arange_64: mt_dump_arange64(mt, entry, min, max, depth, format); break; default: pr_cont(" UNKNOWN TYPE\n"); } } void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); else if (entry) mt_dump_entry(entry, 0, 0, 0, format); else pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); /* * Calculate the maximum gap in a node and check if that's what is reported in * the parent (unless root). */ static void mas_validate_gaps(struct ma_state *mas) { struct maple_enode *mte = mas->node; struct maple_node *p_mn, *node = mte_to_node(mte); enum maple_type mt = mte_node_type(mas->node); unsigned long gap = 0, max_gap = 0; unsigned long p_end, p_start = mas->min; unsigned char p_slot, offset; unsigned long *gaps = NULL; unsigned long *pivots = ma_pivots(node, mt); unsigned int i; if (ma_is_dense(mt)) { for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) { if (gap > max_gap) max_gap = gap; gap = 0; continue; } gap++; } goto counted; } gaps = ma_gaps(node, mt); for (i = 0; i < mt_slot_count(mte); i++) { p_end = mas_safe_pivot(mas, pivots, i, mt); if (!gaps) { if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1; } else { void *entry = mas_get_slot(mas, i); gap = gaps[i]; MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); } } if (gap > max_gap) max_gap = gap; p_start = p_end + 1; if (p_end >= mas->max) break; } counted: if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } } } if (mte_is_root(mte)) return; p_slot = mte_parent_slot(mas->node); p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } } static void mas_validate_parent_slot(struct ma_state *mas) { struct maple_node *parent; struct maple_enode *node; enum maple_type p_type; unsigned char p_slot; void __rcu **slots; int i; if (mte_is_root(mas->node)) return; p_slot = mte_parent_slot(mas->node); p_type = mas_parent_type(mas, mas->node); parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent); /* Check prev/next parent slot for duplicate node entry */ for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } } } static void mas_validate_child_slot(struct ma_state *mas) { enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type); struct maple_enode *child; unsigned char i; if (mte_is_leaf(mas->node)) return; for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) { pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); } if (i < mt_pivots[type] && pivots[i] == mas->max) break; } } /* * Validate all pivots are within mas->min and mas->max, check metadata ends * where the maximum ends and ensure there is no slots or pivots set outside of * the end of the data. */ static void mas_validate_limits(struct ma_state *mas) { int i; unsigned long prev_piv = 0; enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mas_mn(mas), type); for (i = 0; i < mt_slots[type]; i++) { unsigned long piv; piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } prev_piv = piv; if (piv == mas->max) break; } if (mas_data_end(mas) != i) { pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } if (i < mt_pivots[type]) { unsigned long piv = pivots[i]; if (!piv) continue; pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } } } static void mt_validate_nulls(struct maple_tree *mt) { void *entry, *last = (void *)1; unsigned char offset = 0; void __rcu **slots; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); } else { offset++; } } while (!mas_is_overflow(&mas)); } /* * validate a maple tree by checking: * 1. The limits (pivots are within mas->min to mas->max) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) __must_hold(mas->tree->ma_lock) { unsigned char end; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (!mas_is_active(&mas)) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (mas.max != ULONG_MAX))) { pr_err("Invalid size %u of " PTR_FMT "\n", end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); break; case ma_none: pr_err("(ma_none)"); break; case ma_root: pr_err("(ma_root)"); break; case ma_start: pr_err("(ma_start) "); break; case ma_pause: pr_err("(ma_pause) "); break; case ma_overflow: pr_err("(ma_overflow) "); break; case ma_underflow: pr_err("(ma_underflow) "); break; case ma_error: pr_err("(ma_error) "); break; } pr_err("Store Type: "); switch (mas->store_type) { case wr_invalid: pr_err("invalid store type\n"); break; case wr_new_root: pr_err("new_root\n"); break; case wr_store_root: pr_err("store_root\n"); break; case wr_exact_fit: pr_err("exact_fit\n"); break; case wr_split_store: pr_err("split_store\n"); break; case wr_slot_store: pr_err("slot_store\n"); break; case wr_append: pr_err("append\n"); break; case wr_node_store: pr_err("node_store\n"); break; case wr_spanning_store: pr_err("spanning_store\n"); break; case wr_rebalance: pr_err("rebalance\n"); break; } pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); pr_err(" min=%lx max=%lx alloc=" PTR_FMT ", depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); } EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); #endif /* CONFIG_DEBUG_MAPLE_TREE */ |
| 247 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2020 - Google LLC * Author: Quentin Perret <qperret@google.com> */ #include <linux/init.h> #include <linux/kmemleak.h> #include <linux/kvm_host.h> #include <asm/kvm_mmu.h> #include <linux/memblock.h> #include <linux/mutex.h> #include <linux/sort.h> #include <asm/kvm_pkvm.h> #include "hyp_constants.h" DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); static struct memblock_region *hyp_memory = kvm_nvhe_sym(hyp_memory); static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr); phys_addr_t hyp_mem_base; phys_addr_t hyp_mem_size; static int cmp_hyp_memblock(const void *p1, const void *p2) { const struct memblock_region *r1 = p1; const struct memblock_region *r2 = p2; return r1->base < r2->base ? -1 : (r1->base > r2->base); } static void __init sort_memblock_regions(void) { sort(hyp_memory, *hyp_memblock_nr_ptr, sizeof(struct memblock_region), cmp_hyp_memblock, NULL); } static int __init register_memblock_regions(void) { struct memblock_region *reg; for_each_mem_region(reg) { if (*hyp_memblock_nr_ptr >= HYP_MEMBLOCK_REGIONS) return -ENOMEM; hyp_memory[*hyp_memblock_nr_ptr] = *reg; (*hyp_memblock_nr_ptr)++; } sort_memblock_regions(); return 0; } void __init kvm_hyp_reserve(void) { u64 hyp_mem_pages = 0; int ret; if (!is_hyp_mode_available() || is_kernel_in_hyp_mode()) return; if (kvm_get_mode() != KVM_MODE_PROTECTED) return; ret = register_memblock_regions(); if (ret) { *hyp_memblock_nr_ptr = 0; kvm_err("Failed to register hyp memblocks: %d\n", ret); return; } hyp_mem_pages += hyp_s1_pgtable_pages(); hyp_mem_pages += host_s2_pgtable_pages(); hyp_mem_pages += hyp_vm_table_pages(); hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE); hyp_mem_pages += hyp_ffa_proxy_pages(); /* * Try to allocate a PMD-aligned region to reduce TLB pressure once * this is unmapped from the host stage-2, and fallback to PAGE_SIZE. */ hyp_mem_size = hyp_mem_pages << PAGE_SHIFT; hyp_mem_base = memblock_phys_alloc(ALIGN(hyp_mem_size, PMD_SIZE), PMD_SIZE); if (!hyp_mem_base) hyp_mem_base = memblock_phys_alloc(hyp_mem_size, PAGE_SIZE); else hyp_mem_size = ALIGN(hyp_mem_size, PMD_SIZE); if (!hyp_mem_base) { kvm_err("Failed to reserve hyp memory\n"); return; } kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20, hyp_mem_base); } static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm) { if (host_kvm->arch.pkvm.handle) { WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, host_kvm->arch.pkvm.handle)); } host_kvm->arch.pkvm.handle = 0; free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); } /* * Allocates and donates memory for hypervisor VM structs at EL2. * * Allocates space for the VM state, which includes the hyp vm as well as * the hyp vcpus. * * Stores an opaque handler in the kvm struct for future reference. * * Return 0 on success, negative error code on failure. */ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) { size_t pgd_sz, hyp_vm_sz, hyp_vcpu_sz; struct kvm_vcpu *host_vcpu; pkvm_handle_t handle; void *pgd, *hyp_vm; unsigned long idx; int ret; if (host_kvm->created_vcpus < 1) return -EINVAL; pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.mmu.vtcr); /* * The PGD pages will be reclaimed using a hyp_memcache which implies * page granularity. So, use alloc_pages_exact() to get individual * refcounts. */ pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT); if (!pgd) return -ENOMEM; /* Allocate memory to donate to hyp for vm and vcpu pointers. */ hyp_vm_sz = PAGE_ALIGN(size_add(PKVM_HYP_VM_SIZE, size_mul(sizeof(void *), host_kvm->created_vcpus))); hyp_vm = alloc_pages_exact(hyp_vm_sz, GFP_KERNEL_ACCOUNT); if (!hyp_vm) { ret = -ENOMEM; goto free_pgd; } /* Donate the VM memory to hyp and let hyp initialize it. */ ret = kvm_call_hyp_nvhe(__pkvm_init_vm, host_kvm, hyp_vm, pgd); if (ret < 0) goto free_vm; handle = ret; host_kvm->arch.pkvm.handle = handle; /* Donate memory for the vcpus at hyp and initialize it. */ hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE); kvm_for_each_vcpu(idx, host_vcpu, host_kvm) { void *hyp_vcpu; /* Indexing of the vcpus to be sequential starting at 0. */ if (WARN_ON(host_vcpu->vcpu_idx != idx)) { ret = -EINVAL; goto destroy_vm; } hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT); if (!hyp_vcpu) { ret = -ENOMEM; goto destroy_vm; } ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, host_vcpu, hyp_vcpu); if (ret) { free_pages_exact(hyp_vcpu, hyp_vcpu_sz); goto destroy_vm; } } return 0; destroy_vm: __pkvm_destroy_hyp_vm(host_kvm); return ret; free_vm: free_pages_exact(hyp_vm, hyp_vm_sz); free_pgd: free_pages_exact(pgd, pgd_sz); return ret; } int pkvm_create_hyp_vm(struct kvm *host_kvm) { int ret = 0; mutex_lock(&host_kvm->arch.config_lock); if (!host_kvm->arch.pkvm.handle) ret = __pkvm_create_hyp_vm(host_kvm); mutex_unlock(&host_kvm->arch.config_lock); return ret; } void pkvm_destroy_hyp_vm(struct kvm *host_kvm) { mutex_lock(&host_kvm->arch.config_lock); __pkvm_destroy_hyp_vm(host_kvm); mutex_unlock(&host_kvm->arch.config_lock); } int pkvm_init_host_vm(struct kvm *host_kvm) { return 0; } static void __init _kvm_host_prot_finalize(void *arg) { int *err = arg; if (WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize))) WRITE_ONCE(*err, -EINVAL); } static int __init pkvm_drop_host_privileges(void) { int ret = 0; /* * Flip the static key upfront as that may no longer be possible * once the host stage 2 is installed. */ static_branch_enable(&kvm_protected_mode_initialized); on_each_cpu(_kvm_host_prot_finalize, &ret, 1); return ret; } static int __init finalize_pkvm(void) { int ret; if (!is_protected_kvm_enabled() || !is_kvm_arm_initialised()) return 0; /* * Exclude HYP sections from kmemleak so that they don't get peeked * at, which would end badly once inaccessible. */ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); kmemleak_free_part(__hyp_rodata_start, __hyp_rodata_end - __hyp_rodata_start); kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size); ret = pkvm_drop_host_privileges(); if (ret) pr_err("Failed to finalize Hyp protection: %d\n", ret); return ret; } device_initcall_sync(finalize_pkvm); static int cmp_mappings(struct rb_node *node, const struct rb_node *parent) { struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node); struct pkvm_mapping *b = rb_entry(parent, struct pkvm_mapping, node); if (a->gfn < b->gfn) return -1; if (a->gfn > b->gfn) return 1; return 0; } static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn) { struct rb_node *node = root->rb_node, *prev = NULL; struct pkvm_mapping *mapping; while (node) { mapping = rb_entry(node, struct pkvm_mapping, node); if (mapping->gfn == gfn) return node; prev = node; node = (gfn < mapping->gfn) ? node->rb_left : node->rb_right; } return prev; } /* * __tmp is updated to rb_next(__tmp) *before* entering the body of the loop to allow freeing * of __map inline. */ #define for_each_mapping_in_range_safe(__pgt, __start, __end, __map) \ for (struct rb_node *__tmp = find_first_mapping_node(&(__pgt)->pkvm_mappings, \ ((__start) >> PAGE_SHIFT)); \ __tmp && ({ \ __map = rb_entry(__tmp, struct pkvm_mapping, node); \ __tmp = rb_next(__tmp); \ true; \ }); \ ) \ if (__map->gfn < ((__start) >> PAGE_SHIFT)) \ continue; \ else if (__map->gfn >= ((__end) >> PAGE_SHIFT)) \ break; \ else int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops) { pgt->pkvm_mappings = RB_ROOT; pgt->mmu = mmu; return 0; } void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); pkvm_handle_t handle = kvm->arch.pkvm.handle; struct pkvm_mapping *mapping; struct rb_node *node; if (!handle) return; node = rb_first(&pgt->pkvm_mappings); while (node) { mapping = rb_entry(node, struct pkvm_mapping, node); kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn); node = rb_next(node); rb_erase(&mapping->node, &pgt->pkvm_mappings); kfree(mapping); } } int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, void *mc, enum kvm_pgtable_walk_flags flags) { struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); struct pkvm_mapping *mapping = NULL; struct kvm_hyp_memcache *cache = mc; u64 gfn = addr >> PAGE_SHIFT; u64 pfn = phys >> PAGE_SHIFT; int ret; if (size != PAGE_SIZE) return -EINVAL; lockdep_assert_held_write(&kvm->mmu_lock); ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot); if (ret) { /* Is the gfn already mapped due to a racing vCPU? */ if (ret == -EPERM) return -EAGAIN; } swap(mapping, cache->mapping); mapping->gfn = gfn; mapping->pfn = pfn; WARN_ON(rb_find_add(&mapping->node, &pgt->pkvm_mappings, cmp_mappings)); return ret; } int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); pkvm_handle_t handle = kvm->arch.pkvm.handle; struct pkvm_mapping *mapping; int ret = 0; lockdep_assert_held_write(&kvm->mmu_lock); for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) { ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn); if (WARN_ON(ret)) break; rb_erase(&mapping->node, &pgt->pkvm_mappings); kfree(mapping); } return ret; } int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) { struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); pkvm_handle_t handle = kvm->arch.pkvm.handle; struct pkvm_mapping *mapping; int ret = 0; lockdep_assert_held(&kvm->mmu_lock); for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) { ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn); if (WARN_ON(ret)) break; } return ret; } int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) { struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); struct pkvm_mapping *mapping; lockdep_assert_held(&kvm->mmu_lock); for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) __clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE); return 0; } bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold) { struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); pkvm_handle_t handle = kvm->arch.pkvm.handle; struct pkvm_mapping *mapping; bool young = false; lockdep_assert_held(&kvm->mmu_lock); for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn, mkold); return young; } int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags) { return kvm_call_hyp_nvhe(__pkvm_host_relax_perms_guest, addr >> PAGE_SHIFT, prot); } void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags) { WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_mkyoung_guest, addr >> PAGE_SHIFT)); } void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) { WARN_ON_ONCE(1); } kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, enum kvm_pgtable_prot prot, void *mc, bool force_pte) { WARN_ON_ONCE(1); return NULL; } int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc) { WARN_ON_ONCE(1); return -EINVAL; } |
| 15 15 15 15 15 14 14 15 15 15 15 1 14 2 2 2 263 263 263 263 263 263 263 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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. * * Generic socket support routines. Memory allocators, socket lock/release * handler for protocols to use and generic option handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Fixes: * Alan Cox : Numerous verify_area() problems * Alan Cox : Connecting on a connecting socket * now returns an error for tcp. * Alan Cox : sock->protocol is set correctly. * and is not sometimes left as 0. * Alan Cox : connect handles icmp errors on a * connect properly. Unfortunately there * is a restart syscall nasty there. I * can't match BSD without hacking the C * library. Ideas urgently sought! * Alan Cox : Disallow bind() to addresses that are * not ours - especially broadcast ones!! * Alan Cox : Socket 1024 _IS_ ok for users. (fencepost) * Alan Cox : sock_wfree/sock_rfree don't destroy sockets, * instead they leave that for the DESTROY timer. * Alan Cox : Clean up error flag in accept * Alan Cox : TCP ack handling is buggy, the DESTROY timer * was buggy. Put a remove_sock() in the handler * for memory when we hit 0. Also altered the timer * code. The ACK stuff can wait and needs major * TCP layer surgery. * Alan Cox : Fixed TCP ack bug, removed remove sock * and fixed timer/inet_bh race. * Alan Cox : Added zapped flag for TCP * Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code * Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb * Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources * Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing. * Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so... * Rick Sladkey : Relaxed UDP rules for matching packets. * C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support * Pauline Middelink : identd support * Alan Cox : Fixed connect() taking signals I think. * Alan Cox : SO_LINGER supported * Alan Cox : Error reporting fixes * Anonymous : inet_create tidied up (sk->reuse setting) * Alan Cox : inet sockets don't set sk->type! * Alan Cox : Split socket option code * Alan Cox : Callbacks * Alan Cox : Nagle flag for Charles & Johannes stuff * Alex : Removed restriction on inet fioctl * Alan Cox : Splitting INET from NET core * Alan Cox : Fixed bogus SO_TYPE handling in getsockopt() * Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code * Alan Cox : Split IP from generic code * Alan Cox : New kfree_skbmem() * Alan Cox : Make SO_DEBUG superuser only. * Alan Cox : Allow anyone to clear SO_DEBUG * (compatibility fix) * Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput. * Alan Cox : Allocator for a socket is settable. * Alan Cox : SO_ERROR includes soft errors. * Alan Cox : Allow NULL arguments on some SO_ opts * Alan Cox : Generic socket allocation to make hooks * easier (suggested by Craig Metz). * Michael Pall : SO_ERROR returns positive errno again * Steve Whitehouse: Added default destructor to free * protocol private data. * Steve Whitehouse: Added various other default routines * common to several socket families. * Chris Evans : Call suser() check last on F_SETOWN * Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER. * Andi Kleen : Add sock_kmalloc()/sock_kfree_s() * Andi Kleen : Fix write_space callback * Chris Evans : Security fixes - signedness again * Arnaldo C. Melo : cleanups, use skb_queue_purge * * To Fix: */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/unaligned.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> #include <linux/static_key.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> #include <linux/compat.h> #include <linux/mroute.h> #include <linux/mroute6.h> #include <linux/icmpv6.h> #include <linux/uaccess.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> #include <net/proto_memory.h> #include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> #include <net/netprio_cgroup.h> #include <linux/sock_diag.h> #include <linux/filter.h> #include <net/sock_reuseport.h> #include <net/bpf_sk_storage.h> #include <trace/events/sock.h> #include <net/tcp.h> #include <net/busy_poll.h> #include <net/phonet/phonet.h> #include <linux/ethtool.h> #include "dev.h" static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); static void sock_def_write_space_wfree(struct sock *sk); static void sock_def_write_space(struct sock *sk); /** * sk_ns_capable - General socket capability test * @sk: Socket to use a capability on or through * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in the user * namespace @user_ns. */ bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap) { return file_ns_capable(sk->sk_socket->file, user_ns, cap) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(sk_ns_capable); /** * sk_capable - Socket global capability test * @sk: Socket to use a capability on or through * @cap: The global capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in all user * namespaces. */ bool sk_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, &init_user_ns, cap); } EXPORT_SYMBOL(sk_capable); /** * sk_net_capable - Network namespace socket capability test * @sk: Socket to use a capability on or through * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was created * and the current process has the capability @cap over the network namespace * the socket is a member of. */ bool sk_net_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); } EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have * one slock key per address family and separate keys for internal and * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ #define _sock_locks(x) \ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ x "27" , x "28" , x "AF_CAN" , \ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { _sock_locks("clock-") }; static const char *const af_family_kern_key_strings[AF_MAX+1] = { _sock_locks("k-sk_lock-") }; static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { _sock_locks("k-slock-") }; static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; static const char *const af_family_rlock_key_strings[AF_MAX+1] = { _sock_locks("rlock-") }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { _sock_locks("wlock-") }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { _sock_locks("elock-") }; /* * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; static struct lock_class_key af_rlock_keys[AF_MAX]; static struct lock_class_key af_wlock_keys[AF_MAX]; static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC * @sk: socket to set it on * * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. * It's the responsibility of the admin to adjust min_free_kbytes * to meet the requirements */ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward * progress of swapping. SOCK_MEMALLOC may be cleared while * it has rmem allocations due to the last swapfile being deactivated * but there is a risk that the socket is unusable due to exceeding * the rmem limits. Reclaim the reserves and obey rmem limits again. */ sk_mem_reclaim(sk); } EXPORT_SYMBOL_GPL(sk_clear_memalloc); int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int ret; unsigned int noreclaim_flag; /* these should have been dropped before queueing */ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); noreclaim_flag = memalloc_noreclaim_save(); ret = INDIRECT_CALL_INET(sk->sk_backlog_rcv, tcp_v6_do_rcv, tcp_v4_do_rcv, sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); void sk_error_report(struct sock *sk) { sk->sk_error_report(sk); switch (sk->sk_family) { case AF_INET: fallthrough; case AF_INET6: trace_inet_sk_error_report(sk); break; default: break; } } EXPORT_SYMBOL(sk_error_report); int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; tv.tv_usec = 0; } else { tv.tv_sec = timeo / HZ; tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; } if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; *(struct old_timeval32 *)optval = tv32; return sizeof(tv32); } if (old_timeval) { struct __kernel_old_timeval old_tv; old_tv.tv_sec = tv.tv_sec; old_tv.tv_usec = tv.tv_usec; *(struct __kernel_old_timeval *)optval = old_tv; return sizeof(old_tv); } *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } EXPORT_SYMBOL(sock_get_timeout); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval) { if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) return -EINVAL; if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; tv->tv_sec = tv32.tv_sec; tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; if (optlen < sizeof(old_tv)) return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; tv->tv_sec = old_tv.tv_sec; tv->tv_usec = old_tv.tv_usec; } else { if (optlen < sizeof(*tv)) return -EINVAL; if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } return 0; } EXPORT_SYMBOL(sock_copy_user_timeval); static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, bool old_timeval) { struct __kernel_sock_timeval tv; int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); long val; if (err) return err; if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; if (tv.tv_sec < 0) { static int warned __read_mostly; WRITE_ONCE(*timeo_p, 0); if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", __func__, current->comm, task_pid_nr(current)); } return 0; } val = MAX_SCHEDULE_TIMEOUT; if ((tv.tv_sec || tv.tv_usec) && (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))) val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); WRITE_ONCE(*timeo_p, val); return 0; } static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { case AF_UNSPEC: case AF_UNIX: return false; default: return true; } } static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { sk->sk_flags &= ~flags; if (sock_needs_netstamp(sk) && !(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); } } int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } skb->dev = NULL; skb_set_owner_r(skb, sk); /* we escape from rcu protected region, make sure we dont leak * a norefcounted dst */ skb_dst_force(skb); spin_lock_irqsave(&list->lock, flags); sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(__sock_queue_rcv_skb); int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { enum skb_drop_reason drop_reason; int err; err = sk_filter(sk, skb); if (err) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto out; } err = __sock_queue_rcv_skb(sk, skb); switch (err) { case -ENOMEM: drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; break; case -ENOBUFS: drop_reason = SKB_DROP_REASON_PROTO_MEM; break; default: drop_reason = SKB_NOT_DROPPED_YET; break; } out: if (reason) *reason = drop_reason; return err; } EXPORT_SYMBOL(sock_queue_rcv_skb_reason); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } if (nested) bh_lock_sock_nested(sk); else bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* * trylock + unlock semantics: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; } bh_unlock_sock(sk); out: if (refcounted) sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); goto out; } EXPORT_SYMBOL(__sk_receive_skb); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, u32)); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(__sk_dst_check); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(sk_dst_check); static int sock_bindtoindex_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); /* Sorry... */ ret = -EPERM; if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; if (ifindex < 0) goto out; /* Paired with all READ_ONCE() done locklessly. */ WRITE_ONCE(sk->sk_bound_dev_if, ifindex); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); sk_dst_reset(sk); ret = 0; out: #endif return ret; } int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk) { int ret; if (lock_sk) lock_sock(sk); ret = sock_bindtoindex_locked(sk, ifindex); if (lock_sk) release_sock(sk); return ret; } EXPORT_SYMBOL(sock_bindtoindex); static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; ret = -EINVAL; if (optlen < 0) goto out; /* Bind this socket to a particular device like "eth0", * as specified in the passed interface name. If the * name is "" or the option length is zero the socket * is not bound. */ if (optlen > IFNAMSIZ - 1) optlen = IFNAMSIZ - 1; memset(devname, 0, sizeof(devname)); ret = -EFAULT; if (copy_from_sockptr(devname, optval, optlen)) goto out; index = 0; if (devname[0] != '\0') { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, devname); if (dev) index = dev->ifindex; rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; } sockopt_lock_sock(sk); ret = sock_bindtoindex_locked(sk, index); sockopt_release_sock(sk); out: #endif return ret; } static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); struct net *net = sock_net(sk); char devname[IFNAMSIZ]; if (bound_dev_if == 0) { len = 0; goto zero; } ret = -EINVAL; if (len < IFNAMSIZ) goto out; ret = netdev_get_name(net, devname, bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; out: #endif return ret; } bool sk_mc_loop(const struct sock *sk) { if (dev_recursion_level()) return false; if (!sk) return true; /* IPV6_ADDRFORM can change sk->sk_family under us. */ switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_test_bit(MC_LOOP, sk); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_test_bit(MC6_LOOP, sk); #endif } WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); void sock_set_reuseaddr(struct sock *sk) { lock_sock(sk); sk->sk_reuse = SK_CAN_REUSE; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseaddr); void sock_set_reuseport(struct sock *sk) { lock_sock(sk); sk->sk_reuseport = true; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseport); void sock_no_linger(struct sock *sk) { lock_sock(sk); WRITE_ONCE(sk->sk_lingertime, 0); sock_set_flag(sk, SOCK_LINGER); release_sock(sk); } EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { WRITE_ONCE(sk->sk_priority, priority); } EXPORT_SYMBOL(sock_set_priority); void sock_set_sndtimeo(struct sock *sk, s64 secs) { lock_sock(sk); if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) WRITE_ONCE(sk->sk_sndtimeo, secs * HZ); else WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT); release_sock(sk); } EXPORT_SYMBOL(sock_set_sndtimeo); static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) { sock_valbool_flag(sk, SOCK_RCVTSTAMP, val); sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, val && ns); if (val) { sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new); sock_enable_timestamp(sk, SOCK_TIMESTAMP); } } void sock_enable_timestamps(struct sock *sk) { lock_sock(sk); __sock_set_timestamps(sk, true, false, true); release_sock(sk); } EXPORT_SYMBOL(sock_enable_timestamps); void sock_set_timestamp(struct sock *sk, int optname, bool valbool) { switch (optname) { case SO_TIMESTAMP_OLD: __sock_set_timestamps(sk, valbool, false, false); break; case SO_TIMESTAMP_NEW: __sock_set_timestamps(sk, valbool, true, false); break; case SO_TIMESTAMPNS_OLD: __sock_set_timestamps(sk, valbool, false, true); break; case SO_TIMESTAMPNS_NEW: __sock_set_timestamps(sk, valbool, true, true); break; } } static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) { struct net *net = sock_net(sk); struct net_device *dev = NULL; bool match = false; int *vclock_index; int i, num; if (sk->sk_bound_dev_if) dev = dev_get_by_index(net, sk->sk_bound_dev_if); if (!dev) { pr_err("%s: sock not bind to device\n", __func__); return -EOPNOTSUPP; } num = ethtool_get_phc_vclocks(dev, &vclock_index); dev_put(dev); for (i = 0; i < num; i++) { if (*(vclock_index + i) == phc_index) { match = true; break; } } if (num > 0) kfree(vclock_index); if (!match) return -EINVAL; WRITE_ONCE(sk->sk_bind_phc, phc_index); return 0; } int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping) { int val = timestamping.flags; int ret; if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID_TCP && !(val & SOF_TIMESTAMPING_OPT_ID)) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk_is_tcp(sk)) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID_TCP) atomic_set(&sk->sk_tskey, tcp_sk(sk)->write_seq); else atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { atomic_set(&sk->sk_tskey, 0); } } if (val & SOF_TIMESTAMPING_OPT_STATS && !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; if (val & SOF_TIMESTAMPING_BIND_PHC) { ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); if (ret) return ret; } WRITE_ONCE(sk->sk_tsflags, val); sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); return 0; } void sock_set_keepalive(struct sock *sk) { lock_sock(sk); if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, true); sock_valbool_flag(sk, SOCK_KEEPOPEN, true); release_sock(sk); } EXPORT_SYMBOL(sock_set_keepalive); static void __sock_set_rcvbuf(struct sock *sk, int val) { /* Ensure val * 2 fits into an int, to prevent max_t() from treating it * as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* We double it on the way in to account for "struct sk_buff" etc. * overhead. Applications assume that the SO_RCVBUF setting they make * will allow that much actual data to be received on that socket. * * Applications are unaware that "struct sk_buff" and other overheads * allocate from the receive buffer during socket buffer allocation. * * And after considering the possible alternatives, returning the value * we actually used in getsockopt is the most desirable behavior. */ WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); } void sock_set_rcvbuf(struct sock *sk, int val) { lock_sock(sk); __sock_set_rcvbuf(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } void sock_set_mark(struct sock *sk, u32 val) { lock_sock(sk); __sock_set_mark(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_mark); static void sock_release_reserved_memory(struct sock *sk, int bytes) { /* Round down bytes to multiple of pages */ bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } static int sock_reserve_memory(struct sock *sk, int bytes) { long allocated; bool charged; int pages; if (!mem_cgroup_sockets_enabled || !sk->sk_memcg || !sk_has_account(sk)) return -EOPNOTSUPP; if (!bytes) return 0; pages = sk_mem_pages(bytes); /* pre-charge to memcg */ charged = mem_cgroup_charge_skmem(sk->sk_memcg, pages, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!charged) return -ENOMEM; /* pre-charge to forward_alloc */ sk_memory_allocated_add(sk, pages); allocated = sk_memory_allocated(sk); /* If the system goes into memory pressure with this * precharge, give up and return error. */ if (allocated > sk_prot_mem_limits(sk, 1)) { sk_memory_allocated_sub(sk, pages); mem_cgroup_uncharge_skmem(sk->sk_memcg, pages); return -ENOMEM; } sk_forward_alloc_add(sk, pages << PAGE_SHIFT); WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } #ifdef CONFIG_PAGE_POOL /* This is the number of tokens and frags that the user can SO_DEVMEM_DONTNEED * in 1 syscall. The limit exists to limit the amount of memory the kernel * allocates to copy these tokens, and to prevent looping over the frags for * too long. */ #define MAX_DONTNEED_TOKENS 128 #define MAX_DONTNEED_FRAGS 1024 static noinline_for_stack int sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) { unsigned int num_tokens, i, j, k, netmem_num = 0; struct dmabuf_token *tokens; int ret = 0, num_frags = 0; netmem_ref netmems[16]; if (!sk_is_tcp(sk)) return -EBADF; if (optlen % sizeof(*tokens) || optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) return -EINVAL; num_tokens = optlen / sizeof(*tokens); tokens = kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL); if (!tokens) return -ENOMEM; if (copy_from_sockptr(tokens, optval, optlen)) { kvfree(tokens); return -EFAULT; } xa_lock_bh(&sk->sk_user_frags); for (i = 0; i < num_tokens; i++) { for (j = 0; j < tokens[i].token_count; j++) { if (++num_frags > MAX_DONTNEED_FRAGS) goto frag_limit_reached; netmem_ref netmem = (__force netmem_ref)__xa_erase( &sk->sk_user_frags, tokens[i].token_start + j); if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem))) continue; netmems[netmem_num++] = netmem; if (netmem_num == ARRAY_SIZE(netmems)) { xa_unlock_bh(&sk->sk_user_frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); netmem_num = 0; xa_lock_bh(&sk->sk_user_frags); } ret++; } } frag_limit_reached: xa_unlock_bh(&sk->sk_user_frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); kvfree(tokens); return ret; } #endif void sockopt_lock_sock(struct sock *sk) { /* When current->bpf_ctx is set, the setsockopt is called from * a bpf prog. bpf has ensured the sk lock has been * acquired before calling setsockopt(). */ if (has_current_bpf_ctx()) return; lock_sock(sk); } EXPORT_SYMBOL(sockopt_lock_sock); void sockopt_release_sock(struct sock *sk) { if (has_current_bpf_ctx()) return; release_sock(sk); } EXPORT_SYMBOL(sockopt_release_sock); bool sockopt_ns_capable(struct user_namespace *ns, int cap) { return has_current_bpf_ctx() || ns_capable(ns, cap); } EXPORT_SYMBOL(sockopt_ns_capable); bool sockopt_capable(int cap) { return has_current_bpf_ctx() || capable(cap); } EXPORT_SYMBOL(sockopt_capable); static int sockopt_validate_clockid(__kernel_clockid_t value) { switch (value) { case CLOCK_REALTIME: case CLOCK_MONOTONIC: case CLOCK_TAI: return 0; } return -EINVAL; } /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. */ int sk_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct so_timestamping timestamping; struct socket *sock = sk->sk_socket; struct sock_txtime sk_txtime; int val; int valbool; struct linger ling; int ret = 0; /* * Options without arguments */ if (optname == SO_BINDTODEVICE) return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; /* handle options which do not require locking the socket. */ switch (optname) { case SO_PRIORITY: if ((val >= 0 && val <= 6) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { sock_set_priority(sk, val); return 0; } return -EPERM; case SO_PASSSEC: assign_bit(SOCK_PASSSEC, &sock->flags, valbool); return 0; case SO_PASSCRED: assign_bit(SOCK_PASSCRED, &sock->flags, valbool); return 0; case SO_PASSPIDFD: assign_bit(SOCK_PASSPIDFD, &sock->flags, valbool); return 0; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: case SO_ERROR: return -ENOPROTOOPT; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: if (val < 0) return -EINVAL; WRITE_ONCE(sk->sk_ll_usec, val); return 0; case SO_PREFER_BUSY_POLL: if (valbool && !sockopt_capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); return 0; case SO_BUSY_POLL_BUDGET: if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) return -EPERM; if (val < 0 || val > U16_MAX) return -EINVAL; WRITE_ONCE(sk->sk_busy_poll_budget, val); return 0; #endif case SO_MAX_PACING_RATE: { unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; unsigned long pacing_rate; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && copy_from_sockptr(&ulval, optval, sizeof(ulval))) { return -EFAULT; } if (ulval != ~0UL) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); /* Pairs with READ_ONCE() from sk_getsockopt() */ WRITE_ONCE(sk->sk_max_pacing_rate, ulval); pacing_rate = READ_ONCE(sk->sk_pacing_rate); if (ulval < pacing_rate) WRITE_ONCE(sk->sk_pacing_rate, ulval); return 0; } case SO_TXREHASH: if (val < -1 || val > 1) return -EINVAL; if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() * and sk_getsockopt(). */ WRITE_ONCE(sk->sk_txrehash, (u8)val); return 0; case SO_PEEK_OFF: { int (*set_peek_off)(struct sock *sk, int val); set_peek_off = READ_ONCE(sock->ops)->set_peek_off; if (set_peek_off) ret = set_peek_off(sk, val); else ret = -EOPNOTSUPP; return ret; } #ifdef CONFIG_PAGE_POOL case SO_DEVMEM_DONTNEED: return sock_devmem_dontneed(sk, optval, optlen); #endif } sockopt_lock_sock(sk); switch (optname) { case SO_DEBUG: if (val && !sockopt_capable(CAP_NET_ADMIN)) ret = -EACCES; else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: sk->sk_reuseport = valbool; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); sk_dst_reset(sk); break; case SO_BROADCAST: sock_valbool_flag(sk, SOCK_BROADCAST, valbool); break; case SO_SNDBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; case SO_SNDBUFFORCE: if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ if (val < 0) val = 0; goto set_sndbuf; case SO_RCVBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ __sock_set_rcvbuf(sk, max(val, 0)); break; case SO_KEEPALIVE: if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, valbool); sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); break; case SO_OOBINLINE: sock_valbool_flag(sk, SOCK_URGINLINE, valbool); break; case SO_NO_CHECK: sk->sk_no_check_tx = valbool; break; case SO_LINGER: if (optlen < sizeof(ling)) { ret = -EINVAL; /* 1003.1g */ break; } if (copy_from_sockptr(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } if (!ling.l_onoff) { sock_reset_flag(sk, SOCK_LINGER); } else { unsigned long t_sec = ling.l_linger; if (t_sec >= MAX_SCHEDULE_TIMEOUT / HZ) WRITE_ONCE(sk->sk_lingertime, MAX_SCHEDULE_TIMEOUT); else WRITE_ONCE(sk->sk_lingertime, t_sec * HZ); sock_set_flag(sk, SOCK_LINGER); } break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: if (optlen == sizeof(timestamping)) { if (copy_from_sockptr(×tamping, optval, sizeof(timestamping))) { ret = -EFAULT; break; } } else { memset(×tamping, 0, sizeof(timestamping)); timestamping.flags = val; } ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: { int (*set_rcvlowat)(struct sock *sk, int val) = NULL; if (val < 0) val = INT_MAX; if (sock) set_rcvlowat = READ_ONCE(sock->ops)->set_rcvlowat; if (set_rcvlowat) ret = set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; } case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); break; case SO_ATTACH_FILTER: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_attach_filter(&fprog, sk); break; } case SO_ATTACH_BPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_attach_bpf(ufd, sk); } break; case SO_ATTACH_REUSEPORT_CBPF: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_reuseport_attach_filter(&fprog, sk); break; } case SO_ATTACH_REUSEPORT_EBPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_reuseport_attach_bpf(ufd, sk); } break; case SO_DETACH_REUSEPORT_BPF: ret = reuseport_detach_prog(sk); break; case SO_DETACH_FILTER: ret = sk_detach_filter(sk); break; case SO_LOCK_FILTER: if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) ret = -EPERM; else sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); break; case SO_MARK: if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } __sock_set_mark(sk, val); break; case SO_RCVMARK: sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break; case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; case SO_WIFI_STATUS: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; case SO_SELECT_ERR_QUEUE: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; case SO_INCOMING_CPU: reuseport_update_incoming_cpu(sk, val); break; case SO_CNX_ADVICE: if (val == 1) dst_negative_advice(sk); break; case SO_ZEROCOPY: if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { if (!(sk_is_tcp(sk) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -EOPNOTSUPP; } else if (sk->sk_family != PF_RDS) { ret = -EOPNOTSUPP; } if (!ret) { if (val < 0 || val > 1) ret = -EINVAL; else sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); } break; case SO_TXTIME: if (optlen != sizeof(struct sock_txtime)) { ret = -EINVAL; break; } else if (copy_from_sockptr(&sk_txtime, optval, sizeof(struct sock_txtime))) { ret = -EFAULT; break; } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) { ret = -EINVAL; break; } /* CLOCK_MONOTONIC is only used by sch_fq, and this packet * scheduler has enough safe guards. */ if (sk_txtime.clockid != CLOCK_MONOTONIC && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } ret = sockopt_validate_clockid(sk_txtime.clockid); if (ret) break; sock_valbool_flag(sk, SOCK_TXTIME, true); sk->sk_clockid = sk_txtime.clockid; sk->sk_txtime_deadline_mode = !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); sk->sk_txtime_report_errors = !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); break; case SO_BINDTOIFINDEX: ret = sock_bindtoindex_locked(sk, val); break; case SO_BUF_LOCK: if (val & ~SOCK_BUF_LOCK_MASK) { ret = -EINVAL; break; } sk->sk_userlocks = val | (sk->sk_userlocks & ~SOCK_BUF_LOCK_MASK); break; case SO_RESERVE_MEM: { int delta; if (val < 0) { ret = -EINVAL; break; } delta = val - sk->sk_reserved_mem; if (delta < 0) sock_release_reserved_memory(sk, -delta); else ret = sock_reserve_memory(sk, delta); break; } default: ret = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return ret; } int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { return sk_setsockopt(sock->sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_setsockopt); static const struct cred *sk_get_peer_cred(struct sock *sk) { const struct cred *cred; spin_lock(&sk->sk_peer_lock); cred = get_cred(sk->sk_peer_cred); spin_unlock(&sk->sk_peer_lock); return cred; } static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; if (cred) { struct user_namespace *current_ns = current_user_ns(); ucred->uid = from_kuid_munged(current_ns, cred->euid); ucred->gid = from_kgid_munged(current_ns, cred->egid); } } static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; for (i = 0; i < src->ngroups; i++) { gid_t gid = from_kgid_munged(user_ns, src->gid[i]); if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; } return 0; } int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct socket *sock = sk->sk_socket; union { int val; u64 val64; unsigned long ulval; struct linger ling; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; struct so_timestamping timestamping; } v; int lv = sizeof(int); int len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; memset(&v, 0, sizeof(v)); switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; case SO_DONTROUTE: v.val = sock_flag(sk, SOCK_LOCALROUTE); break; case SO_BROADCAST: v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: v.val = sk->sk_reuse; break; case SO_REUSEPORT: v.val = sk->sk_reuseport; break; case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: v.val = sk->sk_type; break; case SO_PROTOCOL: v.val = sk->sk_protocol; break; case SO_DOMAIN: v.val = sk->sk_family; break; case SO_ERROR: v.val = -sock_error(sk); if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; case SO_OOBINLINE: v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: lv = sizeof(v.ling); v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = READ_ONCE(sk->sk_lingertime) / HZ; break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; case SO_TIMESTAMPNS_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMP_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPNS_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only * returning the flags when they were set through the same option. * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. */ if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { v.timestamping.flags = READ_ONCE(sk->sk_tsflags); v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); } break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v, SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: v.val = 1; break; case SO_PASSCRED: v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; case SO_PASSPIDFD: v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags); break; case SO_PEERCRED: { struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); spin_unlock(&sk->sk_peer_lock); if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } case SO_PEERPIDFD: { struct pid *peer_pid; struct file *pidfd_file = NULL; int pidfd; if (len > sizeof(pidfd)) len = sizeof(pidfd); spin_lock(&sk->sk_peer_lock); peer_pid = get_pid(sk->sk_peer_pid); spin_unlock(&sk->sk_peer_lock); if (!peer_pid) return -ENODATA; pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); put_pid(peer_pid); if (pidfd < 0) return pidfd; if (copy_to_sockptr(optval, &pidfd, len) || copy_to_sockptr(optlen, &len, sizeof(int))) { put_unused_fd(pidfd); fput(pidfd_file); return -EFAULT; } fd_install(pidfd, pidfd_file); return 0; } case SO_PEERGROUPS: { const struct cred *cred; int ret, n; cred = sk_get_peer_cred(sk); if (!cred) return -ENODATA; n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); put_cred(cred); return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); ret = groups_to_user(optval, cred->group_info); put_cred(cred); if (ret) return ret; goto lenout; } case SO_PEERNAME: { struct sockaddr_storage address; lv = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; if (copy_to_sockptr(optval, &address, len)) return -EFAULT; goto lenout; } /* Dubious BSD thing... Probably nobody even uses it, but * the UNIX standard wants it for whatever reason... -DaveM */ case SO_ACCEPTCONN: v.val = sk->sk_state == TCP_LISTEN; break; case SO_PASSSEC: v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); break; case SO_PEERSEC: return security_socket_getpeersec_stream(sock, optval, optlen, len); case SO_MARK: v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: v.val = sock_flag(sk, SOCK_RCVMARK); break; case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; case SO_WIFI_STATUS: v.val = sock_flag(sk, SOCK_WIFI_STATUS); break; case SO_PEEK_OFF: if (!READ_ONCE(sock->ops)->set_peek_off) return -EOPNOTSUPP; v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); break; case SO_BINDTODEVICE: return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: len = sk_get_filter(sk, optval, len); if (len < 0) return len; goto lenout; case SO_LOCK_FILTER: v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; case SO_BPF_EXTENSIONS: v.val = bpf_tell_extensions(); break; case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); break; #endif case SO_MAX_PACING_RATE: /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ v.val = min_t(unsigned long, ~0U, READ_ONCE(sk->sk_max_pacing_rate)); } break; case SO_INCOMING_CPU: v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: { u32 meminfo[SK_MEMINFO_VARS]; sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; } #ifdef CONFIG_NET_RX_BUSY_POLL case SO_INCOMING_NAPI_ID: v.val = READ_ONCE(sk->sk_napi_id); /* aggregate non-NAPI IDs down to 0 */ if (v.val < MIN_NAPI_ID) v.val = 0; break; #endif case SO_COOKIE: lv = sizeof(u64); if (len < lv) return -EINVAL; v.val64 = sock_gen_cookie(sk); break; case SO_ZEROCOPY: v.val = sock_flag(sk, SOCK_ZEROCOPY); break; case SO_TXTIME: lv = sizeof(v.txtime); v.txtime.clockid = sk->sk_clockid; v.txtime.flags |= sk->sk_txtime_deadline_mode ? SOF_TXTIME_DEADLINE_MODE : 0; v.txtime.flags |= sk->sk_txtime_report_errors ? SOF_TXTIME_REPORT_ERRORS : 0; break; case SO_BINDTOIFINDEX: v.val = READ_ONCE(sk->sk_bound_dev_if); break; case SO_NETNS_COOKIE: lv = sizeof(u64); if (len != lv) return -EINVAL; v.val64 = sock_net(sk)->net_cookie; break; case SO_BUF_LOCK: v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; break; case SO_RESERVE_MEM: v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: /* Paired with WRITE_ONCE() in sk_setsockopt() */ v.val = READ_ONCE(sk->sk_txrehash); break; default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). */ return -ENOPROTOOPT; } if (len > lv) len = lv; if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } /* * Initialize an sk_lock. * * (We also register the sk_lock with the lock validator.) */ static inline void sock_lock_init(struct sock *sk) { if (sk->sk_kern_sock) sock_lock_init_class_and_name( sk, af_family_kern_slock_key_strings[sk->sk_family], af_family_kern_slock_keys + sk->sk_family, af_family_kern_key_strings[sk->sk_family], af_family_kern_keys + sk->sk_family); else sock_lock_init_class_and_name( sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], af_family_keys + sk->sk_family); } /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarily, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif /* If we move sk_tx_queue_mapping out of the private section, * we must check if sk_tx_queue_clear() is called after * sock_copy() in sk_clone_lock(). */ BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < offsetof(struct sock, sk_dontcopy_begin) || offsetof(struct sock, sk_tx_queue_mapping) >= offsetof(struct sock, sk_dontcopy_end)); memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); unsafe_memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, prot->obj_size - offsetof(struct sock, sk_dontcopy_end), /* alloc is larger than struct, see sk_prot_alloc() */); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { struct sock *sk; struct kmem_cache *slab; slab = prot->slab; if (slab != NULL) { sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); if (!sk) return sk; if (want_init_on_alloc(priority)) sk_prot_clear_nulls(sk, prot->obj_size); } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { if (security_sk_alloc(sk, family, priority)) goto out_free; if (!try_module_get(prot->owner)) goto out_free_sec; } return sk; out_free_sec: security_sk_free(sk); out_free: if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); return NULL; } static void sk_prot_free(struct proto *prot, struct sock *sk) { struct kmem_cache *slab; struct module *owner; owner = prot->owner; slab = prot->slab; cgroup_sk_free(&sk->sk_cgrp_data); mem_cgroup_sk_free(sk); security_sk_free(sk); if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); module_put(owner); } /** * sk_alloc - All socket objects are allocated here * @net: the applicable net namespace * @family: protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance * @kern: is this to be a kernel socket? */ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { struct sock *sk; sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family); if (sk) { sk->sk_family = family; /* * See comment in struct sock definition to understand * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } else { __netns_tracker_alloc(net, &sk->ns_tracker, false, priority); } sock_net_set(sk, net); refcount_set(&sk->sk_wmem_alloc, 1); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); sk_tx_queue_clear(sk); } return sk; } EXPORT_SYMBOL(sk_alloc); /* Sockets having SOCK_RCU_FREE will call this function after one RCU * grace period. This is the case for UDP sockets and TCP listeners. */ static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); struct sk_filter *filter; if (sk->sk_destruct) sk->sk_destruct(sk); filter = rcu_dereference_check(sk->sk_filter, refcount_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); #ifdef CONFIG_BPF_SYSCALL bpf_sk_storage_free(sk); #endif if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; } /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); if (likely(sk->sk_net_refcnt)) put_net_track(sock_net(sk), &sk->ns_tracker); else __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); sk_prot_free(sk->sk_prot_creator, sk); } void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); if (rcu_access_pointer(sk->sk_reuseport_cb)) { reuseport_detach_sock(sk); use_call_rcu = true; } if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); } static void __sk_free(struct sock *sk) { if (likely(sk->sk_net_refcnt)) sock_inuse_add(sock_net(sk), -1); if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk))) sock_diag_broadcast_destroy(sk); else sk_destruct(sk); } void sk_free(struct sock *sk) { /* * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ if (refcount_dec_and_test(&sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sk_free); static void sk_init_common(struct sock *sk) { skb_queue_head_init(&sk->sk_receive_queue); skb_queue_head_init(&sk->sk_write_queue); skb_queue_head_init(&sk->sk_error_queue); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_receive_queue.lock, af_rlock_keys + sk->sk_family, af_family_rlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_write_queue.lock, af_wlock_keys + sk->sk_family, af_family_wlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_error_queue.lock, af_elock_keys + sk->sk_family, af_family_elock_key_strings[sk->sk_family]); if (sk->sk_kern_sock) lockdep_set_class_and_name(&sk->sk_callback_lock, af_kern_callback_keys + sk->sk_family, af_family_kern_clock_key_strings[sk->sk_family]); else lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); } /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) */ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct proto *prot = READ_ONCE(sk->sk_prot); struct sk_filter *filter; bool is_charged = true; struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); if (!newsk) goto out; sock_copy(newsk, sk); newsk->sk_prot_creator = prot; /* SANITY */ if (likely(newsk->sk_net_refcnt)) { get_net_track(sock_net(newsk), &newsk->ns_tracker, priority); sock_inuse_add(sock_net(newsk), 1); } else { /* Kernel sockets are not elevating the struct net refcount. * Instead, use a tracker to more easily detect if a layer * is not properly dismantling its kernel sockets at netns * destroy time. */ __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, false, priority); } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ refcount_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; newsk->sk_reserved_mem = 0; atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); RCU_INIT_POINTER(newsk->sk_filter, filter); rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new * socket if we couldn't charge it in the first place * as otherwise we uncharge the parent's filter. */ if (!is_charged) RCU_INIT_POINTER(newsk->sk_filter, NULL); sk_free_unlock_clone(newsk); newsk = NULL; goto out; } RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); if (bpf_sk_storage_clone(sk, newsk)) { sk_free_unlock_clone(newsk); newsk = NULL; goto out; } /* Clear sk_user_data if parent had the pointer tagged * as not suitable for copying when cloning. */ if (sk_user_data_is_nocopy(newsk)) newsk->sk_user_data = NULL; newsk->sk_err = 0; newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&newsk->sk_refcnt, 2); sk_set_socket(newsk, NULL); sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); out: return newsk; } EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_free_unlock_clone(struct sock *sk) { /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ sk->sk_destruct = NULL; bh_unlock_sock(sk); sk_free(sk); } EXPORT_SYMBOL_GPL(sk_free_unlock_clone); static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst) { bool is_ipv6 = false; u32 max_size; #if IS_ENABLED(CONFIG_IPV6) is_ipv6 = (sk->sk_family == AF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)); #endif /* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ max_size = is_ipv6 ? READ_ONCE(dst->dev->gso_max_size) : READ_ONCE(dst->dev->gso_ipv4_max_size); if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk)) max_size = GSO_LEGACY_MAX_SIZE; return max_size - (MAX_TCP_HEADER + 1); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; sk->sk_route_caps = dst->dev->features; if (sk_is_tcp(sk)) sk->sk_route_caps |= NETIF_F_GSO; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; if (unlikely(sk->sk_gso_disabled)) sk->sk_route_caps &= ~NETIF_F_GSO_MASK; if (sk_can_gso(sk)) { if (dst->header_len && !xfrm_dst_offload_ok(dst)) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dst); /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); } } sk->sk_gso_max_segs = max_segs; sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); /* * Simple resource managers for sockets. */ /* * Write buffer destructor automatically called from kfree_skb. */ void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; bool free; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { if (sock_flag(sk, SOCK_RCU_FREE) && sk->sk_write_space == sock_def_write_space) { rcu_read_lock(); free = refcount_sub_and_test(len, &sk->sk_wmem_alloc); sock_def_write_space_wfree(sk); rcu_read_unlock(); if (unlikely(free)) __sk_free(sk); return; } /* * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call */ WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); sk->sk_write_space(sk); len = 1; } /* * if sk_wmem_alloc reaches 0, we must finish what sk_free() * could not do because of in-flight packets */ if (refcount_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); /* This variant of sock_wfree() is used by TCP, * since it sets SOCK_USE_WRITE_QUEUE. */ void __sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) __sk_free(sk); } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); #ifdef CONFIG_INET if (unlikely(!sk_fullsock(sk))) return skb_set_owner_edemux(skb, sk); #endif skb->sk = sk; skb->destructor = sock_wfree; skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation * is enough to guarantee sk_free() won't free this sock until * all in-flight packets are completed */ refcount_add(skb->truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(skb_set_owner_w); static bool can_skb_orphan_partial(const struct sk_buff *skb) { /* Drivers depend on in-order delivery for crypto offload, * partial orphan breaks out-of-order-OK logic. */ if (skb_is_decrypted(skb)) return false; return (skb->destructor == sock_wfree || (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); } /* This helper is used by netem, as it can hold packets in its * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. * But we also want to keep skb->sk set because some packet schedulers * rely on it (sch_fq for example). */ void skb_orphan_partial(struct sk_buff *skb) { if (skb_is_tcp_pure_ack(skb)) return; if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) return; skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); /* * Read buffer destructor automatically called from kfree_skb. */ void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; atomic_sub(len, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, len); } EXPORT_SYMBOL(sock_rfree); /* * Buffer destructor for skbs that are not used directly in read or write * path, e.g. for error handler skbs. Automatically called from kfree_skb. */ void sock_efree(struct sk_buff *skb) { sock_put(skb->sk); } EXPORT_SYMBOL(sock_efree); /* Buffer destructor for prefetch/receive path where reference count may * not be held, e.g. for listen sockets. */ #ifdef CONFIG_INET void sock_pfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (!sk_is_refcounted(sk)) return; if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { inet_reqsk(sk)->rsk_listener = NULL; reqsk_free(inet_reqsk(sk)); return; } sock_gen_put(sk); } EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); unsigned long __sock_i_ino(struct sock *sk) { unsigned long ino; read_lock(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; read_unlock(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(__sock_i_ino); unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; local_bh_disable(); ino = __sock_i_ino(sk); local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. */ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; } } return NULL; } EXPORT_SYMBOL(sock_wmalloc); static void sock_ofree(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_omem_alloc); } struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority) { struct sk_buff *skb; /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); if (!skb) return NULL; atomic_add(skb->truesize, &sk->sk_omem_alloc); skb->sk = sk; skb->destructor = sock_ofree; return skb; } /* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if ((unsigned int)size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. */ atomic_add(size, &sk->sk_omem_alloc); mem = kmalloc(size, priority); if (mem) return mem; atomic_sub(size, &sk->sk_omem_alloc); } return NULL; } EXPORT_SYMBOL(sock_kmalloc); /* Free an option memory block. Note, we actually want the inline * here as this allows gcc to detect the nullify and fold away the * condition entirely. */ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size, const bool nullify) { if (WARN_ON_ONCE(!mem)) return; if (nullify) kfree_sensitive(mem); else kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } void sock_kfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, false); } EXPORT_SYMBOL(sock_kfree_s); void sock_kzfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, true); } EXPORT_SYMBOL(sock_kzfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); for (;;) { if (!timeo) break; if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; if (READ_ONCE(sk->sk_err)) break; timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(sk), &wait); return timeo; } /* * Generic send/receive buffer handlers */ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order) { struct sk_buff *skb; long timeo; int err; timeo = sock_sndtimeo(sk, noblock); for (;;) { err = sock_error(sk); if (err != 0) goto failure; err = -EPIPE; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto failure; if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; if (!timeo) goto failure; if (signal_pending(current)) goto interrupted; timeo = sock_wait_for_wmem(sk, timeo); } skb = alloc_skb_with_frags(header_len, data_len, max_page_order, errcode, sk->sk_allocation); if (skb) skb_set_owner_w(skb, sk); return skb; interrupted: err = sock_intr_errno(timeo); failure: *errcode = err; return NULL; } EXPORT_SYMBOL(sock_alloc_send_pskb); int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; BUILD_BUG_ON(SOF_TIMESTAMPING_LAST == (1 << 31)); switch (cmsg->cmsg_type) { case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; tsflags = *(u32 *)CMSG_DATA(cmsg); if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) return -EINVAL; sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; case SCM_TXTIME: if (!sock_flag(sk, SOCK_TXTIME)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64))) return -EINVAL; sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg)); break; case SCM_TS_OPT_ID: if (sk_is_tcp(sk)) return -EINVAL; tsflags = READ_ONCE(sk->sk_tsflags); if (!(tsflags & SOF_TIMESTAMPING_OPT_ID)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->ts_opt_id = *(u32 *)CMSG_DATA(cmsg); sockc->tsflags |= SOCKCM_FLAG_TS_OPT_ID; break; /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL(__sock_cmsg_send); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc) { struct cmsghdr *cmsg; int ret; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; ret = __sock_cmsg_send(sk, cmsg, sockc); if (ret) return ret; } return 0; } EXPORT_SYMBOL(sock_cmsg_send); static void sk_enter_memory_pressure(struct sock *sk) { if (!sk->sk_prot->enter_memory_pressure) return; sk->sk_prot->enter_memory_pressure(sk); } static void sk_leave_memory_pressure(struct sock *sk) { if (sk->sk_prot->leave_memory_pressure) { INDIRECT_CALL_INET_1(sk->sk_prot->leave_memory_pressure, tcp_leave_memory_pressure, sk); } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; if (memory_pressure && READ_ONCE(*memory_pressure)) WRITE_ONCE(*memory_pressure, 0); } } DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); /** * skb_page_frag_refill - check that a page_frag contains enough room * @sz: minimum size of the fragment we want to get * @pfrag: pointer to page_frag * @gfp: priority for memory allocation * * Note: While this allocator tries to use high order pages, there is * no guarantee that allocations succeed. Therefore, @sz MUST be * less or equal than PAGE_SIZE. */ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { if (page_ref_count(pfrag->page) == 1) { pfrag->offset = 0; return true; } if (pfrag->offset + sz <= pfrag->size) return true; put_page(pfrag->page); } pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER && !static_branch_unlikely(&net_high_order_alloc_disable_key)) { /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; return true; } } pfrag->page = alloc_page(gfp); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE; return true; } return false; } EXPORT_SYMBOL(skb_page_frag_refill); bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) return true; sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return false; } EXPORT_SYMBOL(sk_page_frag_refill); void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); } void __release_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { struct sk_buff *skb, *next; while ((skb = sk->sk_backlog.head) != NULL) { sk->sk_backlog.head = sk->sk_backlog.tail = NULL; spin_unlock_bh(&sk->sk_lock.slock); do { next = skb->next; prefetch(next); DEBUG_NET_WARN_ON_ONCE(skb_dst_is_noref(skb)); skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); cond_resched(); skb = next; } while (skb != NULL); spin_lock_bh(&sk->sk_lock.slock); } /* * Doing the zeroing here guarantee we can not loop forever * while a wild producer attempts to flood us. */ sk->sk_backlog.len = 0; } void __sk_flush_backlog(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); __release_sock(sk); if (sk->sk_prot->release_cb) INDIRECT_CALL_INET_1(sk->sk_prot->release_cb, tcp_release_cb, sk); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL_GPL(__sk_flush_backlog); /** * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return rc; } EXPORT_SYMBOL(sk_wait_data); /** * __sk_mem_raise_allocated - increase memory_allocated * @sk: socket * @size: memory size to allocate * @amt: pages to allocate * @kind: allocation type * * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc. * * Unlike the globally shared limits among the sockets under same protocol, * consuming the budget of a memcg won't have direct effect on other ones. * So be optimistic about memcg's tolerance, and leave the callers to decide * whether or not to raise allocated through sk_under_memory_pressure() or * its variants. */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct mem_cgroup *memcg = mem_cgroup_sockets_enabled ? sk->sk_memcg : NULL; struct proto *prot = sk->sk_prot; bool charged = false; long allocated; sk_memory_allocated_add(sk, amt); allocated = sk_memory_allocated(sk); if (memcg) { if (!mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge())) goto suppress_allocation; charged = true; } /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } /* Under pressure. */ if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); /* Over hard limit. */ if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* Guarantee minimum buffer size under pressure (either global * or memcg) to make sure features described in RFC 7323 (TCP * Extensions for High Performance) work properly. * * This rule does NOT stand when exceeds global or memcg's hard * limit, or else a DoS attack can be taken place by spawning * lots of sockets whose usage are under minimum buffer size. */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; } else { /* SK_MEM_SEND */ int wmem0 = sk_get_wmem0(sk, prot); if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < wmem0) return 1; } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) { return 1; } } if (sk_has_memory_pressure(sk)) { u64 alloc; /* The following 'average' heuristic is within the * scope of global accounting, so it only makes * sense for global memory pressure. */ if (!sk_under_global_memory_pressure(sk)) return 1; /* Try to be fair among all the sockets under global * pressure by allowing the ones that below average * usage to raise. */ alloc = sk_sockets_allocated_read_positive(sk); if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) return 1; } suppress_allocation: if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) { sk_stream_moderate_sndbuf(sk); /* Fail only if socket is _under_ its sndbuf. * In this case we cannot block, so that we have to fail. */ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { /* Force charge with __GFP_NOFAIL */ if (memcg && !charged) { mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge() | __GFP_NOFAIL); } return 1; } } if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) trace_sock_exceed_buf_limit(sk, prot, allocated, kind); sk_memory_allocated_sub(sk, amt); if (charged) mem_cgroup_uncharge_skmem(memcg, amt); return 0; } /** * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated * @sk: socket * @size: memory size to allocate * @kind: allocation type * * If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means * rmem allocation. This function assumes that protocols which have * memory_pressure use sk_wmem_queued as write buffer accounting. */ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); sk_forward_alloc_add(sk, amt << PAGE_SHIFT); ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) sk_forward_alloc_add(sk, -(amt << PAGE_SHIFT)); return ret; } EXPORT_SYMBOL(__sk_mem_schedule); /** * __sk_mem_reduce_allocated - reclaim memory_allocated * @sk: socket * @amount: number of quanta * * Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc */ void __sk_mem_reduce_allocated(struct sock *sk, int amount) { sk_memory_allocated_sub(sk, amount); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket * @amount: number of bytes (rounded down to a PAGE_SIZE multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { amount >>= PAGE_SHIFT; sk_forward_alloc_add(sk, -(amount << PAGE_SHIFT)); __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); /* * Set of default routines for initialising struct proto_ops when * the protocol does not support a particular function. In certain * cases where it makes no sense for a protocol to have a "do nothing" * function, some default processing is provided. */ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int peer) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_getname); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_shutdown); int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg_locked); int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } EXPORT_SYMBOL(sock_no_mmap); /* * When a file is received (via SCM_RIGHTS, etc), we must bump the * various sock-based usage counts. */ void __receive_sock(struct file *file) { struct socket *sock; sock = sock_from_file(file); if (sock) { sock_update_netprioidx(&sock->sk->sk_cgrp_data); sock_update_classid(&sock->sk->sk_cgrp_data); } } /* * Default Socket Callbacks */ static void sock_def_wakeup(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLERR); sk_wake_async_rcu(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } void sock_def_readable(struct sock *sk) { struct socket_wq *wq; trace_sk_data_ready(sk); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if (sock_writeable(sk)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } /* An optimised version of sock_def_write_space(), should only be called * for SOCK_RCU_FREE sockets under RCU read section and after putting * ->sk_wmem_alloc. */ static void sock_def_write_space_wfree(struct sock *sk) { /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if (sock_writeable(sk)) { struct socket_wq *wq = rcu_dereference(sk->sk_wq); /* rely on refcount_sub from sock_wfree() */ smp_mb__after_atomic(); if (wq && waitqueue_active(&wq->wait)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } } static void sock_def_destruct(struct sock *sk) { } void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) if (send_sigurg(sk->sk_socket->file)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) { if (!mod_timer(timer, expires)) sock_hold(sk); } EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { if (del_timer(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) { if (del_timer_sync(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer_sync); void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk->sk_use_task_frag = true; sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); if (sock) { sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); } sk->sk_uid = uid; sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; spin_lock_init(&sk->sk_peer_lock); sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; #if BITS_PER_LONG==32 seqlock_init(&sk->sk_stamp_seq); #endif atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data_uid); void sock_init_data(struct socket *sock, struct sock *sk) { kuid_t uid = sock ? SOCK_INODE(sock)->i_uid : make_kuid(sock_net(sk)->user_ns, 0); sock_init_data_uid(sock, sk, uid); } EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { /* The sk_lock has mutex_lock() semantics here. */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (sock_owned_by_user_nocheck(sk)) __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); if (sk->sk_prot->release_cb) INDIRECT_CALL_INET_1(sk->sk_prot->release_cb, tcp_release_cb, sk); sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (!sock_owned_by_user_nocheck(sk)) { /* * Fast path return with bottom halves disabled and * sock::sk_lock.slock held. * * The 'mutex' is not contended and holding * sock::sk_lock.slock prevents all other lockers to * proceed so the corresponding unlock_sock_fast() can * avoid the slow path of release_sock() completely and * just release slock. * * From a semantical POV this is equivalent to 'acquiring' * the 'mutex', hence the corresponding lockdep * mutex_release() has to happen in the fast path of * unlock_sock_fast(). */ return false; } __lock_sock(sk); sk->sk_lock.owned = 1; __acquire(&sk->sk_lock.slock); spin_unlock_bh(&sk->sk_lock.slock); return true; } EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) { struct sock *sk = sock->sk; struct timespec64 ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec64(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return -ENOENT; if (ts.tv_sec == 0) { ktime_t kt = ktime_get_real(); sock_write_timestamp(sk, kt); ts = ktime_to_timespec64(kt); } if (timeval) ts.tv_nsec /= 1000; #ifdef CONFIG_COMPAT_32BIT_TIME if (time32) return put_old_timespec32(&ts, userstamp); #endif #ifdef CONFIG_SPARC64 /* beware of padding in sparc64 timeval */ if (timeval && !in_compat_syscall()) { struct __kernel_old_timeval __user tv = { .tv_sec = ts.tv_sec, .tv_usec = ts.tv_nsec, }; if (copy_to_user(userstamp, &tv, sizeof(tv))) return -EFAULT; return 0; } #endif return put_timespec64(&ts, userstamp); } EXPORT_SYMBOL(sock_gettstamp); void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) { if (!sock_flag(sk, flag)) { unsigned long previous_flags = sk->sk_flags; sock_set_flag(sk, flag); /* * we just set one of the two flags which require net * time stamping, but time stamping might have been on * already because of the other one */ if (sock_needs_netstamp(sk) && !(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type) { struct sock_exterr_skb *serr; struct sk_buff *skb; int copied, err; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); msg->msg_flags |= MSG_ERRQUEUE; err = copied; out_free_skb: kfree_skb(skb); out: return err; } EXPORT_SYMBOL(sock_recv_errqueue); /* * Get a socket option on an socket. * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume * this means if you specify SO_ERROR (otherwise what is the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_getsockopt); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; err = sk->sk_prot->recvmsg(sk, msg, size, flags, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(sock_common_recvmsg); /* * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_setsockopt); void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) sk->sk_prot->destroy(sk); /* * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * * A. Remove from hash tables. */ sk->sk_prot->unhash(sk); /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and * did hash table lookup before we unhashed socket. They will achieve * receive queue and will be purged by socket destructor. * * Also we still have packets pending on receive queue and probably, * our own packets waiting in device queues. sock_destroy will drain * receive queue, but transmitted packets will delay socket destruction * until the last reference will be released. */ sock_orphan(sk); xfrm_sk_free_policy(sk); sock_put(sk); } EXPORT_SYMBOL(sk_common_release); void sk_get_meminfo(const struct sock *sk, u32 *mem) { memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk); mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } #ifdef CONFIG_PROC_FS static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); int sock_prot_inuse_get(struct net *net, struct proto *prot) { int cpu, idx = prot->inuse_idx; int res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx]; return res >= 0 ? res : 0; } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); int sock_inuse_get(struct net *net) { int cpu, res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->all; return res; } EXPORT_SYMBOL_GPL(sock_inuse_get); static int __net_init sock_inuse_init_net(struct net *net) { net->core.prot_inuse = alloc_percpu(struct prot_inuse); if (net->core.prot_inuse == NULL) return -ENOMEM; return 0; } static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.prot_inuse); } static struct pernet_operations net_inuse_ops = { .init = sock_inuse_init_net, .exit = sock_inuse_exit_net, }; static __init int net_inuse_init(void) { if (register_pernet_subsys(&net_inuse_ops)) panic("Cannot initialize net inuse counters"); return 0; } core_initcall(net_inuse_init); static int assign_proto_idx(struct proto *prot) { prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { pr_err("PROTO_INUSE_NR exhausted\n"); return -ENOSPC; } set_bit(prot->inuse_idx, proto_inuse_idx); return 0; } static void release_proto_idx(struct proto *prot) { if (prot->inuse_idx != PROTO_INUSE_NR - 1) clear_bit(prot->inuse_idx, proto_inuse_idx); } #else static inline int assign_proto_idx(struct proto *prot) { return 0; } static inline void release_proto_idx(struct proto *prot) { } #endif static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) { if (!twsk_prot) return; kfree(twsk_prot->twsk_slab_name); twsk_prot->twsk_slab_name = NULL; kmem_cache_destroy(twsk_prot->twsk_slab); twsk_prot->twsk_slab = NULL; } static int tw_prot_init(const struct proto *prot) { struct timewait_sock_ops *twsk_prot = prot->twsk_prot; if (!twsk_prot) return 0; twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); if (!twsk_prot->twsk_slab_name) return -ENOMEM; twsk_prot->twsk_slab = kmem_cache_create(twsk_prot->twsk_slab_name, twsk_prot->twsk_obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!twsk_prot->twsk_slab) { pr_crit("%s: Can't create timewait sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) return; kfree(rsk_prot->slab_name); rsk_prot->slab_name = NULL; kmem_cache_destroy(rsk_prot->slab); rsk_prot->slab = NULL; } static int req_prot_init(const struct proto *prot) { struct request_sock_ops *rsk_prot = prot->rsk_prot; if (!rsk_prot) return 0; rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); if (!rsk_prot->slab_name) return -ENOMEM; rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } int proto_register(struct proto *prot, int alloc_slab) { int ret = -ENOBUFS; if (prot->memory_allocated && !prot->sysctl_mem) { pr_err("%s: missing sysctl_mem\n", prot->name); return -EINVAL; } if (prot->memory_allocated && !prot->per_cpu_fw_alloc) { pr_err("%s: missing per_cpu_fw_alloc\n", prot->name); return -EINVAL; } if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | prot->slab_flags, prot->useroffset, prot->usersize, NULL); if (prot->slab == NULL) { pr_crit("%s: Can't create sock SLAB cache!\n", prot->name); goto out; } if (req_prot_init(prot)) goto out_free_request_sock_slab; if (tw_prot_init(prot)) goto out_free_timewait_sock_slab; } mutex_lock(&proto_list_mutex); ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; out_free_timewait_sock_slab: if (alloc_slab) tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); kmem_cache_destroy(prot->slab); prot->slab = NULL; } out: return ret; } EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { mutex_lock(&proto_list_mutex); release_proto_idx(prot); list_del(&prot->node); mutex_unlock(&proto_list_mutex); kmem_cache_destroy(prot->slab); prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); int sock_load_diag_module(int family, int protocol) { if (!protocol) { if (!sock_is_registered(family)) return -ENOENT; return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family); } #ifdef CONFIG_INET if (family == AF_INET && protocol != IPPROTO_RAW && protocol < MAX_INET_PROTOS && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family, protocol); } EXPORT_SYMBOL(sock_load_diag_module); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) { mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &proto_list, pos); } static void proto_seq_stop(struct seq_file *seq, void *v) __releases(proto_list_mutex) { mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } static long sock_prot_memory_allocated(struct proto *proto) { return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; } static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), sock_prot_memory_allocated(proto), sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), proto_method_implemented(proto->close), proto_method_implemented(proto->connect), proto_method_implemented(proto->disconnect), proto_method_implemented(proto->accept), proto_method_implemented(proto->ioctl), proto_method_implemented(proto->init), proto_method_implemented(proto->destroy), proto_method_implemented(proto->shutdown), proto_method_implemented(proto->setsockopt), proto_method_implemented(proto->getsockopt), proto_method_implemented(proto->sendmsg), proto_method_implemented(proto->recvmsg), proto_method_implemented(proto->bind), proto_method_implemented(proto->backlog_rcv), proto_method_implemented(proto->hash), proto_method_implemented(proto->unhash), proto_method_implemented(proto->get_port), proto_method_implemented(proto->enter_memory_pressure)); } static int proto_seq_show(struct seq_file *seq, void *v) { if (v == &proto_list) seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s", "protocol", "size", "sockets", "memory", "press", "maxhdr", "slab", "module", "cl co di ac io in de sh ss gs se re bi br ha uh gp em\n"); else proto_seq_printf(seq, list_entry(v, struct proto, node)); return 0; } static const struct seq_operations proto_seq_ops = { .start = proto_seq_start, .next = proto_seq_next, .stop = proto_seq_stop, .show = proto_seq_show, }; static __net_init int proto_init_net(struct net *net) { if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static __net_exit void proto_exit_net(struct net *net) { remove_proc_entry("protocols", net->proc_net); } static __net_initdata struct pernet_operations proto_net_ops = { .init = proto_init_net, .exit = proto_exit_net, }; static int __init proto_init(void) { return register_pernet_subsys(&proto_net_ops); } subsys_initcall(proto_init); #endif /* PROC_FS */ #ifdef CONFIG_NET_RX_BUSY_POLL bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) return true; if (sk_is_udp(sk) && !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) return true; return sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len) { if (!sk->sk_prot->bind_add) return -EOPNOTSUPP; return sk->sk_prot->bind_add(sk, addr, addr_len); } EXPORT_SYMBOL(sock_bind_add); /* Copy 'size' bytes from userspace and return `size` back to userspace */ int sock_ioctl_inout(struct sock *sk, unsigned int cmd, void __user *arg, void *karg, size_t size) { int ret; if (copy_from_user(karg, arg, size)) return -EFAULT; ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, karg); if (ret) return ret; if (copy_to_user(arg, karg, size)) return -EFAULT; return 0; } EXPORT_SYMBOL(sock_ioctl_inout); /* This is the most common ioctl prep function, where the result (4 bytes) is * copied back to userspace if the ioctl() returns successfully. No input is * copied from userspace as input argument. */ static int sock_ioctl_out(struct sock *sk, unsigned int cmd, void __user *arg) { int ret, karg = 0; ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, &karg); if (ret) return ret; return put_user(karg, (int __user *)arg); } /* A wrapper around sock ioctls, which copies the data from userspace * (depending on the protocol/ioctl), and copies back the result to userspace. * The main motivation for this function is to pass kernel memory to the * protocol ioctl callbacks, instead of userspace memory. */ int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { int rc = 1; if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET) rc = ipmr_sk_ioctl(sk, cmd, arg); else if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET6) rc = ip6mr_sk_ioctl(sk, cmd, arg); else if (sk_is_phonet(sk)) rc = phonet_sk_ioctl(sk, cmd, arg); /* If ioctl was processed, returns its value */ if (rc <= 0) return rc; /* Otherwise call the default handler */ return sock_ioctl_out(sk, cmd, arg); } EXPORT_SYMBOL(sk_ioctl); static int __init sock_struct_check(void) { CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_drops); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_peek_off); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_error_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_receive_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_backlog); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_ifindex); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_cookie); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvbuf); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_filter); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_wq); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_data_ready); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvlowat); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_err); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_socket); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_memcg); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_lock); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_reserved_mem); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_forward_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_tsflags); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_sndbuf); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_queued); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tsq_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_dst_pending_confirm); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_status); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_mark); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_route_caps); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_type); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_allocation); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_txhash); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_shift); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_use_task_frag); return 0; } core_initcall(sock_struct_check); |
| 526 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2005-2010 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: evm.h */ #ifndef __INTEGRITY_EVM_H #define __INTEGRITY_EVM_H #include <linux/xattr.h> #include <linux/security.h> #include "../integrity.h" #define EVM_INIT_HMAC 0x0001 #define EVM_INIT_X509 0x0002 #define EVM_ALLOW_METADATA_WRITES 0x0004 #define EVM_SETUP_COMPLETE 0x80000000 /* userland has signaled key load */ #define EVM_KEY_MASK (EVM_INIT_HMAC | EVM_INIT_X509) #define EVM_INIT_MASK (EVM_INIT_HMAC | EVM_INIT_X509 | EVM_SETUP_COMPLETE | \ EVM_ALLOW_METADATA_WRITES) struct xattr_list { struct list_head list; char *name; bool enabled; }; #define EVM_NEW_FILE 0x00000001 #define EVM_IMMUTABLE_DIGSIG 0x00000002 /* EVM integrity metadata associated with an inode */ struct evm_iint_cache { unsigned long flags; enum integrity_status evm_status:4; struct integrity_inode_attributes metadata_inode; }; extern struct lsm_blob_sizes evm_blob_sizes; static inline struct evm_iint_cache *evm_iint_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + evm_blob_sizes.lbs_inode; } extern int evm_initialized; #define EVM_ATTR_FSUUID 0x0001 extern int evm_hmac_attrs; /* List of EVM protected security xattrs */ extern struct list_head evm_config_xattrnames; struct evm_digest { struct ima_digest_data_hdr hdr; char digest[IMA_MAX_DIGEST_SIZE]; } __packed; int evm_protected_xattr(const char *req_xattr_name); int evm_init_key(void); int evm_update_evmxattr(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len); int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len, struct evm_digest *data, struct evm_iint_cache *iint); int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len, char type, struct evm_digest *data, struct evm_iint_cache *iint); int evm_init_hmac(struct inode *inode, const struct xattr *xattrs, char *hmac_val); int evm_init_secfs(void); #endif |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/magic.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsverity.h> #include <keys/system_keyring.h> #include <uapi/linux/fsverity.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM static char *ima_appraise_cmdline_default __initdata; core_param(ima_appraise, ima_appraise_cmdline_default, charp, 0); void __init ima_appraise_parse_cmdline(void) { const char *str = ima_appraise_cmdline_default; bool sb_state = arch_ima_get_secureboot(); int appraisal_state = ima_appraise; if (!str) return; if (strncmp(str, "off", 3) == 0) appraisal_state = 0; else if (strncmp(str, "log", 3) == 0) appraisal_state = IMA_APPRAISE_LOG; else if (strncmp(str, "fix", 3) == 0) appraisal_state = IMA_APPRAISE_FIX; else if (strncmp(str, "enforce", 7) == 0) appraisal_state = IMA_APPRAISE_ENFORCE; else pr_err("invalid \"%s\" appraise option", str); /* If appraisal state was changed, but secure boot is enabled, * keep its default */ if (sb_state) { if (!(appraisal_state & IMA_APPRAISE_ENFORCE)) pr_info("Secure boot enabled: ignoring ima_appraise=%s option", str); } else { ima_appraise = appraisal_state; } } #endif /* * is_ima_appraise_enabled - return appraise status * * Only return enabled, if not in ima_appraise="fix" or "log" modes. */ bool is_ima_appraise_enabled(void) { return ima_appraise & IMA_APPRAISE_ENFORCE; } /* * ima_must_appraise - set appraise flag * * Return 1 to appraise or hash */ int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { struct lsm_prop prop; if (!ima_appraise) return 0; security_current_getlsmprop_subj(&prop); return ima_match_policy(idmap, inode, current_cred(), &prop, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); } static int ima_fix_xattr(struct dentry *dentry, struct ima_iint_cache *iint) { int rc, offset; u8 algo = iint->ima_hash->algo; if (algo <= HASH_ALGO_SHA1) { offset = 1; iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST; } else { offset = 0; iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG; iint->ima_hash->xattr.ng.algo = algo; } rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, &iint->ima_hash->xattr.data[offset], (sizeof(iint->ima_hash->xattr) - offset) + iint->ima_hash->length, 0); return rc; } /* Return specific func appraised cached result */ enum integrity_status ima_get_cache_status(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: return iint->ima_mmap_status; case BPRM_CHECK: return iint->ima_bprm_status; case CREDS_CHECK: return iint->ima_creds_status; case FILE_CHECK: case POST_SETATTR: return iint->ima_file_status; case MODULE_CHECK ... MAX_CHECK - 1: default: return iint->ima_read_status; } } static void ima_set_cache_status(struct ima_iint_cache *iint, enum ima_hooks func, enum integrity_status status) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->ima_mmap_status = status; break; case BPRM_CHECK: iint->ima_bprm_status = status; break; case CREDS_CHECK: iint->ima_creds_status = status; break; case FILE_CHECK: case POST_SETATTR: iint->ima_file_status = status; break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->ima_read_status = status; break; } } static void ima_cache_flags(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED); break; case BPRM_CHECK: iint->flags |= (IMA_BPRM_APPRAISED | IMA_APPRAISED); break; case CREDS_CHECK: iint->flags |= (IMA_CREDS_APPRAISED | IMA_APPRAISED); break; case FILE_CHECK: case POST_SETATTR: iint->flags |= (IMA_FILE_APPRAISED | IMA_APPRAISED); break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->flags |= (IMA_READ_APPRAISED | IMA_APPRAISED); break; } } enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value, int xattr_len) { struct signature_v2_hdr *sig; enum hash_algo ret; if (!xattr_value || xattr_len < 2) /* return default hash algo */ return ima_hash_algo; switch (xattr_value->type) { case IMA_VERITY_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 3 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case EVM_IMA_XATTR_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 2 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ ret = xattr_value->data[0]; if (ret < HASH_ALGO__LAST) return ret; break; case IMA_XATTR_DIGEST: /* this is for backward compatibility */ if (xattr_len == 21) { unsigned int zero = 0; if (!memcmp(&xattr_value->data[16], &zero, 4)) return HASH_ALGO_MD5; else return HASH_ALGO_SHA1; } else if (xattr_len == 17) return HASH_ALGO_MD5; break; } /* return default hash algo */ return ima_hash_algo; } int ima_read_xattr(struct dentry *dentry, struct evm_ima_xattr_data **xattr_value, int xattr_len) { int ret; ret = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, (char **)xattr_value, xattr_len, GFP_NOFS); if (ret == -EOPNOTSUPP) ret = 0; return ret; } /* * calc_file_id_hash - calculate the hash of the ima_file_id struct data * @type: xattr type [enum evm_ima_xattr_type] * @algo: hash algorithm [enum hash_algo] * @digest: pointer to the digest to be hashed * @hash: (out) pointer to the hash * * IMA signature version 3 disambiguates the data that is signed by * indirectly signing the hash of the ima_file_id structure data. * * Signing the ima_file_id struct is currently only supported for * IMA_VERITY_DIGSIG type xattrs. * * Return 0 on success, error code otherwise. */ static int calc_file_id_hash(enum evm_ima_xattr_type type, enum hash_algo algo, const u8 *digest, struct ima_digest_data *hash) { struct ima_file_id file_id = { .hash_type = IMA_VERITY_DIGSIG, .hash_algorithm = algo}; unsigned int unused = HASH_MAX_DIGESTSIZE - hash_digest_size[algo]; if (type != IMA_VERITY_DIGSIG) return -EINVAL; memcpy(file_id.hash, digest, hash_digest_size[algo]); hash->algo = algo; hash->length = hash_digest_size[algo]; return ima_calc_buffer_hash(&file_id, sizeof(file_id) - unused, hash); } /* * xattr_verify - verify xattr digest or signature * * Verify whether the hash or signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint, struct evm_ima_xattr_data *xattr_value, int xattr_len, enum integrity_status *status, const char **cause) { struct ima_max_digest_data hash; struct signature_v2_hdr *sig; int rc = -EINVAL, hash_start = 0; int mask; switch (xattr_value->type) { case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ hash_start = 1; fallthrough; case IMA_XATTR_DIGEST: if (*status != INTEGRITY_PASS_IMMUTABLE) { if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) *cause = "verity-signature-required"; else *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } clear_bit(IMA_DIGSIG, &iint->atomic_flags); } else { set_bit(IMA_DIGSIG, &iint->atomic_flags); } if (xattr_len - sizeof(xattr_value->type) - hash_start >= iint->ima_hash->length) /* * xattr length may be longer. md5 hash in previous * version occupied 20 bytes in xattr, instead of 16 */ rc = memcmp(&xattr_value->data[hash_start], iint->ima_hash->digest, iint->ima_hash->length); else rc = -EINVAL; if (rc) { *cause = "invalid-hash"; *status = INTEGRITY_FAIL; break; } *status = INTEGRITY_PASS; break; case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); mask = IMA_DIGSIG_REQUIRED | IMA_VERITY_REQUIRED; if ((iint->flags & mask) == mask) { *cause = "verity-signature-required"; *status = INTEGRITY_FAIL; break; } sig = (typeof(sig))xattr_value; if (sig->version >= 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { *status = INTEGRITY_UNKNOWN; break; } if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; case IMA_VERITY_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); if (iint->flags & IMA_DIGSIG_REQUIRED) { if (!(iint->flags & IMA_VERITY_REQUIRED)) { *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } } sig = (typeof(sig))xattr_value; if (sig->version != 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = calc_file_id_hash(IMA_VERITY_DIGSIG, iint->ima_hash->algo, iint->ima_hash->digest, container_of(&hash.hdr, struct ima_digest_data, hdr)); if (rc) { *cause = "sigv3-hashing-error"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, hash.digest, hash.hdr.length); if (rc) { *cause = "invalid-verity-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; default: *status = INTEGRITY_UNKNOWN; *cause = "unknown-ima-data"; break; } return rc; } /* * modsig_verify - verify modsig signature * * Verify whether the signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int modsig_verify(enum ima_hooks func, const struct modsig *modsig, enum integrity_status *status, const char **cause) { int rc; rc = integrity_modsig_verify(INTEGRITY_KEYRING_IMA, modsig); if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_modsig_verify(INTEGRITY_KEYRING_PLATFORM, modsig); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } return rc; } /* * ima_check_blacklist - determine if the binary is blacklisted. * * Add the hash of the blacklisted binary to the measurement list, based * on policy. * * Returns -EPERM if the hash is blacklisted. */ int ima_check_blacklist(struct ima_iint_cache *iint, const struct modsig *modsig, int pcr) { enum hash_algo hash_algo; const u8 *digest = NULL; u32 digestsize = 0; int rc = 0; if (!(iint->flags & IMA_CHECK_BLACKLIST)) return 0; if (iint->flags & IMA_MODSIG_ALLOWED && modsig) { ima_get_modsig_digest(modsig, &hash_algo, &digest, &digestsize); rc = is_binary_blacklisted(digest, digestsize); } else if (iint->flags & IMA_DIGSIG_REQUIRED && iint->ima_hash) rc = is_binary_blacklisted(iint->ima_hash->digest, iint->ima_hash->length); if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) process_buffer_measurement(&nop_mnt_idmap, NULL, digest, digestsize, "blacklisted-hash", NONE, pcr, NULL, false, NULL, 0); return rc; } /* * ima_appraise_measurement - appraise file measurement * * Call evm_verifyxattr() to verify the integrity of 'security.ima'. * Assuming success, compare the xattr hash with the collected measurement. * * Return 0 on success, error code otherwise */ int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig) { static const char op[] = "appraise_data"; const char *cause = "unknown"; struct dentry *dentry = file_dentry(file); struct inode *inode = d_backing_inode(dentry); enum integrity_status status = INTEGRITY_UNKNOWN; int rc = xattr_len; bool try_modsig = iint->flags & IMA_MODSIG_ALLOWED && modsig; /* If not appraising a modsig, we need an xattr. */ if (!(inode->i_opflags & IOP_XATTR) && !try_modsig) return INTEGRITY_UNKNOWN; /* If reading the xattr failed and there's no modsig, error out. */ if (rc <= 0 && !try_modsig) { if (rc && rc != -ENODATA) goto out; if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) cause = "verity-signature-required"; else cause = "IMA-signature-required"; } else { cause = "missing-hash"; } status = INTEGRITY_NOLABEL; if (file->f_mode & FMODE_CREATED) iint->flags |= IMA_NEW_FILE; if ((iint->flags & IMA_NEW_FILE) && (!(iint->flags & IMA_DIGSIG_REQUIRED) || (inode->i_size == 0))) status = INTEGRITY_PASS; goto out; } status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc < 0 ? 0 : rc); switch (status) { case INTEGRITY_PASS: case INTEGRITY_PASS_IMMUTABLE: case INTEGRITY_UNKNOWN: break; case INTEGRITY_NOXATTRS: /* No EVM protected xattrs. */ /* It's fine not to have xattrs when using a modsig. */ if (try_modsig) break; fallthrough; case INTEGRITY_NOLABEL: /* No security.evm xattr. */ cause = "missing-HMAC"; goto out; case INTEGRITY_FAIL_IMMUTABLE: set_bit(IMA_DIGSIG, &iint->atomic_flags); cause = "invalid-fail-immutable"; goto out; case INTEGRITY_FAIL: /* Invalid HMAC/signature. */ cause = "invalid-HMAC"; goto out; default: WARN_ONCE(true, "Unexpected integrity status %d\n", status); } if (xattr_value) rc = xattr_verify(func, iint, xattr_value, xattr_len, &status, &cause); /* * If we have a modsig and either no imasig or the imasig's key isn't * known, then try verifying the modsig. */ if (try_modsig && (!xattr_value || xattr_value->type == IMA_XATTR_DIGEST_NG || rc == -ENOKEY)) rc = modsig_verify(func, modsig, &status, &cause); out: /* * File signatures on some filesystems can not be properly verified. * When such filesystems are mounted by an untrusted mounter or on a * system not willing to accept such a risk, fail the file signature * verification. */ if ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && ((inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) || (iint->flags & IMA_FAIL_UNVERIFIABLE_SIGS))) { status = INTEGRITY_FAIL; cause = "unverifiable-signature"; integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, op, cause, rc, 0); } else if (status != INTEGRITY_PASS) { /* Fix mode, but don't replace file signatures. */ if ((ima_appraise & IMA_APPRAISE_FIX) && !try_modsig && (!xattr_value || xattr_value->type != EVM_IMA_XATTR_DIGSIG)) { if (!ima_fix_xattr(dentry, iint)) status = INTEGRITY_PASS; } /* * Permit new files with file/EVM portable signatures, but * without data. */ if (inode->i_size == 0 && iint->flags & IMA_NEW_FILE && test_bit(IMA_DIGSIG, &iint->atomic_flags)) { status = INTEGRITY_PASS; } integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, op, cause, rc, 0); } else { ima_cache_flags(iint, func); } ima_set_cache_status(iint, func, status); return status; } /* * ima_update_xattr - update 'security.ima' hash value */ void ima_update_xattr(struct ima_iint_cache *iint, struct file *file) { struct dentry *dentry = file_dentry(file); int rc = 0; /* do not collect and update hash for digital signatures */ if (test_bit(IMA_DIGSIG, &iint->atomic_flags)) return; if ((iint->ima_file_status != INTEGRITY_PASS) && !(iint->flags & IMA_HASH)) return; rc = ima_collect_measurement(iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) return; inode_lock(file_inode(file)); ima_fix_xattr(dentry, iint); inode_unlock(file_inode(file)); } /** * ima_inode_post_setattr - reflect file metadata changes * @idmap: idmap of the mount the inode was found from * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * Changes to a dentry's metadata might result in needing to appraise. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { struct inode *inode = d_backing_inode(dentry); struct ima_iint_cache *iint; int action; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode) || !(inode->i_opflags & IOP_XATTR)) return; action = ima_must_appraise(idmap, inode, MAY_ACCESS, POST_SETATTR); iint = ima_iint_find(inode); if (iint) { set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags); if (!action) clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } } /* * ima_protect_xattr - protect 'security.ima' * * Ensure that not just anyone can modify or remove 'security.ima'. */ static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { if (strcmp(xattr_name, XATTR_NAME_IMA) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 1; } return 0; } static void ima_reset_appraise_flags(struct inode *inode, int digsig) { struct ima_iint_cache *iint; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; iint->measured_pcrs = 0; set_bit(IMA_CHANGE_XATTR, &iint->atomic_flags); if (digsig) set_bit(IMA_DIGSIG, &iint->atomic_flags); else clear_bit(IMA_DIGSIG, &iint->atomic_flags); } /** * validate_hash_algo() - Block setxattr with unsupported hash algorithms * @dentry: object of the setxattr() * @xattr_value: userland supplied xattr value * @xattr_value_len: length of xattr_value * * The xattr value is mapped to its hash algorithm, and this algorithm * must be built in the kernel for the setxattr to be allowed. * * Emit an audit message when the algorithm is invalid. * * Return: 0 on success, else an error. */ static int validate_hash_algo(struct dentry *dentry, const struct evm_ima_xattr_data *xattr_value, size_t xattr_value_len) { char *path = NULL, *pathbuf = NULL; enum hash_algo xattr_hash_algo; const char *errmsg = "unavailable-hash-algorithm"; unsigned int allowed_hashes; xattr_hash_algo = ima_get_hash_algo(xattr_value, xattr_value_len); allowed_hashes = atomic_read(&ima_setxattr_allowed_hash_algorithms); if (allowed_hashes) { /* success if the algorithm is allowed in the ima policy */ if (allowed_hashes & (1U << xattr_hash_algo)) return 0; /* * We use a different audit message when the hash algorithm * is denied by a policy rule, instead of not being built * in the kernel image */ errmsg = "denied-hash-algorithm"; } else { if (likely(xattr_hash_algo == ima_hash_algo)) return 0; /* allow any xattr using an algorithm built in the kernel */ if (crypto_has_alg(hash_algo_name[xattr_hash_algo], 0, 0)) return 0; } pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf) return -EACCES; path = dentry_path(dentry, pathbuf, PATH_MAX); integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path, "set_data", errmsg, -EACCES, 0); kfree(pathbuf); return -EACCES; } static int ima_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xvalue = xattr_value; int digsig = 0; int result; int err; result = ima_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); if (result == 1) { if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST)) return -EINVAL; err = validate_hash_algo(dentry, xvalue, xattr_value_len); if (err) return err; digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG); } else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) { digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG); } if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), digsig); if (result == 1) result = 0; } return result; } static int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (evm_revalidate_status(acl_name)) ima_reset_appraise_flags(d_backing_inode(dentry), 0); return 0; } static int ima_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { int result; result = ima_protect_xattr(dentry, xattr_name, NULL, 0); if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), 0); if (result == 1) result = 0; } return result; } static int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ima_inode_set_acl(idmap, dentry, acl_name, NULL); } static struct security_hook_list ima_appraise_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_post_setattr, ima_inode_post_setattr), LSM_HOOK_INIT(inode_setxattr, ima_inode_setxattr), LSM_HOOK_INIT(inode_set_acl, ima_inode_set_acl), LSM_HOOK_INIT(inode_removexattr, ima_inode_removexattr), LSM_HOOK_INIT(inode_remove_acl, ima_inode_remove_acl), }; void __init init_ima_appraise_lsm(const struct lsm_id *lsmid) { security_add_hooks(ima_appraise_hooks, ARRAY_SIZE(ima_appraise_hooks), lsmid); } |
| 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 | // 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; 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); synchronize_rcu(); 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); } synchronize_rcu(); kfree(port); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/gfp_types.h> #include <linux/mmzone.h> #include <linux/topology.h> #include <linux/alloc_tag.h> #include <linux/sched.h> struct vm_area_struct; struct mempolicy; /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * gfp flag masking for nested internal allocations. * * For code that needs to do allocations inside the public allocation API (e.g. * memory allocation tracking code) the allocations need to obey the caller * allocation context constrains to prevent allocation context mismatches (e.g. * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock * situations. * * It is also assumed that these nested allocations are for internal kernel * object storage purposes only and are not going to be used for DMA, etc. Hence * we strip out all the zone information and leave just the context information * intact. * * Further, internal allocations must fail before the higher level allocation * can fail, so we must make them fail faster and fail silently. We also don't * want them to deplete emergency reserves. Hence nested allocations must be * prepared for these allocations to fail. */ static inline gfp_t gfp_nested_mask(gfp_t flags) { return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the case of non-NUMA systems the NODE_DATA() gets optimized to * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct list_head *page_list, struct page **page_array); #define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); #define alloc_pages_bulk_array_mempolicy(...) \ alloc_hooks(alloc_pages_bulk_array_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ #define alloc_pages_bulk_list(_gfp, _nr_pages, _list) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL) #define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, NULL, _page_array) static inline unsigned long alloc_pages_bulk_array_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, NULL, page_array); } #define alloc_pages_bulk_array_node(...) \ alloc_hooks(alloc_pages_bulk_array_node_noprof(__VA_ARGS__)) static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) return; if (node_online(this_node)) return; pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); dump_stack(); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } #define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) static inline struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); return __folio_alloc_noprof(gfp, order, nid, NULL); } #define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node_noprof(nid, gfp_mask, order); } #define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) #ifdef CONFIG_NUMA struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr); #else static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { return alloc_pages_noprof(gfp, order); } static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node_noprof(gfp, order, numa_node_id()); } static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { return folio_alloc_noprof(gfp, order); } #define vma_alloc_folio_noprof(gfp, order, vma, addr) \ folio_alloc_noprof(gfp, order) #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) #define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) #define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) #define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) #define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr); return &folio->page; } #define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); #define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); #define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); #define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) void free_pages_exact(void *virt, size_t size); __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define alloc_pages_exact_nid(...) \ alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init_cpuhp(void); int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); void setup_pcp_cacheinfo(unsigned int cpu); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); static inline bool gfp_has_io_fs(gfp_t gfp) { return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS); } /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); #define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); #ifdef CONFIG_CONTIG_ALLOC static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, int nid, nodemask_t *node) { struct page *page; if (WARN_ON(!order || !(gfp & __GFP_COMP))) return NULL; page = alloc_contig_pages_noprof(1 << order, gfp, nid, node); return page ? page_folio(page) : NULL; } #else static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, int nid, nodemask_t *node) { return NULL; } #endif /* This should be paired with folio_put() rather than free_contig_range(). */ #define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) #endif /* __LINUX_GFP_H */ |
| 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 | // 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(struct sk_buff *skb, struct net_device *dev) { u8 *skb_orig_data = skb->data; int skb_orig_len = skb->len; 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; skb_push(skb, skb->data - skb_mac_header(skb)); vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); if (skb_orig_data != skb->data) { skb->data = skb_orig_data; skb->len = skb_orig_len; } if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) { __be16 proto = skb->protocol; if (unlikely(eth_type_vlan(proto))) { u8 *skb_orig_data = skb->data; int skb_orig_len = skb->len; skb_push(skb, skb->data - skb_mac_header(skb)); proto = __vlan_get_protocol(skb, proto, NULL); if (skb_orig_data != skb->data) { skb->data = skb_orig_data; skb->len = skb_orig_len; } } return proto; } static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_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 = from_timer(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 = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_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 = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_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); sockc.mark = READ_ONCE(sk->sk_mark); 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 = READ_ONCE(sk->sk_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 packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { packet_dev_mc(dev, ml, -1); *mlp = ml->next; kfree(ml); } 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; 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 sock *sk; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); 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); 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(); 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); |
| 648 648 648 644 649 645 646 644 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/memblock.h> #include <linux/page_ext.h> #include <linux/memory.h> #include <linux/vmalloc.h> #include <linux/kmemleak.h> #include <linux/page_owner.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate.h> #include <linux/pgalloc_tag.h> /* * struct page extension * * This is the feature to manage memory for extended data per page. * * Until now, we must modify struct page itself to store extra data per page. * This requires rebuilding the kernel and it is really time consuming process. * And, sometimes, rebuild is impossible due to third party module dependency. * At last, enlarging struct page could cause un-wanted system behaviour change. * * This feature is intended to overcome above mentioned problems. This feature * allocates memory for extended data per page in certain place rather than * the struct page itself. This memory can be accessed by the accessor * functions provided by this code. During the boot process, it checks whether * allocation of huge chunk of memory is needed or not. If not, it avoids * allocating memory at all. With this advantage, we can include this feature * into the kernel in default and can avoid rebuild and solve related problems. * * To help these things to work well, there are two callbacks for clients. One * is the need callback which is mandatory if user wants to avoid useless * memory allocation at boot-time. The other is optional, init callback, which * is used to do proper initialization after memory is allocated. * * The need callback is used to decide whether extended memory allocation is * needed or not. Sometimes users want to deactivate some features in this * boot and extra memory would be unnecessary. In this case, to avoid * allocating huge chunk of memory, each clients represent their need of * extra memory through the need callback. If one of the need callbacks * returns true, it means that someone needs extra memory so that * page extension core should allocates memory for page extension. If * none of need callbacks return true, memory isn't needed at all in this boot * and page extension core can skip to allocate memory. As result, * none of memory is wasted. * * When need callback returns true, page_ext checks if there is a request for * extra memory through size in struct page_ext_operations. If it is non-zero, * extra space is allocated for each page_ext entry and offset is returned to * user through offset in struct page_ext_operations. * * The init callback is used to do proper initialization after page extension * is completely initialized. In sparse memory system, extra memory is * allocated some time later than memmap is allocated. In other words, lifetime * of memory for page extension isn't same with memmap for struct page. * Therefore, clients can't store extra data until page extension is * initialized, even if pages are allocated and used freely. This could * cause inadequate state of extra data per page, so, to prevent it, client * can utilize this callback to initialize the state of it correctly. */ #ifdef CONFIG_SPARSEMEM #define PAGE_EXT_INVALID (0x1) #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) static bool need_page_idle(void) { return true; } static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, .need_shared_flags = true, }; #endif static struct page_ext_operations *page_ext_ops[] __initdata = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif #ifdef CONFIG_MEM_ALLOC_PROFILING &page_alloc_tagging_ops, #endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif }; unsigned long page_ext_size; static unsigned long total_usage; #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG /* * To ensure correct allocation tagging for pages, page_ext should be available * before the first page allocation. Otherwise early task stacks will be * allocated before page_ext initialization and missing tags will be flagged. */ bool early_page_ext __meminitdata = true; #else bool early_page_ext __meminitdata; #endif static int __init setup_early_page_ext(char *str) { early_page_ext = true; return 0; } early_param("early_page_ext", setup_early_page_ext); static bool __init invoke_need_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); bool need = false; for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { if (page_ext_ops[i]->need_shared_flags) { page_ext_size = sizeof(struct page_ext); break; } } } for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { page_ext_ops[i]->offset = page_ext_size; page_ext_size += page_ext_ops[i]->size; need = true; } } return need; } static void __init invoke_init_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); for (i = 0; i < entries; i++) { if (page_ext_ops[i]->init) page_ext_ops[i]->init(); } } static inline struct page_ext *get_entry(void *base, unsigned long index) { return base + page_ext_size * index; } #ifndef CONFIG_SPARSEMEM void __init page_ext_init_flatmem_late(void) { invoke_init_callbacks(); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { pgdat->node_page_ext = NULL; } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); unsigned long index; struct page_ext *base; WARN_ON_ONCE(!rcu_read_lock_held()); base = NODE_DATA(page_to_nid(page))->node_page_ext; /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (unlikely(!base)) return NULL; index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); return get_entry(base, index); } static int __init alloc_node_page_ext(int nid) { struct page_ext *base; unsigned long table_size; unsigned long nr_pages; nr_pages = NODE_DATA(nid)->node_spanned_pages; if (!nr_pages) return 0; /* * Need extra space if node range is not aligned with * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm * checks buddy's status, range could be out of exact node range. */ if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) || !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } void __init page_ext_init_flatmem(void) { int nid, fail; if (!invoke_need_callbacks()) return; for_each_online_node(nid) { fail = alloc_node_page_ext(nid); if (fail) goto fail; } pr_info("allocated %ld bytes of page_ext\n", total_usage); return; fail: pr_crit("allocation of page_ext failed.\n"); panic("Out of memory"); } #else /* CONFIG_SPARSEMEM */ static bool page_ext_invalid(struct page_ext *page_ext) { return !page_ext || (((unsigned long)page_ext & PAGE_EXT_INVALID) == PAGE_EXT_INVALID); } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); struct page_ext *page_ext = READ_ONCE(section->page_ext); WARN_ON_ONCE(!rcu_read_lock_held()); /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (page_ext_invalid(page_ext)) return NULL; return get_entry(page_ext, pfn); } static void *__meminit alloc_page_ext(size_t size, int nid) { gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN; void *addr = NULL; addr = alloc_pages_exact_nid(nid, size, flags); if (addr) kmemleak_alloc(addr, size, 1, flags); else addr = vzalloc_node(size, nid); if (addr) memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } static int __meminit init_section_page_ext(unsigned long pfn, int nid) { struct mem_section *section; struct page_ext *base; unsigned long table_size; section = __pfn_to_section(pfn); if (section->page_ext) return 0; table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* * The value stored in section->page_ext is (base - pfn) * and it does not point to the memory block allocated above, * causing kmemleak false positives. */ kmemleak_not_leak(base); if (!base) { pr_err("page ext allocation failure\n"); return -ENOMEM; } /* * The passed "pfn" may not be aligned to SECTION. For the calculation * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } static void free_page_ext(void *addr) { size_t table_size; struct page *page; table_size = page_ext_size * PAGES_PER_SECTION; memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { vfree(addr); } else { page = virt_to_page(addr); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } } static void __free_page_ext(unsigned long pfn) { struct mem_section *ms; struct page_ext *base; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; base = READ_ONCE(ms->page_ext); /* * page_ext here can be valid while doing the roll back * operation in online_page_ext(). */ if (page_ext_invalid(base)) base = (void *)base - PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, NULL); base = get_entry(base, pfn); free_page_ext(base); } static void __invalidate_page_ext(unsigned long pfn) { struct mem_section *ms; void *val; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; val = (void *)ms->page_ext + PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, val); } static int __meminit online_page_ext(unsigned long start_pfn, unsigned long nr_pages, int nid) { unsigned long start, end, pfn; int fail = 0; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); if (nid == NUMA_NO_NODE) { /* * In this case, "nid" already exists and contains valid memory. * "start_pfn" passed to us is a pfn which is an arg for * online__pages(), and start_pfn should exist. */ nid = pfn_to_nid(start_pfn); VM_BUG_ON(!node_online(nid)); } for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) fail = init_section_page_ext(pfn, nid); if (!fail) return 0; /* rollback */ end = pfn - PAGES_PER_SECTION; for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); return -ENOMEM; } static void __meminit offline_page_ext(unsigned long start_pfn, unsigned long nr_pages) { unsigned long start, end, pfn; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); /* * Freeing of page_ext is done in 3 steps to avoid * use-after-free of it: * 1) Traverse all the sections and mark their page_ext * as invalid. * 2) Wait for all the existing users of page_ext who * started before invalidation to finish. * 3) Free the page_ext. */ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __invalidate_page_ext(pfn); synchronize_rcu(); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); } static int __meminit page_ext_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; int ret = 0; switch (action) { case MEM_GOING_ONLINE: ret = online_page_ext(mn->start_pfn, mn->nr_pages, mn->status_change_nid); break; case MEM_OFFLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_CANCEL_ONLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_GOING_OFFLINE: break; case MEM_ONLINE: case MEM_CANCEL_OFFLINE: break; } return notifier_from_errno(ret); } void __init page_ext_init(void) { unsigned long pfn; int nid; if (!invoke_need_callbacks()) return; for_each_node_state(nid, N_MEMORY) { unsigned long start_pfn, end_pfn; start_pfn = node_start_pfn(nid); end_pfn = node_end_pfn(nid); /* * start_pfn and end_pfn may not be aligned to SECTION and the * page->flags of out of node pages are not initialized. So we * scan [start_pfn, the biggest section's pfn < end_pfn) here. */ for (pfn = start_pfn; pfn < end_pfn; pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { if (!pfn_valid(pfn)) continue; /* * Nodes's pfns can be overlapping. * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... */ if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; cond_resched(); } } hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI); pr_info("allocated %ld bytes of page_ext\n", total_usage); invoke_init_callbacks(); return; oom: panic("Out of memory"); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { } #endif /** * page_ext_get() - Get the extended information for a page. * @page: The page we're interested in. * * Ensures that the page_ext will remain valid until page_ext_put() * is called. * * Return: NULL if no page_ext exists for this page. * Context: Any context. Caller may not sleep until they have called * page_ext_put(). */ struct page_ext *page_ext_get(const struct page *page) { struct page_ext *page_ext; rcu_read_lock(); page_ext = lookup_page_ext(page); if (!page_ext) { rcu_read_unlock(); return NULL; } return page_ext; } /** * page_ext_put() - Working with page extended information is done. * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. * * Return: None. * Context: Any context with corresponding page_ext_get() is called. */ void page_ext_put(struct page_ext *page_ext) { if (unlikely(!page_ext)) return; rcu_read_unlock(); } |
| 102 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_MMU_H #define __ASM_MMU_H #include <asm/cputype.h> #define MMCF_AARCH32 0x1 /* mm context flag for AArch32 executables */ #define USER_ASID_BIT 48 #define USER_ASID_FLAG (UL(1) << USER_ASID_BIT) #define TTBR_ASID_MASK (UL(0xffff) << 48) #ifndef __ASSEMBLY__ #include <linux/refcount.h> #include <asm/cpufeature.h> typedef struct { atomic64_t id; #ifdef CONFIG_COMPAT void *sigpage; #endif refcount_t pinned; void *vdso; unsigned long flags; u8 pkey_allocation_map; } mm_context_t; /* * We use atomic64_read() here because the ASID for an 'mm_struct' can * be reallocated when scheduling one of its threads following a * rollover event (see new_context() and flush_context()). In this case, * a concurrent TLBI (e.g. via try_to_unmap_one() and ptep_clear_flush()) * may use a stale ASID. This is fine in principle as the new ASID is * guaranteed to be clean in the TLB, but the TLBI routines have to take * care to handle the following race: * * CPU 0 CPU 1 CPU 2 * * // ptep_clear_flush(mm) * xchg_relaxed(pte, 0) * DSB ISHST * old = ASID(mm) * | <rollover> * | new = new_context(mm) * \-----------------> atomic_set(mm->context.id, new) * cpu_switch_mm(mm) * // Hardware walk of pte using new ASID * TLBI(old) * * In this scenario, the barrier on CPU 0 and the dependency on CPU 1 * ensure that the page-table walker on CPU 1 *must* see the invalid PTE * written by CPU 0. */ #define ASID(mm) (atomic64_read(&(mm)->context.id) & 0xffff) static inline bool arm64_kernel_unmapped_at_el0(void) { return alternative_has_cap_unlikely(ARM64_UNMAP_KERNEL_AT_EL0); } extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only); extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); /* * This check is triggered during the early boot before the cpufeature * is initialised. Checking the status on the local CPU allows the boot * CPU to detect the need for non-global mappings and thus avoiding a * pagetable re-write after all the CPUs are booted. This check will be * anyway run on individual CPUs, allowing us to get the consistent * state once the SMP CPUs are up and thus make the switch to non-global * mappings if required. */ static inline bool kaslr_requires_kpti(void) { /* * E0PD does a similar job to KPTI so can be used instead * where available. */ if (IS_ENABLED(CONFIG_ARM64_E0PD)) { u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); if (cpuid_feature_extract_unsigned_field(mmfr2, ID_AA64MMFR2_EL1_E0PD_SHIFT)) return false; } /* * Systems affected by Cavium erratum 24756 are incompatible * with KPTI. */ if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { extern const struct midr_range cavium_erratum_27456_cpus[]; if (is_midr_in_range_list(read_cpuid_id(), cavium_erratum_27456_cpus)) return false; } return true; } #define INIT_MM_CONTEXT(name) \ .pgd = swapper_pg_dir, #endif /* !__ASSEMBLY__ */ #endif |
| 217 3 217 214 214 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * * Copyright (C) 1997 Andrew Main <zefram@fysh.org> * * Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org> * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> int file_caps_enabled = 1; static int __init file_caps_disable(char *str) { file_caps_enabled = 0; return 1; } __setup("no_file_caps", file_caps_disable); #ifdef CONFIG_MULTIUSER /* * More recent versions of libcap are available from: * * http://www.kernel.org/pub/linux/libs/security/linux-privs/ */ static void warn_legacy_capability_use(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", get_task_comm(name, current)); } /* * Version 2 capabilities worked fine, but the linux/capability.h file * that accompanied their introduction encouraged their use without * the necessary user-space source code changes. As such, we have * created a version 3 with equivalent functionality to version 2, but * with a header change to protect legacy source code from using * version 2 when it wanted to use version 1. If your system has code * that trips the following warning, it is using version 2 specific * capabilities and may be doing so insecurely. * * The remedy is to either upgrade your version of libcap (to 2.10+, * if the application is linked against it), or recompile your * application with modern kernel headers and this warning will go * away. */ static void warn_deprecated_v2(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", get_task_comm(name, current)); } /* * Version check. Return the number of u32s in each capability flag * array, or a negative value on error. */ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) { __u32 version; if (get_user(version, &header->version)) return -EFAULT; switch (version) { case _LINUX_CAPABILITY_VERSION_1: warn_legacy_capability_use(); *tocopy = _LINUX_CAPABILITY_U32S_1; break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; default: if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; } return 0; } /* * The only thing that can change the capabilities of the current * process is the current process. As such, we can't be in this code * at the same time as we are in the process of setting capabilities * in this process. The net result is that we can limit our use of * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) { int ret; if (pid && (pid != task_pid_vnr(current))) { const struct task_struct *target; rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) ret = -ESRCH; else ret = security_capget(target, pEp, pIp, pPp); rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and * target pid data * @dataptr: pointer to struct that contains the effective, permitted, * and inheritable capabilities that are returned * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) { int ret = 0; pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; struct __user_cap_data_struct kdata[2]; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; if (pid < 0) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); if (ret) return ret; /* * Annoying legacy format with 64-bit capabilities exposed * as two sets of 32-bit fields, so we need to split the * capability values up. */ kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32; kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32; kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32; /* * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability * bits when they perform a: capget/modify/capset * sequence. * * This behavior is considered fail-safe * behavior. Upgrading the application to a newer * version of libcap will enable access to the newer * capabilities. * * An alternative would be to return an error here * (-ERANGE), but that causes legacy applications to * unexpectedly fail; the capget/modify/capset aborts * before modification is attempted and the application * fails. */ if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0]))) return -EFAULT; return 0; } static kernel_cap_t mk_kernel_cap(u32 low, u32 high) { return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK }; } /** * sys_capset - set capabilities for a process or (*) a group of processes * @header: pointer to struct that contains capability version and * target pid data * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * * Set capabilities for the current process only. The ability to any other * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * * I: any raised capabilities must be a subset of the old permitted * P: any raised capabilities must be a subset of the old permitted * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[2] = { { 0, }, }; unsigned tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; pid_t pid; ret = cap_validate_magic(header, &tocopy); if (ret != 0) return ret; if (get_user(pid, &header->pid)) return -EFAULT; /* may only affect current now */ if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; copybytes = tocopy * sizeof(struct __user_cap_data_struct); if (copybytes > sizeof(kdata)) return -EFAULT; if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective); permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted); inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable); new = prepare_creds(); if (!new) return -ENOMEM; ret = security_capset(new, current_cred(), &effective, &inheritable, &permitted); if (ret < 0) goto error; audit_log_capset(new, current_cred()); return commit_creds(new); error: abort_creds(new); return ret; } /** * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); } /** * has_capability - Does a task have a capability in init_user_ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the initial user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability(struct task_struct *t, int cap) { return has_ns_capability(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability); /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) * in a specific user ns. * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } /** * has_capability_noaudit - Does a task have a capability (unaudited) in the * initial user ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to init_user_ns, false if not. Don't write an * audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability_noaudit); static bool ns_capable_common(struct user_namespace *ns, int cap, unsigned int opts) { int capable; if (unlikely(!cap_valid(cap))) { pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; } return false; } /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); /** * ns_capable_noaudit - Determine if the current task has a superior capability * (unaudited) in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_setid(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_INSETID); } EXPORT_SYMBOL(ns_capable_setid); /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool capable(int cap) { return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); #endif /* CONFIG_MULTIUSER */ /** * file_ns_capable - Determine if the file's opener had a capability in effect * @file: The file we want to check * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if task that opened the file had a capability in effect * when the file was opened. * * This does not set PF_SUPERPRIV because the caller may not * actually be privileged. */ bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { if (WARN_ON_ONCE(!cap_valid(cap))) return false; if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; } EXPORT_SYMBOL(file_ns_capable); /** * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? * @ns: The user namespace in question * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, struct mnt_idmap *idmap, const struct inode *inode) { return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) && vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode)); } /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * @cap: The capability in question * * Return true if the current task has the given capability targeted at * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, idmap, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); /** * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace * @tsk: The task that may be ptraced * @ns: The user namespace to search for CAP_SYS_PTRACE in * * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE * in the specified user namespace. */ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } |
| 537 406 511 406 406 512 511 129 435 261 261 261 435 434 21 422 198 2 261 261 260 421 224 227 53 389 5 5 185 293 293 294 9 284 22 22 22 22 22 22 22 12 185 406 160 18 13 184 185 224 225 130 494 493 129 129 21 21 21 21 21 22 8 8 406 21 406 406 406 406 405 5 5 5 5 30 59 59 59 30 623 887 892 728 377 926 44 2 3 885 345 259 64 58 70 147 342 344 345 147 231 204 185 185 185 374 263 263 435 436 294 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 | // SPDX-License-Identifier: GPL-2.0-only /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux hook function implementations. * * Authors: Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com> * Eric Paris <eparis@redhat.com> * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * <dgoeddel@trustedcs.com> * Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> * Copyright (C) 2007 Hitachi Software Engineering Co., Ltd. * Yuichi Nakamura <ynakam@hitachisoft.jp> * Copyright (C) 2016 Mellanox Technologies */ #include <linux/init.h> #include <linux/kd.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/lsm_hooks.h> #include <linux/xattr.h> #include <linux/capability.h> #include <linux/unistd.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/swap.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/dcache.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/inet_connection_sock.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/netdevice.h> /* for network interface checks */ #include <net/netlink.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/structs.h> #include <linux/quota.h> #include <linux/un.h> /* for Unix socket types */ #include <net/af_unix.h> /* for Unix socket types */ #include <linux/parser.h> #include <linux/nfs_mount.h> #include <net/ipv6.h> #include <linux/hugetlb.h> #include <linux/personality.h> #include <linux/audit.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/posix-timers.h> #include <linux/syslog.h> #include <linux/user_namespace.h> #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> #include <uapi/linux/shm.h> #include <linux/bpf.h> #include <linux/kernfs.h> #include <linux/stringhash.h> /* for hashlen_string() */ #include <uapi/linux/mount.h> #include <linux/fsnotify.h> #include <linux/fanotify.h> #include <linux/io_uring/cmd.h> #include <uapi/linux/lsm.h> #include "avc.h" #include "objsec.h" #include "netif.h" #include "netnode.h" #include "netport.h" #include "ibpkey.h" #include "xfrm.h" #include "netlabel.h" #include "audit.h" #include "avc_ss.h" #define SELINUX_INODE_INIT_XATTRS 1 struct selinux_state selinux_state; /* SECMARK reference count */ static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static int selinux_enforcing_boot __initdata; static int __init enforcing_setup(char *str) { unsigned long enforcing; if (!kstrtoul(str, 0, &enforcing)) selinux_enforcing_boot = enforcing ? 1 : 0; return 1; } __setup("enforcing=", enforcing_setup); #else #define selinux_enforcing_boot 1 #endif int selinux_enabled_boot __initdata = 1; #ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM static int __init selinux_enabled_setup(char *str) { unsigned long enabled; if (!kstrtoul(str, 0, &enabled)) selinux_enabled_boot = enabled ? 1 : 0; return 1; } __setup("selinux=", selinux_enabled_setup); #endif static int __init checkreqprot_setup(char *str) { unsigned long checkreqprot; if (!kstrtoul(str, 0, &checkreqprot)) { if (checkreqprot) pr_err("SELinux: checkreqprot set to 1 via kernel parameter. This is no longer supported.\n"); } return 1; } __setup("checkreqprot=", checkreqprot_setup); /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled * * Description: * This function checks the SECMARK reference counter to see if any SECMARK * targets are currently configured, if the reference counter is greater than * zero SECMARK is considered to be enabled. Returns true (1) if SECMARK is * enabled, false (0) if SECMARK is disabled. If the always_check_network * policy capability is enabled, SECMARK is always considered enabled. * */ static int selinux_secmark_enabled(void) { return (selinux_policycap_alwaysnetwork() || atomic_read(&selinux_secmark_refcount)); } /** * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled * * Description: * This function checks if NetLabel or labeled IPSEC is enabled. Returns true * (1) if any are enabled or false (0) if neither are enabled. If the * always_check_network policy capability is enabled, peer labeling * is always considered enabled. * */ static int selinux_peerlbl_enabled(void) { return (selinux_policycap_alwaysnetwork() || netlbl_enabled() || selinux_xfrm_enabled()); } static int selinux_netcache_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_netif_flush(); sel_netnode_flush(); sel_netport_flush(); synchronize_net(); } return 0; } static int selinux_lsm_notifier_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_ib_pkey_flush(); call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL); } return 0; } /* * initialise the security for the init task */ static void cred_init_security(void) { struct task_security_struct *tsec; tsec = selinux_cred(unrcu_pointer(current->real_cred)); tsec->osid = tsec->sid = SECINITSID_KERNEL; } /* * get the security ID of a set of credentials */ static inline u32 cred_sid(const struct cred *cred) { const struct task_security_struct *tsec; tsec = selinux_cred(cred); return tsec->sid; } static void __ad_net_init(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, struct sock *sk, u16 family) { ad->type = LSM_AUDIT_DATA_NET; ad->u.net = net; net->netif = ifindex; net->sk = sk; net->family = family; } static void ad_net_init_from_sk(struct common_audit_data *ad, struct lsm_network_audit *net, struct sock *sk) { __ad_net_init(ad, net, 0, sk, 0); } static void ad_net_init_from_iif(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, u16 family) { __ad_net_init(ad, net, ifindex, NULL, family); } /* * get the objective security ID of a task */ static inline u32 task_sid_obj(const struct task_struct *task) { u32 sid; rcu_read_lock(); sid = cred_sid(__task_cred(task)); rcu_read_unlock(); return sid; } static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry); /* * Try reloading inode security labels that have been marked as invalid. The * @may_sleep parameter indicates when sleeping and thus reloading labels is * allowed; when set to false, returns -ECHILD when the label is * invalid. The @dentry parameter should be set to a dentry of the inode. */ static int __inode_security_revalidate(struct inode *inode, struct dentry *dentry, bool may_sleep) { struct inode_security_struct *isec = selinux_inode(inode); might_sleep_if(may_sleep); /* * The check of isec->initialized below is racy but * inode_doinit_with_dentry() will recheck with * isec->lock held. */ if (selinux_initialized() && data_race(isec->initialized != LABEL_INITIALIZED)) { if (!may_sleep) return -ECHILD; /* * Try reloading the inode security label. This will fail if * @opt_dentry is NULL and no dentry for this inode can be * found; in that case, continue using the old label. */ inode_doinit_with_dentry(inode, dentry); } return 0; } static struct inode_security_struct *inode_security_novalidate(struct inode *inode) { return selinux_inode(inode); } static struct inode_security_struct *inode_security_rcu(struct inode *inode, bool rcu) { int error; error = __inode_security_revalidate(inode, NULL, !rcu); if (error) return ERR_PTR(error); return selinux_inode(inode); } /* * Get the security label of an inode. */ static struct inode_security_struct *inode_security(struct inode *inode) { __inode_security_revalidate(inode, NULL, true); return selinux_inode(inode); } static struct inode_security_struct *backing_inode_security_novalidate(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); return selinux_inode(inode); } /* * Get the security label of a dentry's backing inode. */ static struct inode_security_struct *backing_inode_security(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); __inode_security_revalidate(inode, dentry, true); return selinux_inode(inode); } static void inode_free_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); struct superblock_security_struct *sbsec; if (!isec) return; sbsec = selinux_superblock(inode->i_sb); /* * As not all inode security structures are in a list, we check for * empty list outside of the lock to make sure that we won't waste * time taking a lock doing nothing. * * The list_del_init() function can be safely called more than once. * It should not be possible for this function to be called with * concurrent list_add(), but for better safety against future changes * in the code, we use list_empty_careful() here. */ if (!list_empty_careful(&isec->list)) { spin_lock(&sbsec->isec_lock); list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); } } struct selinux_mnt_opts { u32 fscontext_sid; u32 context_sid; u32 rootcontext_sid; u32 defcontext_sid; }; static void selinux_free_mnt_opts(void *mnt_opts) { kfree(mnt_opts); } enum { Opt_error = -1, Opt_context = 0, Opt_defcontext = 1, Opt_fscontext = 2, Opt_rootcontext = 3, Opt_seclabel = 4, }; #define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg} static const struct { const char *name; int len; int opt; bool has_arg; } tokens[] = { A(context, true), A(fscontext, true), A(defcontext, true), A(rootcontext, true), A(seclabel, false), }; #undef A static int match_opt_prefix(char *s, int l, char **arg) { int i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { size_t len = tokens[i].len; if (len > l || memcmp(s, tokens[i].name, len)) continue; if (tokens[i].has_arg) { if (len == l || s[len] != '=') continue; *arg = s + len + 1; } else if (len != l) continue; return tokens[i].opt; } return Opt_error; } #define SEL_MOUNT_FAIL_MSG "SELinux: duplicate or incompatible mount options\n" static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(tsec->sid, sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, NULL); return rc; } static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, NULL); return rc; } static int selinux_is_genfs_special_handling(struct super_block *sb) { /* Special handling. Genfs but also in-core setxattr handler */ return !strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "rootfs") || (selinux_policycap_cgroupseclabel() && (!strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2"))); } static int selinux_is_sblabel_mnt(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * IMPORTANT: Double-check logic in this function when adding a new * SECURITY_FS_USE_* definition! */ BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7); switch (sbsec->behavior) { case SECURITY_FS_USE_XATTR: case SECURITY_FS_USE_TRANS: case SECURITY_FS_USE_TASK: case SECURITY_FS_USE_NATIVE: return 1; case SECURITY_FS_USE_GENFS: return selinux_is_genfs_special_handling(sb); /* Never allow relabeling on context mounts */ case SECURITY_FS_USE_MNTPOINT: case SECURITY_FS_USE_NONE: default: return 0; } } static int sb_check_xattr_support(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); u32 sid; int rc; /* * Make sure that the xattr handler exists and that no * error other than -ENODATA is returned by getxattr on * the root directory. -ENODATA is ok, as this may be * the first boot of the SELinux kernel before we have * assigned xattr values to the filesystem. */ if (!(root_inode->i_opflags & IOP_XATTR)) { pr_warn("SELinux: (dev %s, type %s) has no xattr support\n", sb->s_id, sb->s_type->name); goto fallback; } rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0 && rc != -ENODATA) { if (rc == -EOPNOTSUPP) { pr_warn("SELinux: (dev %s, type %s) has no security xattr handler\n", sb->s_id, sb->s_type->name); goto fallback; } else { pr_warn("SELinux: (dev %s, type %s) getxattr errno %d\n", sb->s_id, sb->s_type->name, -rc); return rc; } } return 0; fallback: /* No xattr support - try to fallback to genfs if possible. */ rc = security_genfs_sid(sb->s_type->name, "/", SECCLASS_DIR, &sid); if (rc) return -EOPNOTSUPP; pr_warn("SELinux: (dev %s, type %s) falling back to genfs\n", sb->s_id, sb->s_type->name); sbsec->behavior = SECURITY_FS_USE_GENFS; sbsec->sid = sid; return 0; } static int sb_finish_set_opts(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); int rc = 0; if (sbsec->behavior == SECURITY_FS_USE_XATTR) { rc = sb_check_xattr_support(sb); if (rc) return rc; } sbsec->flags |= SE_SBINITIALIZED; /* * Explicitly set or clear SBLABEL_MNT. It's not sufficient to simply * leave the flag untouched because sb_clone_mnt_opts might be handing * us a superblock that needs the flag to be cleared. */ if (selinux_is_sblabel_mnt(sb)) sbsec->flags |= SBLABEL_MNT; else sbsec->flags &= ~SBLABEL_MNT; /* Initialize the root inode. */ rc = inode_doinit_with_dentry(root_inode, root); /* Initialize any other inodes associated with the superblock, e.g. inodes created prior to initial policy load or inodes created during get_sb by a pseudo filesystem that directly populates itself. */ spin_lock(&sbsec->isec_lock); while (!list_empty(&sbsec->isec_head)) { struct inode_security_struct *isec = list_first_entry(&sbsec->isec_head, struct inode_security_struct, list); struct inode *inode = isec->inode; list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { if (!IS_PRIVATE(inode)) inode_doinit_with_dentry(inode, NULL); iput(inode); } spin_lock(&sbsec->isec_lock); } spin_unlock(&sbsec->isec_lock); return rc; } static int bad_option(struct superblock_security_struct *sbsec, char flag, u32 old_sid, u32 new_sid) { char mnt_flags = sbsec->flags & SE_MNTMASK; /* check if the old mount command had the same options */ if (sbsec->flags & SE_SBINITIALIZED) if (!(sbsec->flags & flag) || (old_sid != new_sid)) return 1; /* check if we were passed the same options twice, * aka someone passed context=a,context=b */ if (!(sbsec->flags & SE_SBINITIALIZED)) if (mnt_flags & flag) return 1; return 0; } /* * Allow filesystems with binary mount data to explicitly set mount point * labeling information. */ static int selinux_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { const struct cred *cred = current_cred(); struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct selinux_mnt_opts *opts = mnt_opts; struct inode_security_struct *root_isec; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; u32 defcontext_sid = 0; int rc = 0; /* * Specifying internal flags without providing a place to * place the results is not allowed */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&sbsec->lock); if (!selinux_initialized()) { if (!opts) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { sbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } rc = -EINVAL; pr_warn("SELinux: Unable to set superblock options " "before the security server is initialized\n"); goto out; } /* * Binary mount data FS will come through this function twice. Once * from an explicit call and once from the generic calls from the vfs. * Since the generic VFS calls will not contain any security mount data * we need to skip the double mount verification. * * This does open a hole in which we will not notice if the first * mount using this sb set explicit options and a second mount using * this sb does not set any security options. (The first options * will be used for both mounts) */ if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA) && !opts) goto out; root_isec = backing_inode_security_novalidate(root); /* * parse the mount options, check if they are valid sids. * also check if someone is trying to mount the same sb more * than once with different security options. */ if (opts) { if (opts->fscontext_sid) { fscontext_sid = opts->fscontext_sid; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, fscontext_sid)) goto out_double_mount; sbsec->flags |= FSCONTEXT_MNT; } if (opts->context_sid) { context_sid = opts->context_sid; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, context_sid)) goto out_double_mount; sbsec->flags |= CONTEXT_MNT; } if (opts->rootcontext_sid) { rootcontext_sid = opts->rootcontext_sid; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, rootcontext_sid)) goto out_double_mount; sbsec->flags |= ROOTCONTEXT_MNT; } if (opts->defcontext_sid) { defcontext_sid = opts->defcontext_sid; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, defcontext_sid)) goto out_double_mount; sbsec->flags |= DEFCONTEXT_MNT; } } if (sbsec->flags & SE_SBINITIALIZED) { /* previously mounted with options, but not on this attempt? */ if ((sbsec->flags & SE_MNTMASK) && !opts) goto out_double_mount; rc = 0; goto out; } if (strcmp(sb->s_type->name, "proc") == 0) sbsec->flags |= SE_SBPROC | SE_SBGENFS; if (!strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "binder") || !strcmp(sb->s_type->name, "bpf") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "securityfs")) sbsec->flags |= SE_SBGENFS; if (!strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2")) sbsec->flags |= SE_SBGENFS | SE_SBGENFS_XATTR; if (!sbsec->behavior) { /* * Determine the labeling behavior to use for this * filesystem type. */ rc = security_fs_use(sb); if (rc) { pr_warn("%s: security_fs_use(%s) returned %d\n", __func__, sb->s_type->name, rc); goto out; } } /* * If this is a user namespace mount and the filesystem type is not * explicitly whitelisted, then no contexts are allowed on the command * line and security labels must be ignored. */ if (sb->s_user_ns != &init_user_ns && strcmp(sb->s_type->name, "tmpfs") && strcmp(sb->s_type->name, "ramfs") && strcmp(sb->s_type->name, "devpts") && strcmp(sb->s_type->name, "overlay")) { if (context_sid || fscontext_sid || rootcontext_sid || defcontext_sid) { rc = -EACCES; goto out; } if (sbsec->behavior == SECURITY_FS_USE_XATTR) { sbsec->behavior = SECURITY_FS_USE_MNTPOINT; rc = security_transition_sid(current_sid(), current_sid(), SECCLASS_FILE, NULL, &sbsec->mntpoint_sid); if (rc) goto out; } goto out_set_opts; } /* sets the context of the superblock for the fs being mounted. */ if (fscontext_sid) { rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred); if (rc) goto out; sbsec->sid = fscontext_sid; } /* * Switch to using mount point labeling behavior. * sets the label used on all file below the mountpoint, and will set * the superblock context if not already set. */ if (sbsec->flags & SE_SBNATIVE) { /* * This means we are initializing a superblock that has been * mounted before the SELinux was initialized and the * filesystem requested native labeling. We had already * returned SECURITY_LSM_NATIVE_LABELS in *set_kern_flags * in the original mount attempt, so now we just need to set * the SECURITY_FS_USE_NATIVE behavior. */ sbsec->behavior = SECURITY_FS_USE_NATIVE; } else if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) { sbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (context_sid) { if (!fscontext_sid) { rc = may_context_mount_sb_relabel(context_sid, sbsec, cred); if (rc) goto out; sbsec->sid = context_sid; } else { rc = may_context_mount_inode_relabel(context_sid, sbsec, cred); if (rc) goto out; } if (!rootcontext_sid) rootcontext_sid = context_sid; sbsec->mntpoint_sid = context_sid; sbsec->behavior = SECURITY_FS_USE_MNTPOINT; } if (rootcontext_sid) { rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, cred); if (rc) goto out; root_isec->sid = rootcontext_sid; root_isec->initialized = LABEL_INITIALIZED; } if (defcontext_sid) { if (sbsec->behavior != SECURITY_FS_USE_XATTR && sbsec->behavior != SECURITY_FS_USE_NATIVE) { rc = -EINVAL; pr_warn("SELinux: defcontext option is " "invalid for this filesystem type\n"); goto out; } if (defcontext_sid != sbsec->def_sid) { rc = may_context_mount_inode_relabel(defcontext_sid, sbsec, cred); if (rc) goto out; } sbsec->def_sid = defcontext_sid; } out_set_opts: rc = sb_finish_set_opts(sb); out: mutex_unlock(&sbsec->lock); return rc; out_double_mount: rc = -EINVAL; pr_warn("SELinux: mount invalid. Same superblock, different " "security settings for (dev %s, type %s)\n", sb->s_id, sb->s_type->name); goto out; } static int selinux_cmp_sb_context(const struct super_block *oldsb, const struct super_block *newsb) { struct superblock_security_struct *old = selinux_superblock(oldsb); struct superblock_security_struct *new = selinux_superblock(newsb); char oldflags = old->flags & SE_MNTMASK; char newflags = new->flags & SE_MNTMASK; if (oldflags != newflags) goto mismatch; if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid) goto mismatch; if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid) goto mismatch; if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid) goto mismatch; if (oldflags & ROOTCONTEXT_MNT) { struct inode_security_struct *oldroot = backing_inode_security(oldsb->s_root); struct inode_security_struct *newroot = backing_inode_security(newsb->s_root); if (oldroot->sid != newroot->sid) goto mismatch; } return 0; mismatch: pr_warn("SELinux: mount invalid. Same superblock, " "different security settings for (dev %s, " "type %s)\n", newsb->s_id, newsb->s_type->name); return -EBUSY; } static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { int rc = 0; const struct superblock_security_struct *oldsbsec = selinux_superblock(oldsb); struct superblock_security_struct *newsbsec = selinux_superblock(newsb); int set_fscontext = (oldsbsec->flags & FSCONTEXT_MNT); int set_context = (oldsbsec->flags & CONTEXT_MNT); int set_rootcontext = (oldsbsec->flags & ROOTCONTEXT_MNT); /* * Specifying internal flags without providing a place to * place the results is not allowed. */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&newsbsec->lock); /* * if the parent was able to be mounted it clearly had no special lsm * mount options. thus we can safely deal with this superblock later */ if (!selinux_initialized()) { if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { newsbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } /* how can we clone if the old one wasn't set up?? */ BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED)); /* if fs is reusing a sb, make sure that the contexts match */ if (newsbsec->flags & SE_SBINITIALIZED) { mutex_unlock(&newsbsec->lock); if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; return selinux_cmp_sb_context(oldsb, newsb); } newsbsec->flags = oldsbsec->flags; newsbsec->sid = oldsbsec->sid; newsbsec->def_sid = oldsbsec->def_sid; newsbsec->behavior = oldsbsec->behavior; if (newsbsec->behavior == SECURITY_FS_USE_NATIVE && !(kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) { rc = security_fs_use(newsb); if (rc) goto out; } if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !set_context) { newsbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (set_context) { u32 sid = oldsbsec->mntpoint_sid; if (!set_fscontext) newsbsec->sid = sid; if (!set_rootcontext) { struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = sid; } newsbsec->mntpoint_sid = sid; } if (set_rootcontext) { const struct inode_security_struct *oldisec = backing_inode_security(oldsb->s_root); struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = oldisec->sid; } sb_finish_set_opts(newsb); out: mutex_unlock(&newsbsec->lock); return rc; } /* * NOTE: the caller is responsible for freeing the memory even if on error. */ static int selinux_add_opt(int token, const char *s, void **mnt_opts) { struct selinux_mnt_opts *opts = *mnt_opts; u32 *dst_sid; int rc; if (token == Opt_seclabel) /* eaten and completely ignored */ return 0; if (!s) return -EINVAL; if (!selinux_initialized()) { pr_warn("SELinux: Unable to set superblock options before the security server is initialized\n"); return -EINVAL; } if (!opts) { opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; *mnt_opts = opts; } switch (token) { case Opt_context: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->context_sid; break; case Opt_fscontext: if (opts->fscontext_sid) goto err; dst_sid = &opts->fscontext_sid; break; case Opt_rootcontext: if (opts->rootcontext_sid) goto err; dst_sid = &opts->rootcontext_sid; break; case Opt_defcontext: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->defcontext_sid; break; default: WARN_ON(1); return -EINVAL; } rc = security_context_str_to_sid(s, dst_sid, GFP_KERNEL); if (rc) pr_warn("SELinux: security_context_str_to_sid (%s) failed with errno=%d\n", s, rc); return rc; err: pr_warn(SEL_MOUNT_FAIL_MSG); return -EINVAL; } static int show_sid(struct seq_file *m, u32 sid) { char *context = NULL; u32 len; int rc; rc = security_sid_to_context(sid, &context, &len); if (!rc) { bool has_comma = strchr(context, ','); seq_putc(m, '='); if (has_comma) seq_putc(m, '\"'); seq_escape(m, context, "\"\n\\"); if (has_comma) seq_putc(m, '\"'); } kfree(context); return rc; } static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!selinux_initialized()) return 0; if (sbsec->flags & FSCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, FSCONTEXT_STR); rc = show_sid(m, sbsec->sid); if (rc) return rc; } if (sbsec->flags & CONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, CONTEXT_STR); rc = show_sid(m, sbsec->mntpoint_sid); if (rc) return rc; } if (sbsec->flags & DEFCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, DEFCONTEXT_STR); rc = show_sid(m, sbsec->def_sid); if (rc) return rc; } if (sbsec->flags & ROOTCONTEXT_MNT) { struct dentry *root = sb->s_root; struct inode_security_struct *isec = backing_inode_security(root); seq_putc(m, ','); seq_puts(m, ROOTCONTEXT_STR); rc = show_sid(m, isec->sid); if (rc) return rc; } if (sbsec->flags & SBLABEL_MNT) { seq_putc(m, ','); seq_puts(m, SECLABEL_STR); } return 0; } static inline u16 inode_mode_to_security_class(umode_t mode) { switch (mode & S_IFMT) { case S_IFSOCK: return SECCLASS_SOCK_FILE; case S_IFLNK: return SECCLASS_LNK_FILE; case S_IFREG: return SECCLASS_FILE; case S_IFBLK: return SECCLASS_BLK_FILE; case S_IFDIR: return SECCLASS_DIR; case S_IFCHR: return SECCLASS_CHR_FILE; case S_IFIFO: return SECCLASS_FIFO_FILE; } return SECCLASS_FILE; } static inline int default_protocol_stream(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP || protocol == IPPROTO_MPTCP); } static inline int default_protocol_dgram(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP); } static inline u16 socket_type_to_security_class(int family, int type, int protocol) { bool extsockclass = selinux_policycap_extsockclass(); switch (family) { case PF_UNIX: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: return SECCLASS_UNIX_STREAM_SOCKET; case SOCK_DGRAM: case SOCK_RAW: return SECCLASS_UNIX_DGRAM_SOCKET; } break; case PF_INET: case PF_INET6: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: if (default_protocol_stream(protocol)) return SECCLASS_TCP_SOCKET; else if (extsockclass && protocol == IPPROTO_SCTP) return SECCLASS_SCTP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DGRAM: if (default_protocol_dgram(protocol)) return SECCLASS_UDP_SOCKET; else if (extsockclass && (protocol == IPPROTO_ICMP || protocol == IPPROTO_ICMPV6)) return SECCLASS_ICMP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DCCP: return SECCLASS_DCCP_SOCKET; default: return SECCLASS_RAWIP_SOCKET; } break; case PF_NETLINK: switch (protocol) { case NETLINK_ROUTE: return SECCLASS_NETLINK_ROUTE_SOCKET; case NETLINK_SOCK_DIAG: return SECCLASS_NETLINK_TCPDIAG_SOCKET; case NETLINK_NFLOG: return SECCLASS_NETLINK_NFLOG_SOCKET; case NETLINK_XFRM: return SECCLASS_NETLINK_XFRM_SOCKET; case NETLINK_SELINUX: return SECCLASS_NETLINK_SELINUX_SOCKET; case NETLINK_ISCSI: return SECCLASS_NETLINK_ISCSI_SOCKET; case NETLINK_AUDIT: return SECCLASS_NETLINK_AUDIT_SOCKET; case NETLINK_FIB_LOOKUP: return SECCLASS_NETLINK_FIB_LOOKUP_SOCKET; case NETLINK_CONNECTOR: return SECCLASS_NETLINK_CONNECTOR_SOCKET; case NETLINK_NETFILTER: return SECCLASS_NETLINK_NETFILTER_SOCKET; case NETLINK_DNRTMSG: return SECCLASS_NETLINK_DNRT_SOCKET; case NETLINK_KOBJECT_UEVENT: return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET; case NETLINK_GENERIC: return SECCLASS_NETLINK_GENERIC_SOCKET; case NETLINK_SCSITRANSPORT: return SECCLASS_NETLINK_SCSITRANSPORT_SOCKET; case NETLINK_RDMA: return SECCLASS_NETLINK_RDMA_SOCKET; case NETLINK_CRYPTO: return SECCLASS_NETLINK_CRYPTO_SOCKET; default: return SECCLASS_NETLINK_SOCKET; } case PF_PACKET: return SECCLASS_PACKET_SOCKET; case PF_KEY: return SECCLASS_KEY_SOCKET; case PF_APPLETALK: return SECCLASS_APPLETALK_SOCKET; } if (extsockclass) { switch (family) { case PF_AX25: return SECCLASS_AX25_SOCKET; case PF_IPX: return SECCLASS_IPX_SOCKET; case PF_NETROM: return SECCLASS_NETROM_SOCKET; case PF_ATMPVC: return SECCLASS_ATMPVC_SOCKET; case PF_X25: return SECCLASS_X25_SOCKET; case PF_ROSE: return SECCLASS_ROSE_SOCKET; case PF_DECnet: return SECCLASS_DECNET_SOCKET; case PF_ATMSVC: return SECCLASS_ATMSVC_SOCKET; case PF_RDS: return SECCLASS_RDS_SOCKET; case PF_IRDA: return SECCLASS_IRDA_SOCKET; case PF_PPPOX: return SECCLASS_PPPOX_SOCKET; case PF_LLC: return SECCLASS_LLC_SOCKET; case PF_CAN: return SECCLASS_CAN_SOCKET; case PF_TIPC: return SECCLASS_TIPC_SOCKET; case PF_BLUETOOTH: return SECCLASS_BLUETOOTH_SOCKET; case PF_IUCV: return SECCLASS_IUCV_SOCKET; case PF_RXRPC: return SECCLASS_RXRPC_SOCKET; case PF_ISDN: return SECCLASS_ISDN_SOCKET; case PF_PHONET: return SECCLASS_PHONET_SOCKET; case PF_IEEE802154: return SECCLASS_IEEE802154_SOCKET; case PF_CAIF: return SECCLASS_CAIF_SOCKET; case PF_ALG: return SECCLASS_ALG_SOCKET; case PF_NFC: return SECCLASS_NFC_SOCKET; case PF_VSOCK: return SECCLASS_VSOCK_SOCKET; case PF_KCM: return SECCLASS_KCM_SOCKET; case PF_QIPCRTR: return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; case PF_XDP: return SECCLASS_XDP_SOCKET; case PF_MCTP: return SECCLASS_MCTP_SOCKET; #if PF_MAX > 46 #error New address family defined, please update this function. #endif } } return SECCLASS_SOCKET; } static int selinux_genfs_get_sid(struct dentry *dentry, u16 tclass, u16 flags, u32 *sid) { int rc; struct super_block *sb = dentry->d_sb; char *buffer, *path; buffer = (char *)__get_free_page(GFP_KERNEL); if (!buffer) return -ENOMEM; path = dentry_path_raw(dentry, buffer, PAGE_SIZE); if (IS_ERR(path)) rc = PTR_ERR(path); else { if (flags & SE_SBPROC) { /* each process gets a /proc/PID/ entry. Strip off the * PID part to get a valid selinux labeling. * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */ while (path[1] >= '0' && path[1] <= '9') { path[1] = '/'; path++; } } rc = security_genfs_sid(sb->s_type->name, path, tclass, sid); if (rc == -ENOENT) { /* No match in policy, mark as unlabeled. */ *sid = SECINITSID_UNLABELED; rc = 0; } } free_page((unsigned long)buffer); return rc; } static int inode_doinit_use_xattr(struct inode *inode, struct dentry *dentry, u32 def_sid, u32 *sid) { #define INITCONTEXTLEN 255 char *context; unsigned int len; int rc; len = INITCONTEXTLEN; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); if (rc == -ERANGE) { kfree(context); /* Need a larger buffer. Query for the right size. */ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0) return rc; len = rc; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); } if (rc < 0) { kfree(context); if (rc != -ENODATA) { pr_warn("SELinux: %s: getxattr returned %d for dev=%s ino=%ld\n", __func__, -rc, inode->i_sb->s_id, inode->i_ino); return rc; } *sid = def_sid; return 0; } rc = security_context_to_sid_default(context, rc, sid, def_sid, GFP_NOFS); if (rc) { char *dev = inode->i_sb->s_id; unsigned long ino = inode->i_ino; if (rc == -EINVAL) { pr_notice_ratelimited("SELinux: inode=%lu on dev=%s was found to have an invalid context=%s. This indicates you may need to relabel the inode or the filesystem in question.\n", ino, dev, context); } else { pr_warn("SELinux: %s: context_to_sid(%s) returned %d for dev=%s ino=%ld\n", __func__, context, -rc, dev, ino); } } kfree(context); return 0; } /* The inode's security attributes must be initialized before first use. */ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry) { struct superblock_security_struct *sbsec = NULL; struct inode_security_struct *isec = selinux_inode(inode); u32 task_sid, sid = 0; u16 sclass; struct dentry *dentry; int rc = 0; if (isec->initialized == LABEL_INITIALIZED) return 0; spin_lock(&isec->lock); if (isec->initialized == LABEL_INITIALIZED) goto out_unlock; if (isec->sclass == SECCLASS_FILE) isec->sclass = inode_mode_to_security_class(inode->i_mode); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SE_SBINITIALIZED)) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ spin_lock(&sbsec->isec_lock); if (list_empty(&isec->list)) list_add(&isec->list, &sbsec->isec_head); spin_unlock(&sbsec->isec_lock); goto out_unlock; } sclass = isec->sclass; task_sid = isec->task_sid; sid = isec->sid; isec->initialized = LABEL_PENDING; spin_unlock(&isec->lock); switch (sbsec->behavior) { /* * In case of SECURITY_FS_USE_NATIVE we need to re-fetch the labels * via xattr when called from delayed_superblock_init(). */ case SECURITY_FS_USE_NATIVE: case SECURITY_FS_USE_XATTR: if (!(inode->i_opflags & IOP_XATTR)) { sid = sbsec->def_sid; break; } /* Need a dentry, since the xattr API requires one. Life would be simpler if we could just pass the inode. */ if (opt_dentry) { /* Called from d_instantiate or d_splice_alias. */ dentry = dget(opt_dentry); } else { /* * Called from selinux_complete_init, try to find a dentry. * Some filesystems really want a connected one, so try * that first. We could split SECURITY_FS_USE_XATTR in * two, depending upon that... */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } if (!dentry) { /* * this is can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as these * will get fixed up the next time we go through * inode_doinit with a dentry, before these inodes could * be used again by userspace. */ goto out_invalid; } rc = inode_doinit_use_xattr(inode, dentry, sbsec->def_sid, &sid); dput(dentry); if (rc) goto out; break; case SECURITY_FS_USE_TASK: sid = task_sid; break; case SECURITY_FS_USE_TRANS: /* Default to the fs SID. */ sid = sbsec->sid; /* Try to obtain a transition SID. */ rc = security_transition_sid(task_sid, sid, sclass, NULL, &sid); if (rc) goto out; break; case SECURITY_FS_USE_MNTPOINT: sid = sbsec->mntpoint_sid; break; default: /* Default to the fs superblock SID. */ sid = sbsec->sid; if ((sbsec->flags & SE_SBGENFS) && (!S_ISLNK(inode->i_mode) || selinux_policycap_genfs_seclabel_symlinks())) { /* We must have a dentry to determine the label on * procfs inodes */ if (opt_dentry) { /* Called from d_instantiate or * d_splice_alias. */ dentry = dget(opt_dentry); } else { /* Called from selinux_complete_init, try to * find a dentry. Some filesystems really want * a connected one, so try that first. */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } /* * This can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as * these will get fixed up the next time we go through * inode_doinit() with a dentry, before these inodes * could be used again by userspace. */ if (!dentry) goto out_invalid; rc = selinux_genfs_get_sid(dentry, sclass, sbsec->flags, &sid); if (rc) { dput(dentry); goto out; } if ((sbsec->flags & SE_SBGENFS_XATTR) && (inode->i_opflags & IOP_XATTR)) { rc = inode_doinit_use_xattr(inode, dentry, sid, &sid); if (rc) { dput(dentry); goto out; } } dput(dentry); } break; } out: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { if (rc) { isec->initialized = LABEL_INVALID; goto out_unlock; } isec->initialized = LABEL_INITIALIZED; isec->sid = sid; } out_unlock: spin_unlock(&isec->lock); return rc; out_invalid: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { isec->initialized = LABEL_INVALID; isec->sid = sid; } spin_unlock(&isec->lock); return 0; } /* Convert a Linux signal to an access vector. */ static inline u32 signal_to_av(int sig) { u32 perm = 0; switch (sig) { case SIGCHLD: /* Commonly granted from child to parent. */ perm = PROCESS__SIGCHLD; break; case SIGKILL: /* Cannot be caught or ignored */ perm = PROCESS__SIGKILL; break; case SIGSTOP: /* Cannot be caught or ignored */ perm = PROCESS__SIGSTOP; break; default: /* All other signals. */ perm = PROCESS__SIGNAL; break; } return perm; } #if CAP_LAST_CAP > 63 #error Fix SELinux to handle capabilities > 63. #endif /* Check whether a task is allowed to use a capability. */ static int cred_has_capability(const struct cred *cred, int cap, unsigned int opts, bool initns) { struct common_audit_data ad; struct av_decision avd; u16 sclass; u32 sid = cred_sid(cred); u32 av = CAP_TO_MASK(cap); int rc; ad.type = LSM_AUDIT_DATA_CAP; ad.u.cap = cap; switch (CAP_TO_INDEX(cap)) { case 0: sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS; break; case 1: sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS; break; default: pr_err("SELinux: out of range capability %d\n", cap); BUG(); return -EINVAL; } rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd); if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad); if (rc2) return rc2; } return rc; } /* Check whether a task has a particular permission to an inode. The 'adp' parameter is optional and allows other audit data to be passed (e.g. the dentry). */ static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, struct common_audit_data *adp) { struct inode_security_struct *isec; u32 sid; if (unlikely(IS_PRIVATE(inode))) return 0; sid = cred_sid(cred); isec = selinux_inode(inode); return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing the dentry to help the auditing code to more easily generate the pathname if needed. */ static inline int dentry_has_perm(const struct cred *cred, struct dentry *dentry, u32 av) { struct inode *inode = d_backing_inode(dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; __inode_security_revalidate(inode, dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as inode_has_perm, but pass explicit audit data containing the path to help the auditing code to more easily generate the pathname if needed. */ static inline int path_has_perm(const struct cred *cred, const struct path *path, u32 av) { struct inode *inode = d_backing_inode(path->dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; __inode_security_revalidate(inode, path->dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as path_has_perm, but uses the inode from the file struct. */ static inline int file_path_has_perm(const struct cred *cred, struct file *file, u32 av) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return inode_has_perm(cred, file_inode(file), av, &ad); } #ifdef CONFIG_BPF_SYSCALL static int bpf_fd_pass(const struct file *file, u32 sid); #endif /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to check a particular permission to the file. Access to the descriptor is implicitly granted if it has the same SID as the process. If av is zero, then access to the file is not checked, e.g. for cases where only the descriptor is affected like seek. */ static int file_has_perm(const struct cred *cred, struct file *file, u32 av) { struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct common_audit_data ad; u32 sid = cred_sid(cred); int rc; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, cred_sid(cred)); if (rc) return rc; #endif /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) rc = inode_has_perm(cred, inode, av, &ad); out: return rc; } /* * Determine the label for an inode that might be unioned. */ static int selinux_determine_inode_label(const struct task_security_struct *tsec, struct inode *dir, const struct qstr *name, u16 tclass, u32 *_new_isid) { const struct superblock_security_struct *sbsec = selinux_superblock(dir->i_sb); if ((sbsec->flags & SE_SBINITIALIZED) && (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) { *_new_isid = sbsec->mntpoint_sid; } else if ((sbsec->flags & SBLABEL_MNT) && tsec->create_sid) { *_new_isid = tsec->create_sid; } else { const struct inode_security_struct *dsec = inode_security(dir); return security_transition_sid(tsec->sid, dsec->sid, tclass, name, _new_isid); } return 0; } /* Check whether a task can create a file. */ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; u32 sid, newsid; struct common_audit_data ad; int rc; dsec = inode_security(dir); sbsec = selinux_superblock(dir->i_sb); sid = tsec->sid; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, DIR__ADD_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = selinux_determine_inode_label(tsec, dir, &dentry->d_name, tclass, &newsid); if (rc) return rc; rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } #define MAY_LINK 0 #define MAY_UNLINK 1 #define MAY_RMDIR 2 /* Check whether a task can link, unlink, or rmdir a file/directory. */ static int may_link(struct inode *dir, struct dentry *dentry, int kind) { struct inode_security_struct *dsec, *isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int rc; dsec = inode_security(dir); isec = backing_inode_security(dentry); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; av = DIR__SEARCH; av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME); rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; switch (kind) { case MAY_LINK: av = FILE__LINK; break; case MAY_UNLINK: av = FILE__UNLINK; break; case MAY_RMDIR: av = DIR__RMDIR; break; default: pr_warn("SELinux: %s: unrecognized kind %d\n", __func__, kind); return 0; } rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad); return rc; } static inline int may_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int old_is_dir, new_is_dir; int rc; old_dsec = inode_security(old_dir); old_isec = backing_inode_security(old_dentry); old_is_dir = d_is_dir(old_dentry); new_dsec = inode_security(new_dir); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = old_dentry; rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR, DIR__REMOVE_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, FILE__RENAME, &ad); if (rc) return rc; if (old_is_dir && new_dir != old_dir) { rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, DIR__REPARENT, &ad); if (rc) return rc; } ad.u.dentry = new_dentry; av = DIR__ADD_NAME | DIR__SEARCH; if (d_is_positive(new_dentry)) av |= DIR__REMOVE_NAME; rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; if (d_is_positive(new_dentry)) { new_isec = backing_inode_security(new_dentry); new_is_dir = d_is_dir(new_dentry); rc = avc_has_perm(sid, new_isec->sid, new_isec->sclass, (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad); if (rc) return rc; } return 0; } /* Check whether a task can perform a filesystem operation. */ static int superblock_has_perm(const struct cred *cred, const struct super_block *sb, u32 perms, struct common_audit_data *ad) { struct superblock_security_struct *sbsec; u32 sid = cred_sid(cred); sbsec = selinux_superblock(sb); return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad); } /* Convert a Linux mode and permission mask to an access vector. */ static inline u32 file_mask_to_av(int mode, int mask) { u32 av = 0; if (!S_ISDIR(mode)) { if (mask & MAY_EXEC) av |= FILE__EXECUTE; if (mask & MAY_READ) av |= FILE__READ; if (mask & MAY_APPEND) av |= FILE__APPEND; else if (mask & MAY_WRITE) av |= FILE__WRITE; } else { if (mask & MAY_EXEC) av |= DIR__SEARCH; if (mask & MAY_WRITE) av |= DIR__WRITE; if (mask & MAY_READ) av |= DIR__READ; } return av; } /* Convert a Linux file to an access vector. */ static inline u32 file_to_av(const struct file *file) { u32 av = 0; if (file->f_mode & FMODE_READ) av |= FILE__READ; if (file->f_mode & FMODE_WRITE) { if (file->f_flags & O_APPEND) av |= FILE__APPEND; else av |= FILE__WRITE; } if (!av) { /* * Special file opened with flags 3 for ioctl-only use. */ av = FILE__IOCTL; } return av; } /* * Convert a file to an access vector and include the correct * open permission. */ static inline u32 open_file_to_av(struct file *file) { u32 av = file_to_av(file); struct inode *inode = file_inode(file); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC) av |= FILE__OPEN; return av; } /* Hook functions begin here. */ static int selinux_binder_set_context_mgr(const struct cred *mgr) { return avc_has_perm(current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } static int selinux_binder_transaction(const struct cred *from, const struct cred *to) { u32 mysid = current_sid(); u32 fromsid = cred_sid(from); u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { rc = avc_has_perm(mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL); if (rc) return rc; } return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL); } static int selinux_binder_transfer_binder(const struct cred *from, const struct cred *to) { return avc_has_perm(cred_sid(from), cred_sid(to), SECCLASS_BINDER, BINDER__TRANSFER, NULL); } static int selinux_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; struct common_audit_data ad; int rc; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = file->f_path; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, sid); if (rc) return rc; #endif if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; isec = backing_inode_security(dentry); return avc_has_perm(sid, isec->sid, isec->sclass, file_to_av(file), &ad); } static int selinux_ptrace_access_check(struct task_struct *child, unsigned int mode) { u32 sid = current_sid(); u32 csid = task_sid_obj(child); if (mode & PTRACE_MODE_READ) return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ, NULL); return avc_has_perm(sid, csid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_ptrace_traceme(struct task_struct *parent) { return avc_has_perm(task_sid_obj(parent), task_sid_obj(current), SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return avc_has_perm(current_sid(), task_sid_obj(target), SECCLASS_PROCESS, PROCESS__GETCAP, NULL); } static int selinux_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return avc_has_perm(cred_sid(old), cred_sid(new), SECCLASS_PROCESS, PROCESS__SETCAP, NULL); } /* * (This comment used to live with the selinux_task_setuid hook, * which was removed). * * Since setuid only affects the current process, and since the SELinux * controls are not based on the Linux identity attributes, SELinux does not * need to control this operation. However, SELinux does control the use of * the CAP_SETUID and CAP_SETGID capabilities using the capable hook. */ static int selinux_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return cred_has_capability(cred, cap, opts, ns == &init_user_ns); } static int selinux_quotactl(int cmds, int type, int id, const struct super_block *sb) { const struct cred *cred = current_cred(); int rc = 0; if (!sb) return 0; switch (cmds) { case Q_SYNC: case Q_QUOTAON: case Q_QUOTAOFF: case Q_SETINFO: case Q_SETQUOTA: case Q_XQUOTAOFF: case Q_XQUOTAON: case Q_XSETQLIM: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL); break; case Q_GETFMT: case Q_GETINFO: case Q_GETQUOTA: case Q_XGETQUOTA: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETNEXTQUOTA: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL); break; default: rc = 0; /* let the kernel handle invalid cmds */ break; } return rc; } static int selinux_quota_on(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__QUOTAON); } static int selinux_syslog(int type) { switch (type) { case SYSLOG_ACTION_READ_ALL: /* Read last kernel messages */ case SYSLOG_ACTION_SIZE_BUFFER: /* Return size of the log buffer */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, NULL); case SYSLOG_ACTION_CONSOLE_OFF: /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: /* Enable logging to console */ /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE, NULL); } /* All other syslog types */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, NULL); } /* * Check permission for allocating a new virtual mapping. Returns * 0 if permission is granted, negative error code if not. * * Do not audit the selinux permission check, as this is applied to all * processes that allocate mappings. */ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { return cred_has_capability(current_cred(), CAP_SYS_ADMIN, CAP_OPT_NOAUDIT, true); } /* binprm security operations */ static u32 ptrace_parent_sid(void) { u32 sid = 0; struct task_struct *tracer; rcu_read_lock(); tracer = ptrace_parent(current); if (tracer) sid = task_sid_obj(tracer); rcu_read_unlock(); return sid; } static int check_nnp_nosuid(const struct linux_binprm *bprm, const struct task_security_struct *old_tsec, const struct task_security_struct *new_tsec) { int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS); int nosuid = !mnt_may_suid(bprm->file->f_path.mnt); int rc; u32 av; if (!nnp && !nosuid) return 0; /* neither NNP nor nosuid */ if (new_tsec->sid == old_tsec->sid) return 0; /* No change in credentials */ /* * If the policy enables the nnp_nosuid_transition policy capability, * then we permit transitions under NNP or nosuid if the * policy allows the corresponding permission between * the old and new contexts. */ if (selinux_policycap_nnp_nosuid_transition()) { av = 0; if (nnp) av |= PROCESS2__NNP_TRANSITION; if (nosuid) av |= PROCESS2__NOSUID_TRANSITION; rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS2, av, NULL); if (!rc) return 0; } /* * We also permit NNP or nosuid transitions to bounded SIDs, * i.e. SIDs that are guaranteed to only be allowed a subset * of the permissions of the current SID. */ rc = security_bounded_transition(old_tsec->sid, new_tsec->sid); if (!rc) return 0; /* * On failure, preserve the errno values for NNP vs nosuid. * NNP: Operation not permitted for caller. * nosuid: Permission denied to file. */ if (nnp) return -EPERM; return -EACCES; } static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) { const struct task_security_struct *old_tsec; struct task_security_struct *new_tsec; struct inode_security_struct *isec; struct common_audit_data ad; struct inode *inode = file_inode(bprm->file); int rc; /* SELinux context only depends on initial program or script and not * the script interpreter */ old_tsec = selinux_cred(current_cred()); new_tsec = selinux_cred(bprm->cred); isec = inode_security(inode); /* Default to the current task SID. */ new_tsec->sid = old_tsec->sid; new_tsec->osid = old_tsec->sid; /* Reset fs, key, and sock SIDs on execve. */ new_tsec->create_sid = 0; new_tsec->keycreate_sid = 0; new_tsec->sockcreate_sid = 0; /* * Before policy is loaded, label any task outside kernel space * as SECINITSID_INIT, so that any userspace tasks surviving from * early boot end up with a label different from SECINITSID_KERNEL * (if the policy chooses to set SECINITSID_INIT != SECINITSID_KERNEL). */ if (!selinux_initialized()) { new_tsec->sid = SECINITSID_INIT; /* also clear the exec_sid just in case */ new_tsec->exec_sid = 0; return 0; } if (old_tsec->exec_sid) { new_tsec->sid = old_tsec->exec_sid; /* Reset exec SID on execve. */ new_tsec->exec_sid = 0; /* Fail on NNP or nosuid if not an allowed transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) return rc; } else { /* Check for a default transition on this program. */ rc = security_transition_sid(old_tsec->sid, isec->sid, SECCLASS_PROCESS, NULL, &new_tsec->sid); if (rc) return rc; /* * Fallback to old SID on NNP or nosuid if not an allowed * transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) new_tsec->sid = old_tsec->sid; } ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = bprm->file; if (new_tsec->sid == old_tsec->sid) { rc = avc_has_perm(old_tsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; rc = avc_has_perm(new_tsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; /* Check for shared state */ if (bprm->unsafe & LSM_UNSAFE_SHARE) { rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__SHARE, NULL); if (rc) return -EPERM; } /* Make sure that anyone attempting to ptrace over a task that * changes its SID has the appropriate permit */ if (bprm->unsafe & LSM_UNSAFE_PTRACE) { u32 ptsid = ptrace_parent_sid(); if (ptsid != 0) { rc = avc_has_perm(ptsid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (rc) return -EPERM; } } /* Clear any possibly unsafe personality bits on exec: */ bprm->per_clear |= PER_CLEAR_ON_SETID; /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__NOATSECURE, NULL); bprm->secureexec |= !!rc; } return 0; } static int match_file(const void *p, struct file *file, unsigned fd) { return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0; } /* Derived from fs/exec.c:flush_old_files. */ static inline void flush_unauthorized_files(const struct cred *cred, struct files_struct *files) { struct file *file, *devnull = NULL; struct tty_struct *tty; int drop_tty = 0; unsigned n; tty = get_current_tty(); if (tty) { spin_lock(&tty->files_lock); if (!list_empty(&tty->tty_files)) { struct tty_file_private *file_priv; /* Revalidate access to controlling tty. Use file_path_has_perm on the tty path directly rather than using file_has_perm, as this particular open file may belong to another process and we are only interested in the inode-based check here. */ file_priv = list_first_entry(&tty->tty_files, struct tty_file_private, list); file = file_priv->file; if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE)) drop_tty = 1; } spin_unlock(&tty->files_lock); tty_kref_put(tty); } /* Reset controlling tty. */ if (drop_tty) no_tty(); /* Revalidate access to inherited open files. */ n = iterate_fd(files, 0, match_file, cred); if (!n) /* none found? */ return; devnull = dentry_open(&selinux_null, O_RDWR, cred); if (IS_ERR(devnull)) devnull = NULL; /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); } while ((n = iterate_fd(files, n, match_file, cred)) != 0); if (devnull) fput(devnull); } /* * Prepare a process for imminent new credential changes due to exec */ static void selinux_bprm_committing_creds(const struct linux_binprm *bprm) { struct task_security_struct *new_tsec; struct rlimit *rlim, *initrlim; int rc, i; new_tsec = selinux_cred(bprm->cred); if (new_tsec->sid == new_tsec->osid) return; /* Close files for which the new task SID is not authorized. */ flush_unauthorized_files(bprm->cred, current->files); /* Always clear parent death signal on SID transitions. */ current->pdeath_signal = 0; /* Check whether the new SID can inherit resource limits from the old * SID. If not, reset all soft limits to the lower of the current * task's hard limit and the init task's soft limit. * * Note that the setting of hard limits (even to lower them) can be * controlled by the setrlimit check. The inclusion of the init task's * soft limit into the computation is to avoid resetting soft limits * higher than the default soft limit for cases where the default is * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. */ rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__RLIMITINH, NULL); if (rc) { /* protect against do_prlimit() */ task_lock(current); for (i = 0; i < RLIM_NLIMITS; i++) { rlim = current->signal->rlim + i; initrlim = init_task.signal->rlim + i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } task_unlock(current); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) update_rlimit_cpu(current, rlimit(RLIMIT_CPU)); } } /* * Clean up the process immediately after the installation of new credentials * due to exec */ static void selinux_bprm_committed_creds(const struct linux_binprm *bprm) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 osid, sid; int rc; osid = tsec->osid; sid = tsec->sid; if (sid == osid) return; /* Check whether the new SID can inherit signal state from the old SID. * If not, clear itimers to avoid subsequent signal generation and * flush and unblock signals. * * This must occur _after_ the task SID has been updated so that any * kill done after the flush will be checked against the new SID. */ rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { clear_itimer(); spin_lock_irq(&unrcu_pointer(current->sighand)->siglock); if (!fatal_signal_pending(current)) { flush_sigqueue(¤t->pending); flush_sigqueue(¤t->signal->shared_pending); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); } spin_unlock_irq(&unrcu_pointer(current->sighand)->siglock); } /* Wake up the parent if it is waiting so that it can recheck * wait permission to the new task SID. */ read_lock(&tasklist_lock); __wake_up_parent(current, unrcu_pointer(current->real_parent)); read_unlock(&tasklist_lock); } /* superblock security operations */ static int selinux_sb_alloc_security(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); mutex_init(&sbsec->lock); INIT_LIST_HEAD(&sbsec->isec_head); spin_lock_init(&sbsec->isec_lock); sbsec->sid = SECINITSID_UNLABELED; sbsec->def_sid = SECINITSID_FILE; sbsec->mntpoint_sid = SECINITSID_UNLABELED; return 0; } static inline int opt_len(const char *s) { bool open_quote = false; int len; char c; for (len = 0; (c = s[len]) != '\0'; len++) { if (c == '"') open_quote = !open_quote; if (c == ',' && !open_quote) break; } return len; } static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts) { char *from = options; char *to = options; bool first = true; int rc; while (1) { int len = opt_len(from); int token; char *arg = NULL; token = match_opt_prefix(from, len, &arg); if (token != Opt_error) { char *p, *q; /* strip quotes */ if (arg) { for (p = q = arg; p < from + len; p++) { char c = *p; if (c != '"') *q++ = c; } arg = kmemdup_nul(arg, q - arg, GFP_KERNEL); if (!arg) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, arg, mnt_opts); kfree(arg); arg = NULL; if (unlikely(rc)) { goto free_opt; } } else { if (!first) { // copy with preceding comma from--; len++; } if (to != from) memmove(to, from, len); to += len; first = false; } if (!from[len]) break; from += len + 1; } *to = '\0'; return 0; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * Superblock not initialized (i.e. no options) - reject if any * options specified, otherwise accept. */ if (!(sbsec->flags & SE_SBINITIALIZED)) return opts ? 1 : 0; /* * Superblock initialized and no options specified - reject if * superblock has any options set, otherwise accept. */ if (!opts) return (sbsec->flags & SE_MNTMASK) ? 1 : 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) return 1; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) return 1; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) return 1; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) return 1; } return 0; } static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!opts) return 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) goto out_bad_option; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) goto out_bad_option; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) goto out_bad_option; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) goto out_bad_option; } return 0; out_bad_option: pr_warn("SELinux: unable to change security options " "during remount (dev %s, type=%s)\n", sb->s_id, sb->s_type->name); return -EINVAL; } static int selinux_sb_kern_mount(const struct super_block *sb) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = sb->s_root; return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad); } static int selinux_sb_statfs(struct dentry *dentry) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry->d_sb->s_root; return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad); } static int selinux_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { const struct cred *cred = current_cred(); if (flags & MS_REMOUNT) return superblock_has_perm(cred, path->dentry->d_sb, FILESYSTEM__REMOUNT, NULL); else return path_has_perm(cred, path, FILE__MOUNTON); } static int selinux_move_mount(const struct path *from_path, const struct path *to_path) { const struct cred *cred = current_cred(); return path_has_perm(cred, to_path, FILE__MOUNTON); } static int selinux_umount(struct vfsmount *mnt, int flags) { const struct cred *cred = current_cred(); return superblock_has_perm(cred, mnt->mnt_sb, FILESYSTEM__UNMOUNT, NULL); } static int selinux_fs_context_submount(struct fs_context *fc, struct super_block *reference) { const struct superblock_security_struct *sbsec = selinux_superblock(reference); struct selinux_mnt_opts *opts; /* * Ensure that fc->security remains NULL when no options are set * as expected by selinux_set_mnt_opts(). */ if (!(sbsec->flags & (FSCONTEXT_MNT|CONTEXT_MNT|DEFCONTEXT_MNT))) return 0; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; if (sbsec->flags & FSCONTEXT_MNT) opts->fscontext_sid = sbsec->sid; if (sbsec->flags & CONTEXT_MNT) opts->context_sid = sbsec->mntpoint_sid; if (sbsec->flags & DEFCONTEXT_MNT) opts->defcontext_sid = sbsec->def_sid; fc->security = opts; return 0; } static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { const struct selinux_mnt_opts *src = src_fc->security; if (!src) return 0; fc->security = kmemdup(src, sizeof(*src), GFP_KERNEL); return fc->security ? 0 : -ENOMEM; } static const struct fs_parameter_spec selinux_fs_parameters[] = { fsparam_string(CONTEXT_STR, Opt_context), fsparam_string(DEFCONTEXT_STR, Opt_defcontext), fsparam_string(FSCONTEXT_STR, Opt_fscontext), fsparam_string(ROOTCONTEXT_STR, Opt_rootcontext), fsparam_flag (SECLABEL_STR, Opt_seclabel), {} }; static int selinux_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; int opt; opt = fs_parse(fc, selinux_fs_parameters, param, &result); if (opt < 0) return opt; return selinux_add_opt(opt, param->string, &fc->security); } /* inode security operations */ static int selinux_inode_alloc_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = current_sid(); spin_lock_init(&isec->lock); INIT_LIST_HEAD(&isec->list); isec->inode = inode; isec->sid = SECINITSID_UNLABELED; isec->sclass = SECCLASS_FILE; isec->task_sid = sid; isec->initialized = LABEL_INVALID; return 0; } static void selinux_inode_free_security(struct inode *inode) { inode_free_security(inode); } static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) { u32 newsid; int rc; rc = selinux_determine_inode_label(selinux_cred(current_cred()), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; if (xattr_name) *xattr_name = XATTR_NAME_SELINUX; return security_sid_to_context(newsid, (char **)ctx, ctxlen); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { u32 newsid; int rc; struct task_security_struct *tsec; rc = selinux_determine_inode_label(selinux_cred(old), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; tsec = selinux_cred(new); tsec->create_sid = newsid; return 0; } static int selinux_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; struct xattr *xattr = lsm_get_xattr_slot(xattrs, xattr_count); u32 newsid, clen; u16 newsclass; int rc; char *context; sbsec = selinux_superblock(dir->i_sb); newsid = tsec->create_sid; newsclass = inode_mode_to_security_class(inode->i_mode); rc = selinux_determine_inode_label(tsec, dir, qstr, newsclass, &newsid); if (rc) return rc; /* Possibly defer initialization to selinux_complete_init. */ if (sbsec->flags & SE_SBINITIALIZED) { struct inode_security_struct *isec = selinux_inode(inode); isec->sclass = newsclass; isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; } if (!selinux_initialized() || !(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (xattr) { rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; xattr->value = context; xattr->value_len = clen; xattr->name = XATTR_SELINUX_SUFFIX; } return 0; } static int selinux_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { u32 sid = current_sid(); struct common_audit_data ad; struct inode_security_struct *isec; int rc; if (unlikely(!selinux_initialized())) return 0; isec = selinux_inode(inode); /* * We only get here once per ephemeral inode. The inode has * been initialized via inode_alloc_security but is otherwise * untouched. */ if (context_inode) { struct inode_security_struct *context_isec = selinux_inode(context_inode); if (context_isec->initialized != LABEL_INITIALIZED) { pr_err("SELinux: context_inode is not initialized\n"); return -EACCES; } isec->sclass = context_isec->sclass; isec->sid = context_isec->sid; } else { isec->sclass = SECCLASS_ANON_INODE; rc = security_transition_sid( sid, sid, isec->sclass, name, &isec->sid); if (rc) return rc; } isec->initialized = LABEL_INITIALIZED; /* * Now that we've initialized security, check whether we're * allowed to actually create this type of anonymous inode. */ ad.type = LSM_AUDIT_DATA_ANONINODE; ad.u.anonclass = name ? (const char *)name->name : "?"; return avc_has_perm(sid, isec->sid, isec->sclass, FILE__CREATE, &ad); } static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { return may_create(dir, dentry, SECCLASS_FILE); } static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { return may_link(dir, old_dentry, MAY_LINK); } static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_UNLINK); } static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name) { return may_create(dir, dentry, SECCLASS_LNK_FILE); } static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask) { return may_create(dir, dentry, SECCLASS_DIR); } static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_RMDIR); } static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return may_create(dir, dentry, inode_mode_to_security_class(mode)); } static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry, struct inode *new_inode, struct dentry *new_dentry) { return may_rename(old_inode, old_dentry, new_inode, new_dentry); } static int selinux_inode_readlink(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__READ); } static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { struct common_audit_data ad; struct inode_security_struct *isec; u32 sid = current_sid(); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = inode_security_rcu(inode, rcu); if (IS_ERR(isec)) return PTR_ERR(isec); return avc_has_perm(sid, isec->sid, isec->sclass, FILE__READ, &ad); } static noinline int audit_inode_permission(struct inode *inode, u32 perms, u32 audited, u32 denied, int result) { struct common_audit_data ad; struct inode_security_struct *isec = selinux_inode(inode); ad.type = LSM_AUDIT_DATA_INODE; ad.u.inode = inode; return slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms, audited, denied, result, &ad); } static int selinux_inode_permission(struct inode *inode, int mask) { u32 perms; bool from_access; bool no_block = mask & MAY_NOT_BLOCK; struct inode_security_struct *isec; u32 sid = current_sid(); struct av_decision avd; int rc, rc2; u32 audited, denied; from_access = mask & MAY_ACCESS; mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND); /* No permission to check. Existence test. */ if (!mask) return 0; if (unlikely(IS_PRIVATE(inode))) return 0; perms = file_mask_to_av(inode->i_mode, mask); isec = inode_security_rcu(inode, no_block); if (IS_ERR(isec)) return PTR_ERR(isec); rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd); audited = avc_audit_required(perms, &avd, rc, from_access ? FILE__AUDIT_ACCESS : 0, &denied); if (likely(!audited)) return rc; rc2 = audit_inode_permission(inode, perms, audited, denied, rc); if (rc2) return rc2; return rc; } static int selinux_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { const struct cred *cred = current_cred(); struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = iattr->ia_valid; __u32 av = FILE__WRITE; /* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */ if (ia_valid & ATTR_FORCE) { ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE | ATTR_FORCE); if (!ia_valid) return 0; } if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC && (ia_valid & ATTR_SIZE) && !(ia_valid & ATTR_FILE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); } static int selinux_inode_getattr(const struct path *path) { return path_has_perm(current_cred(), path, FILE__GETATTR); } static bool has_cap_mac_admin(bool audit) { const struct cred *cred = current_cred(); unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT; if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts)) return false; if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true)) return false; return true; } /** * selinux_inode_xattr_skipcap - Skip the xattr capability checks? * @name: name of the xattr * * Returns 1 to indicate that SELinux "owns" the access control rights to xattrs * named @name; the LSM layer should avoid enforcing any traditional * capability based access controls on this xattr. Returns 0 to indicate that * SELinux does not "own" the access control rights to xattrs named @name and is * deferring to the LSM layer for further access controls, including capability * based controls. */ static int selinux_inode_xattr_skipcap(const char *name) { /* require capability check if not a selinux xattr */ return !strcmp(name, XATTR_NAME_SELINUX); } static int selinux_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; struct superblock_security_struct *sbsec; struct common_audit_data ad; u32 newsid, sid = current_sid(); int rc = 0; /* if not a selinux xattr, only check the ordinary setattr perm */ if (strcmp(name, XATTR_NAME_SELINUX)) return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); if (!selinux_initialized()) return (inode_owner_or_capable(idmap, inode) ? 0 : -EPERM); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = backing_inode_security(dentry); rc = avc_has_perm(sid, isec->sid, isec->sclass, FILE__RELABELFROM, &ad); if (rc) return rc; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc == -EINVAL) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (value) { const char *str = value; if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; } else { audit_size = 0; } ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return rc; audit_log_format(ab, "op=setxattr invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return rc; } rc = security_context_to_sid_force(value, size, &newsid); } if (rc) return rc; rc = avc_has_perm(sid, newsid, isec->sclass, FILE__RELABELTO, &ad); if (rc) return rc; rc = security_validate_transition(isec->sid, newsid, sid, isec->sclass); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } static int selinux_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static int selinux_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__GETATTR); } static int selinux_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; u32 newsid; int rc; if (strcmp(name, XATTR_NAME_SELINUX)) { /* Not an attribute we recognize, so nothing to do. */ return; } if (!selinux_initialized()) { /* If we haven't even been initialized, then we can't validate * against a policy, so leave the label as invalid. It may * resolve to a valid label on the next revalidation try if * we've since initialized. */ return; } rc = security_context_to_sid_force(value, size, &newsid); if (rc) { pr_err("SELinux: unable to map context to SID" "for (%s, %lu), rc=%d\n", inode->i_sb->s_id, inode->i_ino, -rc); return; } isec = backing_inode_security(dentry); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_inode_getxattr(struct dentry *dentry, const char *name) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_listxattr(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { /* if not a selinux xattr, only check the ordinary setattr perm */ if (strcmp(name, XATTR_NAME_SELINUX)) return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); if (!selinux_initialized()) return 0; /* No one is allowed to remove a SELinux security label. You can change the label, but all data must be labeled. */ return -EACCES; } static int selinux_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { int ret; u32 perm; struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; /* * Set permission needed based on the type of mark being set. * Performs an additional check for sb watches. */ switch (obj_type) { case FSNOTIFY_OBJ_TYPE_VFSMOUNT: perm = FILE__WATCH_MOUNT; break; case FSNOTIFY_OBJ_TYPE_SB: perm = FILE__WATCH_SB; ret = superblock_has_perm(current_cred(), path->dentry->d_sb, FILESYSTEM__WATCH, &ad); if (ret) return ret; break; case FSNOTIFY_OBJ_TYPE_INODE: perm = FILE__WATCH; break; default: return -EINVAL; } /* blocking watches require the file:watch_with_perm permission */ if (mask & (ALL_FSNOTIFY_PERM_EVENTS)) perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm); } /* * Copy the inode security context value to the user. * * Permission check is handled by selinux_inode_getxattr hook. */ static int selinux_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { u32 size; int error; char *context = NULL; struct inode_security_struct *isec; /* * If we're not initialized yet, then we can't validate contexts, so * just let vfs_getxattr fall back to using the on-disk xattr. */ if (!selinux_initialized() || strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; /* * If the caller has CAP_MAC_ADMIN, then get the raw context * value even if it is not defined by current policy; otherwise, * use the in-core value under current policy. * Use the non-auditing forms of the permission checks since * getxattr may be called by unprivileged processes commonly * and lack of permission just means that we fall back to the * in-core context value, not a denial. */ isec = inode_security(inode); if (has_cap_mac_admin(false)) error = security_sid_to_context_force(isec->sid, &context, &size); else error = security_sid_to_context(isec->sid, &context, &size); if (error) return error; error = size; if (alloc) { *buffer = context; goto out_nofree; } kfree(context); out_nofree: return error; } static int selinux_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct inode_security_struct *isec = inode_security_novalidate(inode); struct superblock_security_struct *sbsec; u32 newsid; int rc; if (strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!value || !size) return -EACCES; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc) return rc; spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return 0; } static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { const int len = sizeof(XATTR_NAME_SELINUX); if (!selinux_initialized()) return 0; if (buffer && len <= buffer_size) memcpy(buffer, XATTR_NAME_SELINUX, len); return len; } static void selinux_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop) { struct inode_security_struct *isec = inode_security_novalidate(inode); prop->selinux.secid = isec->sid; } static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { struct lsm_prop prop; struct task_security_struct *tsec; struct cred *new_creds = *new; if (new_creds == NULL) { new_creds = prepare_creds(); if (!new_creds) return -ENOMEM; } tsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ selinux_inode_getlsmprop(d_inode(src), &prop); tsec->create_sid = prop.selinux.secid; *new = new_creds; return 0; } static int selinux_inode_copy_up_xattr(struct dentry *dentry, const char *name) { /* The copy_up hook above sets the initial context on an inode, but we * don't then want to overwrite it by blindly copying all the lower * xattrs up. Instead, filter out SELinux-related xattrs following * policy load. */ if (selinux_initialized() && !strcmp(name, XATTR_NAME_SELINUX)) return -ECANCELED; /* Discard */ /* * Any other attribute apart from SELINUX is not claimed, supported * by selinux. */ return -EOPNOTSUPP; } /* kernfs node operations */ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 parent_sid, newsid, clen; int rc; char *context; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, NULL, 0); if (rc == -ENODATA) return 0; else if (rc < 0) return rc; clen = (u32)rc; context = kmalloc(clen, GFP_KERNEL); if (!context) return -ENOMEM; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, context, clen); if (rc < 0) { kfree(context); return rc; } rc = security_context_to_sid(context, clen, &parent_sid, GFP_KERNEL); kfree(context); if (rc) return rc; if (tsec->create_sid) { newsid = tsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); struct qstr q; q.name = kn->name; q.hash_len = hashlen_string(kn_dir, kn->name); rc = security_transition_sid(tsec->sid, parent_sid, secclass, &q, &newsid); if (rc) return rc; } rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; rc = kernfs_xattr_set(kn, XATTR_NAME_SELINUX, context, clen, XATTR_CREATE); kfree(context); return rc; } /* file security operations */ static int selinux_revalidate_file_permission(struct file *file, int mask) { const struct cred *cred = current_cred(); struct inode *inode = file_inode(file); /* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */ if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE)) mask |= MAY_APPEND; return file_has_perm(cred, file, file_mask_to_av(inode->i_mode, mask)); } static int selinux_file_permission(struct file *file, int mask) { struct inode *inode = file_inode(file); struct file_security_struct *fsec = selinux_file(file); struct inode_security_struct *isec; u32 sid = current_sid(); if (!mask) /* No permission to check. Existence test. */ return 0; isec = inode_security(inode); if (sid == fsec->sid && fsec->isid == isec->sid && fsec->pseqno == avc_policy_seqno()) /* No change since file_open check. */ return 0; return selinux_revalidate_file_permission(file, mask); } static int selinux_file_alloc_security(struct file *file) { struct file_security_struct *fsec = selinux_file(file); u32 sid = current_sid(); fsec->sid = sid; fsec->fown_sid = sid; return 0; } /* * Check whether a task has the ioctl permission and cmd * operation to an inode. */ static int ioctl_has_perm(const struct cred *cred, struct file *file, u32 requested, u16 cmd) { struct common_audit_data ad; struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct inode_security_struct *isec; struct lsm_ioctlop_audit ioctl; u32 ssid = cred_sid(cred); int rc; u8 driver = cmd >> 8; u8 xperm = cmd & 0xff; ad.type = LSM_AUDIT_DATA_IOCTL_OP; ad.u.op = &ioctl; ad.u.op->cmd = cmd; ad.u.op->path = file->f_path; if (ssid != fsec->sid) { rc = avc_has_perm(ssid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } if (unlikely(IS_PRIVATE(inode))) return 0; isec = inode_security(inode); rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested, driver, xperm, &ad); out: return rc; } static int selinux_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int error = 0; switch (cmd) { case FIONREAD: case FIBMAP: case FIGETBSZ: case FS_IOC_GETFLAGS: case FS_IOC_GETVERSION: error = file_has_perm(cred, file, FILE__GETATTR); break; case FS_IOC_SETFLAGS: case FS_IOC_SETVERSION: error = file_has_perm(cred, file, FILE__SETATTR); break; /* sys_ioctl() checks */ case FIONBIO: case FIOASYNC: error = file_has_perm(cred, file, 0); break; case KDSKBENT: case KDSKBSENT: error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG, CAP_OPT_NONE, true); break; case FIOCLEX: case FIONCLEX: if (!selinux_policycap_ioctl_skip_cloexec()) error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); break; /* default case assumes that the command will go * to the file's ioctl() function. */ default: error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); } return error; } static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { /* * If we are in a 64-bit kernel running 32-bit userspace, we need to * make sure we don't compare 32-bit flags to 64-bit flags. */ switch (cmd) { case FS_IOC32_GETFLAGS: cmd = FS_IOC_GETFLAGS; break; case FS_IOC32_SETFLAGS: cmd = FS_IOC_SETFLAGS; break; case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; case FS_IOC32_SETVERSION: cmd = FS_IOC_SETVERSION; break; default: break; } return selinux_file_ioctl(file, cmd, arg); } static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); int rc = 0; if (default_noexec && (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) || (!shared && (prot & PROT_WRITE)))) { /* * We are making executable an anonymous mapping or a * private file mapping that will also be writable. * This has an additional check. */ rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM, NULL); if (rc) goto error; } if (file) { /* read access is always possible with a mapping */ u32 av = FILE__READ; /* write access only matters if the mapping is shared */ if (shared && (prot & PROT_WRITE)) av |= FILE__WRITE; if (prot & PROT_EXEC) av |= FILE__EXECUTE; return file_has_perm(cred, file, av); } error: return rc; } static int selinux_mmap_addr(unsigned long addr) { int rc = 0; if (addr < CONFIG_LSM_MMAP_MIN_ADDR) { u32 sid = current_sid(); rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, NULL); } return rc; } static int selinux_mmap_file(struct file *file, unsigned long reqprot __always_unused, unsigned long prot, unsigned long flags) { struct common_audit_data ad; int rc; if (file) { ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; rc = inode_has_perm(current_cred(), file_inode(file), FILE__MAP, &ad); if (rc) return rc; } return file_map_prot_check(file, prot, (flags & MAP_TYPE) == MAP_SHARED); } static int selinux_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot __always_unused, unsigned long prot) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; /* * We don't use the vma_is_initial_heap() helper as it has * a history of problems and is currently broken on systems * where there is no heap, e.g. brk == start_brk. Before * replacing the conditional below with vma_is_initial_heap(), * or something similar, please ensure that the logic is the * same as what we have below or you have tested every possible * corner case you can think to test. */ if (vma->vm_start >= vma->vm_mm->start_brk && vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || vma_is_stack_for_current(vma))) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECSTACK, NULL); } else if (vma->vm_file && vma->anon_vma) { /* * We are making executable a file mapping that has * had some COW done. Since pages might have been * written, check ability to execute the possibly * modified content. This typically should only * occur for text relocations. */ rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD); } if (rc) return rc; } return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED); } static int selinux_file_lock(struct file *file, unsigned int cmd) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, FILE__LOCK); } static int selinux_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int err = 0; switch (cmd) { case F_SETFL: if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) { err = file_has_perm(cred, file, FILE__WRITE); break; } fallthrough; case F_SETOWN: case F_SETSIG: case F_GETFL: case F_GETOWN: case F_GETSIG: case F_GETOWNER_UIDS: /* Just check FD__USE permission */ err = file_has_perm(cred, file, 0); break; case F_GETLK: case F_SETLK: case F_SETLKW: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: #if BITS_PER_LONG == 32 case F_GETLK64: case F_SETLK64: case F_SETLKW64: #endif err = file_has_perm(cred, file, FILE__LOCK); break; } return err; } static void selinux_file_set_fowner(struct file *file) { struct file_security_struct *fsec; fsec = selinux_file(file); fsec->fown_sid = current_sid(); } static int selinux_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { struct file *file; u32 sid = task_sid_obj(tsk); u32 perm; struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ file = fown->file; fsec = selinux_file(file); if (!signum) perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */ else perm = signal_to_av(signum); return avc_has_perm(fsec->fown_sid, sid, SECCLASS_PROCESS, perm, NULL); } static int selinux_file_receive(struct file *file) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, file_to_av(file)); } static int selinux_file_open(struct file *file) { struct file_security_struct *fsec; struct inode_security_struct *isec; fsec = selinux_file(file); isec = inode_security(file_inode(file)); /* * Save inode label and policy sequence number * at open-time so that selinux_file_permission * can determine whether revalidation is necessary. * Task label is already saved in the file security * struct as its SID. */ fsec->isid = isec->sid; fsec->pseqno = avc_policy_seqno(); /* * Since the inode label or policy seqno may have changed * between the selinux_inode_permission check and the saving * of state above, recheck that access is still permitted. * Otherwise, access might never be revalidated against the * new inode label or new policy. * This check is not redundant - do not remove. */ return file_path_has_perm(file->f_cred, file, open_file_to_av(file)); } /* task security operations */ static int selinux_task_alloc(struct task_struct *task, unsigned long clone_flags) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } /* * prepare a new set of credentials for modification */ static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; return 0; } /* * transfer the SELinux data to a blank set of creds */ static void selinux_cred_transfer(struct cred *new, const struct cred *old) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; } static void selinux_cred_getsecid(const struct cred *c, u32 *secid) { *secid = cred_sid(c); } static void selinux_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop) { prop->selinux.secid = cred_sid(c); } /* * set the security data for a kernel service * - all the creation contexts are set to unlabelled */ static int selinux_kernel_act_as(struct cred *new, u32 secid) { struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, secid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, NULL); if (ret == 0) { tsec->sid = secid; tsec->create_sid = 0; tsec->keycreate_sid = 0; tsec->sockcreate_sid = 0; } return ret; } /* * set the file creation context in a security record to the same as the * objective context of the specified inode */ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) { struct inode_security_struct *isec = inode_security(inode); struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, isec->sid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, NULL); if (ret == 0) tsec->create_sid = isec->sid; return ret; } static int selinux_kernel_module_request(char *kmod_name) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_KMOD; ad.u.kmod_name = kmod_name; return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__MODULE_REQUEST, &ad); } static int selinux_kernel_module_from_file(struct file *file) { struct common_audit_data ad; struct inode_security_struct *isec; struct file_security_struct *fsec; u32 sid = current_sid(); int rc; /* init_module */ if (file == NULL) return avc_has_perm(sid, sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, NULL); /* finit_module */ ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; fsec = selinux_file(file); if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } isec = inode_security(file_inode(file)); return avc_has_perm(sid, isec->sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, &ad); } static int selinux_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int rc = 0; switch (id) { case READING_MODULE: rc = selinux_kernel_module_from_file(contents ? file : NULL); break; default: break; } return rc; } static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents) { int rc = 0; switch (id) { case LOADING_MODULE: rc = selinux_kernel_module_from_file(NULL); break; default: break; } return rc; } static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETPGID, NULL); } static int selinux_task_getpgid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETPGID, NULL); } static int selinux_task_getsid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSESSION, NULL); } static void selinux_current_getlsmprop_subj(struct lsm_prop *prop) { prop->selinux.secid = current_sid(); } static void selinux_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop) { prop->selinux.secid = task_sid_obj(p); } static int selinux_task_setnice(struct task_struct *p, int nice) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_setioprio(struct task_struct *p, int ioprio) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getioprio(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { u32 av = 0; if (!flags) return 0; if (flags & LSM_PRLIMIT_WRITE) av |= PROCESS__SETRLIMIT; if (flags & LSM_PRLIMIT_READ) av |= PROCESS__GETRLIMIT; return avc_has_perm(cred_sid(cred), cred_sid(tcred), SECCLASS_PROCESS, av, NULL); } static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { struct rlimit *old_rlim = p->signal->rlim + resource; /* Control the ability to change the hard limit (whether lowering or raising it), so that the hard limit can later be used as a safe reset point for the soft limit upon context transitions. See selinux_bprm_committing_creds. */ if (old_rlim->rlim_max != new_rlim->rlim_max) return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETRLIMIT, NULL); return 0; } static int selinux_task_setscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_movememory(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { u32 secid; u32 perm; if (!sig) perm = PROCESS__SIGNULL; /* null signal; existence test */ else perm = signal_to_av(sig); if (!cred) secid = current_sid(); else secid = cred_sid(cred); return avc_has_perm(secid, task_sid_obj(p), SECCLASS_PROCESS, perm, NULL); } static void selinux_task_to_inode(struct task_struct *p, struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = task_sid_obj(p); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = sid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_userns_create(const struct cred *cred) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_USER_NAMESPACE, USER_NAMESPACE__CREATE, NULL); } /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv4(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ihlen, ret = -EINVAL; struct iphdr _iph, *ih; offset = skb_network_offset(skb); ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) goto out; ihlen = ih->ihl * 4; if (ihlen < sizeof(_iph)) goto out; ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; ret = 0; if (proto) *proto = ih->protocol; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif default: break; } out: return ret; } #if IS_ENABLED(CONFIG_IPV6) /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv6(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { u8 nexthdr; int ret = -EINVAL, offset; struct ipv6hdr _ipv6h, *ip6; __be16 frag_off; offset = skb_network_offset(skb); ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (ip6 == NULL) goto out; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; ret = 0; nexthdr = ip6->nexthdr; offset += sizeof(_ipv6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) goto out; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif /* includes fragments */ default: break; } out: return ret; } #endif /* IPV6 */ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad, char **_addrp, int src, u8 *proto) { char *addrp; int ret; switch (ad->u.net->family) { case PF_INET: ret = selinux_parse_skb_ipv4(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v4info.saddr : &ad->u.net->v4info.daddr); goto okay; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: ret = selinux_parse_skb_ipv6(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v6info.saddr : &ad->u.net->v6info.daddr); goto okay; #endif /* IPV6 */ default: addrp = NULL; goto okay; } parse_error: pr_warn( "SELinux: failure in selinux_parse_skb()," " unable to parse packet\n"); return ret; okay: if (_addrp) *_addrp = addrp; return 0; } /** * selinux_skb_peerlbl_sid - Determine the peer label of a packet * @skb: the packet * @family: protocol family * @sid: the packet's peer label SID * * Description: * Check the various different forms of network peer labeling and determine * the peer label/SID for the packet; most of the magic actually occurs in * the security server function security_net_peersid_cmp(). The function * returns zero if the value in @sid is valid (although it may be SECSID_NULL) * or -EACCES if @sid is invalid due to inconsistencies with the different * peer labels. * */ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) { int err; u32 xfrm_sid; u32 nlbl_sid; u32 nlbl_type; err = selinux_xfrm_skb_sid(skb, &xfrm_sid); if (unlikely(err)) return -EACCES; err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid); if (unlikely(err)) return -EACCES; err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid); if (unlikely(err)) { pr_warn( "SELinux: failure in selinux_skb_peerlbl_sid()," " unable to determine packet's peer label\n"); return -EACCES; } return 0; } /** * selinux_conn_sid - Determine the child socket label for a connection * @sk_sid: the parent socket's SID * @skb_sid: the packet's SID * @conn_sid: the resulting connection SID * * If @skb_sid is valid then the user:role:type information from @sk_sid is * combined with the MLS information from @skb_sid in order to create * @conn_sid. If @skb_sid is not valid then @conn_sid is simply a copy * of @sk_sid. Returns zero on success, negative values on failure. * */ static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) { int err = 0; if (skb_sid != SECSID_NULL) err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid); else *conn_sid = sk_sid; return err; } /* socket security operations */ static int socket_sockcreate_sid(const struct task_security_struct *tsec, u16 secclass, u32 *socksid) { if (tsec->sockcreate_sid > SECSID_NULL) { *socksid = tsec->sockcreate_sid; return 0; } return security_transition_sid(tsec->sid, tsec->sid, secclass, NULL, socksid); } static bool sock_skip_has_perm(u32 sid) { if (sid == SECINITSID_KERNEL) return true; /* * Before POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT, sockets that * inherited the kernel context from early boot used to be skipped * here, so preserve that behavior unless the capability is set. * * By setting the capability the policy signals that it is ready * for this quirk to be fixed. Note that sockets created by a kernel * thread or a usermode helper executed without a transition will * still be skipped in this check regardless of the policycap * setting. */ if (!selinux_policycap_userspace_initial_context() && sid == SECINITSID_INIT) return true; return false; } static int sock_has_perm(struct sock *sk, u32 perms) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; if (sock_skip_has_perm(sksec->sid)) return 0; ad_net_init_from_sk(&ad, &net, sk); return avc_has_perm(current_sid(), sksec->sid, sksec->sclass, perms, &ad); } static int selinux_socket_create(int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 newsid; u16 secclass; int rc; if (kern) return 0; secclass = socket_type_to_security_class(family, type, protocol); rc = socket_sockcreate_sid(tsec, secclass, &newsid); if (rc) return rc; return avc_has_perm(tsec->sid, newsid, secclass, SOCKET__CREATE, NULL); } static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock)); struct sk_security_struct *sksec; u16 sclass = socket_type_to_security_class(family, type, protocol); u32 sid = SECINITSID_KERNEL; int err = 0; if (!kern) { err = socket_sockcreate_sid(tsec, sclass, &sid); if (err) return err; } isec->sclass = sclass; isec->sid = sid; isec->initialized = LABEL_INITIALIZED; if (sock->sk) { sksec = selinux_sock(sock->sk); sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) sksec->sctp_assoc_state = SCTP_ASSOC_UNSET; err = selinux_netlbl_socket_post_create(sock->sk, family); } return err; } static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { struct sk_security_struct *sksec_a = selinux_sock(socka->sk); struct sk_security_struct *sksec_b = selinux_sock(sockb->sk); sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; return 0; } /* Range of port numbers used to automatically bind. Need to determine whether we should perform a name_bind permission check between the socket and the port number. */ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = selinux_sock(sk); u16 family; int err; err = sock_has_perm(sk, SOCKET__BIND); if (err) goto out; /* If PF_INET or PF_INET6, check name_bind permission for the port. */ family = sk->sk_family; if (family == PF_INET || family == PF_INET6) { char *addrp; struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; u16 family_sa; unsigned short snum; u32 sid, node_perm; /* * sctp_bindx(3) calls via selinux_sctp_bind_connect() * that validates multiple binding addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; family_sa = address->sa_family; switch (family_sa) { case AF_UNSPEC: case AF_INET: if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; addr4 = (struct sockaddr_in *)address; if (family_sa == AF_UNSPEC) { if (family == PF_INET6) { /* Length check from inet6_bind_sk() */ if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; /* Family check from __inet6_bind() */ goto err_af; } /* see __inet_bind(), we only want to allow * AF_UNSPEC if the address is INADDR_ANY */ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) goto err_af; family_sa = AF_INET; } snum = ntohs(addr4->sin_port); addrp = (char *)&addr4->sin_addr.s_addr; break; case AF_INET6: if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; addr6 = (struct sockaddr_in6 *)address; snum = ntohs(addr6->sin6_port); addrp = (char *)&addr6->sin6_addr.s6_addr; break; default: goto err_af; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sport = htons(snum); ad.u.net->family = family_sa; if (snum) { int low, high; inet_get_local_port_range(sock_net(sk), &low, &high); if (inet_port_requires_bind_service(sock_net(sk), snum) || snum < low || snum > high) { err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) goto out; err = avc_has_perm(sksec->sid, sid, sksec->sclass, SOCKET__NAME_BIND, &ad); if (err) goto out; } } switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: node_perm = TCP_SOCKET__NODE_BIND; break; case SECCLASS_UDP_SOCKET: node_perm = UDP_SOCKET__NODE_BIND; break; case SECCLASS_DCCP_SOCKET: node_perm = DCCP_SOCKET__NODE_BIND; break; case SECCLASS_SCTP_SOCKET: node_perm = SCTP_SOCKET__NODE_BIND; break; default: node_perm = RAWIP_SOCKET__NODE_BIND; break; } err = sel_netnode_sid(addrp, family_sa, &sid); if (err) goto out; if (family_sa == AF_INET) ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; else ad.u.net->v6info.saddr = addr6->sin6_addr; err = avc_has_perm(sksec->sid, sid, sksec->sclass, node_perm, &ad); if (err) goto out; } out: return err; err_af: /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; return -EAFNOSUPPORT; } /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst */ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = selinux_sock(sk); int err; err = sock_has_perm(sk, SOCKET__CONNECT); if (err) return err; if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* connect(AF_UNSPEC) has special handling, as it is a documented * way to disconnect the socket */ if (address->sa_family == AF_UNSPEC) return 0; /* * If a TCP, DCCP or SCTP socket, check name_connect permission * for the port. */ if (sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_DCCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) { struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; unsigned short snum; u32 sid, perm; /* sctp_connectx(3) calls via selinux_sctp_bind_connect() * that validates multiple connect addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ switch (address->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)address; if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; snum = ntohs(addr4->sin_port); break; case AF_INET6: addr6 = (struct sockaddr_in6 *)address; if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; snum = ntohs(addr6->sin6_port); break; default: /* Note that SCTP services expect -EINVAL, whereas * others expect -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; else return -EAFNOSUPPORT; } err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) return err; switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: perm = TCP_SOCKET__NAME_CONNECT; break; case SECCLASS_DCCP_SOCKET: perm = DCCP_SOCKET__NAME_CONNECT; break; case SECCLASS_SCTP_SOCKET: perm = SCTP_SOCKET__NAME_CONNECT; break; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->dport = htons(snum); ad.u.net->family = address->sa_family; err = avc_has_perm(sksec->sid, sid, sksec->sclass, perm, &ad); if (err) return err; } return 0; } /* Supports connect(2), see comments in selinux_socket_connect_helper() */ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { int err; struct sock *sk = sock->sk; err = selinux_socket_connect_helper(sock, address, addrlen); if (err) return err; return selinux_netlbl_socket_connect(sk, address); } static int selinux_socket_listen(struct socket *sock, int backlog) { return sock_has_perm(sock->sk, SOCKET__LISTEN); } static int selinux_socket_accept(struct socket *sock, struct socket *newsock) { int err; struct inode_security_struct *isec; struct inode_security_struct *newisec; u16 sclass; u32 sid; err = sock_has_perm(sock->sk, SOCKET__ACCEPT); if (err) return err; isec = inode_security_novalidate(SOCK_INODE(sock)); spin_lock(&isec->lock); sclass = isec->sclass; sid = isec->sid; spin_unlock(&isec->lock); newisec = inode_security_novalidate(SOCK_INODE(newsock)); newisec->sclass = sclass; newisec->sid = sid; newisec->initialized = LABEL_INITIALIZED; return 0; } static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return sock_has_perm(sock->sk, SOCKET__WRITE); } static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return sock_has_perm(sock->sk, SOCKET__READ); } static int selinux_socket_getsockname(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_getpeername(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_setsockopt(struct socket *sock, int level, int optname) { int err; err = sock_has_perm(sock->sk, SOCKET__SETOPT); if (err) return err; return selinux_netlbl_socket_setsockopt(sock, level, optname); } static int selinux_socket_getsockopt(struct socket *sock, int level, int optname) { return sock_has_perm(sock->sk, SOCKET__GETOPT); } static int selinux_socket_shutdown(struct socket *sock, int how) { return sock_has_perm(sock->sk, SOCKET__SHUTDOWN); } static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { struct sk_security_struct *sksec_sock = selinux_sock(sock); struct sk_security_struct *sksec_other = selinux_sock(other); struct sk_security_struct *sksec_new = selinux_sock(newsk); struct common_audit_data ad; struct lsm_network_audit net; int err; ad_net_init_from_sk(&ad, &net, other); err = avc_has_perm(sksec_sock->sid, sksec_other->sid, sksec_other->sclass, UNIX_STREAM_SOCKET__CONNECTTO, &ad); if (err) return err; /* server child socket */ sksec_new->peer_sid = sksec_sock->sid; err = security_sid_mls_copy(sksec_other->sid, sksec_sock->sid, &sksec_new->sid); if (err) return err; /* connecting socket */ sksec_sock->peer_sid = sksec_new->sid; return 0; } static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { struct sk_security_struct *ssec = selinux_sock(sock->sk); struct sk_security_struct *osec = selinux_sock(other->sk); struct common_audit_data ad; struct lsm_network_audit net; ad_net_init_from_sk(&ad, &net, other->sk); return avc_has_perm(ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO, &ad); } static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex, char *addrp, u16 family, u32 peer_sid, struct common_audit_data *ad) { int err; u32 if_sid; u32 node_sid; err = sel_netif_sid(ns, ifindex, &if_sid); if (err) return err; err = avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__INGRESS, ad); if (err) return err; err = sel_netnode_sid(addrp, family, &node_sid); if (err) return err; return avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__RECVFROM, ad); } static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; struct sk_security_struct *sksec = selinux_sock(sk); u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (selinux_secmark_enabled()) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } err = selinux_netlbl_sock_rcv_skb(sksec, skb, family, &ad); if (err) return err; err = selinux_xfrm_sock_rcv_skb(sksec->sid, skb, &ad); return err; } static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err, peerlbl_active, secmark_active; struct sk_security_struct *sksec = selinux_sock(sk); u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; if (family != PF_INET && family != PF_INET6) return 0; /* Handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_sock_rcv_skb_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_sock_rcv_skb_compat(sk, skb, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return 0; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (peerlbl_active) { u32 peer_sid; err = selinux_skb_peerlbl_sid(skb, family, &peer_sid); if (err) return err; err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } } if (secmark_active) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } return err; } static int selinux_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { int err = 0; char *scontext = NULL; u32 scontext_len; struct sk_security_struct *sksec = selinux_sock(sock->sk); u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) peer_sid = sksec->peer_sid; if (peer_sid == SECSID_NULL) return -ENOPROTOOPT; err = security_sid_to_context(peer_sid, &scontext, &scontext_len); if (err) return err; if (scontext_len > len) { err = -ERANGE; goto out_len; } if (copy_to_sockptr(optval, scontext, scontext_len)) err = -EFAULT; out_len: if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len))) err = -EFAULT; kfree(scontext); return err; } static int selinux_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { u32 peer_secid = SECSID_NULL; u16 family; if (skb && skb->protocol == htons(ETH_P_IP)) family = PF_INET; else if (skb && skb->protocol == htons(ETH_P_IPV6)) family = PF_INET6; else if (sock) family = sock->sk->sk_family; else { *secid = SECSID_NULL; return -EINVAL; } if (sock && family == PF_UNIX) { struct inode_security_struct *isec; isec = inode_security_novalidate(SOCK_INODE(sock)); peer_secid = isec->sid; } else if (skb) selinux_skb_peerlbl_sid(skb, family, &peer_secid); *secid = peer_secid; if (peer_secid == SECSID_NULL) return -ENOPROTOOPT; return 0; } static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { struct sk_security_struct *sksec = selinux_sock(sk); sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); return 0; } static void selinux_sk_free_security(struct sock *sk) { struct sk_security_struct *sksec = selinux_sock(sk); selinux_netlbl_sk_security_free(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = selinux_sock(sk); struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; newsksec->sclass = sksec->sclass; selinux_netlbl_sk_security_reset(newsksec); } static void selinux_sk_getsecid(const struct sock *sk, u32 *secid) { if (!sk) *secid = SECINITSID_ANY_SOCKET; else { const struct sk_security_struct *sksec = selinux_sock(sk); *secid = sksec->sid; } } static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); struct sk_security_struct *sksec = selinux_sock(sk); if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) isec->sid = sksec->sid; sksec->sclass = isec->sclass; } /* * Determines peer_secid for the asoc and updates socket's peer label * if it's the first association on the socket. */ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, struct sk_buff *skb) { struct sock *sk = asoc->base.sk; u16 family = sk->sk_family; struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; struct lsm_network_audit net; int err; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; if (selinux_peerlbl_enabled()) { asoc->peer_secid = SECSID_NULL; /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ err = selinux_skb_peerlbl_sid(skb, family, &asoc->peer_secid); if (err) return err; if (asoc->peer_secid == SECSID_NULL) asoc->peer_secid = SECINITSID_UNLABELED; } else { asoc->peer_secid = SECINITSID_UNLABELED; } if (sksec->sctp_assoc_state == SCTP_ASSOC_UNSET) { sksec->sctp_assoc_state = SCTP_ASSOC_SET; /* Here as first association on socket. As the peer SID * was allowed by peer recv (and the netif/node checks), * then it is approved by policy and used as the primary * peer SID for getpeercon(3). */ sksec->peer_sid = asoc->peer_secid; } else if (sksec->peer_sid != asoc->peer_secid) { /* Other association peer SIDs are checked to enforce * consistency among the peer SIDs. */ ad_net_init_from_sk(&ad, &net, asoc->base.sk); err = avc_has_perm(sksec->peer_sid, asoc->peer_secid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); if (err) return err; } return 0; } /* Called whenever SCTP receives an INIT or COOKIE ECHO chunk. This * happens on an incoming connect(2), sctp_connectx(3) or * sctp_sendmsg(3) (with no association already present). */ static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); u32 conn_sid; int err; if (!selinux_policycap_extsockclass()) return 0; err = selinux_sctp_process_new_assoc(asoc, skb); if (err) return err; /* Compute the MLS component for the connection and store * the information in asoc. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. */ err = selinux_conn_sid(sksec->sid, asoc->peer_secid, &conn_sid); if (err) return err; asoc->secid = conn_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ return selinux_netlbl_sctp_assoc_request(asoc, skb); } /* Called when SCTP receives a COOKIE ACK chunk as the final * response to an association request (initited by us). */ static int selinux_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); if (!selinux_policycap_extsockclass()) return 0; /* Inherit secid from the parent socket - this will be picked up * by selinux_sctp_sk_clone() if the association gets peeled off * into a new socket. */ asoc->secid = sksec->sid; return selinux_sctp_process_new_assoc(asoc, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting * based on their @optname. */ static int selinux_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { int len, err = 0, walk_size = 0; void *addr_buf; struct sockaddr *addr; struct socket *sock; if (!selinux_policycap_extsockclass()) return 0; /* Process one or more addresses that may be IPv4 or IPv6 */ sock = sk->sk_socket; addr_buf = address; while (walk_size < addrlen) { if (walk_size + sizeof(sa_family_t) > addrlen) return -EINVAL; addr = addr_buf; switch (addr->sa_family) { case AF_UNSPEC: case AF_INET: len = sizeof(struct sockaddr_in); break; case AF_INET6: len = sizeof(struct sockaddr_in6); break; default: return -EINVAL; } if (walk_size + len > addrlen) return -EINVAL; err = -EINVAL; switch (optname) { /* Bind checks */ case SCTP_PRIMARY_ADDR: case SCTP_SET_PEER_PRIMARY_ADDR: case SCTP_SOCKOPT_BINDX_ADD: err = selinux_socket_bind(sock, addr, len); break; /* Connect checks */ case SCTP_SOCKOPT_CONNECTX: case SCTP_PARAM_SET_PRIMARY: case SCTP_PARAM_ADD_IP: case SCTP_SENDMSG_CONNECT: err = selinux_socket_connect_helper(sock, addr, len); if (err) return err; /* As selinux_sctp_bind_connect() is called by the * SCTP protocol layer, the socket is already locked, * therefore selinux_netlbl_socket_connect_locked() * is called here. The situations handled are: * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2), * whenever a new IP address is added or when a new * primary address is selected. * Note that an SCTP connect(2) call happens before * the SCTP protocol layer and is handled via * selinux_socket_connect(). */ err = selinux_netlbl_socket_connect_locked(sk, addr); break; } if (err) return err; addr_buf += len; walk_size += len; } return 0; } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = selinux_sock(sk); struct sk_security_struct *newsksec = selinux_sock(newsk); /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. */ if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); newsksec->sid = asoc->secid; newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { struct sk_security_struct *ssksec = selinux_sock(ssk); struct sk_security_struct *sksec = selinux_sock(sk); ssksec->sclass = sksec->sclass; ssksec->sid = sksec->sid; /* replace the existing subflow label deleting the existing one * and re-recreating a new label using the updated context */ selinux_netlbl_sk_security_free(ssksec); return selinux_netlbl_socket_post_create(ssk, ssk->sk_family); } static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct sk_security_struct *sksec = selinux_sock(sk); int err; u16 family = req->rsk_ops->family; u32 connsid; u32 peersid; err = selinux_skb_peerlbl_sid(skb, family, &peersid); if (err) return err; err = selinux_conn_sid(sksec->sid, peersid, &connsid); if (err) return err; req->secid = connsid; req->peer_secid = peersid; return selinux_netlbl_inet_conn_request(req, family); } static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; /* NOTE: Ideally, we should also get the isec->sid for the new socket in sync, but we don't have the isec available yet. So we will wait until sock_graft to do it, by which time it will have been created and available. */ /* We don't need to take any sort of lock here as we are the only * thread with access to newsksec */ selinux_netlbl_inet_csk_clone(newsk, req->rsk_ops->family); } static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; struct sk_security_struct *sksec = selinux_sock(sk); /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } static int selinux_secmark_relabel_packet(u32 sid) { return avc_has_perm(current_sid(), sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL); } static void selinux_secmark_refcount_inc(void) { atomic_inc(&selinux_secmark_refcount); } static void selinux_secmark_refcount_dec(void) { atomic_dec(&selinux_secmark_refcount); } static void selinux_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { flic->flowic_secid = req->secid; } static int selinux_tun_dev_alloc_security(void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); tunsec->sid = current_sid(); return 0; } static int selinux_tun_dev_create(void) { u32 sid = current_sid(); /* we aren't taking into account the "sockcreate" SID since the socket * that is being created here is not a socket in the traditional sense, * instead it is a private sock, accessible only to the kernel, and * representing a wide range of network traffic spanning multiple * connections unlike traditional sockets - check the TUN driver to * get a better understanding of why this socket is special */ return avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__CREATE, NULL); } static int selinux_tun_dev_attach_queue(void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__ATTACH_QUEUE, NULL); } static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); struct sk_security_struct *sksec = selinux_sock(sk); /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply * labeling without the support of the TUN user the resulting labeled * traffic from the other end of the connection would almost certainly * cause confusion to the TUN user that had no idea network labeling * protocols were being used */ sksec->sid = tunsec->sid; sksec->sclass = SECCLASS_TUN_SOCKET; return 0; } static int selinux_tun_dev_open(void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); u32 sid = current_sid(); int err; err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELFROM, NULL); if (err) return err; err = avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELTO, NULL); if (err) return err; tunsec->sid = sid; return 0; } #ifdef CONFIG_NETFILTER static unsigned int selinux_ip_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int ifindex; u16 family; char *addrp; u32 peer_sid; struct common_audit_data ad; struct lsm_network_audit net; int secmark_active, peerlbl_active; if (!selinux_policycap_netpeer()) return NF_ACCEPT; secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; family = state->pf; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid) != 0) return NF_DROP; ifindex = state->in->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0) return NF_DROP; if (peerlbl_active) { int err; err = selinux_inet_sys_rcv_skb(state->net, ifindex, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 1); return NF_DROP; } } if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, PACKET__FORWARD_IN, &ad)) return NF_DROP; if (netlbl_enabled()) /* we do this in the FORWARD path and not the POST_ROUTING * path because we want to make sure we apply the necessary * labeling before IPsec is applied so we can leverage AH * protection */ if (selinux_netlbl_skbuff_setsid(skb, family, peer_sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; u32 sid; if (!netlbl_enabled()) return NF_ACCEPT; /* we do this in the LOCAL_OUT path and not the POST_ROUTING path * because we want to make sure we apply the necessary labeling * before IPsec is applied so we can leverage AH protection */ sk = sk_to_full_sk(skb->sk); if (sk) { struct sk_security_struct *sksec; if (sk_listener(sk)) /* if the socket is the listening state then this * packet is a SYN-ACK packet which means it needs to * be labeled based on the connection/request_sock and * not the parent socket. unfortunately, we can't * lookup the request_sock yet as it isn't queued on * the parent socket until after the SYN-ACK is sent. * the "solution" is to simply pass the packet as-is * as any IP option based labeling should be copied * from the initial connection request (in the IP * layer). it is far from ideal, but until we get a * security label in the packet itself this is the * best we can do. */ return NF_ACCEPT; /* standard practice, label using the parent socket */ sksec = selinux_sock(sk); sid = sksec->sid; } else sid = SECINITSID_KERNEL; if (selinux_netlbl_skbuff_setsid(skb, state->pf, sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; struct sk_security_struct *sksec; struct common_audit_data ad; struct lsm_network_audit net; u8 proto = 0; sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; sksec = selinux_sock(sk); ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf); if (selinux_parse_skb(skb, &ad, NULL, 0, &proto)) return NF_DROP; if (selinux_secmark_enabled()) if (avc_has_perm(sksec->sid, skb->secmark, SECCLASS_PACKET, PACKET__SEND, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto)) return NF_DROP_ERR(-ECONNREFUSED); return NF_ACCEPT; } static unsigned int selinux_ip_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { u16 family; u32 secmark_perm; u32 peer_sid; int ifindex; struct sock *sk; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; int secmark_active, peerlbl_active; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_ip_postroute_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_ip_postroute_compat(skb, state); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; sk = skb_to_full_sk(skb); #ifdef CONFIG_XFRM /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec * packet transformation so allow the packet to pass without any checks * since we'll have another chance to perform access control checks * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst * is NULL, in this case go ahead and apply access control. * NOTE: if this is a local socket (skb->sk != NULL) that is in the * TCP listening state we cannot wait until the XFRM processing * is done as we will miss out on the SA label if we do; * unfortunately, this means more work, but it is only once per * connection. */ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && !(sk && sk_listener(sk))) return NF_ACCEPT; #endif family = state->pf; if (sk == NULL) { /* Without an associated socket the packet is either coming * from the kernel or it is being forwarded; check the packet * to determine which and if the packet is being forwarded * query the packet directly to determine the security label. */ if (skb->skb_iif) { secmark_perm = PACKET__FORWARD_OUT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid)) return NF_DROP; } else { secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } } else if (sk_listener(sk)) { /* Locally generated packet but the associated socket is in the * listening state which means this is a SYN-ACK packet. In * this particular case the correct security label is assigned * to the connection/request_sock but unfortunately we can't * query the request_sock as it isn't queued on the parent * socket until after the SYN-ACK packet is sent; the only * viable choice is to regenerate the label like we do in * selinux_inet_conn_request(). See also selinux_ip_output() * for similar problems. */ u32 skb_sid; struct sk_security_struct *sksec; sksec = selinux_sock(sk); if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL * and the packet has been through at least one XFRM * transformation then we must be dealing with the "final" * form of labeled IPsec packet; since we've already applied * all of our access controls on this packet we can safely * pass the packet. */ if (skb_sid == SECSID_NULL) { switch (family) { case PF_INET: if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; case PF_INET6: if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; default: return NF_DROP_ERR(-ECONNREFUSED); } } if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) return NF_DROP; secmark_perm = PACKET__SEND; } else { /* Locally generated packet, fetch the security label from the * associated socket. */ struct sk_security_struct *sksec = selinux_sock(sk); peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } ifindex = state->out->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL)) return NF_DROP; if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, secmark_perm, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (peerlbl_active) { u32 if_sid; u32 node_sid; if (sel_netif_sid(state->net, ifindex, &if_sid)) return NF_DROP; if (avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__EGRESS, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (sel_netnode_sid(addrp, family, &node_sid)) return NF_DROP; if (avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__SENDTO, &ad)) return NF_DROP_ERR(-ECONNREFUSED); } return NF_ACCEPT; } #endif /* CONFIG_NETFILTER */ static int nlmsg_sock_has_extended_perms(struct sock *sk, u32 perms, u16 nlmsg_type) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; u8 driver; u8 xperm; if (sock_skip_has_perm(sksec->sid)) return 0; ad_net_init_from_sk(&ad, &net, sk); driver = nlmsg_type >> 8; xperm = nlmsg_type & 0xff; return avc_has_extended_perms(current_sid(), sksec->sid, sksec->sclass, perms, driver, xperm, &ad); } static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { int rc = 0; unsigned int msg_len; unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; struct sk_security_struct *sksec = selinux_sock(sk); u16 sclass = sksec->sclass; u32 perm; while (data_len >= nlmsg_total_size(0)) { nlh = (struct nlmsghdr *)data; /* NOTE: the nlmsg_len field isn't reliably set by some netlink * users which means we can't reject skb's with bogus * length fields; our solution is to follow what * netlink_rcv_skb() does and simply skip processing at * messages with length fields that are clearly junk */ if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len) return 0; rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm); if (rc == 0) { if (selinux_policycap_netlink_xperm()) { rc = nlmsg_sock_has_extended_perms( sk, perm, nlh->nlmsg_type); } else { rc = sock_has_perm(sk, perm); } if (rc) return rc; } else if (rc == -EINVAL) { /* -EINVAL is a missing msg/perm mapping */ pr_warn_ratelimited("SELinux: unrecognized netlink" " message: protocol=%hu nlmsg_type=%hu sclass=%s" " pid=%d comm=%s\n", sk->sk_protocol, nlh->nlmsg_type, secclass_map[sclass - 1].name, task_pid_nr(current), current->comm); if (enforcing_enabled() && !security_get_allow_unknown()) return rc; rc = 0; } else if (rc == -ENOENT) { /* -ENOENT is a missing socket/class mapping, ignore */ rc = 0; } else { return rc; } /* move to the next message after applying netlink padding */ msg_len = NLMSG_ALIGN(nlh->nlmsg_len); if (msg_len >= data_len) return 0; data_len -= msg_len; data += msg_len; } return rc; } static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) { isec->sclass = sclass; isec->sid = current_sid(); } static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(ipc_perms); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = ipc_perms->key; return avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad); } static int selinux_msg_msg_alloc_security(struct msg_msg *msg) { struct msg_security_struct *msec; msec = selinux_msg_msg(msg); msec->sid = SECINITSID_UNLABELED; return 0; } /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ipc_init_security(isec, SECCLASS_MSGQ); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); } static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__ASSOCIATE, &ad); } static int selinux_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case MSG_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: perms = MSGQ__GETATTR | MSGQ__ASSOCIATE; break; case IPC_SET: perms = MSGQ__SETATTR; break; case IPC_RMID: perms = MSGQ__DESTROY; break; default: return 0; } return ipc_has_perm(msq, perms); } static int selinux_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); /* * First time through, need to assign label to the message */ if (msec->sid == SECINITSID_UNLABELED) { /* * Compute new sid based on current process and * message queue this message will be stored in */ rc = security_transition_sid(sid, isec->sid, SECCLASS_MSG, NULL, &msec->sid); if (rc) return rc; } ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; /* Can this process write to the queue? */ rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__WRITE, &ad); if (!rc) /* Can this process send the message */ rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__SEND, &ad); if (!rc) /* Can the message be put in the queue? */ rc = avc_has_perm(msec->sid, isec->sid, SECCLASS_MSGQ, MSGQ__ENQUEUE, &ad); return rc; } static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = task_sid_obj(target); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__READ, &ad); if (!rc) rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__RECEIVE, &ad); return rc; } /* Shared Memory security operations */ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ipc_init_security(isec, SECCLASS_SHM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); } static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__ASSOCIATE, &ad); } /* Note, at this point, shp is locked down */ static int selinux_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case SHM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case SHM_STAT: case SHM_STAT_ANY: perms = SHM__GETATTR | SHM__ASSOCIATE; break; case IPC_SET: perms = SHM__SETATTR; break; case SHM_LOCK: case SHM_UNLOCK: perms = SHM__LOCK; break; case IPC_RMID: perms = SHM__DESTROY; break; default: return 0; } return ipc_has_perm(shp, perms); } static int selinux_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { u32 perms; if (shmflg & SHM_RDONLY) perms = SHM__READ; else perms = SHM__READ | SHM__WRITE; return ipc_has_perm(shp, perms); } /* Semaphore security operations */ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ipc_init_security(isec, SECCLASS_SEM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); } static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__ASSOCIATE, &ad); } /* Note, at this point, sma is locked down */ static int selinux_sem_semctl(struct kern_ipc_perm *sma, int cmd) { int err; u32 perms; switch (cmd) { case IPC_INFO: case SEM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case GETPID: case GETNCNT: case GETZCNT: perms = SEM__GETATTR; break; case GETVAL: case GETALL: perms = SEM__READ; break; case SETVAL: case SETALL: perms = SEM__WRITE; break; case IPC_RMID: perms = SEM__DESTROY; break; case IPC_SET: perms = SEM__SETATTR; break; case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: perms = SEM__GETATTR | SEM__ASSOCIATE; break; default: return 0; } err = ipc_has_perm(sma, perms); return err; } static int selinux_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { u32 perms; if (alter) perms = SEM__READ | SEM__WRITE; else perms = SEM__READ; return ipc_has_perm(sma, perms); } static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { u32 av = 0; av = 0; if (flag & S_IRUGO) av |= IPC__UNIX_READ; if (flag & S_IWUGO) av |= IPC__UNIX_WRITE; if (av == 0) return 0; return ipc_has_perm(ipcp, av); } static void selinux_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop) { struct ipc_security_struct *isec = selinux_ipc(ipcp); prop->selinux.secid = isec->sid; } static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) { if (inode) inode_doinit_with_dentry(inode, dentry); } static int selinux_lsm_getattr(unsigned int attr, struct task_struct *p, char **value) { const struct task_security_struct *tsec; int error; u32 sid; u32 len; rcu_read_lock(); tsec = selinux_cred(__task_cred(p)); if (p != current) { error = avc_has_perm(current_sid(), tsec->sid, SECCLASS_PROCESS, PROCESS__GETATTR, NULL); if (error) goto err_unlock; } switch (attr) { case LSM_ATTR_CURRENT: sid = tsec->sid; break; case LSM_ATTR_PREV: sid = tsec->osid; break; case LSM_ATTR_EXEC: sid = tsec->exec_sid; break; case LSM_ATTR_FSCREATE: sid = tsec->create_sid; break; case LSM_ATTR_KEYCREATE: sid = tsec->keycreate_sid; break; case LSM_ATTR_SOCKCREATE: sid = tsec->sockcreate_sid; break; default: error = -EOPNOTSUPP; goto err_unlock; } rcu_read_unlock(); if (sid == SECSID_NULL) { *value = NULL; return 0; } error = security_sid_to_context(sid, value, &len); if (error) return error; return len; err_unlock: rcu_read_unlock(); return error; } static int selinux_lsm_setattr(u64 attr, void *value, size_t size) { struct task_security_struct *tsec; struct cred *new; u32 mysid = current_sid(), sid = 0, ptsid; int error; char *str = value; /* * Basic control over ability to set these attributes at all. */ switch (attr) { case LSM_ATTR_EXEC: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETEXEC, NULL); break; case LSM_ATTR_FSCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETFSCREATE, NULL); break; case LSM_ATTR_KEYCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETKEYCREATE, NULL); break; case LSM_ATTR_SOCKCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETSOCKCREATE, NULL); break; case LSM_ATTR_CURRENT: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETCURRENT, NULL); break; default: error = -EOPNOTSUPP; break; } if (error) return error; /* Obtain a SID for the context, if one was specified. */ if (size && str[0] && str[0] != '\n') { if (str[size-1] == '\n') { str[size-1] = 0; size--; } error = security_context_to_sid(value, size, &sid, GFP_KERNEL); if (error == -EINVAL && attr == LSM_ATTR_FSCREATE) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, * otherwise the context contains a nul and * we should audit that */ if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return error; audit_log_format(ab, "op=fscreate invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return error; } error = security_context_to_sid_force(value, size, &sid); } if (error) return error; } new = prepare_creds(); if (!new) return -ENOMEM; /* Permission checking based on the specified context is performed during the actual operation (execve, open/mkdir/...), when we know the full context of the operation. See selinux_bprm_creds_for_exec for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ tsec = selinux_cred(new); if (attr == LSM_ATTR_EXEC) { tsec->exec_sid = sid; } else if (attr == LSM_ATTR_FSCREATE) { tsec->create_sid = sid; } else if (attr == LSM_ATTR_KEYCREATE) { if (sid) { error = avc_has_perm(mysid, sid, SECCLASS_KEY, KEY__CREATE, NULL); if (error) goto abort_change; } tsec->keycreate_sid = sid; } else if (attr == LSM_ATTR_SOCKCREATE) { tsec->sockcreate_sid = sid; } else if (attr == LSM_ATTR_CURRENT) { error = -EINVAL; if (sid == 0) goto abort_change; if (!current_is_single_threaded()) { error = security_bounded_transition(tsec->sid, sid); if (error) goto abort_change; } /* Check permissions for the transition. */ error = avc_has_perm(tsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) goto abort_change; /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = ptrace_parent_sid(); if (ptsid != 0) { error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (error) goto abort_change; } tsec->sid = sid; } else { error = -EINVAL; goto abort_change; } commit_creds(new); return size; abort_change: abort_creds(new); return error; } /** * selinux_getselfattr - Get SELinux current task attributes * @attr: the requested attribute * @ctx: buffer to receive the result * @size: buffer size (input), buffer size used (output) * @flags: unused * * Fill the passed user space @ctx with the details of the requested * attribute. * * Returns the number of attributes on success, an error code otherwise. * There will only ever be one attribute. */ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, u32 *size, u32 flags) { int rc; char *val = NULL; int val_len; val_len = selinux_lsm_getattr(attr, current, &val); if (val_len < 0) return val_len; rc = lsm_fill_user_ctx(ctx, size, val, val_len, LSM_ID_SELINUX, 0); kfree(val); return (!rc ? 1 : rc); } static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) { int rc; rc = selinux_lsm_setattr(attr, ctx->ctx, ctx->ctx_len); if (rc > 0) return 0; return rc; } static int selinux_getprocattr(struct task_struct *p, const char *name, char **value) { unsigned int attr = lsm_name_to_attr(name); int rc; if (attr) { rc = selinux_lsm_getattr(attr, p, value); if (rc != -EOPNOTSUPP) return rc; } return -EINVAL; } static int selinux_setprocattr(const char *name, void *value, size_t size) { int attr = lsm_name_to_attr(name); if (attr) return selinux_lsm_setattr(attr, value, size); return -EINVAL; } static int selinux_ismaclabel(const char *name) { return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { return security_sid_to_context(secid, secdata, seclen); } static int selinux_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, u32 *seclen) { return selinux_secid_to_secctx(prop->selinux.secid, secdata, seclen); } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { return security_context_to_sid(secdata, seclen, secid, GFP_KERNEL); } static void selinux_release_secctx(char *secdata, u32 seclen) { kfree(secdata); } static void selinux_inode_invalidate_secctx(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); spin_lock(&isec->lock); isec->initialized = LABEL_INVALID; spin_unlock(&isec->lock); } /* * called with inode->i_mutex locked */ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { int rc = selinux_inode_setsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, ctxlen, 0); /* Do not return error when suppressing label (SBLABEL_MNT not set). */ return rc == -EOPNOTSUPP ? 0 : rc; } /* * called with inode->i_mutex locked */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0, NULL); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; len = selinux_inode_getsecurity(&nop_mnt_idmap, inode, XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; *ctxlen = len; return 0; } #ifdef CONFIG_KEYS static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; struct key_security_struct *ksec = selinux_key(k); tsec = selinux_cred(cred); if (tsec->keycreate_sid) ksec->sid = tsec->keycreate_sid; else ksec->sid = tsec->sid; return 0; } static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { struct key *key; struct key_security_struct *ksec; u32 perm, sid; switch (need_perm) { case KEY_NEED_VIEW: perm = KEY__VIEW; break; case KEY_NEED_READ: perm = KEY__READ; break; case KEY_NEED_WRITE: perm = KEY__WRITE; break; case KEY_NEED_SEARCH: perm = KEY__SEARCH; break; case KEY_NEED_LINK: perm = KEY__LINK; break; case KEY_NEED_SETATTR: perm = KEY__SETATTR; break; case KEY_NEED_UNLINK: case KEY_SYSADMIN_OVERRIDE: case KEY_AUTHTOKEN_OVERRIDE: case KEY_DEFER_PERM_CHECK: return 0; default: WARN_ON(1); return -EPERM; } sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); ksec = selinux_key(key); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { struct key_security_struct *ksec = selinux_key(key); char *context = NULL; unsigned len; int rc; rc = security_sid_to_context(ksec->sid, &context, &len); if (!rc) rc = len; *_buffer = context; return rc; } #ifdef CONFIG_KEY_NOTIFICATIONS static int selinux_watch_key(struct key *key) { struct key_security_struct *ksec = selinux_key(key); u32 sid = current_sid(); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, KEY__VIEW, NULL); } #endif #endif #ifdef CONFIG_SECURITY_INFINIBAND static int selinux_ib_pkey_access(void *ib_sec, u64 subnet_prefix, u16 pkey_val) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibpkey_audit ibpkey; err = sel_ib_pkey_sid(subnet_prefix, pkey_val, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBPKEY; ibpkey.subnet_prefix = subnet_prefix; ibpkey.pkey = pkey_val; ad.u.ibpkey = &ibpkey; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_PKEY, INFINIBAND_PKEY__ACCESS, &ad); } static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, u8 port_num) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibendport_audit ibendport; err = security_ib_endport_sid(dev_name, port_num, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBENDPORT; ibendport.dev_name = dev_name; ibendport.port = port_num; ad.u.ibendport = &ibendport; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_ENDPORT, INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad); } static int selinux_ib_alloc_security(void *ib_sec) { struct ib_security_struct *sec = selinux_ib(ib_sec); sec->sid = current_sid(); return 0; } #endif #ifdef CONFIG_BPF_SYSCALL static int selinux_bpf(int cmd, union bpf_attr *attr, unsigned int size) { u32 sid = current_sid(); int ret; switch (cmd) { case BPF_MAP_CREATE: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); break; case BPF_PROG_LOAD: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); break; default: ret = 0; break; } return ret; } static u32 bpf_map_fmode_to_av(fmode_t fmode) { u32 av = 0; if (fmode & FMODE_READ) av |= BPF__MAP_READ; if (fmode & FMODE_WRITE) av |= BPF__MAP_WRITE; return av; } /* This function will check the file pass through unix socket or binder to see * if it is a bpf related object. And apply corresponding checks on the bpf * object based on the type. The bpf maps and programs, not like other files and * socket, are using a shared anonymous inode inside the kernel as their inode. * So checking that inode cannot identify if the process have privilege to * access the bpf object and that's why we have to add this additional check in * selinux_file_receive and selinux_binder_transfer_files. */ static int bpf_fd_pass(const struct file *file, u32 sid) { struct bpf_security_struct *bpfsec; struct bpf_prog *prog; struct bpf_map *map; int ret; if (file->f_op == &bpf_map_fops) { map = file->private_data; bpfsec = map->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(file->f_mode), NULL); if (ret) return ret; } else if (file->f_op == &bpf_prog_fops) { prog = file->private_data; bpfsec = prog->aux->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); if (ret) return ret; } return 0; } static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = map->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(fmode), NULL); } static int selinux_bpf_prog(struct bpf_prog *prog) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = prog->aux->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); } static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); map->security = bpfsec; return 0; } static void selinux_bpf_map_free(struct bpf_map *map) { struct bpf_security_struct *bpfsec = map->security; map->security = NULL; kfree(bpfsec); } static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); prog->aux->security = bpfsec; return 0; } static void selinux_bpf_prog_free(struct bpf_prog *prog) { struct bpf_security_struct *bpfsec = prog->aux->security; prog->aux->security = NULL; kfree(bpfsec); } static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, const struct path *path) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); token->security = bpfsec; return 0; } static void selinux_bpf_token_free(struct bpf_token *token) { struct bpf_security_struct *bpfsec = token->security; token->security = NULL; kfree(bpfsec); } #endif struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_key = sizeof(struct key_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), #ifdef CONFIG_PERF_EVENTS .lbs_perf_event = sizeof(struct perf_event_security_struct), #endif .lbs_sock = sizeof(struct sk_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, .lbs_tun_dev = sizeof(struct tun_security_struct), .lbs_ib = sizeof(struct ib_security_struct), }; #ifdef CONFIG_PERF_EVENTS static int selinux_perf_event_open(struct perf_event_attr *attr, int type) { u32 requested, sid = current_sid(); if (type == PERF_SECURITY_OPEN) requested = PERF_EVENT__OPEN; else if (type == PERF_SECURITY_CPU) requested = PERF_EVENT__CPU; else if (type == PERF_SECURITY_KERNEL) requested = PERF_EVENT__KERNEL; else if (type == PERF_SECURITY_TRACEPOINT) requested = PERF_EVENT__TRACEPOINT; else return -EINVAL; return avc_has_perm(sid, sid, SECCLASS_PERF_EVENT, requested, NULL); } static int selinux_perf_event_alloc(struct perf_event *event) { struct perf_event_security_struct *perfsec; perfsec = selinux_perf_event(event->security); perfsec->sid = current_sid(); return 0; } static int selinux_perf_event_read(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL); } static int selinux_perf_event_write(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL); } #endif #ifdef CONFIG_IO_URING /** * selinux_uring_override_creds - check the requested cred override * @new: the target creds * * Check to see if the current task is allowed to override it's credentials * to service an io_uring operation. */ static int selinux_uring_override_creds(const struct cred *new) { return avc_has_perm(current_sid(), cred_sid(new), SECCLASS_IO_URING, IO_URING__OVERRIDE_CREDS, NULL); } /** * selinux_uring_sqpoll - check if a io_uring polling thread can be created * * Check to see if the current task is allowed to create a new io_uring * kernel polling thread. */ static int selinux_uring_sqpoll(void) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_IO_URING, IO_URING__SQPOLL, NULL); } /** * selinux_uring_cmd - check if IORING_OP_URING_CMD is allowed * @ioucmd: the io_uring command structure * * Check to see if the current domain is allowed to execute an * IORING_OP_URING_CMD against the device/file specified in @ioucmd. * */ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd) { struct file *file = ioucmd->file; struct inode *inode = file_inode(file); struct inode_security_struct *isec = selinux_inode(inode); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return avc_has_perm(current_sid(), isec->sid, SECCLASS_IO_URING, IO_URING__CMD, &ad); } #endif /* CONFIG_IO_URING */ static const struct lsm_id selinux_lsmid = { .name = "selinux", .id = LSM_ID_SELINUX, }; /* * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order: * 1. any hooks that don't belong to (2.) or (3.) below, * 2. hooks that both access structures allocated by other hooks, and allocate * structures that can be later accessed by other hooks (mostly "cloning" * hooks), * 3. hooks that only allocate structures that can be later accessed by other * hooks ("allocating" hooks). * * Please follow block comment delimiters in the list to keep this order. */ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), LSM_HOOK_INIT(binder_transfer_binder, selinux_binder_transfer_binder), LSM_HOOK_INIT(binder_transfer_file, selinux_binder_transfer_file), LSM_HOOK_INIT(ptrace_access_check, selinux_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, selinux_ptrace_traceme), LSM_HOOK_INIT(capget, selinux_capget), LSM_HOOK_INIT(capset, selinux_capset), LSM_HOOK_INIT(capable, selinux_capable), LSM_HOOK_INIT(quotactl, selinux_quotactl), LSM_HOOK_INIT(quota_on, selinux_quota_on), LSM_HOOK_INIT(syslog, selinux_syslog), LSM_HOOK_INIT(vm_enough_memory, selinux_vm_enough_memory), LSM_HOOK_INIT(netlink_send, selinux_netlink_send), LSM_HOOK_INIT(bprm_creds_for_exec, selinux_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds), LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts), LSM_HOOK_INIT(sb_mnt_opts_compat, selinux_sb_mnt_opts_compat), LSM_HOOK_INIT(sb_remount, selinux_sb_remount), LSM_HOOK_INIT(sb_kern_mount, selinux_sb_kern_mount), LSM_HOOK_INIT(sb_show_options, selinux_sb_show_options), LSM_HOOK_INIT(sb_statfs, selinux_sb_statfs), LSM_HOOK_INIT(sb_mount, selinux_mount), LSM_HOOK_INIT(sb_umount, selinux_umount), LSM_HOOK_INIT(sb_set_mnt_opts, selinux_set_mnt_opts), LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts), LSM_HOOK_INIT(move_mount, selinux_move_mount), LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security), LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as), LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security), LSM_HOOK_INIT(inode_init_security, selinux_inode_init_security), LSM_HOOK_INIT(inode_init_security_anon, selinux_inode_init_security_anon), LSM_HOOK_INIT(inode_create, selinux_inode_create), LSM_HOOK_INIT(inode_link, selinux_inode_link), LSM_HOOK_INIT(inode_unlink, selinux_inode_unlink), LSM_HOOK_INIT(inode_symlink, selinux_inode_symlink), LSM_HOOK_INIT(inode_mkdir, selinux_inode_mkdir), LSM_HOOK_INIT(inode_rmdir, selinux_inode_rmdir), LSM_HOOK_INIT(inode_mknod, selinux_inode_mknod), LSM_HOOK_INIT(inode_rename, selinux_inode_rename), LSM_HOOK_INIT(inode_readlink, selinux_inode_readlink), LSM_HOOK_INIT(inode_follow_link, selinux_inode_follow_link), LSM_HOOK_INIT(inode_permission, selinux_inode_permission), LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr), LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr), LSM_HOOK_INIT(inode_xattr_skipcap, selinux_inode_xattr_skipcap), LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr), LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr), LSM_HOOK_INIT(inode_listxattr, selinux_inode_listxattr), LSM_HOOK_INIT(inode_removexattr, selinux_inode_removexattr), LSM_HOOK_INIT(inode_set_acl, selinux_inode_set_acl), LSM_HOOK_INIT(inode_get_acl, selinux_inode_get_acl), LSM_HOOK_INIT(inode_remove_acl, selinux_inode_remove_acl), LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity), LSM_HOOK_INIT(inode_getlsmprop, selinux_inode_getlsmprop), LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up), LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(path_notify, selinux_path_notify), LSM_HOOK_INIT(kernfs_init_security, selinux_kernfs_init_security), LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), LSM_HOOK_INIT(file_lock, selinux_file_lock), LSM_HOOK_INIT(file_fcntl, selinux_file_fcntl), LSM_HOOK_INIT(file_set_fowner, selinux_file_set_fowner), LSM_HOOK_INIT(file_send_sigiotask, selinux_file_send_sigiotask), LSM_HOOK_INIT(file_receive, selinux_file_receive), LSM_HOOK_INIT(file_open, selinux_file_open), LSM_HOOK_INIT(task_alloc, selinux_task_alloc), LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), LSM_HOOK_INIT(cred_getlsmprop, selinux_cred_getlsmprop), LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data), LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file), LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), LSM_HOOK_INIT(current_getlsmprop_subj, selinux_current_getlsmprop_subj), LSM_HOOK_INIT(task_getlsmprop_obj, selinux_task_getlsmprop_obj), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio), LSM_HOOK_INIT(task_prlimit, selinux_task_prlimit), LSM_HOOK_INIT(task_setrlimit, selinux_task_setrlimit), LSM_HOOK_INIT(task_setscheduler, selinux_task_setscheduler), LSM_HOOK_INIT(task_getscheduler, selinux_task_getscheduler), LSM_HOOK_INIT(task_movememory, selinux_task_movememory), LSM_HOOK_INIT(task_kill, selinux_task_kill), LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode), LSM_HOOK_INIT(userns_create, selinux_userns_create), LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission), LSM_HOOK_INIT(ipc_getlsmprop, selinux_ipc_getlsmprop), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv), LSM_HOOK_INIT(shm_associate, selinux_shm_associate), LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl), LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat), LSM_HOOK_INIT(sem_associate, selinux_sem_associate), LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl), LSM_HOOK_INIT(sem_semop, selinux_sem_semop), LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate), LSM_HOOK_INIT(getselfattr, selinux_getselfattr), LSM_HOOK_INIT(setselfattr, selinux_setselfattr), LSM_HOOK_INIT(getprocattr, selinux_getprocattr), LSM_HOOK_INIT(setprocattr, selinux_setprocattr), LSM_HOOK_INIT(ismaclabel, selinux_ismaclabel), LSM_HOOK_INIT(secctx_to_secid, selinux_secctx_to_secid), LSM_HOOK_INIT(release_secctx, selinux_release_secctx), LSM_HOOK_INIT(inode_invalidate_secctx, selinux_inode_invalidate_secctx), LSM_HOOK_INIT(inode_notifysecctx, selinux_inode_notifysecctx), LSM_HOOK_INIT(inode_setsecctx, selinux_inode_setsecctx), LSM_HOOK_INIT(unix_stream_connect, selinux_socket_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, selinux_socket_unix_may_send), LSM_HOOK_INIT(socket_create, selinux_socket_create), LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create), LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair), LSM_HOOK_INIT(socket_bind, selinux_socket_bind), LSM_HOOK_INIT(socket_connect, selinux_socket_connect), LSM_HOOK_INIT(socket_listen, selinux_socket_listen), LSM_HOOK_INIT(socket_accept, selinux_socket_accept), LSM_HOOK_INIT(socket_sendmsg, selinux_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, selinux_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, selinux_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, selinux_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, selinux_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, selinux_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, selinux_socket_shutdown), LSM_HOOK_INIT(socket_sock_rcv_skb, selinux_socket_sock_rcv_skb), LSM_HOOK_INIT(socket_getpeersec_stream, selinux_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, selinux_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_free_security, selinux_sk_free_security), LSM_HOOK_INIT(sk_clone_security, selinux_sk_clone_security), LSM_HOOK_INIT(sk_getsecid, selinux_sk_getsecid), LSM_HOOK_INIT(sock_graft, selinux_sock_graft), LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established), LSM_HOOK_INIT(mptcp_add_subflow, selinux_mptcp_add_subflow), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), LSM_HOOK_INIT(secmark_relabel_packet, selinux_secmark_relabel_packet), LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc), LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec), LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow), LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create), LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue), LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach), LSM_HOOK_INIT(tun_dev_open, selinux_tun_dev_open), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access), LSM_HOOK_INIT(ib_endport_manage_subnet, selinux_ib_endport_manage_subnet), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free), LSM_HOOK_INIT(xfrm_policy_delete_security, selinux_xfrm_policy_delete), LSM_HOOK_INIT(xfrm_state_free_security, selinux_xfrm_state_free), LSM_HOOK_INIT(xfrm_state_delete_security, selinux_xfrm_state_delete), LSM_HOOK_INIT(xfrm_policy_lookup, selinux_xfrm_policy_lookup), LSM_HOOK_INIT(xfrm_state_pol_flow_match, selinux_xfrm_state_pol_flow_match), LSM_HOOK_INIT(xfrm_decode_session, selinux_xfrm_decode_session), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS LSM_HOOK_INIT(watch_key, selinux_watch_key), #endif #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_known, selinux_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), #endif #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, selinux_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, selinux_uring_sqpoll), LSM_HOOK_INIT(uring_cmd, selinux_uring_cmd), #endif /* * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE */ LSM_HOOK_INIT(fs_context_submount, selinux_fs_context_submount), LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone), #endif /* * PUT "ALLOCATING" HOOKS HERE */ LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security), LSM_HOOK_INIT(msg_queue_alloc_security, selinux_msg_queue_alloc_security), LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security), LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), LSM_HOOK_INIT(lsmprop_to_secctx, selinux_lsmprop_to_secctx), LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx), LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security), LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_alloc_security, selinux_ib_alloc_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_alloc_security, selinux_xfrm_policy_alloc), LSM_HOOK_INIT(xfrm_state_alloc, selinux_xfrm_state_alloc), LSM_HOOK_INIT(xfrm_state_alloc_acquire, selinux_xfrm_state_alloc_acquire), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, selinux_key_alloc), #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), #endif }; static __init int selinux_init(void) { pr_info("SELinux: Initializing.\n"); memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(selinux_enforcing_boot); selinux_avc_init(); mutex_init(&selinux_state.status_lock); mutex_init(&selinux_state.policy_mutex); /* Set the security state for the initial task. */ cred_init_security(); default_noexec = !(VM_DATA_DEFAULT_FLAGS & VM_EXEC); if (!default_noexec) pr_notice("SELinux: virtual memory is executable by default\n"); avc_init(); avtab_cache_init(); ebitmap_cache_init(); hashtab_cache_init(); security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), &selinux_lsmid); if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC netcache callback\n"); if (avc_add_callback(selinux_lsm_notifier_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC LSM notifier callback\n"); if (selinux_enforcing_boot) pr_debug("SELinux: Starting in enforcing mode\n"); else pr_debug("SELinux: Starting in permissive mode\n"); fs_validate_description("selinux", selinux_fs_parameters); return 0; } static void delayed_superblock_init(struct super_block *sb, void *unused) { selinux_set_mnt_opts(sb, NULL, 0, NULL); } void selinux_complete_init(void) { pr_debug("SELinux: Completing initialization.\n"); /* Set up any superblocks initialized prior to the policy load. */ pr_debug("SELinux: Setting up existing superblocks.\n"); iterate_supers(delayed_superblock_init, NULL); } /* SELinux requires early initialization in order to label all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled_boot, .blobs = &selinux_blob_sizes, .init = selinux_init, }; #if defined(CONFIG_NETFILTER) static const struct nf_hook_ops selinux_nf_ops[] = { { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif /* IPV6 */ }; static int __net_init selinux_nf_register(struct net *net) { return nf_register_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static void __net_exit selinux_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, }; static int __init selinux_nf_ip_init(void) { int err; if (!selinux_enabled_boot) return 0; pr_debug("SELinux: Registering netfilter hooks\n"); err = register_pernet_subsys(&selinux_net_ops); if (err) panic("SELinux: register_pernet_subsys: error %d\n", err); return 0; } __initcall(selinux_nf_ip_init); #endif /* CONFIG_NETFILTER */ |
| 4 4 4 4 216 216 216 216 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the multi-level security (MLS) policy. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. * * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support to import/export the MLS label from NetLabel * Copyright (C) Hewlett-Packard Development Company, L.P., 2006 */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <net/netlabel.h> #include "sidtab.h" #include "mls.h" #include "policydb.h" #include "services.h" /* * Return the length in bytes for the MLS fields of the * security context string representation of `context'. */ int mls_compute_context_len(struct policydb *p, struct context *context) { int i, l, len, head, prev; char *nm; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return 0; len = 1; /* for the beginning ":" */ for (l = 0; l < 2; l++) { u32 index_sens = context->range.level[l].sens; len += strlen(sym_name(p, SYM_LEVELS, index_sens - 1)); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (head != prev) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } nm = sym_name(p, SYM_CATS, i); len += strlen(nm) + 1; head = i; } prev = i; } if (prev != head) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else len++; } } return len; } /* * Write the security context string representation of * the MLS fields of `context' into the string `*scontext'. * Update `*scontext' to point to the end of the MLS fields. */ void mls_sid_to_context(struct policydb *p, struct context *context, char **scontext) { char *scontextp, *nm; int i, l, head, prev; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return; scontextp = *scontext; *scontextp = ':'; scontextp++; for (l = 0; l < 2; l++) { strcpy(scontextp, sym_name(p, SYM_LEVELS, context->range.level[l].sens - 1)); scontextp += strlen(scontextp); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (prev < 0) *scontextp++ = ':'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, i); strcpy(scontextp, nm); scontextp += strlen(nm); head = i; } prev = i; } if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else *scontextp++ = '-'; } } *scontext = scontextp; } int mls_level_isvalid(struct policydb *p, struct mls_level *l) { struct level_datum *levdatum; if (!l->sens || l->sens > p->p_levels.nprim) return 0; levdatum = symtab_search(&p->p_levels, sym_name(p, SYM_LEVELS, l->sens - 1)); if (!levdatum) return 0; /* * Return 1 iff all the bits set in l->cat are also be set in * levdatum->level->cat and no bit in l->cat is larger than * p->p_cats.nprim. */ return ebitmap_contains(&levdatum->level->cat, &l->cat, p->p_cats.nprim); } int mls_range_isvalid(struct policydb *p, struct mls_range *r) { return (mls_level_isvalid(p, &r->level[0]) && mls_level_isvalid(p, &r->level[1]) && mls_level_dom(&r->level[1], &r->level[0])); } /* * Return 1 if the MLS fields in the security context * structure `c' are valid. Return 0 otherwise. */ int mls_context_isvalid(struct policydb *p, struct context *c) { struct user_datum *usrdatum; if (!p->mls_enabled) return 1; if (!mls_range_isvalid(p, &c->range)) return 0; if (c->role == OBJECT_R_VAL) return 1; /* * User must be authorized for the MLS range. */ if (!c->user || c->user > p->p_users.nprim) return 0; usrdatum = p->user_val_to_struct[c->user - 1]; if (!mls_range_contains(usrdatum->range, c->range)) return 0; /* user may not be associated with range */ return 1; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `scontext'. * * This function modifies the string in place, inserting * NULL characters to terminate the MLS fields. * * If a def_sid is provided and no MLS field is present, * copy the MLS field of the associated default context. * Used for upgraded to MLS systems where objects may lack * MLS fields. * * Policy read-lock must be held for sidtab lookup. * */ int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext, struct context *context, struct sidtab *s, u32 def_sid) { char *sensitivity, *cur_cat, *next_cat, *rngptr; struct level_datum *levdatum; struct cat_datum *catdatum, *rngdatum; u32 i; int l, rc; char *rangep[2]; if (!pol->mls_enabled) { /* * With no MLS, only return -EINVAL if there is a MLS field * and it did not come from an xattr. */ if (oldc && def_sid == SECSID_NULL) return -EINVAL; return 0; } /* * No MLS component to the security context, try and map to * default if provided. */ if (!oldc) { struct context *defcon; if (def_sid == SECSID_NULL) return -EINVAL; defcon = sidtab_search(s, def_sid); if (!defcon) return -EINVAL; return mls_context_cpy(context, defcon); } /* * If we're dealing with a range, figure out where the two parts * of the range begin. */ rangep[0] = scontext; rangep[1] = strchr(scontext, '-'); if (rangep[1]) { rangep[1][0] = '\0'; rangep[1]++; } /* For each part of the range: */ for (l = 0; l < 2; l++) { /* Split sensitivity and category set. */ sensitivity = rangep[l]; if (sensitivity == NULL) break; next_cat = strchr(sensitivity, ':'); if (next_cat) *(next_cat++) = '\0'; /* Parse sensitivity. */ levdatum = symtab_search(&pol->p_levels, sensitivity); if (!levdatum) return -EINVAL; context->range.level[l].sens = levdatum->level->sens; /* Extract category set. */ while (next_cat != NULL) { cur_cat = next_cat; next_cat = strchr(next_cat, ','); if (next_cat != NULL) *(next_cat++) = '\0'; /* Separate into range if exists */ rngptr = strchr(cur_cat, '.'); if (rngptr != NULL) { /* Remove '.' */ *rngptr++ = '\0'; } catdatum = symtab_search(&pol->p_cats, cur_cat); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&context->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; /* If range, set all categories in range */ if (rngptr == NULL) continue; rngdatum = symtab_search(&pol->p_cats, rngptr); if (!rngdatum) return -EINVAL; if (catdatum->value >= rngdatum->value) return -EINVAL; for (i = catdatum->value; i < rngdatum->value; i++) { rc = ebitmap_set_bit( &context->range.level[l].cat, i, 1); if (rc) return rc; } } } /* If we didn't see a '-', the range start is also the range end. */ if (rangep[1] == NULL) { context->range.level[1].sens = context->range.level[0].sens; rc = ebitmap_cpy(&context->range.level[1].cat, &context->range.level[0].cat); if (rc) return rc; } return 0; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `str'. This function will allocate temporary memory with the * given constraints of gfp_mask. */ int mls_from_string(struct policydb *p, char *str, struct context *context, gfp_t gfp_mask) { char *tmpstr; int rc; if (!p->mls_enabled) return -EINVAL; tmpstr = kstrdup(str, gfp_mask); if (!tmpstr) { rc = -ENOMEM; } else { rc = mls_context_to_sid(p, ':', tmpstr, context, NULL, SECSID_NULL); kfree(tmpstr); } return rc; } /* * Copies the MLS range `range' into `context'. */ int mls_range_set(struct context *context, struct mls_range *range) { int l, rc = 0; /* Copy the MLS range into the context */ for (l = 0; l < 2; l++) { context->range.level[l].sens = range->level[l].sens; rc = ebitmap_cpy(&context->range.level[l].cat, &range->level[l].cat); if (rc) break; } return rc; } int mls_setup_user_range(struct policydb *p, struct context *fromcon, struct user_datum *user, struct context *usercon) { if (p->mls_enabled) { struct mls_level *fromcon_sen = &(fromcon->range.level[0]); struct mls_level *fromcon_clr = &(fromcon->range.level[1]); struct mls_level *user_low = &(user->range.level[0]); struct mls_level *user_clr = &(user->range.level[1]); struct mls_level *user_def = &(user->dfltlevel); struct mls_level *usercon_sen = &(usercon->range.level[0]); struct mls_level *usercon_clr = &(usercon->range.level[1]); /* Honor the user's default level if we can */ if (mls_level_between(user_def, fromcon_sen, fromcon_clr)) *usercon_sen = *user_def; else if (mls_level_between(fromcon_sen, user_def, user_clr)) *usercon_sen = *fromcon_sen; else if (mls_level_between(fromcon_clr, user_low, user_def)) *usercon_sen = *user_low; else return -EINVAL; /* Lower the clearance of available contexts if the clearance of "fromcon" is lower than that of the user's default clearance (but only if the "fromcon" clearance dominates the user's computed sensitivity level) */ if (mls_level_dom(user_clr, fromcon_clr)) *usercon_clr = *fromcon_clr; else if (mls_level_dom(fromcon_clr, user_clr)) *usercon_clr = *user_clr; else return -EINVAL; } return 0; } /* * Convert the MLS fields in the security context * structure `oldc' from the values specified in the * policy `oldp' to the values specified in the policy `newp', * storing the resulting context in `newc'. */ int mls_convert_context(struct policydb *oldp, struct policydb *newp, struct context *oldc, struct context *newc) { struct level_datum *levdatum; struct cat_datum *catdatum; struct ebitmap_node *node; u32 i; int l; if (!oldp->mls_enabled || !newp->mls_enabled) return 0; for (l = 0; l < 2; l++) { char *name = sym_name(oldp, SYM_LEVELS, oldc->range.level[l].sens - 1); levdatum = symtab_search(&newp->p_levels, name); if (!levdatum) return -EINVAL; newc->range.level[l].sens = levdatum->level->sens; ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node, i) { int rc; catdatum = symtab_search(&newp->p_cats, sym_name(oldp, SYM_CATS, i)); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&newc->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; } } return 0; } int mls_compute_sid(struct policydb *p, struct context *scontext, struct context *tcontext, u16 tclass, u32 specified, struct context *newcontext, bool sock) { struct range_trans rtr; struct mls_range *r; struct class_datum *cladatum; char default_range = 0; if (!p->mls_enabled) return 0; switch (specified) { case AVTAB_TRANSITION: /* Look for a range transition rule. */ rtr.source_type = scontext->type; rtr.target_type = tcontext->type; rtr.target_class = tclass; r = policydb_rangetr_search(p, &rtr); if (r) return mls_range_set(newcontext, r); if (tclass && tclass <= p->p_classes.nprim) { cladatum = p->class_val_to_struct[tclass - 1]; if (cladatum) default_range = cladatum->default_range; } switch (default_range) { case DEFAULT_SOURCE_LOW: return mls_context_cpy_low(newcontext, scontext); case DEFAULT_SOURCE_HIGH: return mls_context_cpy_high(newcontext, scontext); case DEFAULT_SOURCE_LOW_HIGH: return mls_context_cpy(newcontext, scontext); case DEFAULT_TARGET_LOW: return mls_context_cpy_low(newcontext, tcontext); case DEFAULT_TARGET_HIGH: return mls_context_cpy_high(newcontext, tcontext); case DEFAULT_TARGET_LOW_HIGH: return mls_context_cpy(newcontext, tcontext); case DEFAULT_GLBLUB: return mls_context_glblub(newcontext, scontext, tcontext); } fallthrough; case AVTAB_CHANGE: if ((tclass == p->process_class) || sock) /* Use the process MLS attributes. */ return mls_context_cpy(newcontext, scontext); else /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); case AVTAB_MEMBER: /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); } return -EINVAL; } #ifdef CONFIG_NETLABEL /** * mls_export_netlbl_lvl - Export the MLS sensitivity levels to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS sensitivity level into the * NetLabel MLS sensitivity level field. * */ void mls_export_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; secattr->attr.mls.lvl = context->range.level[0].sens - 1; secattr->flags |= NETLBL_SECATTR_MLS_LVL; } /** * mls_import_netlbl_lvl - Import the NetLabel MLS sensitivity levels * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context and the NetLabel security attributes, copy the * NetLabel MLS sensitivity level into the context. * */ void mls_import_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; context->range.level[0].sens = secattr->attr.mls.lvl + 1; context->range.level[1].sens = context->range.level[0].sens; } /** * mls_export_netlbl_cat - Export the MLS categories to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS categories into the NetLabel * MLS category field. Returns zero on success, negative values on failure. * */ int mls_export_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_export(&context->range.level[0].cat, &secattr->attr.mls.cat); if (rc == 0 && secattr->attr.mls.cat != NULL) secattr->flags |= NETLBL_SECATTR_MLS_CAT; return rc; } /** * mls_import_netlbl_cat - Import the MLS categories from NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Copy the NetLabel security attributes into the SELinux context; since the * NetLabel security attribute only contains a single MLS category use it for * both the low and high categories of the context. Returns zero on success, * negative values on failure. * */ int mls_import_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_import(&context->range.level[0].cat, secattr->attr.mls.cat); if (rc) goto import_netlbl_cat_failure; memcpy(&context->range.level[1].cat, &context->range.level[0].cat, sizeof(context->range.level[0].cat)); return 0; import_netlbl_cat_failure: ebitmap_destroy(&context->range.level[0].cat); return rc; } #endif /* CONFIG_NETLABEL */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* * include/net/tipc.h: Include file for TIPC message header routines * * Copyright (c) 2017 Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_HDR_H #define _TIPC_HDR_H #include <linux/random.h> #define KEEPALIVE_MSG_MASK 0x0e080000 /* LINK_PROTOCOL + MSG_IS_KEEPALIVE */ struct tipc_basic_hdr { __be32 w[4]; }; static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr) { u32 w0 = ntohl(hdr->w[0]); bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK; __be32 key; /* Return source node identity as key */ if (likely(!keepalive_msg)) return hdr->w[3]; /* Spread PROBE/PROBE_REPLY messages across the cores */ get_random_bytes(&key, sizeof(key)); return key; } #endif |
| 1 1 1 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | /* * llc_station.c - station component of LLC * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <net/llc.h> #include <net/llc_sap.h> #include <net/llc_conn.h> #include <net/llc_c_ac.h> #include <net/llc_s_ac.h> #include <net/llc_c_ev.h> #include <net/llc_c_st.h> #include <net/llc_s_ev.h> #include <net/llc_s_st.h> #include <net/llc_pdu.h> static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) { u8 mac_da[ETH_ALEN], dsap; int rc = 1; struct sk_buff *nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, sizeof(struct llc_xid_info)); if (!nskb) goto out; llc_pdu_decode_sa(skb, mac_da); llc_pdu_decode_ssap(skb, &dsap); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, 0, dsap, LLC_PDU_RSP); llc_pdu_init_as_xid_rsp(nskb, LLC_XID_NULL_CLASS_2, 127); rc = llc_mac_hdr_init(nskb, skb->dev->dev_addr, mac_da); if (unlikely(rc)) goto free; dev_queue_xmit(nskb); out: return rc; free: kfree_skb(nskb); goto out; } static int llc_station_ac_send_test_r(struct sk_buff *skb) { u8 mac_da[ETH_ALEN], dsap; int rc = 1; u32 data_size; struct sk_buff *nskb; if (skb->mac_len < ETH_HLEN) goto out; /* The test request command is type U (llc_len = 3) */ data_size = ntohs(eth_hdr(skb)->h_proto) - 3; nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, data_size); if (!nskb) goto out; llc_pdu_decode_sa(skb, mac_da); llc_pdu_decode_ssap(skb, &dsap); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, 0, dsap, LLC_PDU_RSP); llc_pdu_init_as_test_rsp(nskb, skb); rc = llc_mac_hdr_init(nskb, skb->dev->dev_addr, mac_da); if (unlikely(rc)) goto free; dev_queue_xmit(nskb); out: return rc; free: kfree_skb(nskb); goto out; } /** * llc_station_rcv - send received pdu to the station state machine * @skb: received frame. * * Sends data unit to station state machine. */ static void llc_station_rcv(struct sk_buff *skb) { if (llc_stat_ev_rx_null_dsap_xid_c(skb)) llc_station_ac_send_xid_r(skb); else if (llc_stat_ev_rx_null_dsap_test_c(skb)) llc_station_ac_send_test_r(skb); kfree_skb(skb); } void __init llc_station_init(void) { llc_set_station_handler(llc_station_rcv); } void llc_station_exit(void) { llc_set_station_handler(NULL); } |
| 87 83 4 88 87 87 88 87 88 2 3 3 2 83 78 74 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 | // SPDX-License-Identifier: GPL-2.0-only /* * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd * Authors: Alex Bennée <alex.bennee@linaro.org> * Oliver Upton <oliver.upton@linux.dev> */ #include <linux/kvm_host.h> #include <linux/hw_breakpoint.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * * @vcpu: the vcpu pointer * * This ensures we will trap access to: * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * - Self-hosted Trace (MDCR_EL2_TTRF/MDCR_EL2_E2TB) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { preempt_disable(); /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN, *host_data_ptr(nr_event_counters)); vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); /* Is the VM being debugged by userspace? */ if (vcpu->guest_debug) /* Route all software debug exceptions to EL2 */ vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* * Trap debug registers if the guest doesn't have ownership of them. */ if (!kvm_guest_owns_debug_regs(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; /* Write MDCR_EL2 directly if we're already at EL2 */ if (has_vhe()) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); preempt_enable(); } void kvm_init_host_debug_data(void) { u64 dfr0 = read_sysreg(id_aa64dfr0_el1); if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, read_sysreg(pmcr_el0)); *host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0); *host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0); if (has_vhe()) return; if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P)) host_data_set_flag(HAS_SPE); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) host_data_set_flag(HAS_TRBE); } /* * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host * has taken over MDSCR_EL1. * * - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1. * * - Userspace is using the breakpoint/watchpoint registers to debug the * guest, and MDSCR_EL1.MDE is forced to 1. * * - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0, * masking all debug exceptions affected by the OS Lock. */ static void setup_external_mdscr(struct kvm_vcpu *vcpu) { /* * Use the guest's MDSCR_EL1 as a starting point, since there are * several other features controlled by MDSCR_EL1 that are not relevant * to the host. * * Clear the bits that KVM may use which also satisfies emulation of * the OS Lock as MDSCR_EL1.MDE is cleared. */ u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS | MDSCR_EL1_MDE | MDSCR_EL1_KDE); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) mdscr |= MDSCR_EL1_SS; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE; vcpu->arch.external_mdscr_el1 = mdscr; } void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) { u64 mdscr; /* Must be called before kvm_vcpu_load_vhe() */ KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); /* * Determine which of the possible debug states we're in: * * - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's * breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do * software step or emulate the effects of the OS Lock being enabled. * * - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and * the breakpoint/watchpoint registers need to be loaded eagerly. * * - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint * context needs to be loaded on the CPU. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED; setup_external_mdscr(vcpu); /* * Steal the guest's single-step state machine if userspace wants * single-step the guest. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS) vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING); else vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING); if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } } else { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE)) vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; else vcpu->arch.debug_owner = VCPU_DEBUG_FREE; } kvm_arm_setup_mdcr_el2(vcpu); } void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) { if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) return; /* * Save the host's software step state and restore the guest's before * potentially returning to userspace. */ if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING); else vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; else *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; } /* * Updates ownership of the debug registers after a trapped guest access to a * breakpoint/watchpoint register. Host ownership of the debug registers is of * strictly higher priority, and it is the responsibility of the VMM to emulate * guest debug exceptions in this configuration. */ void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu) { if (kvm_host_owns_debug_regs(vcpu)) return; vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; kvm_arm_setup_mdcr_el2(vcpu); } void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val) { if (val & OSLAR_EL1_OSLK) __vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK; else __vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK; preempt_disable(); kvm_arch_vcpu_put(vcpu); kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); } |
| 721 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include "flask.h" #include "avc.h" struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ } __randomize_layout; enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct * selinux_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct * selinux_msg_msg(const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct * selinux_ipc(const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } static inline struct superblock_security_struct * selinux_superblock(const struct super_block *superblock) { return superblock->s_security + selinux_blob_sizes.lbs_superblock; } #ifdef CONFIG_KEYS static inline struct key_security_struct *selinux_key(const struct key *key) { return key->security + selinux_blob_sizes.lbs_key; } #endif /* CONFIG_KEYS */ static inline struct sk_security_struct *selinux_sock(const struct sock *sock) { return sock->sk_security + selinux_blob_sizes.lbs_sock; } static inline struct tun_security_struct *selinux_tun_dev(void *security) { return security + selinux_blob_sizes.lbs_tun_dev; } static inline struct ib_security_struct *selinux_ib(void *ib_sec) { return ib_sec + selinux_blob_sizes.lbs_ib; } static inline struct perf_event_security_struct * selinux_perf_event(void *perf_event) { return perf_event + selinux_blob_sizes.lbs_perf_event; } #endif /* _SELINUX_OBJSEC_H_ */ |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 | // 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/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; } } static bool bond_xdp_check(struct bonding *bond) { switch (BOND_MODE(bond)) { 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; if (!bond_dev) return NULL; 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 * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ static int bond_ipsec_add_sa(struct xfrm_state *xs, struct netlink_ext_ack *extack) { struct net_device *bond_dev = xs->xso.dev; 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; } xs->xso.real_dev = real_dev; err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack); if (!err) { 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; ipsec->xs->xso.real_dev = real_dev; if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) { slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__); ipsec->xs->xso.real_dev = NULL; } } out: mutex_unlock(&bond->ipsec_lock); } /** * bond_ipsec_del_sa - clear out this specific SA * @xs: pointer to transformer state struct **/ static void bond_ipsec_del_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; if (!bond_dev) return; 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 (!slave) goto out; if (!xs->xso.real_dev) goto out; WARN_ON(xs->xso.real_dev != 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__); goto out; } real_dev->xfrmdev_ops->xdo_dev_state_delete(xs); out: netdev_put(real_dev, &tracker); mutex_lock(&bond->ipsec_lock); 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); } 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__); } else { real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); if (real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs); } } mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_free_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; netdevice_tracker tracker; struct bonding *bond; struct slave *slave; if (!bond_dev) return; 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 (!slave) goto out; if (!xs->xso.real_dev) goto out; WARN_ON(xs->xso.real_dev != real_dev); if (real_dev && real_dev->xfrmdev_ops && real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(xs); out: netdev_put(real_dev, &tracker); } /** * 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; bool ok = false; 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_offload_ok || netif_is_bond_master(real_dev)) goto out; ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); out: rcu_read_unlock(); return ok; } /** * 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; int (*ioctl)(struct net_device *, struct ifreq *, int); struct ifreq ifr; struct mii_ioctl_data *mii; 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) return slave_dev->ethtool_ops->get_link(slave_dev) ? BMSR_LSTATUS : 0; /* Ethtool can't be used, fallback to MII ioctls. */ ioctl = slave_ops->ndo_eth_ioctl; if (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 (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { mii->reg_num = MII_BMSR; if (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, (struct sockaddr *)&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, (struct sockaddr *)&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) #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_GSO_SOFTWARE) static void bond_compute_features(struct bonding *bond) { unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; netdev_features_t gso_partial_features = NETIF_F_GSO_ESP; 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 */ if (slave->dev->hw_enc_features & NETIF_F_GSO_PARTIAL) gso_partial_features &= slave->dev->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; if (gso_partial_features & NETIF_F_GSO_ESP) bond_dev->gso_partial_features |= NETIF_F_GSO_ESP; else bond_dev->gso_partial_features &= ~NETIF_F_GSO_ESP; done: 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_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); ss.ss_family = slave_dev->type; res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, extack); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); goto err_restore_mtu; } } /* 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, (struct sockaddr *)&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_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, (struct sockaddr *)&ss, NULL); } if (unregister) __dev_set_mtu(slave_dev, slave->original_mtu); 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, (struct sockaddr *)&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_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_local = 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; #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_batch_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_batch_rtnl(struct list_head *net_list, struct list_head *dev_kill_list) { struct bond_net *bn; struct net *net; /* Kill off any bonds created after unregistering bond rtnl ops */ list_for_each_entry(net, net_list, exit_list) { struct bonding *bond, *tmp_bond; bn = net_generic(net, bond_net_id); 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_batch_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_batch_rtnl = bond_net_exit_batch_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"); |
| 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 | /* 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_ */ |
| 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Authors: Karl MacMillan <kmacmillan@tresys.com> * Frank Mayer <mayerf@tresys.com> * Copyright (C) 2003 - 2004 Tresys Technology, LLC */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/spinlock.h> #include <linux/slab.h> #include "security.h" #include "conditional.h" #include "services.h" /* * cond_evaluate_expr evaluates a conditional expr * in reverse polish notation. It returns true (1), false (0), * or undefined (-1). Undefined occurs when the expression * exceeds the stack depth of COND_EXPR_MAXDEPTH. */ static int cond_evaluate_expr(struct policydb *p, struct cond_expr *expr) { u32 i; int s[COND_EXPR_MAXDEPTH]; int sp = -1; if (expr->len == 0) return -1; for (i = 0; i < expr->len; i++) { struct cond_expr_node *node = &expr->nodes[i]; switch (node->expr_type) { case COND_BOOL: if (sp == (COND_EXPR_MAXDEPTH - 1)) return -1; sp++; s[sp] = p->bool_val_to_struct[node->boolean - 1]->state; break; case COND_NOT: if (sp < 0) return -1; s[sp] = !s[sp]; break; case COND_OR: if (sp < 1) return -1; sp--; s[sp] |= s[sp + 1]; break; case COND_AND: if (sp < 1) return -1; sp--; s[sp] &= s[sp + 1]; break; case COND_XOR: if (sp < 1) return -1; sp--; s[sp] ^= s[sp + 1]; break; case COND_EQ: if (sp < 1) return -1; sp--; s[sp] = (s[sp] == s[sp + 1]); break; case COND_NEQ: if (sp < 1) return -1; sp--; s[sp] = (s[sp] != s[sp + 1]); break; default: return -1; } } return s[0]; } /* * evaluate_cond_node evaluates the conditional stored in * a struct cond_node and if the result is different than the * current state of the node it sets the rules in the true/false * list appropriately. If the result of the expression is undefined * all of the rules are disabled for safety. */ static void evaluate_cond_node(struct policydb *p, struct cond_node *node) { struct avtab_node *avnode; int new_state; u32 i; new_state = cond_evaluate_expr(p, &node->expr); if (new_state != node->cur_state) { node->cur_state = new_state; if (new_state == -1) pr_err("SELinux: expression result was undefined - disabling all rules.\n"); /* turn the rules on or off */ for (i = 0; i < node->true_list.len; i++) { avnode = node->true_list.nodes[i]; if (new_state <= 0) avnode->key.specified &= ~AVTAB_ENABLED; else avnode->key.specified |= AVTAB_ENABLED; } for (i = 0; i < node->false_list.len; i++) { avnode = node->false_list.nodes[i]; /* -1 or 1 */ if (new_state) avnode->key.specified &= ~AVTAB_ENABLED; else avnode->key.specified |= AVTAB_ENABLED; } } } void evaluate_cond_nodes(struct policydb *p) { u32 i; for (i = 0; i < p->cond_list_len; i++) evaluate_cond_node(p, &p->cond_list[i]); } void cond_policydb_init(struct policydb *p) { p->bool_val_to_struct = NULL; p->cond_list = NULL; p->cond_list_len = 0; avtab_init(&p->te_cond_avtab); } static void cond_node_destroy(struct cond_node *node) { kfree(node->expr.nodes); /* the avtab_ptr_t nodes are destroyed by the avtab */ kfree(node->true_list.nodes); kfree(node->false_list.nodes); } static void cond_list_destroy(struct policydb *p) { u32 i; for (i = 0; i < p->cond_list_len; i++) cond_node_destroy(&p->cond_list[i]); kfree(p->cond_list); p->cond_list = NULL; p->cond_list_len = 0; } void cond_policydb_destroy(struct policydb *p) { kfree(p->bool_val_to_struct); avtab_destroy(&p->te_cond_avtab); cond_list_destroy(p); } int cond_init_bool_indexes(struct policydb *p) { kfree(p->bool_val_to_struct); p->bool_val_to_struct = kmalloc_array( p->p_bools.nprim, sizeof(*p->bool_val_to_struct), GFP_KERNEL); if (!p->bool_val_to_struct) return -ENOMEM; avtab_hash_eval(&p->te_cond_avtab, "conditional_rules"); return 0; } int cond_destroy_bool(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } int cond_index_bool(void *key, void *datum, void *datap) { struct policydb *p; struct cond_bool_datum *booldatum; booldatum = datum; p = datap; if (!booldatum->value || booldatum->value > p->p_bools.nprim) return -EINVAL; p->sym_val_to_name[SYM_BOOLS][booldatum->value - 1] = key; p->bool_val_to_struct[booldatum->value - 1] = booldatum; return 0; } static int bool_isvalid(struct cond_bool_datum *b) { if (!(b->state == 0 || b->state == 1)) return 0; return 1; } int cond_read_bool(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct cond_bool_datum *booldatum; __le32 buf[3]; u32 len; int rc; booldatum = kzalloc(sizeof(*booldatum), GFP_KERNEL); if (!booldatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof(buf)); if (rc) goto err; booldatum->value = le32_to_cpu(buf[0]); booldatum->state = le32_to_cpu(buf[1]); rc = -EINVAL; if (!bool_isvalid(booldatum)) goto err; len = le32_to_cpu(buf[2]); if (((len == 0) || (len == (u32)-1))) goto err; rc = -ENOMEM; key = kmalloc(len + 1, GFP_KERNEL); if (!key) goto err; rc = next_entry(key, fp, len); if (rc) goto err; key[len] = '\0'; rc = symtab_insert(s, key, booldatum); if (rc) goto err; return 0; err: cond_destroy_bool(key, booldatum, NULL); return rc; } struct cond_insertf_data { struct policydb *p; struct avtab_node **dst; struct cond_av_list *other; }; static int cond_insertf(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *ptr) { struct cond_insertf_data *data = ptr; struct policydb *p = data->p; struct cond_av_list *other = data->other; struct avtab_node *node_ptr; u32 i; bool found; /* * For type rules we have to make certain there aren't any * conflicting rules by searching the te_avtab and the * cond_te_avtab. */ if (k->specified & AVTAB_TYPE) { if (avtab_search_node(&p->te_avtab, k)) { pr_err("SELinux: type rule already exists outside of a conditional.\n"); return -EINVAL; } /* * If we are reading the false list other will be a pointer to * the true list. We can have duplicate entries if there is only * 1 other entry and it is in our true list. * * If we are reading the true list (other == NULL) there shouldn't * be any other entries. */ if (other) { node_ptr = avtab_search_node(&p->te_cond_avtab, k); if (node_ptr) { if (avtab_search_node_next(node_ptr, k->specified)) { pr_err("SELinux: too many conflicting type rules.\n"); return -EINVAL; } found = false; for (i = 0; i < other->len; i++) { if (other->nodes[i] == node_ptr) { found = true; break; } } if (!found) { pr_err("SELinux: conflicting type rules.\n"); return -EINVAL; } } } else { if (avtab_search_node(&p->te_cond_avtab, k)) { pr_err("SELinux: conflicting type rules when adding type rule for true.\n"); return -EINVAL; } } } node_ptr = avtab_insert_nonunique(&p->te_cond_avtab, k, d); if (!node_ptr) { pr_err("SELinux: could not insert rule.\n"); return -ENOMEM; } *data->dst = node_ptr; return 0; } static int cond_read_av_list(struct policydb *p, void *fp, struct cond_av_list *list, struct cond_av_list *other) { int rc; __le32 buf[1]; u32 i, len; struct cond_insertf_data data; rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; len = le32_to_cpu(buf[0]); if (len == 0) return 0; list->nodes = kcalloc(len, sizeof(*list->nodes), GFP_KERNEL); if (!list->nodes) return -ENOMEM; data.p = p; data.other = other; for (i = 0; i < len; i++) { data.dst = &list->nodes[i]; rc = avtab_read_item(&p->te_cond_avtab, fp, p, cond_insertf, &data); if (rc) { kfree(list->nodes); list->nodes = NULL; return rc; } } list->len = len; return 0; } static int expr_node_isvalid(struct policydb *p, struct cond_expr_node *expr) { if (expr->expr_type <= 0 || expr->expr_type > COND_LAST) { pr_err("SELinux: conditional expressions uses unknown operator.\n"); return 0; } if (expr->boolean > p->p_bools.nprim) { pr_err("SELinux: conditional expressions uses unknown bool.\n"); return 0; } return 1; } static int cond_read_node(struct policydb *p, struct cond_node *node, void *fp) { __le32 buf[2]; u32 i, len; int rc; rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) return rc; node->cur_state = le32_to_cpu(buf[0]); /* expr */ len = le32_to_cpu(buf[1]); node->expr.nodes = kcalloc(len, sizeof(*node->expr.nodes), GFP_KERNEL); if (!node->expr.nodes) return -ENOMEM; node->expr.len = len; for (i = 0; i < len; i++) { struct cond_expr_node *expr = &node->expr.nodes[i]; rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) return rc; expr->expr_type = le32_to_cpu(buf[0]); expr->boolean = le32_to_cpu(buf[1]); if (!expr_node_isvalid(p, expr)) return -EINVAL; } rc = cond_read_av_list(p, fp, &node->true_list, NULL); if (rc) return rc; return cond_read_av_list(p, fp, &node->false_list, &node->true_list); } int cond_read_list(struct policydb *p, void *fp) { __le32 buf[1]; u32 i, len; int rc; rc = next_entry(buf, fp, sizeof(buf)); if (rc) return rc; len = le32_to_cpu(buf[0]); p->cond_list = kcalloc(len, sizeof(*p->cond_list), GFP_KERNEL); if (!p->cond_list) return -ENOMEM; rc = avtab_alloc(&(p->te_cond_avtab), p->te_avtab.nel); if (rc) goto err; p->cond_list_len = len; for (i = 0; i < len; i++) { rc = cond_read_node(p, &p->cond_list[i], fp); if (rc) goto err; } return 0; err: cond_list_destroy(p); return rc; } int cond_write_bool(void *vkey, void *datum, void *ptr) { char *key = vkey; struct cond_bool_datum *booldatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; __le32 buf[3]; u32 len; int rc; len = strlen(key); buf[0] = cpu_to_le32(booldatum->value); buf[1] = cpu_to_le32(booldatum->state); buf[2] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; return 0; } /* * cond_write_cond_av_list doesn't write out the av_list nodes. * Instead it writes out the key/value pairs from the avtab. This * is necessary because there is no way to uniquely identifying rules * in the avtab so it is not possible to associate individual rules * in the avtab with a conditional without saving them as part of * the conditional. This means that the avtab with the conditional * rules will not be saved but will be rebuilt on policy load. */ static int cond_write_av_list(struct policydb *p, struct cond_av_list *list, struct policy_file *fp) { __le32 buf[1]; u32 i; int rc; buf[0] = cpu_to_le32(list->len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < list->len; i++) { rc = avtab_write_item(p, list->nodes[i], fp); if (rc) return rc; } return 0; } static int cond_write_node(struct policydb *p, struct cond_node *node, struct policy_file *fp) { __le32 buf[2]; int rc; u32 i; buf[0] = cpu_to_le32(node->cur_state); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf[0] = cpu_to_le32(node->expr.len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < node->expr.len; i++) { buf[0] = cpu_to_le32(node->expr.nodes[i].expr_type); buf[1] = cpu_to_le32(node->expr.nodes[i].boolean); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; } rc = cond_write_av_list(p, &node->true_list, fp); if (rc) return rc; rc = cond_write_av_list(p, &node->false_list, fp); if (rc) return rc; return 0; } int cond_write_list(struct policydb *p, void *fp) { u32 i; __le32 buf[1]; int rc; buf[0] = cpu_to_le32(p->cond_list_len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < p->cond_list_len; i++) { rc = cond_write_node(p, &p->cond_list[i], fp); if (rc) return rc; } return 0; } void cond_compute_xperms(struct avtab *ctab, struct avtab_key *key, struct extended_perms_decision *xpermd) { struct avtab_node *node; if (!ctab || !key || !xpermd) return; for (node = avtab_search_node(ctab, key); node; node = avtab_search_node_next(node, key->specified)) { if (node->key.specified & AVTAB_ENABLED) services_compute_xperms_decision(xpermd, node); } } /* Determine whether additional permissions are granted by the conditional * av table, and if so, add them to the result */ void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd, struct extended_perms *xperms) { struct avtab_node *node; if (!ctab || !key || !avd) return; for (node = avtab_search_node(ctab, key); node; node = avtab_search_node_next(node, key->specified)) { if ((u16)(AVTAB_ALLOWED | AVTAB_ENABLED) == (node->key.specified & (AVTAB_ALLOWED | AVTAB_ENABLED))) avd->allowed |= node->datum.u.data; if ((u16)(AVTAB_AUDITDENY | AVTAB_ENABLED) == (node->key.specified & (AVTAB_AUDITDENY | AVTAB_ENABLED))) /* Since a '0' in an auditdeny mask represents a * permission we do NOT want to audit (dontaudit), we use * the '&' operand to ensure that all '0's in the mask * are retained (much unlike the allow and auditallow cases). */ avd->auditdeny &= node->datum.u.data; if ((u16)(AVTAB_AUDITALLOW | AVTAB_ENABLED) == (node->key.specified & (AVTAB_AUDITALLOW | AVTAB_ENABLED))) avd->auditallow |= node->datum.u.data; if (xperms && (node->key.specified & AVTAB_ENABLED) && (node->key.specified & AVTAB_XPERMS)) services_compute_xperms_drivers(xperms, node); } } static int cond_dup_av_list(struct cond_av_list *new, const struct cond_av_list *orig, struct avtab *avtab) { u32 i; memset(new, 0, sizeof(*new)); new->nodes = kcalloc(orig->len, sizeof(*new->nodes), GFP_KERNEL); if (!new->nodes) return -ENOMEM; for (i = 0; i < orig->len; i++) { new->nodes[i] = avtab_insert_nonunique( avtab, &orig->nodes[i]->key, &orig->nodes[i]->datum); if (!new->nodes[i]) return -ENOMEM; new->len++; } return 0; } static int duplicate_policydb_cond_list(struct policydb *newp, const struct policydb *origp) { int rc; u32 i; rc = avtab_alloc_dup(&newp->te_cond_avtab, &origp->te_cond_avtab); if (rc) return rc; newp->cond_list_len = 0; newp->cond_list = kcalloc(origp->cond_list_len, sizeof(*newp->cond_list), GFP_KERNEL); if (!newp->cond_list) goto error; for (i = 0; i < origp->cond_list_len; i++) { struct cond_node *newn = &newp->cond_list[i]; const struct cond_node *orign = &origp->cond_list[i]; newp->cond_list_len++; newn->cur_state = orign->cur_state; newn->expr.nodes = kmemdup(orign->expr.nodes, orign->expr.len * sizeof(*orign->expr.nodes), GFP_KERNEL); if (!newn->expr.nodes) goto error; newn->expr.len = orign->expr.len; rc = cond_dup_av_list(&newn->true_list, &orign->true_list, &newp->te_cond_avtab); if (rc) goto error; rc = cond_dup_av_list(&newn->false_list, &orign->false_list, &newp->te_cond_avtab); if (rc) goto error; } return 0; error: avtab_destroy(&newp->te_cond_avtab); cond_list_destroy(newp); return -ENOMEM; } static int cond_bools_destroy(void *key, void *datum, void *args) { /* key was not copied so no need to free here */ kfree(datum); return 0; } static int cond_bools_copy(struct hashtab_node *new, const struct hashtab_node *orig, void *args) { struct cond_bool_datum *datum; datum = kmemdup(orig->datum, sizeof(struct cond_bool_datum), GFP_KERNEL); if (!datum) return -ENOMEM; new->key = orig->key; /* No need to copy, never modified */ new->datum = datum; return 0; } static int cond_bools_index(void *key, void *datum, void *args) { struct cond_bool_datum *booldatum, **cond_bool_array; booldatum = datum; cond_bool_array = args; cond_bool_array[booldatum->value - 1] = booldatum; return 0; } static int duplicate_policydb_bools(struct policydb *newdb, const struct policydb *orig) { struct cond_bool_datum **cond_bool_array; int rc; cond_bool_array = kmalloc_array(orig->p_bools.nprim, sizeof(*orig->bool_val_to_struct), GFP_KERNEL); if (!cond_bool_array) return -ENOMEM; rc = hashtab_duplicate(&newdb->p_bools.table, &orig->p_bools.table, cond_bools_copy, cond_bools_destroy, NULL); if (rc) { kfree(cond_bool_array); return -ENOMEM; } hashtab_map(&newdb->p_bools.table, cond_bools_index, cond_bool_array); newdb->bool_val_to_struct = cond_bool_array; newdb->p_bools.nprim = orig->p_bools.nprim; return 0; } void cond_policydb_destroy_dup(struct policydb *p) { hashtab_map(&p->p_bools.table, cond_bools_destroy, NULL); hashtab_destroy(&p->p_bools.table); cond_policydb_destroy(p); } int cond_policydb_dup(struct policydb *new, const struct policydb *orig) { cond_policydb_init(new); if (duplicate_policydb_bools(new, orig)) return -ENOMEM; if (duplicate_policydb_cond_list(new, orig)) { cond_policydb_destroy_dup(new); return -ENOMEM; } return 0; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/jump_label.h> #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern bool cpuset_cpu_is_isolated(int cpu); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); #else static inline void cpuset_memory_pressure_bump(void) { } #endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { return false; } static inline bool cpuset_cpu_is_isolated(int cpu) { return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 30 30 7 1 6 1 1 1 1 1 2 249 248 246 2 7 244 64 64 63 23 23 77 71 70 44 2 1 2 2 1 1 2 2 1 1 2 2 2 2 2 4 1 1 20 248 248 41 41 41 41 41 41 9 9 2 87 87 87 87 87 85 86 88 87 87 87 86 88 77 78 78 78 78 25 1 1 4 1 1 1 1 2 2 88 83 7 7 7 7 7 4 87 9 1 9 38 51 1 86 84 14 10 10 10 10 13 13 10 2 2 2 1 83 17 14 13 14 14 14 14 1 1 13 79 5 5 51 37 84 88 85 10 73 87 76 83 85 85 85 12 16 28 84 82 51 36 84 81 59 83 84 84 84 50 31 77 2 2 2 4 3 15 15 1 4 4 1 2 1 3 73 73 73 73 73 73 73 1 1 73 65 10 10 61 69 69 69 68 69 76 74 69 3 2 49 29 76 70 1 71 24 48 4 3 307 207 78 76 2 207 206 138 67 1 1 5 4 2 2 35 33 13 12 6 5 2 18 16 1 5 2 1 2 1 1 1 16 87 1 1 5 3 48 3 1 3 2 4 2 17 17 6 4 65 63 63 63 65 65 63 11 24 24 24 24 2 3 24 3 5 24 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/bug.h> #include <linux/cpu_pm.h> #include <linux/entry-kvm.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> #include <linux/kvm.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> #include <linux/psci.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS #include "trace_arm.h" #include <linux/uaccess.h> #include <asm/ptrace.h> #include <asm/mman.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/virt.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/kvm_pkvm.h> #include <asm/kvm_ptrauth.h> #include <asm/sections.h> #include <kvm/arm_hypercalls.h> #include <kvm/arm_pmu.h> #include <kvm/arm_psci.h> #include "sys_regs.h" static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT; enum kvm_wfx_trap_policy { KVM_WFX_NOTRAP_SINGLE_TASK, /* Default option */ KVM_WFX_NOTRAP, KVM_WFX_TRAP, }; static enum kvm_wfx_trap_policy kvm_wfi_trap_policy __read_mostly = KVM_WFX_NOTRAP_SINGLE_TASK; static enum kvm_wfx_trap_policy kvm_wfe_trap_policy __read_mostly = KVM_WFX_NOTRAP_SINGLE_TASK; DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector); DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); static bool vgic_present, kvm_arm_initialised; static DEFINE_PER_CPU(unsigned char, kvm_hyp_initialized); bool is_kvm_arm_initialised(void) { return kvm_arm_initialised; } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { int r = -EINVAL; if (cap->flags) return -EINVAL; if (kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(cap->cap)) return -EINVAL; switch (cap->cap) { case KVM_CAP_ARM_NISV_TO_USER: r = 0; set_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER, &kvm->arch.flags); break; case KVM_CAP_ARM_MTE: mutex_lock(&kvm->lock); if (system_supports_mte() && !kvm->created_vcpus) { r = 0; set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags); } mutex_unlock(&kvm->lock); break; case KVM_CAP_ARM_SYSTEM_SUSPEND: r = 0; set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags); break; case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE: mutex_lock(&kvm->slots_lock); /* * To keep things simple, allow changing the chunk * size only when no memory slots have been created. */ if (kvm_are_all_memslots_empty(kvm)) { u64 new_cap = cap->args[0]; if (!new_cap || kvm_is_block_size_supported(new_cap)) { r = 0; kvm->arch.mmu.split_page_chunk_size = new_cap; } } mutex_unlock(&kvm->slots_lock); break; default: break; } return r; } static int kvm_arm_default_max_vcpus(void) { return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; } /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct * @type: kvm device type */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int ret; mutex_init(&kvm->arch.config_lock); #ifdef CONFIG_LOCKDEP /* Clue in lockdep that the config_lock must be taken inside kvm->lock */ mutex_lock(&kvm->lock); mutex_lock(&kvm->arch.config_lock); mutex_unlock(&kvm->arch.config_lock); mutex_unlock(&kvm->lock); #endif kvm_init_nested(kvm); ret = kvm_share_hyp(kvm, kvm + 1); if (ret) return ret; ret = pkvm_init_host_vm(kvm); if (ret) goto err_unshare_kvm; if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL_ACCOUNT)) { ret = -ENOMEM; goto err_unshare_kvm; } cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask); ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu, type); if (ret) goto err_free_cpumask; kvm_vgic_early_init(kvm); kvm_timer_init_vm(kvm); /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->max_vcpus = kvm_arm_default_max_vcpus(); kvm_arm_init_hypercalls(kvm); bitmap_zero(kvm->arch.vcpu_features, KVM_VCPU_MAX_FEATURES); return 0; err_free_cpumask: free_cpumask_var(kvm->arch.supported_cpus); err_unshare_kvm: kvm_unshare_hyp(kvm, kvm + 1); return ret; } vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } void kvm_arch_create_vm_debugfs(struct kvm *kvm) { kvm_sys_regs_create_debugfs(kvm); kvm_s2_ptdump_create_debugfs(kvm); } static void kvm_destroy_mpidr_data(struct kvm *kvm) { struct kvm_mpidr_data *data; mutex_lock(&kvm->arch.config_lock); data = rcu_dereference_protected(kvm->arch.mpidr_data, lockdep_is_held(&kvm->arch.config_lock)); if (data) { rcu_assign_pointer(kvm->arch.mpidr_data, NULL); synchronize_rcu(); kfree(data); } mutex_unlock(&kvm->arch.config_lock); } /** * kvm_arch_destroy_vm - destroy the VM data structure * @kvm: pointer to the KVM struct */ void kvm_arch_destroy_vm(struct kvm *kvm) { bitmap_free(kvm->arch.pmu_filter); free_cpumask_var(kvm->arch.supported_cpus); kvm_vgic_destroy(kvm); if (is_protected_kvm_enabled()) pkvm_destroy_hyp_vm(kvm); kvm_destroy_mpidr_data(kvm); kfree(kvm->arch.sysreg_masks); kvm_destroy_vcpus(kvm); kvm_unshare_hyp(kvm, kvm + 1); kvm_arm_teardown_hypercalls(kvm); } static bool kvm_has_full_ptr_auth(void) { bool apa, gpa, api, gpi, apa3, gpa3; u64 isar1, isar2, val; /* * Check that: * * - both Address and Generic auth are implemented for a given * algorithm (Q5, IMPDEF or Q3) * - only a single algorithm is implemented. */ if (!system_has_full_ptr_auth()) return false; isar1 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); apa = !!FIELD_GET(ID_AA64ISAR1_EL1_APA_MASK, isar1); val = FIELD_GET(ID_AA64ISAR1_EL1_GPA_MASK, isar1); gpa = (val == ID_AA64ISAR1_EL1_GPA_IMP); api = !!FIELD_GET(ID_AA64ISAR1_EL1_API_MASK, isar1); val = FIELD_GET(ID_AA64ISAR1_EL1_GPI_MASK, isar1); gpi = (val == ID_AA64ISAR1_EL1_GPI_IMP); apa3 = !!FIELD_GET(ID_AA64ISAR2_EL1_APA3_MASK, isar2); val = FIELD_GET(ID_AA64ISAR2_EL1_GPA3_MASK, isar2); gpa3 = (val == ID_AA64ISAR2_EL1_GPA3_IMP); return (apa == gpa && api == gpi && apa3 == gpa3 && (apa + api + apa3) == 1); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r; if (kvm && kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(ext)) return 0; switch (ext) { case KVM_CAP_IRQCHIP: r = vgic_present; break; case KVM_CAP_IOEVENTFD: case KVM_CAP_USER_MEMORY: case KVM_CAP_SYNC_MMU: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_ONE_REG: case KVM_CAP_ARM_PSCI: case KVM_CAP_ARM_PSCI_0_2: case KVM_CAP_READONLY_MEM: case KVM_CAP_MP_STATE: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2: case KVM_CAP_ARM_NISV_TO_USER: case KVM_CAP_ARM_INJECT_EXT_DABT: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: case KVM_CAP_ARM_SYSTEM_SUSPEND: case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_COUNTER_OFFSET: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; case KVM_CAP_ARM_SET_DEVICE_ADDR: r = 1; break; case KVM_CAP_NR_VCPUS: /* * ARM64 treats KVM_CAP_NR_CPUS differently from all other * architectures, as it does not always bound it to * KVM_CAP_MAX_VCPUS. It should not matter much because * this is just an advisory value. */ r = min_t(unsigned int, num_online_cpus(), kvm_arm_default_max_vcpus()); break; case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: if (kvm) r = kvm->max_vcpus; else r = kvm_arm_default_max_vcpus(); break; case KVM_CAP_MSI_DEVID: if (!kvm) r = -EINVAL; else r = kvm->arch.vgic.msis_require_devid; break; case KVM_CAP_ARM_USER_IRQ: /* * 1: EL1_VTIMER, EL1_PTIMER, and PMU. * (bump this number if adding more devices) */ r = 1; break; case KVM_CAP_ARM_MTE: r = system_supports_mte(); break; case KVM_CAP_STEAL_TIME: r = kvm_arm_pvtime_supported(); break; case KVM_CAP_ARM_EL1_32BIT: r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1); break; case KVM_CAP_GUEST_DEBUG_HW_BPS: r = get_num_brps(); break; case KVM_CAP_GUEST_DEBUG_HW_WPS: r = get_num_wrps(); break; case KVM_CAP_ARM_PMU_V3: r = kvm_arm_support_pmu_v3(); break; case KVM_CAP_ARM_INJECT_SERROR_ESR: r = cpus_have_final_cap(ARM64_HAS_RAS_EXTN); break; case KVM_CAP_ARM_VM_IPA_SIZE: r = get_kvm_ipa_limit(); break; case KVM_CAP_ARM_SVE: r = system_supports_sve(); break; case KVM_CAP_ARM_PTRAUTH_ADDRESS: case KVM_CAP_ARM_PTRAUTH_GENERIC: r = kvm_has_full_ptr_auth(); break; case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE: if (kvm) r = kvm->arch.mmu.split_page_chunk_size; else r = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT; break; case KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES: r = kvm_supported_block_sizes(); break; case KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES: r = BIT(0); break; default: r = 0; } return r; } long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -EINVAL; } struct kvm *kvm_arch_alloc_vm(void) { size_t sz = sizeof(struct kvm); if (!has_vhe()) return kzalloc(sz, GFP_KERNEL_ACCOUNT); return __vmalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM | __GFP_ZERO); } int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) return -EBUSY; if (id >= kvm->max_vcpus) return -EINVAL; return 0; } int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int err; spin_lock_init(&vcpu->arch.mp_state_lock); #ifdef CONFIG_LOCKDEP /* Inform lockdep that the config_lock is acquired after vcpu->mutex */ mutex_lock(&vcpu->mutex); mutex_lock(&vcpu->kvm->arch.config_lock); mutex_unlock(&vcpu->kvm->arch.config_lock); mutex_unlock(&vcpu->mutex); #endif /* Force users to call KVM_ARM_VCPU_INIT */ vcpu_clear_flag(vcpu, VCPU_INITIALIZED); vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO; /* Set up the timer */ kvm_timer_vcpu_init(vcpu); kvm_pmu_vcpu_init(vcpu); kvm_arm_pvtime_vcpu_init(&vcpu->arch); vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; /* * This vCPU may have been created after mpidr_data was initialized. * Throw out the pre-computed mappings if that is the case which forces * KVM to fall back to iteratively searching the vCPUs. */ kvm_destroy_mpidr_data(vcpu->kvm); err = kvm_vgic_vcpu_init(vcpu); if (err) return err; return kvm_share_hyp(vcpu, vcpu + 1); } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { if (!is_protected_kvm_enabled()) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); else free_hyp_memcache(&vcpu->arch.pkvm_memcache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); kvm_vgic_vcpu_destroy(vcpu); kvm_arm_vcpu_destroy(vcpu); } void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { } static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu) { if (vcpu_has_ptrauth(vcpu) && !is_protected_kvm_enabled()) { /* * Either we're running an L2 guest, and the API/APK bits come * from L1's HCR_EL2, or API/APK are both set. */ if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) { u64 val; val = __vcpu_sys_reg(vcpu, HCR_EL2); val &= (HCR_API | HCR_APK); vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK); vcpu->arch.hcr_el2 |= val; } else { vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK); } /* * Save the host keys if there is any chance for the guest * to use pauth, as the entry code will reload the guest * keys in that case. */ if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) { struct kvm_cpu_context *ctxt; ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt); ptrauth_save_keys(ctxt); } } } static bool kvm_vcpu_should_clear_twi(struct kvm_vcpu *vcpu) { if (unlikely(kvm_wfi_trap_policy != KVM_WFX_NOTRAP_SINGLE_TASK)) return kvm_wfi_trap_policy == KVM_WFX_NOTRAP; return single_task_running() && (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || vcpu->kvm->arch.vgic.nassgireq); } static bool kvm_vcpu_should_clear_twe(struct kvm_vcpu *vcpu) { if (unlikely(kvm_wfe_trap_policy != KVM_WFX_NOTRAP_SINGLE_TASK)) return kvm_wfe_trap_policy == KVM_WFX_NOTRAP; return single_task_running(); } void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_s2_mmu *mmu; int *last_ran; if (is_protected_kvm_enabled()) goto nommu; if (vcpu_has_nv(vcpu)) kvm_vcpu_load_hw_mmu(vcpu); mmu = vcpu->arch.hw_mmu; last_ran = this_cpu_ptr(mmu->last_vcpu_ran); /* * We guarantee that both TLBs and I-cache are private to each * vcpu. If detecting that a vcpu from the same VM has * previously run on the same physical CPU, call into the * hypervisor code to nuke the relevant contexts. * * We might get preempted before the vCPU actually runs, but * over-invalidation doesn't affect correctness. */ if (*last_ran != vcpu->vcpu_idx) { kvm_call_hyp(__kvm_flush_cpu_context, mmu); *last_ran = vcpu->vcpu_idx; } nommu: vcpu->cpu = cpu; kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); kvm_vcpu_load_debug(vcpu); if (has_vhe()) kvm_vcpu_load_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); kvm_vcpu_pmu_restore_guest(vcpu); if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu); if (kvm_vcpu_should_clear_twe(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_TWE; else vcpu->arch.hcr_el2 |= HCR_TWE; if (kvm_vcpu_should_clear_twi(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_TWI; else vcpu->arch.hcr_el2 |= HCR_TWI; vcpu_set_pauth_traps(vcpu); if (is_protected_kvm_enabled()) { kvm_call_hyp_nvhe(__pkvm_vcpu_load, vcpu->kvm->arch.pkvm.handle, vcpu->vcpu_idx, vcpu->arch.hcr_el2); kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, &vcpu->arch.vgic_cpu.vgic_v3); } if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus)) vcpu_set_on_unsupported_cpu(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { if (is_protected_kvm_enabled()) { kvm_call_hyp(__vgic_v3_save_vmcr_aprs, &vcpu->arch.vgic_cpu.vgic_v3); kvm_call_hyp_nvhe(__pkvm_vcpu_put); } kvm_vcpu_put_debug(vcpu); kvm_arch_vcpu_put_fp(vcpu); if (has_vhe()) kvm_vcpu_put_vhe(vcpu); kvm_timer_vcpu_put(vcpu); kvm_vgic_put(vcpu); kvm_vcpu_pmu_restore_host(vcpu); if (vcpu_has_nv(vcpu)) kvm_vcpu_put_hw_mmu(vcpu); kvm_arm_vmid_clear_active(); vcpu_clear_on_unsupported_cpu(vcpu); vcpu->cpu = -1; } static void __kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) { WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); kvm_make_request(KVM_REQ_SLEEP, vcpu); kvm_vcpu_kick(vcpu); } void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) { spin_lock(&vcpu->arch.mp_state_lock); __kvm_arm_vcpu_power_off(vcpu); spin_unlock(&vcpu->arch.mp_state_lock); } bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_STOPPED; } static void kvm_arm_vcpu_suspend(struct kvm_vcpu *vcpu) { WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_SUSPENDED); kvm_make_request(KVM_REQ_SUSPEND, vcpu); kvm_vcpu_kick(vcpu); } static bool kvm_arm_vcpu_suspended(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_SUSPENDED; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { *mp_state = READ_ONCE(vcpu->arch.mp_state); return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { int ret = 0; spin_lock(&vcpu->arch.mp_state_lock); switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: WRITE_ONCE(vcpu->arch.mp_state, *mp_state); break; case KVM_MP_STATE_STOPPED: __kvm_arm_vcpu_power_off(vcpu); break; case KVM_MP_STATE_SUSPENDED: kvm_arm_vcpu_suspend(vcpu); break; default: ret = -EINVAL; } spin_unlock(&vcpu->arch.mp_state_lock); return ret; } /** * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled * @v: The VCPU pointer * * If the guest CPU is not waiting for interrupts or an interrupt line is * asserted, the CPU is by definition runnable. */ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF); return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) && !kvm_arm_vcpu_stopped(v) && !v->arch.pause); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { return vcpu_mode_priv(vcpu); } #ifdef CONFIG_GUEST_PERF_EVENTS unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) { return *vcpu_pc(vcpu); } #endif static void kvm_init_mpidr_data(struct kvm *kvm) { struct kvm_mpidr_data *data = NULL; unsigned long c, mask, nr_entries; u64 aff_set = 0, aff_clr = ~0UL; struct kvm_vcpu *vcpu; mutex_lock(&kvm->arch.config_lock); if (rcu_access_pointer(kvm->arch.mpidr_data) || atomic_read(&kvm->online_vcpus) == 1) goto out; kvm_for_each_vcpu(c, vcpu, kvm) { u64 aff = kvm_vcpu_get_mpidr_aff(vcpu); aff_set |= aff; aff_clr &= aff; } /* * A significant bit can be either 0 or 1, and will only appear in * aff_set. Use aff_clr to weed out the useless stuff. */ mask = aff_set ^ aff_clr; nr_entries = BIT_ULL(hweight_long(mask)); /* * Don't let userspace fool us. If we need more than a single page * to describe the compressed MPIDR array, just fall back to the * iterative method. Single vcpu VMs do not need this either. */ if (struct_size(data, cmpidr_to_idx, nr_entries) <= PAGE_SIZE) data = kzalloc(struct_size(data, cmpidr_to_idx, nr_entries), GFP_KERNEL_ACCOUNT); if (!data) goto out; data->mpidr_mask = mask; kvm_for_each_vcpu(c, vcpu, kvm) { u64 aff = kvm_vcpu_get_mpidr_aff(vcpu); u16 index = kvm_mpidr_index(data, aff); data->cmpidr_to_idx[index] = c; } rcu_assign_pointer(kvm->arch.mpidr_data, data); out: mutex_unlock(&kvm->arch.config_lock); } /* * Handle both the initialisation that is being done when the vcpu is * run for the first time, as well as the updates that must be * performed each time we get a new thread dealing with this vcpu. */ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; int ret; if (!kvm_vcpu_initialized(vcpu)) return -ENOEXEC; if (!kvm_arm_vcpu_is_finalized(vcpu)) return -EPERM; ret = kvm_arch_vcpu_run_map_fp(vcpu); if (ret) return ret; if (likely(vcpu_has_run_once(vcpu))) return 0; kvm_init_mpidr_data(kvm); if (likely(irqchip_in_kernel(kvm))) { /* * Map the VGIC hardware resources before running a vcpu the * first time on this VM. */ ret = kvm_vgic_map_resources(kvm); if (ret) return ret; } ret = kvm_finalize_sys_regs(vcpu); if (ret) return ret; /* * This needs to happen after any restriction has been applied * to the feature set. */ kvm_calculate_traps(vcpu); ret = kvm_timer_enable(vcpu); if (ret) return ret; ret = kvm_arm_pmu_v3_enable(vcpu); if (ret) return ret; if (is_protected_kvm_enabled()) { ret = pkvm_create_hyp_vm(kvm); if (ret) return ret; } mutex_lock(&kvm->arch.config_lock); set_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags); mutex_unlock(&kvm->arch.config_lock); return ret; } bool kvm_arch_intc_initialized(struct kvm *kvm) { return vgic_initialized(kvm); } void kvm_arm_halt_guest(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) vcpu->arch.pause = true; kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP); } void kvm_arm_resume_guest(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; __kvm_vcpu_wake_up(vcpu); } } static void kvm_vcpu_sleep(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); rcuwait_wait_event(wait, (!kvm_arm_vcpu_stopped(vcpu)) && (!vcpu->arch.pause), TASK_INTERRUPTIBLE); if (kvm_arm_vcpu_stopped(vcpu) || vcpu->arch.pause) { /* Awaken to handle a signal, request we sleep again later. */ kvm_make_request(KVM_REQ_SLEEP, vcpu); } /* * Make sure we will observe a potential reset request if we've * observed a change to the power state. Pairs with the smp_wmb() in * kvm_psci_vcpu_on(). */ smp_rmb(); } /** * kvm_vcpu_wfi - emulate Wait-For-Interrupt behavior * @vcpu: The VCPU pointer * * Suspend execution of a vCPU until a valid wake event is detected, i.e. until * the vCPU is runnable. The vCPU may or may not be scheduled out, depending * on when a wake event arrives, e.g. there may already be a pending wake event. */ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) { /* * Sync back the state of the GIC CPU interface so that we have * the latest PMR and group enables. This ensures that * kvm_arch_vcpu_runnable has up-to-date data to decide whether * we have pending interrupts, e.g. when determining if the * vCPU should block. * * For the same reason, we want to tell GICv4 that we need * doorbells to be signalled, should an interrupt become pending. */ preempt_disable(); vcpu_set_flag(vcpu, IN_WFI); kvm_vgic_put(vcpu); preempt_enable(); kvm_vcpu_halt(vcpu); vcpu_clear_flag(vcpu, IN_WFIT); preempt_disable(); vcpu_clear_flag(vcpu, IN_WFI); kvm_vgic_load(vcpu); preempt_enable(); } static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu) { if (!kvm_arm_vcpu_suspended(vcpu)) return 1; kvm_vcpu_wfi(vcpu); /* * The suspend state is sticky; we do not leave it until userspace * explicitly marks the vCPU as runnable. Request that we suspend again * later. */ kvm_make_request(KVM_REQ_SUSPEND, vcpu); /* * Check to make sure the vCPU is actually runnable. If so, exit to * userspace informing it of the wakeup condition. */ if (kvm_arch_vcpu_runnable(vcpu)) { memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = KVM_SYSTEM_EVENT_WAKEUP; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; return 0; } /* * Otherwise, we were unblocked to process a different event, such as a * pending signal. Return 1 and allow kvm_arch_vcpu_ioctl_run() to * process the event. */ return 1; } /** * check_vcpu_requests - check and handle pending vCPU requests * @vcpu: the VCPU pointer * * Return: 1 if we should enter the guest * 0 if we should exit to userspace * < 0 if we should exit to userspace, where the return value indicates * an error */ static int check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) return -EIO; if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) kvm_vcpu_sleep(vcpu); if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) kvm_reset_vcpu(vcpu); /* * Clear IRQ_PENDING requests that were made to guarantee * that a VCPU sees new virtual interrupts. */ kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu); if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu)) kvm_update_stolen_time(vcpu); if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { /* The distributor enable bits were changed */ preempt_disable(); vgic_v4_put(vcpu); vgic_v4_load(vcpu); preempt_enable(); } if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu)) kvm_vcpu_reload_pmu(vcpu); if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu)) kvm_vcpu_pmu_restore_guest(vcpu); if (kvm_check_request(KVM_REQ_SUSPEND, vcpu)) return kvm_vcpu_suspend(vcpu); if (kvm_dirty_ring_check_request(vcpu)) return 0; check_nested_vcpu_requests(vcpu); } return 1; } static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu) { if (likely(!vcpu_mode_is_32bit(vcpu))) return false; if (vcpu_has_nv(vcpu)) return true; return !kvm_supports_32bit_el0(); } /** * kvm_vcpu_exit_request - returns true if the VCPU should *not* enter the guest * @vcpu: The VCPU pointer * @ret: Pointer to write optional return code * * Returns: true if the VCPU needs to return to a preemptible + interruptible * and skip guest entry. * * This function disambiguates between two different types of exits: exits to a * preemptible + interruptible kernel context and exits to userspace. For an * exit to userspace, this function will write the return code to ret and return * true. For an exit to preemptible + interruptible kernel context (i.e. check * for pending work and re-enter), return true without writing to ret. */ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret) { struct kvm_run *run = vcpu->run; /* * If we're using a userspace irqchip, then check if we need * to tell a userspace irqchip about timer or PMU level * changes and if so, exit to userspace (the actual level * state gets updated in kvm_timer_update_run and * kvm_pmu_update_run below). */ if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { if (kvm_timer_should_notify_user(vcpu) || kvm_pmu_should_notify_user(vcpu)) { *ret = -EINTR; run->exit_reason = KVM_EXIT_INTR; return true; } } if (unlikely(vcpu_on_unsupported_cpu(vcpu))) { run->exit_reason = KVM_EXIT_FAIL_ENTRY; run->fail_entry.hardware_entry_failure_reason = KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED; run->fail_entry.cpu = smp_processor_id(); *ret = 0; return true; } return kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); } /* * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while * the vCPU is running. * * This must be noinstr as instrumentation may make use of RCU, and this is not * safe during the EQS. */ static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu) { int ret; guest_state_enter_irqoff(); ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu); guest_state_exit_irqoff(); return ret; } /** * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code * @vcpu: The VCPU pointer * * This function is called through the VCPU_RUN ioctl called from user space. It * will execute VM code in a loop until the time slice for the process is used * or some emulation is needed from user space in which case the function will * return with return value 0 and with the kvm_run structure filled in with the * required data for the requested emulation. */ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; int ret; if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_handle_mmio_return(vcpu); if (ret <= 0) return ret; } vcpu_load(vcpu); if (!vcpu->wants_to_run) { ret = -EINTR; goto out; } kvm_sigset_activate(vcpu); ret = 1; run->exit_reason = KVM_EXIT_UNKNOWN; run->flags = 0; while (ret > 0) { /* * Check conditions before entering the guest */ ret = xfer_to_guest_mode_handle_work(vcpu); if (!ret) ret = 1; if (ret > 0) ret = check_vcpu_requests(vcpu); /* * Preparing the interrupts to be injected also * involves poking the GIC, which must be done in a * non-preemptible context. */ preempt_disable(); /* * The VMID allocator only tracks active VMIDs per * physical CPU, and therefore the VMID allocated may not be * preserved on VMID roll-over if the task was preempted, * making a thread's VMID inactive. So we need to call * kvm_arm_vmid_update() in non-premptible context. */ if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) && has_vhe()) __load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch); kvm_pmu_flush_hwstate(vcpu); local_irq_disable(); kvm_vgic_flush_hwstate(vcpu); kvm_pmu_update_vcpu_events(vcpu); /* * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and * Documentation/virt/kvm/vcpu-requests.rst */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) { vcpu->mode = OUTSIDE_GUEST_MODE; isb(); /* Ensure work in x_flush_hwstate is committed */ kvm_pmu_sync_hwstate(vcpu); if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); preempt_enable(); continue; } kvm_arch_vcpu_ctxflush_fp(vcpu); /************************************************************** * Enter the guest */ trace_kvm_entry(*vcpu_pc(vcpu)); guest_timing_enter_irqoff(); ret = kvm_arm_vcpu_enter_exit(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; /* * Back from guest *************************************************************/ /* * We must sync the PMU state before the vgic state so * that the vgic can properly sample the updated state of the * interrupt line. */ kvm_pmu_sync_hwstate(vcpu); /* * Sync the vgic state before syncing the timer state because * the timer code needs to know if the virtual timer * interrupts are active. */ kvm_vgic_sync_hwstate(vcpu); /* * Sync the timer hardware state before enabling interrupts as * we don't want vtimer interrupts to race with syncing the * timer virtual interrupt state. */ if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); if (is_hyp_ctxt(vcpu)) kvm_timer_sync_nested(vcpu); kvm_arch_vcpu_ctxsync_fp(vcpu); /* * We must ensure that any pending interrupts are taken before * we exit guest timing so that timer ticks are accounted as * guest time. Transiently unmask interrupts so that any * pending interrupts are taken. * * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other * context synchronization event) is necessary to ensure that * pending interrupts are taken. */ if (ARM_EXCEPTION_CODE(ret) == ARM_EXCEPTION_IRQ) { local_irq_enable(); isb(); local_irq_disable(); } guest_timing_exit_irqoff(); local_irq_enable(); trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); /* Exit types that need handling before we can be preempted */ handle_exit_early(vcpu, ret); preempt_enable(); /* * The ARMv8 architecture doesn't give the hypervisor * a mechanism to prevent a guest from dropping to AArch32 EL0 * if implemented by the CPU. If we spot the guest in such * state and that we decided it wasn't supposed to do so (like * with the asymmetric AArch32 case), return to userspace with * a fatal error. */ if (vcpu_mode_is_bad_32bit(vcpu)) { /* * As we have caught the guest red-handed, decide that * it isn't fit for purpose anymore by making the vcpu * invalid. The VMM can try and fix it by issuing a * KVM_ARM_VCPU_INIT if it really wants to. */ vcpu_clear_flag(vcpu, VCPU_INITIALIZED); ret = ARM_EXCEPTION_IL; } ret = handle_exit(vcpu, ret); } /* Tell userspace about in-kernel device output levels */ if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { kvm_timer_update_run(vcpu); kvm_pmu_update_run(vcpu); } kvm_sigset_deactivate(vcpu); out: /* * In the unlikely event that we are returning to userspace * with pending exceptions or PC adjustment, commit these * adjustments in order to give userspace a consistent view of * the vcpu state. Note that this relies on __kvm_adjust_pc() * being preempt-safe on VHE. */ if (unlikely(vcpu_get_flag(vcpu, PENDING_EXCEPTION) || vcpu_get_flag(vcpu, INCREMENT_PC))) kvm_call_hyp(__kvm_adjust_pc, vcpu); vcpu_put(vcpu); return ret; } static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level) { int bit_index; bool set; unsigned long *hcr; if (number == KVM_ARM_IRQ_CPU_IRQ) bit_index = __ffs(HCR_VI); else /* KVM_ARM_IRQ_CPU_FIQ */ bit_index = __ffs(HCR_VF); hcr = vcpu_hcr(vcpu); if (level) set = test_and_set_bit(bit_index, hcr); else set = test_and_clear_bit(bit_index, hcr); /* * If we didn't change anything, no need to wake up or kick other CPUs */ if (set == level) return 0; /* * The vcpu irq_lines field was updated, wake up sleeping VCPUs and * trigger a world-switch round on the running physical CPU to set the * virtual IRQ/FIQ fields in the HCR appropriately. */ kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); return 0; } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status) { u32 irq = irq_level->irq; unsigned int irq_type, vcpu_id, irq_num; struct kvm_vcpu *vcpu = NULL; bool level = irq_level->level; irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; vcpu_id = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; vcpu_id += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1); irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK; trace_kvm_irq_line(irq_type, vcpu_id, irq_num, irq_level->level); switch (irq_type) { case KVM_ARM_IRQ_TYPE_CPU: if (irqchip_in_kernel(kvm)) return -ENXIO; vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); if (!vcpu) return -EINVAL; if (irq_num > KVM_ARM_IRQ_CPU_FIQ) return -EINVAL; return vcpu_interrupt_line(vcpu, irq_num, level); case KVM_ARM_IRQ_TYPE_PPI: if (!irqchip_in_kernel(kvm)) return -ENXIO; vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); if (!vcpu) return -EINVAL; if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS) return -EINVAL; return kvm_vgic_inject_irq(kvm, vcpu, irq_num, level, NULL); case KVM_ARM_IRQ_TYPE_SPI: if (!irqchip_in_kernel(kvm)) return -ENXIO; if (irq_num < VGIC_NR_PRIVATE_IRQS) return -EINVAL; return kvm_vgic_inject_irq(kvm, NULL, irq_num, level, NULL); } return -EINVAL; } static unsigned long system_supported_vcpu_features(void) { unsigned long features = KVM_VCPU_VALID_FEATURES; if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1)) clear_bit(KVM_ARM_VCPU_EL1_32BIT, &features); if (!kvm_arm_support_pmu_v3()) clear_bit(KVM_ARM_VCPU_PMU_V3, &features); if (!system_supports_sve()) clear_bit(KVM_ARM_VCPU_SVE, &features); if (!kvm_has_full_ptr_auth()) { clear_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features); clear_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features); } if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT)) clear_bit(KVM_ARM_VCPU_HAS_EL2, &features); return features; } static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { unsigned long features = init->features[0]; int i; if (features & ~KVM_VCPU_VALID_FEATURES) return -ENOENT; for (i = 1; i < ARRAY_SIZE(init->features); i++) { if (init->features[i]) return -ENOENT; } if (features & ~system_supported_vcpu_features()) return -EINVAL; /* * For now make sure that both address/generic pointer authentication * features are requested by the userspace together. */ if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features) != test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features)) return -EINVAL; if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features)) return 0; /* MTE is incompatible with AArch32 */ if (kvm_has_mte(vcpu->kvm)) return -EINVAL; /* NV is incompatible with AArch32 */ if (test_bit(KVM_ARM_VCPU_HAS_EL2, &features)) return -EINVAL; return 0; } static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { unsigned long features = init->features[0]; return !bitmap_equal(vcpu->kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES); } static int kvm_setup_vcpu(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; int ret = 0; /* * When the vCPU has a PMU, but no PMU is set for the guest * yet, set the default one. */ if (kvm_vcpu_has_pmu(vcpu) && !kvm->arch.arm_pmu) ret = kvm_arm_set_default_pmu(kvm); /* Prepare for nested if required */ if (!ret && vcpu_has_nv(vcpu)) ret = kvm_vcpu_init_nested(vcpu); return ret; } static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { unsigned long features = init->features[0]; struct kvm *kvm = vcpu->kvm; int ret = -EINVAL; mutex_lock(&kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags) && kvm_vcpu_init_changed(vcpu, init)) goto out_unlock; bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES); ret = kvm_setup_vcpu(vcpu); if (ret) goto out_unlock; /* Now we know what it is, we can reset it. */ kvm_reset_vcpu(vcpu); set_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags); vcpu_set_flag(vcpu, VCPU_INITIALIZED); ret = 0; out_unlock: mutex_unlock(&kvm->arch.config_lock); return ret; } static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { int ret; if (init->target != KVM_ARM_TARGET_GENERIC_V8 && init->target != kvm_target_cpu()) return -EINVAL; ret = kvm_vcpu_init_check_features(vcpu, init); if (ret) return ret; if (!kvm_vcpu_initialized(vcpu)) return __kvm_vcpu_set_target(vcpu, init); if (kvm_vcpu_init_changed(vcpu, init)) return -EINVAL; kvm_reset_vcpu(vcpu); return 0; } static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { bool power_off = false; int ret; /* * Treat the power-off vCPU feature as ephemeral. Clear the bit to avoid * reflecting it in the finalized feature set, thus limiting its scope * to a single KVM_ARM_VCPU_INIT call. */ if (init->features[0] & BIT(KVM_ARM_VCPU_POWER_OFF)) { init->features[0] &= ~BIT(KVM_ARM_VCPU_POWER_OFF); power_off = true; } ret = kvm_vcpu_set_target(vcpu, init); if (ret) return ret; /* * Ensure a rebooted VM will fault in RAM pages and detect if the * guest MMU is turned off and flush the caches as needed. * * S2FWB enforces all memory accesses to RAM being cacheable, * ensuring that the data side is always coherent. We still * need to invalidate the I-cache though, as FWB does *not* * imply CTR_EL0.DIC. */ if (vcpu_has_run_once(vcpu)) { if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) stage2_unmap_vm(vcpu->kvm); else icache_inval_all_pou(); } vcpu_reset_hcr(vcpu); /* * Handle the "start in power-off" case. */ spin_lock(&vcpu->arch.mp_state_lock); if (power_off) __kvm_arm_vcpu_power_off(vcpu); else WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); spin_unlock(&vcpu->arch.mp_state_lock); return 0; } static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = -ENXIO; switch (attr->group) { default: ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr); break; } return ret; } static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = -ENXIO; switch (attr->group) { default: ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr); break; } return ret; } static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int ret = -ENXIO; switch (attr->group) { default: ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr); break; } return ret; } static int kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { memset(events, 0, sizeof(*events)); return __kvm_arm_vcpu_get_events(vcpu, events); } static int kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { int i; /* check whether the reserved field is zero */ for (i = 0; i < ARRAY_SIZE(events->reserved); i++) if (events->reserved[i]) return -EINVAL; /* check whether the pad field is zero */ for (i = 0; i < ARRAY_SIZE(events->exception.pad); i++) if (events->exception.pad[i]) return -EINVAL; return __kvm_arm_vcpu_set_events(vcpu, events); } long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; struct kvm_device_attr attr; long r; switch (ioctl) { case KVM_ARM_VCPU_INIT: { struct kvm_vcpu_init init; r = -EFAULT; if (copy_from_user(&init, argp, sizeof(init))) break; r = kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); break; } case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) break; r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) break; /* * We could owe a reset due to PSCI. Handle the pending reset * here to ensure userspace register accesses are ordered after * the reset. */ if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) kvm_reset_vcpu(vcpu); if (ioctl == KVM_SET_ONE_REG) r = kvm_arm_set_reg(vcpu, ®); else r = kvm_arm_get_reg(vcpu, ®); break; } case KVM_GET_REG_LIST: { struct kvm_reg_list __user *user_list = argp; struct kvm_reg_list reg_list; unsigned n; r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) break; r = -EPERM; if (!kvm_arm_vcpu_is_finalized(vcpu)) break; r = -EFAULT; if (copy_from_user(®_list, user_list, sizeof(reg_list))) break; n = reg_list.n; reg_list.n = kvm_arm_num_regs(vcpu); if (copy_to_user(user_list, ®_list, sizeof(reg_list))) break; r = -E2BIG; if (n < reg_list.n) break; r = kvm_arm_copy_reg_indices(vcpu, user_list->reg); break; } case KVM_SET_DEVICE_ATTR: { r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) break; r = kvm_arm_vcpu_set_attr(vcpu, &attr); break; } case KVM_GET_DEVICE_ATTR: { r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) break; r = kvm_arm_vcpu_get_attr(vcpu, &attr); break; } case KVM_HAS_DEVICE_ATTR: { r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) break; r = kvm_arm_vcpu_has_attr(vcpu, &attr); break; } case KVM_GET_VCPU_EVENTS: { struct kvm_vcpu_events events; if (kvm_arm_vcpu_get_events(vcpu, &events)) return -EINVAL; if (copy_to_user(argp, &events, sizeof(events))) return -EFAULT; return 0; } case KVM_SET_VCPU_EVENTS: { struct kvm_vcpu_events events; if (copy_from_user(&events, argp, sizeof(events))) return -EFAULT; return kvm_arm_vcpu_set_events(vcpu, &events); } case KVM_ARM_VCPU_FINALIZE: { int what; if (!kvm_vcpu_initialized(vcpu)) return -ENOEXEC; if (get_user(what, (const int __user *)argp)) return -EFAULT; return kvm_arm_vcpu_finalize(vcpu, what); } default: r = -EINVAL; } return r; } void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { } static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr) { switch (FIELD_GET(KVM_ARM_DEVICE_ID_MASK, dev_addr->id)) { case KVM_ARM_DEVICE_VGIC_V2: if (!vgic_present) return -ENXIO; return kvm_set_legacy_vgic_v2_addr(kvm, dev_addr); default: return -ENODEV; } } static int kvm_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_ARM_VM_SMCCC_CTRL: return kvm_vm_smccc_has_attr(kvm, attr); default: return -ENXIO; } } static int kvm_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_ARM_VM_SMCCC_CTRL: return kvm_vm_smccc_set_attr(kvm, attr); default: return -ENXIO; } } int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; struct kvm_device_attr attr; switch (ioctl) { case KVM_CREATE_IRQCHIP: { int ret; if (!vgic_present) return -ENXIO; mutex_lock(&kvm->lock); ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); mutex_unlock(&kvm->lock); return ret; } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; if (copy_from_user(&dev_addr, argp, sizeof(dev_addr))) return -EFAULT; return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); } case KVM_ARM_PREFERRED_TARGET: { struct kvm_vcpu_init init = { .target = KVM_ARM_TARGET_GENERIC_V8, }; if (copy_to_user(argp, &init, sizeof(init))) return -EFAULT; return 0; } case KVM_ARM_MTE_COPY_TAGS: { struct kvm_arm_copy_mte_tags copy_tags; if (copy_from_user(©_tags, argp, sizeof(copy_tags))) return -EFAULT; return kvm_vm_ioctl_mte_copy_tags(kvm, ©_tags); } case KVM_ARM_SET_COUNTER_OFFSET: { struct kvm_arm_counter_offset offset; if (copy_from_user(&offset, argp, sizeof(offset))) return -EFAULT; return kvm_vm_ioctl_set_counter_offset(kvm, &offset); } case KVM_HAS_DEVICE_ATTR: { if (copy_from_user(&attr, argp, sizeof(attr))) return -EFAULT; return kvm_vm_has_attr(kvm, &attr); } case KVM_SET_DEVICE_ATTR: { if (copy_from_user(&attr, argp, sizeof(attr))) return -EFAULT; return kvm_vm_set_attr(kvm, &attr); } case KVM_ARM_GET_REG_WRITABLE_MASKS: { struct reg_mask_range range; if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; return kvm_vm_ioctl_get_reg_writable_masks(kvm, &range); } default: return -EINVAL; } } /* unlocks vcpus from @vcpu_lock_idx and smaller */ static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx) { struct kvm_vcpu *tmp_vcpu; for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); mutex_unlock(&tmp_vcpu->mutex); } } void unlock_all_vcpus(struct kvm *kvm) { lockdep_assert_held(&kvm->lock); unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1); } /* Returns true if all vcpus were locked, false otherwise */ bool lock_all_vcpus(struct kvm *kvm) { struct kvm_vcpu *tmp_vcpu; unsigned long c; lockdep_assert_held(&kvm->lock); /* * Any time a vcpu is in an ioctl (including running), the * core KVM code tries to grab the vcpu->mutex. * * By grabbing the vcpu->mutex of all VCPUs we ensure that no * other VCPUs can fiddle with the state while we access it. */ kvm_for_each_vcpu(c, tmp_vcpu, kvm) { if (!mutex_trylock(&tmp_vcpu->mutex)) { unlock_vcpus(kvm, c - 1); return false; } } return true; } static unsigned long nvhe_percpu_size(void) { return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) - (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_start); } static unsigned long nvhe_percpu_order(void) { unsigned long size = nvhe_percpu_size(); return size ? get_order(size) : 0; } static size_t pkvm_host_sve_state_order(void) { return get_order(pkvm_host_sve_state_size()); } /* A lookup table holding the hypervisor VA for each vector slot */ static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS]; static void kvm_init_vector_slot(void *base, enum arm64_hyp_spectre_vector slot) { hyp_spectre_vector_selector[slot] = __kvm_vector_slot2addr(base, slot); } static int kvm_init_vector_slots(void) { int err; void *base; base = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector)); kvm_init_vector_slot(base, HYP_VECTOR_DIRECT); base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); if (kvm_system_needs_idmapped_vectors() && !is_protected_kvm_enabled()) { err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), __BP_HARDEN_HYP_VECS_SZ, &base); if (err) return err; } kvm_init_vector_slot(base, HYP_VECTOR_INDIRECT); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_INDIRECT); return 0; } static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); unsigned long tcr; /* * Calculate the raw per-cpu offset without a translation from the * kernel's mapping to the linear mapping, and store it in tpidr_el2 * so that we can use adr_l to access per-cpu variables in EL2. * Also drop the KASAN tag which gets in the way... */ params->tpidr_el2 = (unsigned long)kasan_reset_tag(per_cpu_ptr_nvhe_sym(__per_cpu_start, cpu)) - (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start)); params->mair_el2 = read_sysreg(mair_el1); tcr = read_sysreg(tcr_el1); if (cpus_have_final_cap(ARM64_KVM_HVHE)) { tcr |= TCR_EPD1_MASK; } else { tcr &= TCR_EL2_MASK; tcr |= TCR_EL2_RES1; } tcr &= ~TCR_T0SZ_MASK; tcr |= TCR_T0SZ(hyp_va_bits); tcr &= ~TCR_EL2_PS_MASK; tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0)); if (kvm_lpa2_is_enabled()) tcr |= TCR_EL2_DS; params->tcr_el2 = tcr; params->pgd_pa = kvm_mmu_get_httbr(); if (is_protected_kvm_enabled()) params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS; else params->hcr_el2 = HCR_HOST_NVHE_FLAGS; if (cpus_have_final_cap(ARM64_KVM_HVHE)) params->hcr_el2 |= HCR_E2H; params->vttbr = params->vtcr = 0; /* * Flush the init params from the data cache because the struct will * be read while the MMU is off. */ kvm_flush_dcache_to_poc(params, sizeof(*params)); } static void hyp_install_host_vector(void) { struct kvm_nvhe_init_params *params; struct arm_smccc_res res; /* Switch from the HYP stub to our own HYP init vector */ __hyp_set_vectors(kvm_get_idmap_vector()); /* * Call initialization code, and switch to the full blown HYP code. * If the cpucaps haven't been finalized yet, something has gone very * wrong, and hyp will crash and burn when it uses any * cpus_have_*_cap() wrapper. */ BUG_ON(!system_capabilities_finalized()); params = this_cpu_ptr_nvhe_sym(kvm_init_params); arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init), virt_to_phys(params), &res); WARN_ON(res.a0 != SMCCC_RET_SUCCESS); } static void cpu_init_hyp_mode(void) { hyp_install_host_vector(); /* * Disabling SSBD on a non-VHE system requires us to enable SSBS * at EL2. */ if (this_cpu_has_cap(ARM64_SSBS) && arm64_get_spectre_v4_state() == SPECTRE_VULNERABLE) { kvm_call_hyp_nvhe(__kvm_enable_ssbs); } } static void cpu_hyp_reset(void) { if (!is_kernel_in_hyp_mode()) __hyp_reset_vectors(); } /* * EL2 vectors can be mapped and rerouted in a number of ways, * depending on the kernel configuration and CPU present: * * - If the CPU is affected by Spectre-v2, the hardening sequence is * placed in one of the vector slots, which is executed before jumping * to the real vectors. * * - If the CPU also has the ARM64_SPECTRE_V3A cap, the slot * containing the hardening sequence is mapped next to the idmap page, * and executed before jumping to the real vectors. * * - If the CPU only has the ARM64_SPECTRE_V3A cap, then an * empty slot is selected, mapped next to the idmap page, and * executed before jumping to the real vectors. * * Note that ARM64_SPECTRE_V3A is somewhat incompatible with * VHE, as we don't have hypervisor-specific mappings. If the system * is VHE and yet selects this capability, it will be ignored. */ static void cpu_set_hyp_vector(void) { struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); void *vector = hyp_spectre_vector_selector[data->slot]; if (!is_protected_kvm_enabled()) *this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)vector; else kvm_call_hyp_nvhe(__pkvm_cpu_set_vector, data->slot); } static void cpu_hyp_init_context(void) { kvm_init_host_cpu_context(host_data_ptr(host_ctxt)); kvm_init_host_debug_data(); if (!is_kernel_in_hyp_mode()) cpu_init_hyp_mode(); } static void cpu_hyp_init_features(void) { cpu_set_hyp_vector(); if (is_kernel_in_hyp_mode()) kvm_timer_init_vhe(); if (vgic_present) kvm_vgic_init_cpu_hardware(); } static void cpu_hyp_reinit(void) { cpu_hyp_reset(); cpu_hyp_init_context(); cpu_hyp_init_features(); } static void cpu_hyp_init(void *discard) { if (!__this_cpu_read(kvm_hyp_initialized)) { cpu_hyp_reinit(); __this_cpu_write(kvm_hyp_initialized, 1); } } static void cpu_hyp_uninit(void *discard) { if (__this_cpu_read(kvm_hyp_initialized)) { cpu_hyp_reset(); __this_cpu_write(kvm_hyp_initialized, 0); } } int kvm_arch_enable_virtualization_cpu(void) { /* * Most calls to this function are made with migration * disabled, but not with preemption disabled. The former is * enough to ensure correctness, but most of the helpers * expect the later and will throw a tantrum otherwise. */ preempt_disable(); cpu_hyp_init(NULL); kvm_vgic_cpu_up(); kvm_timer_cpu_up(); preempt_enable(); return 0; } void kvm_arch_disable_virtualization_cpu(void) { kvm_timer_cpu_down(); kvm_vgic_cpu_down(); if (!is_protected_kvm_enabled()) cpu_hyp_uninit(NULL); } #ifdef CONFIG_CPU_PM static int hyp_init_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { /* * kvm_hyp_initialized is left with its old value over * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should * re-enable hyp. */ switch (cmd) { case CPU_PM_ENTER: if (__this_cpu_read(kvm_hyp_initialized)) /* * don't update kvm_hyp_initialized here * so that the hyp will be re-enabled * when we resume. See below. */ cpu_hyp_reset(); return NOTIFY_OK; case CPU_PM_ENTER_FAILED: case CPU_PM_EXIT: if (__this_cpu_read(kvm_hyp_initialized)) /* The hyp was enabled before suspend. */ cpu_hyp_reinit(); return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block hyp_init_cpu_pm_nb = { .notifier_call = hyp_init_cpu_pm_notifier, }; static void __init hyp_cpu_pm_init(void) { if (!is_protected_kvm_enabled()) cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); } static void __init hyp_cpu_pm_exit(void) { if (!is_protected_kvm_enabled()) cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); } #else static inline void __init hyp_cpu_pm_init(void) { } static inline void __init hyp_cpu_pm_exit(void) { } #endif static void __init init_cpu_logical_map(void) { unsigned int cpu; /* * Copy the MPIDR <-> logical CPU ID mapping to hyp. * Only copy the set of online CPUs whose features have been checked * against the finalized system capabilities. The hypervisor will not * allow any other CPUs from the `possible` set to boot. */ for_each_online_cpu(cpu) hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu); } #define init_psci_0_1_impl_state(config, what) \ config.psci_0_1_ ## what ## _implemented = psci_ops.what static bool __init init_psci_relay(void) { /* * If PSCI has not been initialized, protected KVM cannot install * itself on newly booted CPUs. */ if (!psci_ops.get_version) { kvm_err("Cannot initialize protected mode without PSCI\n"); return false; } kvm_host_psci_config.version = psci_ops.get_version(); kvm_host_psci_config.smccc_version = arm_smccc_get_version(); if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) { kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids(); init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend); init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on); init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off); init_psci_0_1_impl_state(kvm_host_psci_config, migrate); } return true; } static int __init init_subsystems(void) { int err = 0; /* * Enable hardware so that subsystem initialisation can access EL2. */ on_each_cpu(cpu_hyp_init, NULL, 1); /* * Register CPU lower-power notifier */ hyp_cpu_pm_init(); /* * Init HYP view of VGIC */ err = kvm_vgic_hyp_init(); switch (err) { case 0: vgic_present = true; break; case -ENODEV: case -ENXIO: vgic_present = false; err = 0; break; default: goto out; } /* * Init HYP architected timer support */ err = kvm_timer_hyp_init(vgic_present); if (err) goto out; kvm_register_perf_callbacks(NULL); out: if (err) hyp_cpu_pm_exit(); if (err || !is_protected_kvm_enabled()) on_each_cpu(cpu_hyp_uninit, NULL, 1); return err; } static void __init teardown_subsystems(void) { kvm_unregister_perf_callbacks(); hyp_cpu_pm_exit(); } static void __init teardown_hyp_mode(void) { bool free_sve = system_supports_sve() && is_protected_kvm_enabled(); int cpu; free_hyp_pgds(); for_each_possible_cpu(cpu) { free_page(per_cpu(kvm_arm_hyp_stack_page, cpu)); free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order()); if (free_sve) { struct cpu_sve_state *sve_state; sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state; free_pages((unsigned long) sve_state, pkvm_host_sve_state_order()); } } } static int __init do_pkvm_init(u32 hyp_va_bits) { void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)); int ret; preempt_disable(); cpu_hyp_init_context(); ret = kvm_call_hyp_nvhe(__pkvm_init, hyp_mem_base, hyp_mem_size, num_possible_cpus(), kern_hyp_va(per_cpu_base), hyp_va_bits); cpu_hyp_init_features(); /* * The stub hypercalls are now disabled, so set our local flag to * prevent a later re-init attempt in kvm_arch_enable_virtualization_cpu(). */ __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); return ret; } static u64 get_hyp_id_aa64pfr0_el1(void) { /* * Track whether the system isn't affected by spectre/meltdown in the * hypervisor's view of id_aa64pfr0_el1, used for protected VMs. * Although this is per-CPU, we make it global for simplicity, e.g., not * to have to worry about vcpu migration. * * Unlike for non-protected VMs, userspace cannot override this for * protected VMs. */ u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3)); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), arm64_get_meltdown_state() == SPECTRE_UNAFFECTED); return val; } static void kvm_hyp_init_symbols(void) { kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = get_hyp_id_aa64pfr0_el1(); kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); kvm_nvhe_sym(id_aa64isar2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1); kvm_nvhe_sym(__icache_flags) = __icache_flags; kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; } static int __init kvm_hyp_init_protection(u32 hyp_va_bits) { void *addr = phys_to_virt(hyp_mem_base); int ret; ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP); if (ret) return ret; ret = do_pkvm_init(hyp_va_bits); if (ret) return ret; free_hyp_pgds(); return 0; } static int init_pkvm_host_sve_state(void) { int cpu; if (!system_supports_sve()) return 0; /* Allocate pages for host sve state in protected mode. */ for_each_possible_cpu(cpu) { struct page *page = alloc_pages(GFP_KERNEL, pkvm_host_sve_state_order()); if (!page) return -ENOMEM; per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = page_address(page); } /* * Don't map the pages in hyp since these are only used in protected * mode, which will (re)create its own mapping when initialized. */ return 0; } /* * Finalizes the initialization of hyp mode, once everything else is initialized * and the initialziation process cannot fail. */ static void finalize_init_hyp_mode(void) { int cpu; if (system_supports_sve() && is_protected_kvm_enabled()) { for_each_possible_cpu(cpu) { struct cpu_sve_state *sve_state; sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state; per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state); } } else { for_each_possible_cpu(cpu) { struct user_fpsimd_state *fpsimd_state; fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs; per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state = kern_hyp_va(fpsimd_state); } } } static void pkvm_hyp_init_ptrauth(void) { struct kvm_cpu_context *hyp_ctxt; int cpu; for_each_possible_cpu(cpu) { hyp_ctxt = per_cpu_ptr_nvhe_sym(kvm_hyp_ctxt, cpu); hyp_ctxt->sys_regs[APIAKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APIAKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APIBKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APIBKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDAKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDAKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDBKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APDBKEYHI_EL1] = get_random_long(); hyp_ctxt->sys_regs[APGAKEYLO_EL1] = get_random_long(); hyp_ctxt->sys_regs[APGAKEYHI_EL1] = get_random_long(); } } /* Inits Hyp-mode on all online CPUs */ static int __init init_hyp_mode(void) { u32 hyp_va_bits; int cpu; int err = -ENOMEM; /* * The protected Hyp-mode cannot be initialized if the memory pool * allocation has failed. */ if (is_protected_kvm_enabled() && !hyp_mem_base) goto out_err; /* * Allocate Hyp PGD and setup Hyp identity mapping */ err = kvm_mmu_init(&hyp_va_bits); if (err) goto out_err; /* * Allocate stack pages for Hypervisor-mode */ for_each_possible_cpu(cpu) { unsigned long stack_page; stack_page = __get_free_page(GFP_KERNEL); if (!stack_page) { err = -ENOMEM; goto out_err; } per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page; } /* * Allocate and initialize pages for Hypervisor-mode percpu regions. */ for_each_possible_cpu(cpu) { struct page *page; void *page_addr; page = alloc_pages(GFP_KERNEL, nvhe_percpu_order()); if (!page) { err = -ENOMEM; goto out_err; } page_addr = page_address(page); memcpy(page_addr, CHOOSE_NVHE_SYM(__per_cpu_start), nvhe_percpu_size()); kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu] = (unsigned long)page_addr; } /* * Map the Hyp-code called directly from the host */ err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start), kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC); if (err) { kvm_err("Cannot map world-switch code\n"); goto out_err; } err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start), kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO); if (err) { kvm_err("Cannot map .hyp.rodata section\n"); goto out_err; } err = create_hyp_mappings(kvm_ksym_ref(__start_rodata), kvm_ksym_ref(__end_rodata), PAGE_HYP_RO); if (err) { kvm_err("Cannot map rodata section\n"); goto out_err; } /* * .hyp.bss is guaranteed to be placed at the beginning of the .bss * section thanks to an assertion in the linker script. Map it RW and * the rest of .bss RO. */ err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_start), kvm_ksym_ref(__hyp_bss_end), PAGE_HYP); if (err) { kvm_err("Cannot map hyp bss section: %d\n", err); goto out_err; } err = create_hyp_mappings(kvm_ksym_ref(__hyp_bss_end), kvm_ksym_ref(__bss_stop), PAGE_HYP_RO); if (err) { kvm_err("Cannot map bss section\n"); goto out_err; } /* * Map the Hyp stack pages */ for_each_possible_cpu(cpu) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu); err = create_hyp_stack(__pa(stack_page), ¶ms->stack_hyp_va); if (err) { kvm_err("Cannot map hyp stack\n"); goto out_err; } /* * Save the stack PA in nvhe_init_params. This will be needed * to recreate the stack mapping in protected nVHE mode. * __hyp_pa() won't do the right thing there, since the stack * has been mapped in the flexible private VA space. */ params->stack_pa = __pa(stack_page); } for_each_possible_cpu(cpu) { char *percpu_begin = (char *)kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu]; char *percpu_end = percpu_begin + nvhe_percpu_size(); /* Map Hyp percpu pages */ err = create_hyp_mappings(percpu_begin, percpu_end, PAGE_HYP); if (err) { kvm_err("Cannot map hyp percpu region\n"); goto out_err; } /* Prepare the CPU initialization parameters */ cpu_prepare_hyp_mode(cpu, hyp_va_bits); } kvm_hyp_init_symbols(); if (is_protected_kvm_enabled()) { if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH)) pkvm_hyp_init_ptrauth(); init_cpu_logical_map(); if (!init_psci_relay()) { err = -ENODEV; goto out_err; } err = init_pkvm_host_sve_state(); if (err) goto out_err; err = kvm_hyp_init_protection(hyp_va_bits); if (err) { kvm_err("Failed to init hyp memory protection\n"); goto out_err; } } return 0; out_err: teardown_hyp_mode(); kvm_err("error initializing Hyp mode: %d\n", err); return err; } struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { struct kvm_vcpu *vcpu = NULL; struct kvm_mpidr_data *data; unsigned long i; mpidr &= MPIDR_HWID_BITMASK; rcu_read_lock(); data = rcu_dereference(kvm->arch.mpidr_data); if (data) { u16 idx = kvm_mpidr_index(data, mpidr); vcpu = kvm_get_vcpu(kvm, data->cmpidr_to_idx[idx]); if (mpidr != kvm_vcpu_get_mpidr_aff(vcpu)) vcpu = NULL; } rcu_read_unlock(); if (vcpu) return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu)) return vcpu; } return NULL; } bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) { return irqchip_in_kernel(kvm); } bool kvm_arch_has_irq_bypass(void) { return true; } int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq, &irqfd->irq_entry); } void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq, &irqfd->irq_entry); } void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); kvm_arm_halt_guest(irqfd->kvm); } void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); kvm_arm_resume_guest(irqfd->kvm); } /* Initialize Hyp-mode and memory mappings on all CPUs */ static __init int kvm_arm_init(void) { int err; bool in_hyp_mode; if (!is_hyp_mode_available()) { kvm_info("HYP mode not available\n"); return -ENODEV; } if (kvm_get_mode() == KVM_MODE_NONE) { kvm_info("KVM disabled from command line\n"); return -ENODEV; } err = kvm_sys_reg_table_init(); if (err) { kvm_info("Error initializing system register tables"); return err; } in_hyp_mode = is_kernel_in_hyp_mode(); if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) || cpus_have_final_cap(ARM64_WORKAROUND_1508412)) kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ "Only trusted guests should be used on this system.\n"); err = kvm_set_ipa_limit(); if (err) return err; err = kvm_arm_init_sve(); if (err) return err; err = kvm_arm_vmid_alloc_init(); if (err) { kvm_err("Failed to initialize VMID allocator.\n"); return err; } if (!in_hyp_mode) { err = init_hyp_mode(); if (err) goto out_err; } err = kvm_init_vector_slots(); if (err) { kvm_err("Cannot initialise vector slots\n"); goto out_hyp; } err = init_subsystems(); if (err) goto out_hyp; kvm_info("%s%sVHE mode initialized successfully\n", in_hyp_mode ? "" : (is_protected_kvm_enabled() ? "Protected " : "Hyp "), in_hyp_mode ? "" : (cpus_have_final_cap(ARM64_KVM_HVHE) ? "h" : "n")); /* * FIXME: Do something reasonable if kvm_init() fails after pKVM * hypervisor protection is finalized. */ err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (err) goto out_subs; /* * This should be called after initialization is done and failure isn't * possible anymore. */ if (!in_hyp_mode) finalize_init_hyp_mode(); kvm_arm_initialised = true; return 0; out_subs: teardown_subsystems(); out_hyp: if (!in_hyp_mode) teardown_hyp_mode(); out_err: kvm_arm_vmid_alloc_free(); return err; } static int __init early_kvm_mode_cfg(char *arg) { if (!arg) return -EINVAL; if (strcmp(arg, "none") == 0) { kvm_mode = KVM_MODE_NONE; return 0; } if (!is_hyp_mode_available()) { pr_warn_once("KVM is not available. Ignoring kvm-arm.mode\n"); return 0; } if (strcmp(arg, "protected") == 0) { if (!is_kernel_in_hyp_mode()) kvm_mode = KVM_MODE_PROTECTED; else pr_warn_once("Protected KVM not available with VHE\n"); return 0; } if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode())) { kvm_mode = KVM_MODE_DEFAULT; return 0; } if (strcmp(arg, "nested") == 0 && !WARN_ON(!is_kernel_in_hyp_mode())) { kvm_mode = KVM_MODE_NV; return 0; } return -EINVAL; } early_param("kvm-arm.mode", early_kvm_mode_cfg); static int __init early_kvm_wfx_trap_policy_cfg(char *arg, enum kvm_wfx_trap_policy *p) { if (!arg) return -EINVAL; if (strcmp(arg, "trap") == 0) { *p = KVM_WFX_TRAP; return 0; } if (strcmp(arg, "notrap") == 0) { *p = KVM_WFX_NOTRAP; return 0; } return -EINVAL; } static int __init early_kvm_wfi_trap_policy_cfg(char *arg) { return early_kvm_wfx_trap_policy_cfg(arg, &kvm_wfi_trap_policy); } early_param("kvm-arm.wfi_trap_policy", early_kvm_wfi_trap_policy_cfg); static int __init early_kvm_wfe_trap_policy_cfg(char *arg) { return early_kvm_wfx_trap_policy_cfg(arg, &kvm_wfe_trap_policy); } early_param("kvm-arm.wfe_trap_policy", early_kvm_wfe_trap_policy_cfg); enum kvm_mode kvm_get_mode(void) { return kvm_mode; } module_init(kvm_arm_init); |
| 6 6 364 208 119 119 38 1 1 1 287 196 366 10 254 368 7 364 214 39 196 3 195 16 189 190 14 131 9 138 1 138 289 119 37 9 29 363 364 365 1 364 365 160 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/fault.c * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 1995-2004 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/extable.h> #include <linux/kfence.h> #include <linux/signal.h> #include <linux/mm.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/kasan.h> #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/page-flags.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/highmem.h> #include <linux/perf_event.h> #include <linux/pkeys.h> #include <linux/preempt.h> #include <linux/hugetlb.h> #include <asm/acpi.h> #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> #include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kprobes.h> #include <asm/mte.h> #include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/tlbflush.h> #include <asm/traps.h> struct fault_info { int (*fn)(unsigned long far, unsigned long esr, struct pt_regs *regs); int sig; int code; const char *name; }; static const struct fault_info fault_info[]; static struct fault_info debug_fault_info[]; static inline const struct fault_info *esr_to_fault_info(unsigned long esr) { return fault_info + (esr & ESR_ELx_FSC); } static inline const struct fault_info *esr_to_debug_fault_info(unsigned long esr) { return debug_fault_info + DBG_ESR_EVT(esr); } static void data_abort_decode(unsigned long esr) { unsigned long iss2 = ESR_ELx_ISS2(esr); pr_alert("Data abort info:\n"); if (esr & ESR_ELx_ISV) { pr_alert(" Access size = %u byte(s)\n", 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT)); pr_alert(" SSE = %lu, SRT = %lu\n", (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT, (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT); pr_alert(" SF = %lu, AR = %lu\n", (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { pr_alert(" ISV = 0, ISS = 0x%08lx, ISS2 = 0x%08lx\n", esr & ESR_ELx_ISS_MASK, iss2); } pr_alert(" CM = %lu, WnR = %lu, TnD = %lu, TagAccess = %lu\n", (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT, (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT, (iss2 & ESR_ELx_TnD) >> ESR_ELx_TnD_SHIFT, (iss2 & ESR_ELx_TagAccess) >> ESR_ELx_TagAccess_SHIFT); pr_alert(" GCS = %ld, Overlay = %lu, DirtyBit = %lu, Xs = %llu\n", (iss2 & ESR_ELx_GCS) >> ESR_ELx_GCS_SHIFT, (iss2 & ESR_ELx_Overlay) >> ESR_ELx_Overlay_SHIFT, (iss2 & ESR_ELx_DirtyBit) >> ESR_ELx_DirtyBit_SHIFT, (iss2 & ESR_ELx_Xs_MASK) >> ESR_ELx_Xs_SHIFT); } static void mem_abort_decode(unsigned long esr) { pr_alert("Mem abort info:\n"); pr_alert(" ESR = 0x%016lx\n", esr); pr_alert(" EC = 0x%02lx: %s, IL = %u bits\n", ESR_ELx_EC(esr), esr_get_class_string(esr), (esr & ESR_ELx_IL) ? 32 : 16); pr_alert(" SET = %lu, FnV = %lu\n", (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT, (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT); pr_alert(" EA = %lu, S1PTW = %lu\n", (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT, (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT); pr_alert(" FSC = 0x%02lx: %s\n", (esr & ESR_ELx_FSC), esr_to_fault_info(esr)->name); if (esr_is_data_abort(esr)) data_abort_decode(esr); } static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ if (mm == &init_mm) return __pa_symbol(mm->pgd); return (unsigned long)virt_to_phys(mm->pgd); } /* * Dump out the page tables associated with 'addr' in the currently active mm. */ static void show_pte(unsigned long addr) { struct mm_struct *mm; pgd_t *pgdp; pgd_t pgd; if (is_ttbr0_addr(addr)) { /* TTBR0 */ mm = current->active_mm; if (mm == &init_mm) { pr_alert("[%016lx] user address but active_mm is swapper\n", addr); return; } } else if (is_ttbr1_addr(addr)) { /* TTBR1 */ mm = &init_mm; } else { pr_alert("[%016lx] address between user and kernel address ranges\n", addr); return; } pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, vabits_actual, mm_to_pgd_phys(mm)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; if (pgd_none(pgd) || pgd_bad(pgd)) break; p4dp = p4d_offset(pgdp, addr); p4d = READ_ONCE(*p4dp); pr_cont(", p4d=%016llx", p4d_val(p4d)); if (p4d_none(p4d) || p4d_bad(p4d)) break; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); pr_cont(", pud=%016llx", pud_val(pud)); if (pud_none(pud) || pud_bad(pud)) break; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); pr_cont(", pmd=%016llx", pmd_val(pmd)); if (pmd_none(pmd) || pmd_bad(pmd)) break; ptep = pte_offset_map(pmdp, addr); if (!ptep) break; pte = __ptep_get(ptep); pr_cont(", pte=%016llx", pte_val(pte)); pte_unmap(ptep); } while(0); pr_cont("\n"); } /* * This function sets the access flags (dirty, accessed), as well as write * permission, and only to a more permissive setting. * * It needs to cope with hardware update of the accessed/dirty state by other * agents in the system and can safely skip the __sync_icache_dcache() call as, * like __set_ptes(), the PTE is never changed from no-exec to exec here. * * Returns whether or not the PTE actually changed. */ int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { pteval_t old_pteval, pteval; pte_t pte = __ptep_get(ptep); if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY; /* * Setting the flags must be done atomically to avoid racing with the * hardware update of the access/dirty state. The PTE_RDONLY bit must * be set to the most permissive (lowest value) of *ptep and entry * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; pteval |= pte_val(entry); pteval ^= PTE_RDONLY; pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); /* Invalidate a stale read-only entry */ if (dirty) flush_tlb_page(vma, address); return 1; } static bool is_el1_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; } static bool is_el1_data_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_CUR; } static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; if (esr_fsc_is_permission_fault(esr)) return true; if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) return esr_fsc_is_translation_fault(esr) && (regs->pstate & PSR_PAN_BIT); return false; } static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { unsigned long flags; u64 par, dfsc; if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr)) return false; local_irq_save(flags); asm volatile("at s1e1r, %0" :: "r" (addr)); isb(); par = read_sysreg_par(); local_irq_restore(flags); /* * If we now have a valid translation, treat the translation fault as * spurious. */ if (!(par & SYS_PAR_EL1_F)) return true; /* * If we got a different type of fault from the AT instruction, * treat the translation fault as spurious. */ dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); return !esr_fsc_is_translation_fault(dfsc); } static void die_kernel_fault(const char *msg, unsigned long addr, unsigned long esr, struct pt_regs *regs) { bust_spinlocks(1); pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg, addr); kasan_non_canonical_hook(addr); mem_abort_decode(esr); show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); make_task_dead(SIGKILL); } #ifdef CONFIG_KASAN_HW_TAGS static void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { /* * SAS bits aren't set for all faults reported in EL1, so we can't * find out access size. */ bool is_write = !!(esr & ESR_ELx_WNR); kasan_report((void *)addr, 0, is_write, regs->pc); } #else /* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */ static inline void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { } #endif static void do_tag_recovery(unsigned long addr, unsigned long esr, struct pt_regs *regs) { report_tag_fault(addr, esr, regs); /* * Disable MTE Tag Checking on the local CPU for the current EL. * It will be done lazily on the other CPUs when they will hit a * tag fault. */ sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK, SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF, NONE)); isb(); } static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) { unsigned long fsc = esr & ESR_ELx_FSC; if (!is_el1_data_abort(esr)) return false; if (fsc == ESR_ELx_FSC_MTE) return true; return false; } static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { const char *msg; /* * Are we prepared to handle this kernel fault? * We are almost certainly not prepared to handle instruction faults. */ if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs), "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr)) return; if (is_el1_mte_sync_tag_check_fault(esr)) { do_tag_recovery(addr, esr, regs); return; } if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; else if (is_el1_instruction_abort(esr)) msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { if (esr_fsc_is_translation_fault(esr) && kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; } if (efi_runtime_fixup_exception(regs, msg)) return; die_kernel_fault(msg, addr, esr, regs); } static void set_thread_esr(unsigned long address, unsigned long esr) { current->thread.fault_address = address; /* * If the faulting address is in the kernel, we must sanitize the ESR. * From userspace's point of view, kernel-only mappings don't exist * at all, so we report them as level 0 translation faults. * (This is not quite the way that "no mapping there at all" behaves: * an alignment fault not caused by the memory type would take * precedence over translation fault for a real access to empty * space. Unfortunately we can't easily distinguish "alignment fault * not caused by memory type" from "alignment fault caused by memory * type", so we ignore this wrinkle and just return the translation * fault.) */ if (!is_ttbr0_addr(current->thread.fault_address)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* * These bits provide only information about the * faulting instruction, which userspace knows already. * We explicitly clear bits which are architecturally * RES0 in case they are given meanings in future. * We always report the ESR as if the fault was taken * to EL1 and so ISV and the bits in ISS[23:14] are * clear. (In fact it always will be a fault to EL1.) */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL | ESR_ELx_CM | ESR_ELx_WNR; esr |= ESR_ELx_FSC_FAULT; break; case ESR_ELx_EC_IABT_LOW: /* * Claim a level 0 translation fault. * All other bits are architecturally RES0 for faults * reported with that DFSC value, so we clear them. */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL; esr |= ESR_ELx_FSC_FAULT; break; default: /* * This should never happen (entry.S only brings us * into this code for insn and data aborts from a lower * exception level). Fail safe by not providing an ESR * context record at all. */ WARN(1, "ESR 0x%lx is not DABT or IABT from EL0\n", esr); esr = 0; break; } } current->thread.fault_code = esr; } static void do_bad_area(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (user_mode(regs)) { const struct fault_info *inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); arm64_force_sig_fault(inf->sig, inf->code, far, inf->name); } else { __do_kernel_fault(addr, esr, regs); } } static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma, unsigned int mm_flags) { unsigned long iss2 = ESR_ELx_ISS2(esr); if (!system_supports_poe()) return false; if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay)) return true; return !arch_vma_access_permitted(vma, mm_flags & FAULT_FLAG_WRITE, mm_flags & FAULT_FLAG_INSTRUCTION, false); } static bool is_gcs_fault(unsigned long esr) { if (!esr_is_data_abort(esr)) return false; return ESR_ELx_ISS2(esr) & ESR_ELx_GCS; } static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; } /* * Note: not valid for EL1 DC IVAC, but we never use that such that it * should fault. EL0 cannot issue DC IVAC (undef). */ static bool is_write_abort(unsigned long esr) { return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } static bool is_invalid_gcs_access(struct vm_area_struct *vma, u64 esr) { if (!system_supports_gcs()) return false; if (unlikely(is_gcs_fault(esr))) { /* GCS accesses must be performed on a GCS page */ if (!(vma->vm_flags & VM_SHADOW_STACK)) return true; } else if (unlikely(vma->vm_flags & VM_SHADOW_STACK)) { /* Only GCS operations can write to a GCS page */ return esr_is_data_abort(esr) && is_write_abort(esr); } return false; } static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; struct mm_struct *mm = current->mm; vm_fault_t fault; unsigned long vm_flags; unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; int si_code; int pkey = -1; if (kprobe_page_fault(regs, esr)) return 0; /* * If we're in an interrupt or have no user context, we must not take * the fault. */ if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) mm_flags |= FAULT_FLAG_USER; /* * vm_flags tells us what bits we must have in vma->vm_flags * for the fault to be benign, __do_page_fault() would check * vma->vm_flags & vm_flags and returns an error if the * intersection is empty */ if (is_el0_instruction_abort(esr)) { /* It was exec fault */ vm_flags = VM_EXEC; mm_flags |= FAULT_FLAG_INSTRUCTION; } else if (is_gcs_fault(esr)) { /* * The GCS permission on a page implies both read and * write so always handle any GCS fault as a write fault, * we need to trigger CoW even for GCS reads. */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else if (is_write_abort(esr)) { /* It was write fault */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else { /* It was read fault */ vm_flags = VM_READ; /* Write implies read */ vm_flags |= VM_WRITE; /* If EPAN is absent then exec implies read */ if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; } if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { if (is_el1_instruction_abort(esr)) die_kernel_fault("execution of user memory", addr, esr, regs); if (!search_exception_tables(regs->pc)) die_kernel_fault("access to user memory outside uaccess routines", addr, esr, regs); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (!(mm_flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, addr); if (!vma) goto lock_mmap; if (is_invalid_gcs_access(vma, esr)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } if (fault_from_pkey(esr, vma, mm_flags)) { pkey = vma_pkey(vma); vma_end_read(vma); fault = 0; si_code = SEGV_PKUERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); if (fault & VM_FAULT_MAJOR) mm_flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { fault = 0; si_code = SEGV_MAPERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { mmap_read_unlock(mm); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (fault_from_pkey(esr, vma, mm_flags)) { pkey = vma_pkey(vma); mmap_read_unlock(mm); fault = 0; si_code = SEGV_PKUERR; goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return 0; if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); done: /* Handle the "normal" (no error) case first. */ if (likely(!(fault & VM_FAULT_ERROR))) return 0; si_code = SEGV_MAPERR; bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (!user_mode(regs)) goto no_context; if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to * userspace (which will retry the fault, or kill us if we got * oom-killed). */ pagefault_out_of_memory(); return 0; } inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to successfully fix up * this page fault. */ arm64_force_sig_fault(SIGBUS, BUS_ADRERR, far, inf->name); } else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) { unsigned int lsb; lsb = PAGE_SHIFT; if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { /* * The pkey value that we return to userspace can be different * from the pkey that caused the fault. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set POR_EL0 to deny access to pkey=4, touches, page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ /* Something tried to access memory that out of memory map */ if (si_code == SEGV_PKUERR) arm64_force_sig_fault_pkey(far, inf->name, pkey); else arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; no_context: __do_kernel_fault(addr, esr, regs); return 0; } static int __kprobes do_translation_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); if (is_ttbr0_addr(addr)) return do_page_fault(far, esr, regs); do_bad_area(far, esr, regs); return 0; } static int do_alignment_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_COMPAT_ALIGNMENT_FIXUPS) && compat_user_mode(regs)) return do_compat_alignment_fixup(far, regs); do_bad_area(far, esr, regs); return 0; } static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs) { return 1; /* "fault" */ } static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; unsigned long siaddr; inf = esr_to_fault_info(esr); if (user_mode(regs) && apei_claim_sea(regs) == 0) { /* * APEI claimed this as a firmware-first notification. * Some processing deferred to task_work before ret_to_user(). */ return 0; } if (esr & ESR_ELx_FnV) { siaddr = 0; } else { /* * The architecture specifies that the tag bits of FAR_EL1 are * UNKNOWN for synchronous external aborts. Mask them out now * so that userspace doesn't see them. */ siaddr = untagged_addr(far); } arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; } static int do_tag_check_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { /* * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN * for tag check faults. Set them to corresponding bits in the untagged * address. */ far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "ttbr address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 2 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 3 address size fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" }, { do_tag_check_fault, SIGSEGV, SEGV_MTESERR, "synchronous tag check fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 18" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 3 (translation table walk)" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 25" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 26" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 32" }, { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 34" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 35" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 36" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 37" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 38" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 39" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 40" }, { do_bad, SIGKILL, SI_KERNEL, "level -1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 42" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level -1 translation fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 44" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 45" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 46" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 47" }, { do_bad, SIGKILL, SI_KERNEL, "TLB conflict abort" }, { do_bad, SIGKILL, SI_KERNEL, "Unsupported atomic hardware update fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 50" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 51" }, { do_bad, SIGKILL, SI_KERNEL, "implementation fault (lockdown abort)" }, { do_bad, SIGBUS, BUS_OBJERR, "implementation fault (unsupported exclusive)" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 54" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 55" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 56" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 57" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 58" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 59" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 60" }, { do_bad, SIGKILL, SI_KERNEL, "section domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "page domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); unsigned long addr = untagged_addr(far); if (!inf->fn(far, esr, regs)) return; if (!user_mode(regs)) die_kernel_fault(inf->name, addr, esr, regs); /* * At this point we have an unrecognized fault type whose tag bits may * have been defined as UNKNOWN. Therefore we only expose the untagged * address to the signal handler. */ arm64_notify_die(inf->name, regs, inf->sig, inf->code, addr, esr); } NOKPROBE_SYMBOL(do_mem_abort); void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs) { arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, addr, esr); } NOKPROBE_SYMBOL(do_sp_pc_abort); /* * __refdata because early_brk64 is __init, but the reference to it is * clobbered at arch_initcall time. * See traps.c and debug-monitors.c:debug_traps_init(). */ static struct fault_info __refdata debug_fault_info[] = { { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 3" }, { do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" }, { do_bad, SIGKILL, SI_KERNEL, "aarch32 vector catch" }, { early_brk64, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 7" }, }; void __init hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned long, struct pt_regs *), int sig, int code, const char *name) { BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info)); debug_fault_info[nr].fn = fn; debug_fault_info[nr].sig = sig; debug_fault_info[nr].code = code; debug_fault_info[nr].name = name; } /* * In debug exception context, we explicitly disable preemption despite * having interrupts disabled. * This serves two purposes: it makes it much less likely that we would * accidentally schedule in exception context and it will force a warning * if we somehow manage to schedule by accident. */ static void debug_exception_enter(struct pt_regs *regs) { preempt_disable(); /* This code is a bit fragile. Test it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work"); } NOKPROBE_SYMBOL(debug_exception_enter); static void debug_exception_exit(struct pt_regs *regs) { preempt_enable_no_resched(); } NOKPROBE_SYMBOL(debug_exception_exit); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); debug_exception_enter(regs); if (user_mode(regs) && !is_ttbr0_addr(pc)) arm64_apply_bp_hardening(); if (inf->fn(addr_if_watchpoint, esr, regs)) { arm64_notify_die(inf->name, regs, inf->sig, inf->code, pc, esr); } debug_exception_exit(regs); } NOKPROBE_SYMBOL(do_debug_exception); /* * Used during anonymous page fault handling. */ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO; /* * If the page is mapped with PROT_MTE, initialise the tags at the * point of allocation and page zeroing as this is usually faster than * separate DC ZVA and STGM. */ if (vma->vm_flags & VM_MTE) flags |= __GFP_ZEROTAGS; return vma_alloc_folio(flags, 0, vma, vaddr); } void tag_clear_highpage(struct page *page) { /* Newly allocated page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } |
| 287 279 17 213 242 279 2 263 3 7 7 7 7 301 7 13 13 8 8 2 13 13 13 13 13 13 2 2 1 2 14 263 9 1 8 8 8 279 263 263 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <net/flow_dissector.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> #include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/netmem.h> /** * DOC: skb checksums * * The interface for checksum offload between the stack and networking drivers * is as follows... * * IP checksum related features * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * .. flat-table:: Checksum related device features * :widths: 1 10 * * * - %NETIF_F_HW_CSUM * - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * * - %NETIF_F_IP_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_RXCSUM * - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * Checksumming of received packets by device * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Indication of checksum verification is set in &sk_buff.ip_summed. * Possible values are: * * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * %CHECKSUM_UNNECESSARY is applicable to following protocols: * * - TCP: IPv6 and IPv4. * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * - GRE: only if the checksum is present in the header. * - SCTP: indicates the CRC in SCTP header has been validated. * - FCOE: indicates the CRC in FC frame has been validated. * * &sk_buff.csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * Checksumming on transmit for non-GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. * Values are: * * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() * from &sk_buff.csum_start up to the end, and to record/write the checksum at * offset &sk_buff.csum_start + &sk_buff.csum_offset. * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of * &sk_buff.csum_not_inet, see :ref:`crc`) * is called to resolve the checksum. * * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * - %CHECKSUM_COMPLETE * * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. * * .. _crc: * * Non-IP checksum (CRC) offloads * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * .. flat-table:: * :widths: 1 10 * * * - %NETIF_F_SCTP_CRC * - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * * - %NETIF_F_FCOE_CRC * - This feature indicates that a device is capable of offloading the FCOE * CRC in a packet. To perform this offload the stack will set ip_summed * to %CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * Checksumming on output with GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) /* For X bytes available in skb->head, what is the minimal * allocation needed, knowing struct skb_shared_info needs * to be aligned. */ #define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct ahash_request; struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; struct ts_config; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { union { u64 act_miss_cookie; __u32 chain; }; __u16 mru; __u16 zone; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif struct sk_buff_head { /* These two members must be first to match sk_buff. */ struct_group_tagged(sk_buff_list, list, struct sk_buff *next; struct sk_buff *prev; ); __u32 qlen; spinlock_t lock; }; struct sk_buff; #ifndef CONFIG_MAX_SKB_FRAGS # define CONFIG_MAX_SKB_FRAGS 17 #endif #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct skb_frag { netmem_ref netmem; unsigned int len; unsigned int offset; } skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @netdev_data: address/cookie of network device driver used as * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { union { ktime_t hwtstamp; void *netdev_data; }; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* generate hardware time stamp based on cycles if supported */ SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { /* use zcopy routines */ SKBFL_ZEROCOPY_ENABLE = BIT(0), /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), /* segment contains only zerocopy data and should not be * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), /* page references are managed by the ubuf_info, so it's safe to * use frags only up until ubuf_info is released */ SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); /* has to be compatible with skb_zcopy_set() */ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; struct ubuf_info_msgzc { struct ubuf_info ubuf; union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) #define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); /* Preserve some data across TX submission and completion. * * Note, this state is stored in the driver. Extending the layout * might need some special care. */ struct xsk_tx_metadata_compl { __u64 *tx_timestamp; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; union { struct skb_shared_hwtstamps hwtstamps; struct xsk_tx_metadata_compl xsk_meta; }; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ void * destructor_arg; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /** * DOC: dataref and headerless skbs * * Transport layers send out clones of payload skbs they hold for * retransmissions. To allow lower layers of the stack to prepend their headers * we split &skb_shared_info.dataref into two halves. * The lower 16 bits count the overall number of references. * The higher 16 bits indicate how many of the references are payload-only. * skb_header_cloned() checks if skb is allowed to add / write the headers. * * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr * (via __skb_header_release()). Any clone created from marked skb will get * &sk_buff.hdr_len populated with the available headroom. * If there's the only clone in existence it's able to modify the headroom * at will. The sequence of calls inside the transport layer is:: * * <alloc skb> * skb_reserve() * __skb_header_release() * skb_clone() * // send the clone down the stack * * This is not a very generic construct and it depends on the transport layers * doing the right thing. In practice there's usually only one payload-only skb. * Having multiple payload-only skbs with different lengths of hdr_len is not * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, SKB_CLOCK_TAI, __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** * DOC: Basic sk_buff geometry * * struct sk_buff itself is a metadata structure and does not hold any packet * data. All the data is held in associated buffers. * * &sk_buff.head points to the main "head" buffer. The head buffer is divided * into two parts: * * - data buffer, containing headers and sometimes payload; * this is the part of the skb operated on by the common helpers * such as skb_put() or skb_pull(); * - shared info (struct skb_shared_info) which holds an array of pointers * to read-only data in the (page, offset, length) format. * * Optionally &skb_shared_info.frag_list may point to another skb. * * Basic diagram may look like this:: * * --------------- * | sk_buff | * --------------- * ,--------------------------- + head * / ,----------------- + data * / / ,----------- + tail * | | | , + end * | | | | * v v v v * ----------------------------------------------- * | headroom | data | tailroom | skb_shared_info | * ----------------------------------------------- * + [page frag] * + [page frag] * + [page frag] * + [page frag] --------- * + frag_list --> | sk_buff | * --------- * */ /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @pp_recycle: mark the packet for recycling instead of freeing (implies * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @unreadable: indicates that at least 1 of the fragments in this skb is * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @tstamp_type: When set, skb->tstamp has the * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; struct llist_node ll_node; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; #ifdef CONFIG_NET_SOCK_MSG unsigned long _sk_redir; #endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1, pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; /* private: */ __u8 __mono_tc_offset[0]; /* public: */ __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; #ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; #endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif #if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; #endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif #ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif u16 alloc_cpu; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) /* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD #define SKB_TSTAMP_TYPE_MASK (3 << 6) #define SKB_TSTAMP_TYPE_RSHIFT (6) #define TC_AT_INGRESS_MASK (1 << 5) #else #define SKB_TSTAMP_TYPE_MASK (3) #define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) { #ifdef CONFIG_WIRELESS return skb->wifi_acked_valid; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } static inline bool skb_data_unref(const struct sk_buff *skb, struct skb_shared_info *shinfo) { int bias; if (!skb->cloned) return true; bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; if (atomic_read(&shinfo->dataref) == bias) smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref)) return false; return true; } void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason); static inline void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { sk_skb_reason_drop(NULL, skb, reason); } /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason * @skb: buffer to free */ static inline void kfree_skb(struct sk_buff *skb) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } void skb_release_head_state(struct sk_buff *skb); void kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); static inline void kfree_skb_list(struct sk_buff *segs) { kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); } #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && READ_ONCE(fclones->skb2.sk) == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; __u32 frag_off; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { return __skb_get_hash_symmetric_net(NULL, skb); } void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen_proto); static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) { return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(net, skb); return skb->hash; } static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(NULL, skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { #ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } static inline bool skb_is_decrypted(const struct sk_buff *skb) { #ifdef CONFIG_SKB_DECRYPTED return skb->decrypted; #else return false; #endif } static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = offset; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = skb->head + offset; } #endif extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } static inline bool skb_zcopy_pure(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } static inline bool skb_zcopy_managed(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; } static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); } static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) { skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->flags |= uarg->flags; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); } } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } void __skb_zcopy_downgrade_managed(struct sk_buff *skb); static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) { if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb); } /* Return true if frags in this skb are readable by the host. */ static inline bool skb_frags_readable(const struct sk_buff *skb) { return !skb->unreadable; } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } static inline void skb_poison_list(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET skb->next = SKB_LIST_POISON_NEXT; #endif } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /* This variant of skb_unclone() makes sure skb->truesize * and skb_end_offset() are not changed, whenever a new skb->head is needed. * * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) * when various debugging features are in place. */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return __skb_unclone_keeptruesize(skb, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release() - allow clones to use the headroom * @skb: buffer to operate on * * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet that's being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, netmem_ref netmem, int off, int size) { frag->netmem = netmem; frag->offset = off; skb_frag_size_set(frag, size); } static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); } static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, int i, netmem_ref netmem, int off, int size) { skb_frag_t *frag = &shinfo->frags[i]; skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, size); } /** * skb_len_add - adds a number to len fields of skb * @skb: buffer to add len to * @delta: number of bytes to add */ static inline void skb_len_add(struct sk_buff *skb, int delta) { skb->len += delta; skb->data_len += delta; skb->truesize += delta; } /** * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised * @i: fragment index to initialise * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); if (netmem_is_net_iov(netmem)) { skb->unreadable = true; return; } page = netmem_to_page(netmem); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** * skb_fill_page_desc_noacc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Variant of skb_fill_page_desc() which does not deal with * pfmemalloc, if page is not owned by us. */ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, struct page *page, int off, int size) { struct skb_shared_info *shinfo = skb_shinfo(skb); __skb_fill_page_desc_noacc(shinfo, i, page, off, size); shinfo->nr_frags = i + 1; } void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize); static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, truesize); } void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } #if defined(CONFIG_FAIL_SKB_REALLOC) void skb_might_realloc(struct sk_buff *skb); #else static inline void skb_might_realloc(struct sk_buff *skb) {} #endif /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) skb->len += len; pr_err("__skb_pull(len=%u)\n", len); skb_dump(KERN_ERR, skb, false); #endif BUG(); } return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb)))) return SKB_DROP_REASON_NOMEM; return SKB_NOT_DROPPED_YET; } static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; skb->len -= len; return skb->data += len; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_len(struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) { DEBUG_NET_WARN_ON_ONCE(1); skb->mac_len = 0; } else { skb->mac_len = skb->network_header - skb->mac_header; } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) { return skb->inner_network_header > 0; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); skb->transport_header = offset; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline enum skb_drop_reason pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, skb_network_offset(skb) + len); } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb_reason(skb, reason); } static inline void __skb_queue_purge(struct sk_buff_head *list) { __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason); static inline void skb_queue_purge(struct sk_buff_head *list) { skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } unsigned int skb_rbtree_purge(struct rb_root *root); void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ static inline void *netdev_alloc_frag(unsigned int fragsz) { return __netdev_alloc_frag_align(fragsz, ~0u); } static inline void *netdev_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __netdev_alloc_frag_align(fragsz, -align); } struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); static inline void *napi_alloc_frag(unsigned int fragsz) { return __napi_alloc_frag_align(fragsz, ~0u); } static inline void *napi_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __napi_alloc_frag_align(fragsz, -align); } struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { return __dev_alloc_pages_noprof(gfp_mask, 0); } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx * @page: the page to test * * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * * Returns false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) { return likely(page_to_nid(page) == numa_mem_id() && !page_is_pfmemalloc(page)); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(const struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->offset = fragfrom->offset; } /* Return: true if the skb_frag contains a net_iov. */ static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) { return netmem_is_net_iov(frag->netmem); } /** * skb_frag_net_iov - retrieve the net_iov referred to by fragment * @frag: the fragment * * Return: the &struct net_iov associated with @frag. Returns NULL if this * frag has no associated net_iov. */ static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) { if (!skb_frag_is_net_iov(frag)) return NULL; return netmem_to_net_iov(frag->netmem); } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Return: the &struct page associated with @frag. Returns NULL if this frag * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { if (skb_frag_is_net_iov(frag)) return NULL; return netmem_to_page(frag->netmem); } /** * skb_frag_netmem - retrieve the netmem referred to by a fragment * @frag: the fragment * * Return: the &netmem_ref associated with @frag. */ static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) { return frag->netmem; } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { if (!skb_frag_page(frag)) return NULL; return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { void *ptr = page_address(skb_frag_page(frag)); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, &csum, from)) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) return 0; __skb_trim(skb, off); return -EFAULT; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_hash_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, struct ahash_request *hash); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } struct skb_checksum_ops { __wsum (*update)(const void *mem, int len, __wsum wsum); __wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len); }; extern const struct skb_checksum_ops *crc32c_csum_stub __read_mostly; __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, const void *data, int hlen, void *buffer) { if (likely(hlen - offset >= len)) return (void *)data + offset; if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; } static inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { if (likely(skb_headlen(skb) - offset >= len)) return skb->data + offset; return NULL; } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, u8 tstamp_type) { skb->tstamp = kt; if (kt) skb->tstamp_type = tstamp_type; else skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, ktime_t kt, clockid_t clockid) { u8 tstamp_type = SKB_CLOCK_REALTIME; switch (clockid) { case CLOCK_REALTIME: break; case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; case CLOCK_TAI: tstamp_type = SKB_CLOCK_TAI; break; default: WARN_ON_ONCE(1); kt = 0; } skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else skb->tstamp = 0; } } static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->tstamp_type) return; skb->tstamp = 0; } static inline ktime_t skb_tstamp(const struct sk_buff *skb) { if (skb->tstamp_type) return 0; return skb->tstamp; } static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) return ktime_get_real(); return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); u64 diffs = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || BITS_PER_LONG != 64) goto slow; /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; default: slow: return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) skb_tstamp_tx(skb, NULL); } /** * skb_complete_wifi_ack - deliver skb with wifi status * * @skb: the original outgoing packet * @acked: ack status * */ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || skb->csum_valid || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) >= 0)); } /** * skb_checksum_complete - Calculate checksum of an entire packet * @skb: packet to process * * This function calculates the checksum over the entire packet plus * the value of skb->csum. The latter can be used to supply the * checksum of a pseudo header as used by TCP/UDP. It returns the * checksum. * * For protocols that contain complete checksums such as ICMP/TCP/UDP, * this function can be used to verify that checksum on received * packets. In that case the function should return zero if the * checksum is correct. In particular, this function will return zero * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the * hardware has already verified the correctness of the checksum. */ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level == 0) skb->ip_summed = CHECKSUM_NONE; else skb->csum_level--; } } static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) skb->csum_level++; } else if (skb->ip_summed == CHECKSUM_NONE) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = 0; } } static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { skb->ip_summed = CHECKSUM_NONE; skb->csum_level = 0; } } /* Check if we need to perform checksum complete validation. * * Returns true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { skb->csum_valid = 1; __skb_decr_checksum_unnecessary(skb); return false; } return true; } /* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 /* Unset checksum-complete * * Unset checksum complete can be done when packet is being modified * (uncompressed for instance) and checksum-complete value is * invalidated. */ static inline void skb_checksum_complete_unset(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /* Validate (init) checksum based on checksum complete. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete. In the latter * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo * checksum is stored in skb->csum for use in __skb_checksum_complete * non-zero: value of invalid checksum * */ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, bool complete, __wsum psum) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { skb->csum_valid = 1; return 0; } } skb->csum = psum; if (complete || skb->len <= CHECKSUM_BREAK) { __sum16 csum; csum = __skb_checksum_complete(skb); skb->csum_valid = !csum; return csum; } return 0; } static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) { return 0; } /* Perform checksum validate (init). Note that this is a macro since we only * want to calculate the pseudo header which is an input function if necessary. * First we try to validate without any computation (checksum unnecessary) and * then calculate based on checksum complete calling the function to compute * pseudo header. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete * non-zero: value of invalid checksum */ #define __skb_checksum_validate(skb, proto, complete, \ zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ __ret; \ }) #define skb_checksum_init(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) #define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) #define skb_checksum_validate(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } #define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, u16 start, u16 offset) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = ((unsigned char *)ptr + start) - skb->head; skb->csum_offset = offset - start; } /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, bool nopartial) { __wsum delta; if (!nopartial) { skb_remcsum_adjust_partial(skb, ptr, start, offset); return; } if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } delta = remcsum_adjust(ptr, skb->csum, start, offset); /* Adjust skb->csum since we changed the packet */ skb->csum = csum_add(skb->csum, delta); } static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return skb->_nfct; #else return 0UL; #endif } static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) SKB_EXT_BRIDGE_NF, #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif SKB_EXT_NUM, /* must be last */ }; /** * struct skb_ext - sk_buff extensions * @refcnt: 1 on allocation, deallocated on 0 * @offset: offset to add to @data to obtain extension address * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units * @data: start of extension data, variable sized * * Note: offsets/lengths are stored in chunks of 8 bytes, this allows * to use 'u8' types while allowing up to 2kb worth of extension data. */ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); static inline void skb_ext_put(struct sk_buff *skb) { if (skb->active_extensions) __skb_ext_put(skb->extensions); } static inline void __skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { dst->active_extensions = src->active_extensions; if (src->active_extensions) { struct skb_ext *ext = src->extensions; refcount_inc(&ext->refcnt); dst->extensions = ext; } } static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { skb_ext_put(dst); __skb_ext_copy(dst, src); } static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) { return !!ext->offset[i]; } static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) { return skb->active_extensions & (1 << id); } static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) __skb_ext_del(skb, id); } static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) { struct skb_ext *ext = skb->extensions; return (void *)ext + (ext->offset[id] << 3); } return NULL; } static inline void skb_ext_reset(struct sk_buff *skb) { if (unlikely(skb->active_extensions)) { __skb_ext_put(skb->extensions); skb->active_extensions = 0; } } static inline bool skb_has_extensions(struct sk_buff *skb) { return unlikely(skb->active_extensions); } #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif } static inline void nf_reset_trace(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } static inline void ipvs_reset(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_VS) skb->ipvs_property = 0; #endif } /* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline int secpath_exists(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_exist(skb, SKB_EXT_SEC_PATH); #else return 0; #endif } static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; } static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { to->queue_mapping = from->queue_mapping; } static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) { skb->queue_mapping = rx_queue + 1; } static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return skb->queue_mapping != 0; } static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) { skb->dst_pending_confirm = val; } static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) { return skb->dst_pending_confirm != 0; } static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif } static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_v6(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; skb_shinfo(skb)->gso_segs = 0; skb_shinfo(skb)->gso_type = 0; } static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, u16 increment) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size += increment; } static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, u16 decrement) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size -= decrement; } void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ const struct skb_shared_info *shinfo = skb_shinfo(skb); if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } return false; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /** * skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE * @skb: skb to check * * fresh skbs have their ip_summed set to CHECKSUM_NONE. * Instead of forcing ip_summed to CHECKSUM_NONE, we can * use this helper, to document places where we make this assertion. */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check * * The head on skbs build around a head frag can be removed if they are * not cloned. This function returns true if the skb head is locked down * due to either being allocated via kmalloc, or by being a clone with * multiple references to the head. */ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. */ static inline __wsum lco_csum(struct sk_buff *skb) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *l4_hdr = skb_transport_header(skb); __wsum partial; /* Start with complement of inner checksum adjustment */ partial = ~csum_unfold(*(__force __sum16 *)(csum_start + skb->csum_offset)); /* Add in checksum of our headers (incl. outer checksum * adjustment filled in by caller) and return result. */ return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } static inline bool skb_is_redirected(const struct sk_buff *skb) { return skb->redirected; } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb_clear_tstamp(skb); #endif } static inline void skb_reset_redirect(struct sk_buff *skb) { skb->redirected = 0; } static inline void skb_set_redirected_noclear(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; #endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; #else return 0; #endif } static inline void skb_reset_csum_not_inet(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; #if IS_ENABLED(CONFIG_IP_SCTP) skb->csum_not_inet = 0; #endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { #ifdef CONFIG_KCOV skb->kcov_handle = kcov_handle; #endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { #ifdef CONFIG_KCOV return skb->kcov_handle; #else return 0; #endif } static inline void skb_mark_for_recycle(struct sk_buff *skb) { #ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; #endif } ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize, gfp_t gfp); #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |
| 230 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ /* * PTE markers are used to persist information onto PTEs that otherwise * should be a none pte. As its name "PTE" hints, it should only be * applied to the leaves of pgtables. */ #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif /* * Page migration support. * * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and * indicates that the referenced (part of) an anonymous page is exclusive to * a single process. For SWP_MIGRATION_WRITE, that information is implicit: * (part of) an anonymous page that are mapped writable are exclusive to a * single process. */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 3 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { /* pages reclaimed outside of LRU-based reclaim */ unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; /* * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based * reclaim * @pages: number of pages reclaimed * * If the current process is undergoing a reclaim operation, increment the * number of reclaimed pages by @pages. */ static inline void mm_account_reclaimed_pages(unsigned long pages) { if (current->reclaim_state) current->reclaim_state->reclaimed += pages; } #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ #define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The flags field determines if a cluster is free. This is * protected by cluster lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * other than list, and swap_info_struct->swap_map * elements corresponding to the swap cluster. */ u16 count; u8 flags; u8 order; struct list_head list; }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */ #define CLUSTER_FLAG_FRAG 4 /* This cluster is on nonfull list */ #define CLUSTER_FLAG_FULL 8 /* This cluster is on full list */ /* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as * a sentinel to indicate next is not valid in percpu_cluster. */ #define SWAP_NEXT_INVALID 0 #ifdef CONFIG_THP_SWAP #define SWAP_NR_ORDERS (PMD_ORDER + 1) #else #define SWAP_NR_ORDERS 1 #endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct list_head free_clusters; /* free clusters list */ struct list_head full_clusters; /* full clusters list */ struct list_head nonfull_clusters[SWAP_NR_ORDERS]; /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; /* list of cluster that are fragmented or contented */ unsigned int frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, * cluster_nr, lowest_alloc, * highest_alloc, free/discard cluster * list. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ spinlock_t cont_lock; /* * protect swap count continuation page * list. */ struct work_struct discard_work; /* discard worker */ struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the * array is nr_node_ids, which is not * a fixed value so have to allocate * dynamically. * And it has to be an array so that * plist_for_each_* can work. */ }; static inline swp_entry_t page_swap_entry(struct page *page) { struct folio *folio = page_folio(page); swp_entry_t entry = folio->swap; entry.val += folio_page_idx(folio, page); return entry; } /* linux/mm/workingset.c */ bool workingset_test_recent(void *shadow, bool file, bool *workingset, bool flush); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated); void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) { return atomic_read(&lru_disable_count); } static inline void lru_cache_enable(void) { atomic_dec(&lru_disable_count); } extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); void folio_deactivate(struct folio *folio); void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) #define MIN_SWAPPINESS 0 #define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #else #define node_reclaim_mode 0 #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } void check_move_unevictable_folios(struct folio_batch *fbatch); extern void __meminit kswapd_run(int nid); extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } void free_swap_cache(struct folio *folio); void free_page_and_swap_cache(struct page *); void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t entry, int nr); extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_folio_sector(struct folio *folio); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; } static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; } static inline void put_swap_device(struct swap_info_struct *si) { } #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) { } static inline void free_swap_cache(struct folio *folio) { } static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } static inline void swap_shmem_alloc(swp_entry_t swp, int nr) { } static inline int swap_duplicate(swp_entry_t swp) { return 0; } static inline int swapcache_prepare(swp_entry_t swp, int nr) { return 0; } static inline void swap_free_nr(swp_entry_t entry, int nr_pages) { } static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { return 0; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } static inline bool folio_free_swap(struct folio *folio) { return false; } static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { return -EINVAL; } #endif /* CONFIG_SWAP */ static inline void free_swap_and_cache(swp_entry_t entry) { free_swap_and_cache_nr(entry, 1); } static inline void swap_free(swp_entry_t entry) { swap_free_nr(entry, 1); } #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return READ_ONCE(vm_swappiness); return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return READ_ONCE(vm_swappiness); } #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; __folio_throttle_swaprate(folio, gfp); } #else static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { } #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_swap(entry, nr_pages); } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ |
| 84 84 84 84 83 83 84 83 84 84 86 88 87 88 88 88 87 87 88 86 78 78 78 78 76 78 78 78 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/sysreg-sr.h> #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_nested.h> static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu) { /* These registers are common with EL1 */ __vcpu_sys_reg(vcpu, PAR_EL1) = read_sysreg(par_el1); __vcpu_sys_reg(vcpu, TPIDR_EL1) = read_sysreg(tpidr_el1); __vcpu_sys_reg(vcpu, ESR_EL2) = read_sysreg_el1(SYS_ESR); __vcpu_sys_reg(vcpu, AFSR0_EL2) = read_sysreg_el1(SYS_AFSR0); __vcpu_sys_reg(vcpu, AFSR1_EL2) = read_sysreg_el1(SYS_AFSR1); __vcpu_sys_reg(vcpu, FAR_EL2) = read_sysreg_el1(SYS_FAR); __vcpu_sys_reg(vcpu, MAIR_EL2) = read_sysreg_el1(SYS_MAIR); __vcpu_sys_reg(vcpu, VBAR_EL2) = read_sysreg_el1(SYS_VBAR); __vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR); __vcpu_sys_reg(vcpu, AMAIR_EL2) = read_sysreg_el1(SYS_AMAIR); /* * In VHE mode those registers are compatible between EL1 and EL2, * and the guest uses the _EL1 versions on the CPU naturally. * So we save them into their _EL2 versions here. * For nVHE mode we trap accesses to those registers, so our * _EL2 copy in sys_regs[] is always up-to-date and we don't need * to save anything here. */ if (vcpu_el2_e2h_is_set(vcpu)) { u64 val; /* * We don't save CPTR_EL2, as accesses to CPACR_EL1 * are always trapped, ensuring that the in-memory * copy is always up-to-date. A small blessing... */ __vcpu_sys_reg(vcpu, SCTLR_EL2) = read_sysreg_el1(SYS_SCTLR); __vcpu_sys_reg(vcpu, TTBR0_EL2) = read_sysreg_el1(SYS_TTBR0); __vcpu_sys_reg(vcpu, TTBR1_EL2) = read_sysreg_el1(SYS_TTBR1); __vcpu_sys_reg(vcpu, TCR_EL2) = read_sysreg_el1(SYS_TCR); if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { __vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2); if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { __vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0); __vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR); } if (ctxt_has_s1poe(&vcpu->arch.ctxt)) __vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR); } /* * The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where * the interesting CNTHCTL_EL2 bits live. So preserve these * bits when reading back the guest-visible value. */ val = read_sysreg_el1(SYS_CNTKCTL); val &= CNTKCTL_VALID_BITS; __vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS; __vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val; } __vcpu_sys_reg(vcpu, SP_EL2) = read_sysreg(sp_el1); __vcpu_sys_reg(vcpu, ELR_EL2) = read_sysreg_el1(SYS_ELR); __vcpu_sys_reg(vcpu, SPSR_EL2) = read_sysreg_el1(SYS_SPSR); } static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu) { u64 val; /* These registers are common with EL1 */ write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1), par_el1); write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1), tpidr_el1); write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2); write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR); write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR); write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR); if (vcpu_el2_e2h_is_set(vcpu)) { /* * In VHE mode those registers are compatible between * EL1 and EL2. */ write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2), SYS_SCTLR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2), SYS_CPACR); write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2), SYS_TTBR0); write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2), SYS_TTBR1); write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2), SYS_TCR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CNTHCTL_EL2), SYS_CNTKCTL); } else { /* * CNTHCTL_EL2 only affects EL1 when running nVHE, so * no need to restore it. */ val = translate_sctlr_el2_to_sctlr_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2)); write_sysreg_el1(val, SYS_SCTLR); val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2)); write_sysreg_el1(val, SYS_CPACR); val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2)); write_sysreg_el1(val, SYS_TTBR0); val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2)); write_sysreg_el1(val, SYS_TCR); } if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR2_EL2), SYS_TCR2); if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { write_sysreg_el1(__vcpu_sys_reg(vcpu, PIR_EL2), SYS_PIR); write_sysreg_el1(__vcpu_sys_reg(vcpu, PIRE0_EL2), SYS_PIRE0); } if (ctxt_has_s1poe(&vcpu->arch.ctxt)) write_sysreg_el1(__vcpu_sys_reg(vcpu, POR_EL2), SYS_POR); } write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2), SYS_ESR); write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2), SYS_AFSR0); write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2), SYS_AFSR1); write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2), SYS_FAR); write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2), sp_el1); write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2), SYS_ELR); write_sysreg_el1(__vcpu_sys_reg(vcpu, SPSR_EL2), SYS_SPSR); } /* * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and * pstate, which are handled as part of the el2 return state) on every * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. */ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); /** * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU * * @vcpu: The VCPU pointer * * Load system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_load() function * and loading system register state early avoids having to load them on * every entry to the VM. */ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; u64 mpidr; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_user_state(host_ctxt); /* * When running a normal EL1 guest, we only load a new vcpu * after a context switch, which imvolves a DSB, so all * speculative EL1&0 walks will have already completed. * If running NV, the vcpu may transition between vEL1 and * vEL2 without a context switch, so make sure we complete * those walks before loading a new context. */ if (vcpu_has_nv(vcpu)) dsb(nsh); /* * Load guest EL1 and user state * * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_user_state(guest_ctxt); if (unlikely(__is_hyp_ctxt(guest_ctxt))) { __sysreg_restore_vel2_state(vcpu); } else { if (vcpu_has_nv(vcpu)) { /* * Use the guest hypervisor's VPIDR_EL2 when in a * nested state. The hardware value of MIDR_EL1 gets * restored on put. */ write_sysreg(ctxt_sys_reg(guest_ctxt, VPIDR_EL2), vpidr_el2); /* * As we're restoring a nested guest, set the value * provided by the guest hypervisor. */ mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2); } else { mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1); } __sysreg_restore_el1_state(guest_ctxt, mpidr); } vcpu_set_flag(vcpu, SYSREGS_ON_CPU); } /** * __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU * * @vcpu: The VCPU pointer * * Save guest system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_put() function * and deferring saving system register state until we're no longer running the * VCPU avoids having to save them on every exit from the VM. */ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = host_data_ptr(host_ctxt); if (unlikely(__is_hyp_ctxt(guest_ctxt))) __sysreg_save_vel2_state(vcpu); else __sysreg_save_el1_state(guest_ctxt); __sysreg_save_user_state(guest_ctxt); __sysreg32_save_state(vcpu); /* Restore host user state */ __sysreg_restore_user_state(host_ctxt); /* If leaving a nesting guest, restore MIDR_EL1 default view */ if (vcpu_has_nv(vcpu)) write_sysreg(read_cpuid_id(), vpidr_el2); vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); } |
| 372 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(folio) ( \ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); __entry->lru = folio_lru_list(folio); __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); ), TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 2 2 1 3 3 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2015, 2016 ARM Ltd. */ #ifndef __KVM_ARM_VGIC_NEW_H__ #define __KVM_ARM_VGIC_NEW_H__ #include <linux/irqchip/arm-gic-common.h> #include <asm/kvm_mmu.h> #define PRODUCT_ID_KVM 0x4b /* ASCII code K */ #define IMPLEMENTER_ARM 0x43b #define VGIC_ADDR_UNDEF (-1) #define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF) #define INTERRUPT_ID_BITS_SPIS 10 #define INTERRUPT_ID_BITS_ITS 16 #define VGIC_LPI_MAX_INTID ((1 << INTERRUPT_ID_BITS_ITS) - 1) #define VGIC_PRI_BITS 5 #define vgic_irq_is_sgi(intid) ((intid) < VGIC_NR_SGIS) #define VGIC_AFFINITY_0_SHIFT 0 #define VGIC_AFFINITY_0_MASK (0xffUL << VGIC_AFFINITY_0_SHIFT) #define VGIC_AFFINITY_1_SHIFT 8 #define VGIC_AFFINITY_1_MASK (0xffUL << VGIC_AFFINITY_1_SHIFT) #define VGIC_AFFINITY_2_SHIFT 16 #define VGIC_AFFINITY_2_MASK (0xffUL << VGIC_AFFINITY_2_SHIFT) #define VGIC_AFFINITY_3_SHIFT 24 #define VGIC_AFFINITY_3_MASK (0xffUL << VGIC_AFFINITY_3_SHIFT) #define VGIC_AFFINITY_LEVEL(reg, level) \ ((((reg) & VGIC_AFFINITY_## level ##_MASK) \ >> VGIC_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level)) /* * The Userspace encodes the affinity differently from the MPIDR, * Below macro converts vgic userspace format to MPIDR reg format. */ #define VGIC_TO_MPIDR(val) (VGIC_AFFINITY_LEVEL(val, 0) | \ VGIC_AFFINITY_LEVEL(val, 1) | \ VGIC_AFFINITY_LEVEL(val, 2) | \ VGIC_AFFINITY_LEVEL(val, 3)) /* * As per Documentation/virt/kvm/devices/arm-vgic-v3.rst, * below macros are defined for CPUREG encoding. */ #define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000 #define KVM_REG_ARM_VGIC_SYSREG_OP0_SHIFT 14 #define KVM_REG_ARM_VGIC_SYSREG_OP1_MASK 0x0000000000003800 #define KVM_REG_ARM_VGIC_SYSREG_OP1_SHIFT 11 #define KVM_REG_ARM_VGIC_SYSREG_CRN_MASK 0x0000000000000780 #define KVM_REG_ARM_VGIC_SYSREG_CRN_SHIFT 7 #define KVM_REG_ARM_VGIC_SYSREG_CRM_MASK 0x0000000000000078 #define KVM_REG_ARM_VGIC_SYSREG_CRM_SHIFT 3 #define KVM_REG_ARM_VGIC_SYSREG_OP2_MASK 0x0000000000000007 #define KVM_REG_ARM_VGIC_SYSREG_OP2_SHIFT 0 #define KVM_DEV_ARM_VGIC_SYSREG_MASK (KVM_REG_ARM_VGIC_SYSREG_OP0_MASK | \ KVM_REG_ARM_VGIC_SYSREG_OP1_MASK | \ KVM_REG_ARM_VGIC_SYSREG_CRN_MASK | \ KVM_REG_ARM_VGIC_SYSREG_CRM_MASK | \ KVM_REG_ARM_VGIC_SYSREG_OP2_MASK) /* * As per Documentation/virt/kvm/devices/arm-vgic-its.rst, * below macros are defined for ITS table entry encoding. */ #define KVM_ITS_CTE_VALID_SHIFT 63 #define KVM_ITS_CTE_VALID_MASK BIT_ULL(63) #define KVM_ITS_CTE_RDBASE_SHIFT 16 #define KVM_ITS_CTE_ICID_MASK GENMASK_ULL(15, 0) #define KVM_ITS_ITE_NEXT_SHIFT 48 #define KVM_ITS_ITE_PINTID_SHIFT 16 #define KVM_ITS_ITE_PINTID_MASK GENMASK_ULL(47, 16) #define KVM_ITS_ITE_ICID_MASK GENMASK_ULL(15, 0) #define KVM_ITS_DTE_VALID_SHIFT 63 #define KVM_ITS_DTE_VALID_MASK BIT_ULL(63) #define KVM_ITS_DTE_NEXT_SHIFT 49 #define KVM_ITS_DTE_NEXT_MASK GENMASK_ULL(62, 49) #define KVM_ITS_DTE_ITTADDR_SHIFT 5 #define KVM_ITS_DTE_ITTADDR_MASK GENMASK_ULL(48, 5) #define KVM_ITS_DTE_SIZE_MASK GENMASK_ULL(4, 0) #define KVM_ITS_L1E_VALID_MASK BIT_ULL(63) /* we only support 64 kB translation table page size */ #define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16) #define KVM_VGIC_V3_RDIST_INDEX_MASK GENMASK_ULL(11, 0) #define KVM_VGIC_V3_RDIST_FLAGS_MASK GENMASK_ULL(15, 12) #define KVM_VGIC_V3_RDIST_FLAGS_SHIFT 12 #define KVM_VGIC_V3_RDIST_BASE_MASK GENMASK_ULL(51, 16) #define KVM_VGIC_V3_RDIST_COUNT_MASK GENMASK_ULL(63, 52) #define KVM_VGIC_V3_RDIST_COUNT_SHIFT 52 #ifdef CONFIG_DEBUG_SPINLOCK #define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p) #else #define DEBUG_SPINLOCK_BUG_ON(p) #endif static inline u32 vgic_get_implementation_rev(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.vgic.implementation_rev; } /* Requires the irq_lock to be held by the caller. */ static inline bool irq_is_pending(struct vgic_irq *irq) { if (irq->config == VGIC_CONFIG_EDGE) return irq->pending_latch; else return irq->pending_latch || irq->line_level; } static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq) { return irq->config == VGIC_CONFIG_LEVEL && irq->hw; } static inline int vgic_irq_get_lr_count(struct vgic_irq *irq) { /* Account for the active state as an interrupt */ if (vgic_irq_is_sgi(irq->intid) && irq->source) return hweight8(irq->source) + irq->active; return irq_is_pending(irq) || irq->active; } static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq) { return vgic_irq_get_lr_count(irq) > 1; } static inline int vgic_write_guest_lock(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { struct vgic_dist *dist = &kvm->arch.vgic; int ret; dist->table_write_in_progress = true; ret = kvm_write_guest_lock(kvm, gpa, data, len); dist->table_write_in_progress = false; return ret; } /* * This struct provides an intermediate representation of the fields contained * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC * state to userspace can generate either GICv2 or GICv3 CPU interface * registers regardless of the hardware backed GIC used. */ struct vgic_vmcr { u32 grpen0; u32 grpen1; u32 ackctl; u32 fiqen; u32 cbpr; u32 eoim; u32 abpr; u32 bpr; u32 pmr; /* Priority mask field in the GICC_PMR and * ICC_PMR_EL1 priority field format */ }; struct vgic_reg_attr { struct kvm_vcpu *vcpu; gpa_t addr; }; int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr); int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr); const struct vgic_register_region * vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, int len); struct vgic_irq *vgic_get_irq(struct kvm *kvm, u32 intid); struct vgic_irq *vgic_get_vcpu_irq(struct kvm_vcpu *vcpu, u32 intid); void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq); bool vgic_get_phys_line_level(struct vgic_irq *irq); void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending); void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, unsigned long flags) __releases(&irq->irq_lock); void vgic_kick_vcpus(struct kvm *kvm); void vgic_irq_handle_resampling(struct vgic_irq *irq, bool lr_deactivated, bool lr_pending); int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr, phys_addr_t addr, phys_addr_t alignment, phys_addr_t size); void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu); void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr); void vgic_v2_set_underflow(struct kvm_vcpu *vcpu); int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val); int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val); void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v2_enable(struct kvm_vcpu *vcpu); int vgic_v2_probe(const struct gic_kvm_info *info); int vgic_v2_map_resources(struct kvm *kvm); int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, enum vgic_type); void vgic_v2_init_lrs(void); void vgic_v2_load(struct kvm_vcpu *vcpu); void vgic_v2_put(struct kvm_vcpu *vcpu); void vgic_v2_save_state(struct kvm_vcpu *vcpu); void vgic_v2_restore_state(struct kvm_vcpu *vcpu); static inline bool vgic_try_get_irq_kref(struct vgic_irq *irq) { if (!irq) return false; if (irq->intid < VGIC_MIN_LPI) return true; return kref_get_unless_zero(&irq->refcount); } static inline void vgic_get_irq_kref(struct vgic_irq *irq) { WARN_ON_ONCE(!vgic_try_get_irq_kref(irq)); } void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu); void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr); void vgic_v3_set_underflow(struct kvm_vcpu *vcpu); void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v3_enable(struct kvm_vcpu *vcpu); int vgic_v3_probe(const struct gic_kvm_info *info); int vgic_v3_map_resources(struct kvm *kvm); int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); int vgic_v3_save_pending_tables(struct kvm *kvm); int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu); bool vgic_v3_check_base(struct kvm *kvm); void vgic_v3_load(struct kvm_vcpu *vcpu); void vgic_v3_put(struct kvm_vcpu *vcpu); bool vgic_has_its(struct kvm *kvm); int kvm_vgic_register_its_device(void); void vgic_enable_lpis(struct kvm_vcpu *vcpu); void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu); int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi); int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val); int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val); int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr, bool is_write); int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write, u32 intid, u32 *val); int kvm_register_vgic_device(unsigned long type); void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); int vgic_lazy_init(struct kvm *kvm); int vgic_init(struct kvm *kvm); void vgic_debug_init(struct kvm *kvm); void vgic_debug_destroy(struct kvm *kvm); static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu) { struct vgic_cpu *cpu_if = &vcpu->arch.vgic_cpu; /* * num_pri_bits are initialized with HW supported values. * We can rely safely on num_pri_bits even if VM has not * restored ICC_CTLR_EL1 before restoring APnR registers. */ switch (cpu_if->num_pri_bits) { case 7: return 3; case 6: return 1; default: return 0; } } static inline bool vgic_v3_redist_region_full(struct vgic_redist_region *region) { if (!region->count) return false; return (region->free_index >= region->count); } struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs); static inline size_t vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) { if (!rdreg->count) return atomic_read(&kvm->online_vcpus) * KVM_VGIC_V3_REDIST_SIZE; else return rdreg->count * KVM_VGIC_V3_REDIST_SIZE; } struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index); void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg); bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size) { struct vgic_dist *d = &kvm->arch.vgic; return (base + size > d->vgic_dist_base) && (base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE); } bool vgic_lpis_enabled(struct kvm_vcpu *vcpu); int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq); struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi); int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi); void vgic_its_invalidate_all_caches(struct kvm *kvm); /* GICv4.1 MMIO interface */ int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq); int vgic_its_invall(struct kvm_vcpu *vcpu); bool vgic_supports_direct_msis(struct kvm *kvm); int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); void vgic_v4_configure_vsgis(struct kvm *kvm); void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq); void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu); static inline bool kvm_has_gicv3(struct kvm *kvm) { return kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP); } #endif |
| 304 304 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static inline void bit_spin_lock(int bitnum, unsigned long *addr) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(bitlock); } /* * Return true if it was acquired */ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(bitlock); return 1; } /* * bit-based spin_unlock() */ static inline void bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static inline void __bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */ |
| 887 887 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/irq.c * * Copyright (C) 1992 Linus Torvalds * Modifications for ARM processor Copyright (C) 1995-2000 Russell King. * Support for Dynamic Tick Timer Copyright (C) 2004-2005 Nokia Corporation. * Dynamic Tick Timer written by Tony Lindgren <tony@atomide.com> and * Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>. * Copyright (C) 2012 ARM Ltd. */ #include <linux/hardirq.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/irqchip.h> #include <linux/kprobes.h> #include <linux/memory.h> #include <linux/scs.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/vmalloc.h> #include <asm/daifflags.h> #include <asm/exception.h> #include <asm/numa.h> #include <asm/softirq_stack.h> #include <asm/stacktrace.h> #include <asm/vmap_stack.h> /* Only access this in an NMI enter/exit */ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); DEFINE_PER_CPU(unsigned long *, irq_stack_ptr); DECLARE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #ifdef CONFIG_SHADOW_CALL_STACK DEFINE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #endif static void init_irq_scs(void) { int cpu; if (!scs_is_enabled()) return; for_each_possible_cpu(cpu) per_cpu(irq_shadow_call_stack_ptr, cpu) = scs_alloc(early_cpu_to_node(cpu)); } #ifdef CONFIG_VMAP_STACK static void __init init_irq_stacks(void) { int cpu; unsigned long *p; for_each_possible_cpu(cpu) { p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu)); per_cpu(irq_stack_ptr, cpu) = p; } } #else /* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ DEFINE_PER_CPU_ALIGNED(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack); static void init_irq_stacks(void) { int cpu; for_each_possible_cpu(cpu) per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu); } #endif #ifndef CONFIG_PREEMPT_RT static void ____do_softirq(struct pt_regs *regs) { __do_softirq(); } void do_softirq_own_stack(void) { call_on_irq_stack(NULL, ____do_softirq); } #endif static void default_handle_irq(struct pt_regs *regs) { panic("IRQ taken without a root IRQ handler\n"); } static void default_handle_fiq(struct pt_regs *regs) { panic("FIQ taken without a root FIQ handler\n"); } void (*handle_arch_irq)(struct pt_regs *) __ro_after_init = default_handle_irq; void (*handle_arch_fiq)(struct pt_regs *) __ro_after_init = default_handle_fiq; int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) { if (handle_arch_irq != default_handle_irq) return -EBUSY; handle_arch_irq = handle_irq; pr_info("Root IRQ handler: %ps\n", handle_irq); return 0; } int __init set_handle_fiq(void (*handle_fiq)(struct pt_regs *)) { if (handle_arch_fiq != default_handle_fiq) return -EBUSY; handle_arch_fiq = handle_fiq; pr_info("Root FIQ handler: %ps\n", handle_fiq); return 0; } void __init init_IRQ(void) { init_irq_stacks(); init_irq_scs(); irqchip_init(); if (system_uses_irq_prio_masking()) { /* * Now that we have a stack for our IRQ handler, set * the PMR/PSR pair to a consistent state. */ WARN_ON(read_sysreg(daif) & PSR_A_BIT); local_daif_restore(DAIF_PROCCTX_NOIRQ); } } |
| 415 417 417 922 917 417 416 329 417 841 839 841 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /* * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock). * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @fast_path determine the * tracepoints being added, allowing us to diagnose "flush" related * operations without handling high-frequency fast-path "update" events. */ static __always_inline unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, const bool fast_path) { unsigned long flags; bool contended; /* * The _irqsave() is needed because cgroup_rstat_lock is * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring * this lock with the _irq() suffix only disables interrupts on * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables * interrupts on both configurations. The _irqsave() ensures * that interrupts are always disabled and later restored. */ contended = !raw_spin_trylock_irqsave(cpu_lock, flags); if (contended) { if (fast_path) trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended); raw_spin_lock_irqsave(cpu_lock, flags); } if (fast_path) trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended); return flags; } static __always_inline void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, unsigned long flags, const bool fast_path) { if (fast_path) trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false); else trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false); raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) return; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true); /* put @cgrp and all ancestors on the corresponding updated lists */ while (true) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = cgrp; break; } prstatc = cgroup_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; cgrp = parent; } _cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true); } /** * cgroup_rstat_push_children - push children cgroups into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of cgroups to be flush * * Iteratively traverse down the cgroup_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list built from the tail backward like "pushing" * cgroups into a stack. The root is pushed by the caller. */ static struct cgroup *cgroup_rstat_push_children(struct cgroup *head, struct cgroup *child, int cpu) { struct cgroup *chead = child; /* Head of child cgroup level */ struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */ struct cgroup *parent, *grandchild; struct cgroup_rstat_cpu *crstatc; child->rstat_flush_next = NULL; next_level: while (chead) { child = chead; chead = child->rstat_flush_next; parent = cgroup_parent(child); /* updated_next is parent cgroup terminated */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = cgroup_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { chead = ghead; ghead = NULL; goto next_level; } return head; } /** * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed * @root: root of the cgroup subtree to traverse * @cpu: target cpu * Return: A singly linked list of cgroups to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned cgroup is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child cgroups if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent cgroup. An exception * here is the cgroup root whose updated_next can be self terminated. */ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu); struct cgroup *head = NULL, *parent, *child; unsigned long flags; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) goto unlock_ret; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = cgroup_parent(root); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = cgroup_rstat_push_children(head, child, cpu); unlock_ret: _cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for cgroup_rstat_updated() and * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking cgroup_rstat_lock. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop) __acquires(&cgroup_rstat_lock) { bool contended; contended = !spin_trylock_irq(&cgroup_rstat_lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(&cgroup_rstat_lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop) __releases(&cgroup_rstat_lock) { trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(&cgroup_rstat_lock); } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu); for (; pos; pos = pos->rstat_flush_next) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); bpf_rstat_flush(pos, cgroup_parent(pos), cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { __cgroup_rstat_unlock(cgrp, cpu); if (!cond_resched()) cpu_relax(); __cgroup_rstat_lock(cgrp, cpu); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); __cgroup_rstat_unlock(cgrp, -1); } /** * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() * @cgrp: cgroup used by tracepoint */ void cgroup_rstat_flush_release(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) { __cgroup_rstat_unlock(cgrp, -1); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif dst_bstat->ntime += src_bstat->ntime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif dst_bstat->ntime -= src_bstat->ntime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); delta = rstatc->bstat; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); cgroup_base_stat_add(&rstatc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatc->subtree_bstat; prstatc = cgroup_rstat_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat); cgroup_base_stat_add(&prstatc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_NICE: rstatc->bstat.ntime += delta_exec; fallthrough; case CPUTIME_USER: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif bstat->ntime += cpustat[CPUTIME_NICE]; } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime, ntime; if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); ntime = cgrp->bstat.ntime; cgroup_rstat_flush_release(cgrp); } else { /* cgrp->bstat of root is not actually used, reuse it */ root_cgroup_cputime(&cgrp->bstat); usage = cgrp->bstat.cputime.sum_exec_runtime; utime = cgrp->bstat.cputime.utime; stime = cgrp->bstat.cputime.stime; ntime = cgrp->bstat.ntime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); do_div(ntime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n" "nice_usec %llu\n", usage, utime, stime, ntime); cgroup_force_idle_show(seq, &cgrp->bstat); } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, cgroup_rstat_updated) BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/cacheflush.h * * Copyright (C) 1999-2002 Russell King. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_CACHEFLUSH_H #define __ASM_CACHEFLUSH_H #include <linux/kgdb.h> #include <linux/mm.h> /* * This flag is used to indicate that the page pointed to by a pte is clean * and does not require cleaning before returning it to the user. */ #define PG_dcache_clean PG_arch_1 /* * MM Cache Management * =================== * * The arch/arm64/mm/cache.S implements these methods. * * Start addresses are inclusive and end addresses are exclusive; start * addresses should be rounded down, end addresses up. * * See Documentation/core-api/cachetlb.rst for more information. Please note that * the implementation assumes non-aliasing VIPT D-cache and (aliasing) * VIPT I-cache. * * All functions below apply to the interval [start, end) * - start - virtual start address (inclusive) * - end - virtual end address (exclusive) * * caches_clean_inval_pou(start, end) * * Ensure coherency between the I-cache and the D-cache region to * the Point of Unification. * * caches_clean_inval_user_pou(start, end) * * Ensure coherency between the I-cache and the D-cache region to * the Point of Unification. * Use only if the region might access user memory. * * icache_inval_pou(start, end) * * Invalidate I-cache region to the Point of Unification. * * dcache_clean_inval_poc(start, end) * * Clean and invalidate D-cache region to the Point of Coherency. * * dcache_inval_poc(start, end) * * Invalidate D-cache region to the Point of Coherency. * * dcache_clean_poc(start, end) * * Clean D-cache region to the Point of Coherency. * * dcache_clean_pop(start, end) * * Clean D-cache region to the Point of Persistence. * * dcache_clean_pou(start, end) * * Clean D-cache region to the Point of Unification. */ extern void caches_clean_inval_pou(unsigned long start, unsigned long end); extern void icache_inval_pou(unsigned long start, unsigned long end); extern void dcache_clean_inval_poc(unsigned long start, unsigned long end); extern void dcache_inval_poc(unsigned long start, unsigned long end); extern void dcache_clean_poc(unsigned long start, unsigned long end); extern void dcache_clean_pop(unsigned long start, unsigned long end); extern void dcache_clean_pou(unsigned long start, unsigned long end); extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end); extern void sync_icache_aliases(unsigned long start, unsigned long end); static inline void flush_icache_range(unsigned long start, unsigned long end) { caches_clean_inval_pou(start, end); /* * IPI all online CPUs so that they undergo a context synchronization * event and are forced to refetch the new instructions. */ /* * KGDB performs cache maintenance with interrupts disabled, so we * will deadlock trying to IPI the secondary CPUs. In theory, we can * set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that * just means that KGDB will elide the maintenance altogether! As it * turns out, KGDB uses IPIs to round-up the secondary CPUs during * the patching operation, so we don't need extra IPIs here anyway. * In which case, add a KGDB-specific bodge and return early. */ if (in_dbg_master()) return; kick_all_cpus_sync(); } #define flush_icache_range flush_icache_range /* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user * space" model to handle this. */ extern void copy_to_user_page(struct vm_area_struct *, struct page *, unsigned long, void *, const void *, unsigned long); #define copy_to_user_page copy_to_user_page /* * flush_dcache_folio is used when the kernel has written to the page * cache page at virtual address page->virtual. * * If this page isn't mapped (ie, folio_mapping == NULL), or it might * have userspace mappings, then we _must_ always clean + invalidate * the dcache entries associated with the kernel mapping. * * Otherwise we can defer the operation, and clean the cache when we are * about to change to user space. This is the same method as used on SPARC64. * See update_mmu_cache for the user space part. */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); void flush_dcache_folio(struct folio *); #define flush_dcache_folio flush_dcache_folio static __always_inline void icache_inval_all_pou(void) { if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC)) return; asm("ic ialluis"); dsb(ish); } #include <asm-generic/cacheflush.h> #endif /* __ASM_CACHEFLUSH_H */ |
| 193 10 10 203 1 201 202 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; kasan_check_write(dst, count); check_object_size(dst, count, false); if (can_do_masked_user_access()) { long retval; src = masked_user_access_begin(src); retval = do_strncpy_from_user(dst, src, count, count); user_read_access_end(); return retval; } max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 373 46 46 85 373 40 372 374 374 374 374 372 85 372 370 85 85 372 371 40 368 257 164 165 371 371 85 84 85 85 85 85 372 372 40 40 40 85 85 14 14 326 21 369 369 417 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(struct folio *folio) { return !folio_test_swapbacked(folio); } static inline int page_is_file_lru(struct page *page) { return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment in folio_lru_refs() */ return order_base_2(refs + 1); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); bool workingset = flags & BIT(PG_workingset); /* * Return the number of accesses beyond PG_referenced, i.e., N-1 if the * total number of accesses is N>1, since N=0,1 both map to the first * tier. lru_tier_from_refs() will account for this off-by-one. Also see * the comment on MAX_NR_TIERS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; } static inline void folio_clear_lru_refs(struct folio *folio) { set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); } static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; unsigned long mask; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* * There are four common cases for this page: * 1. If it's hot, i.e., freshly faulted in, add it to the youngest * generation, and it's protected over the rest below. * 2. If it can't be evicted immediately, i.e., a dirty page pending * writeback, add it to the second youngest generation. * 3. If it should be evicted first, e.g., cold and clean from * folio_rotate_reclaimable(), add it to the oldest generation. * 4. Everything else falls between 2 & 3 above and is added to the * second oldest generation if it's considered inactive, or the * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) seq = lrugen->max_seq - 1; else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; else seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ mask = LRU_GEN_MASK; /* * Don't clear PG_workingset here because it can affect PSI accounting * if the activation is due to workingset refault. */ if (folio_test_active(folio)) mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active); set_mask_bits(&folio->flags, mask, flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; set_mask_bits(&new->flags, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( swp_entry_t entry, struct vm_area_struct *dst_vma) { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } #endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. */ static inline void pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { #ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); #endif } static inline bool vma_has_recency(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif |
| 396 396 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/blkdev.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/kthread.h> #include <linux/backing-dev.h> #include <linux/blk-cgroup.h> #include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> #include <trace/events/writeback.h> #include "internal.h" struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); static u64 bdi_id_cursor; static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> struct wb_stats { unsigned long nr_dirty; unsigned long nr_io; unsigned long nr_more_io; unsigned long nr_dirty_time; unsigned long nr_writeback; unsigned long nr_reclaimable; unsigned long nr_dirtied; unsigned long nr_written; unsigned long dirty_thresh; unsigned long wb_thresh; }; static struct dentry *bdi_debug_root; static void bdi_debug_init(void) { bdi_debug_root = debugfs_create_dir("bdi", NULL); } static void collect_wb_stats(struct wb_stats *stats, struct bdi_writeback *wb) { struct inode *inode; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) if (inode->i_state & I_DIRTY_TIME) stats->nr_dirty_time++; spin_unlock(&wb->list_lock); stats->nr_writeback += wb_stat(wb, WB_WRITEBACK); stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE); stats->nr_dirtied += wb_stat(wb, WB_DIRTIED); stats->nr_written += wb_stat(wb, WB_WRITTEN); stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh); } #ifdef CONFIG_CGROUP_WRITEBACK static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { struct bdi_writeback *wb; rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { if (!wb_tryget(wb)) continue; collect_wb_stats(stats, wb); wb_put(wb); } rcu_read_unlock(); } #else static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { collect_wb_stats(stats, &bdi->wb); } #endif static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct wb_stats stats; unsigned long tot_bw; global_dirty_limits(&background_thresh, &dirty_thresh); memset(&stats, 0, sizeof(stats)); stats.dirty_thresh = dirty_thresh; bdi_collect_stats(bdi, &stats); tot_bw = atomic_long_read(&bdi->tot_write_bandwidth); seq_printf(m, "BdiWriteback: %10lu kB\n" "BdiReclaimable: %10lu kB\n" "BdiDirtyThresh: %10lu kB\n" "DirtyThresh: %10lu kB\n" "BackgroundThresh: %10lu kB\n" "BdiDirtied: %10lu kB\n" "BdiWritten: %10lu kB\n" "BdiWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", K(stats.nr_writeback), K(stats.nr_reclaimable), K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), K(stats.nr_dirtied), K(stats.nr_written), K(tot_bw), stats.nr_dirty, stats.nr_io, stats.nr_more_io, stats.nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, struct wb_stats *stats) { seq_printf(m, "WbCgIno: %10lu\n" "WbWriteback: %10lu kB\n" "WbReclaimable: %10lu kB\n" "WbDirtyThresh: %10lu kB\n" "WbDirtied: %10lu kB\n" "WbWritten: %10lu kB\n" "WbWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "state: %10lx\n\n", #ifdef CONFIG_CGROUP_WRITEBACK cgroup_ino(wb->memcg_css->cgroup), #else 1ul, #endif K(stats->nr_writeback), K(stats->nr_reclaimable), K(stats->wb_thresh), K(stats->nr_dirtied), K(stats->nr_written), K(wb->avg_write_bandwidth), stats->nr_dirty, stats->nr_io, stats->nr_more_io, stats->nr_dirty_time, wb->state); } static int cgwb_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct bdi_writeback *wb; global_dirty_limits(&background_thresh, &dirty_thresh); rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { struct wb_stats stats = { .dirty_thresh = dirty_thresh }; if (!wb_tryget(wb)) continue; collect_wb_stats(&stats, wb); /* * Calculate thresh of wb in writeback cgroup which is min of * thresh in global domain and thresh in cgroup domain. Drop * rcu lock because cgwb_calc_thresh may sleep in * cgroup_rstat_flush. We can do so here because we have a ref. */ if (mem_cgroup_wb_domain(wb)) { rcu_read_unlock(); stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); rcu_read_lock(); } wb_stats_show(m, wb, &stats); wb_put(wb); } rcu_read_unlock(); return 0; } DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, &cgwb_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } #else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } #endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned long read_ahead_kb; ssize_t ret; ret = kstrtoul(buf, 10, &read_ahead_kb); if (ret < 0) return ret; bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10); return count; } #define BDI_SHOW(name, expr) \ static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return sysfs_emit(buf, "%lld\n", (long long)expr); \ } \ static DEVICE_ATTR_RW(name); BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) static ssize_t min_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE) static ssize_t min_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio_fine, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE) static ssize_t max_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio_fine, bdi->max_ratio) static ssize_t min_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi)); } static ssize_t min_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_min_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(min_bytes); static ssize_t max_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi)); } static ssize_t max_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_max_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(max_bytes); static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, char *buf) { dev_warn_once(dev, "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); return sysfs_emit(buf, "%d\n", 0); } static DEVICE_ATTR_RO(stable_pages_required); static ssize_t strict_limit_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int strict_limit; ssize_t ret; ret = kstrtouint(buf, 10, &strict_limit); if (ret < 0) return ret; ret = bdi_set_strict_limit(bdi, strict_limit); if (!ret) ret = count; return ret; } static ssize_t strict_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%d\n", !!(bdi->capabilities & BDI_CAP_STRICTLIMIT)); } static DEVICE_ATTR_RW(strict_limit); static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, &dev_attr_min_ratio_fine.attr, &dev_attr_max_ratio.attr, &dev_attr_max_ratio_fine.attr, &dev_attr_min_bytes.attr, &dev_attr_max_bytes.attr, &dev_attr_stable_pages_required.attr, &dev_attr_strict_limit.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); static const struct class bdi_class = { .name = "bdi", .dev_groups = bdi_dev_groups, }; static __init int bdi_class_init(void) { int ret; ret = class_register(&bdi_class); if (ret) return ret; bdi_debug_init(); return 0; } postcore_initcall(bdi_class_init); static int __init default_bdi_init(void) { bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; return 0; } subsys_initcall(default_bdi_init); static void wb_update_bandwidth_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, bw_dwork); wb_update_bandwidth(wb); } /* * Initial write bandwidth: 100 MB/s */ #define INIT_BW (100 << (20 - PAGE_SHIFT)) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp) { int err; memset(wb, 0, sizeof(*wb)); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); atomic_set(&wb->writeback_inodes, 0); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; wb->write_bandwidth = INIT_BW; wb->avg_write_bandwidth = INIT_BW; spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); err = fprop_local_init_percpu(&wb->completions, gfp); if (err) return err; err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); if (err) fprop_local_destroy_percpu(&wb->completions); return err; } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); /* * Remove bdi from the global list and shutdown any threads we have running */ static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ spin_lock_irq(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_irq(&wb->work_lock); return; } spin_unlock_irq(&wb->work_lock); cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to * be drained no matter what. */ mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); flush_delayed_work(&wb->bw_dwork); } static void wb_exit(struct bdi_writeback *wb) { WARN_ON(delayed_work_pending(&wb->dwork)); percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/memcontrol.h> /* * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; static LIST_HEAD(offline_cgwbs); static void cleanup_offline_cgwbs_workfn(struct work_struct *work); static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); static void cgwb_free_rcu(struct rcu_head *rcu_head) { struct bdi_writeback *wb = container_of(rcu_head, struct bdi_writeback, rcu); percpu_ref_exit(&wb->refcnt); kfree(wb); } static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); /* triggers blkg destruction if no online users left */ blkcg_unpin_online(wb->blkcg_css); fprop_local_destroy_percpu(&wb->memcg_completions); spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); wb_exit(wb); bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) { lockdep_assert_held(&cgwb_lock); WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { spin_lock_irq(&cgwb_lock); list_del_rcu(&wb->bdi_node); spin_unlock_irq(&cgwb_lock); } static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; int ret = 0; memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); memcg_cgwb_list = &memcg->cgwb_list; blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb && wb->blkcg_css != blkcg_css) { cgwb_kill(wb); wb = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); if (wb) goto out_put; /* need to create a new one */ wb = kmalloc(sizeof(*wb), gfp); if (!wb) { ret = -ENOMEM; goto out_put; } ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); if (ret) goto err_wb_exit; ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); if (ret) goto err_ref_exit; wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate * whether they're still online. Don't link @wb if any is dead. * See wb_memcg_offline() and wb_blkcg_offline(). */ ret = -ENODEV; spin_lock_irqsave(&cgwb_lock, flags); if (test_bit(WB_registered, &bdi->wb.state) && blkcg_cgwb_list->next && memcg_cgwb_list->next) { /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } } spin_unlock_irqrestore(&cgwb_lock, flags); if (ret) { if (ret == -EEXIST) ret = 0; goto err_fprop_exit; } goto out_put; err_fprop_exit: bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); err_wb_exit: wb_exit(wb); err_free: kfree(wb); out_put: css_put(blkcg_css); return ret; } /** * wb_get_lookup - get wb for a given memcg * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * * Try to get the wb for @memcg_css on @bdi. The returned wb has its * refcount incremented. * * This function uses css_get() on @memcg_css and thus expects its refcnt * to be positive on invocation. IOW, rcu_read_lock() protection on * @memcg_css isn't enough. try_get it before calling this function. * * A wb is keyed by its associated memcg. As blkcg implicitly enables * memcg on the default hierarchy, memcg association is guaranteed to be * more specific (equal or descendant to the associated blkcg) and thus can * identify both the memcg and blkcg associations. * * Because the blkcg associated with a memcg may change as blkcg is enabled * and disabled closer to root in the hierarchy, each wb keeps track of * both the memcg and blkcg associated with it and verifies the blkcg on * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css) { struct bdi_writeback *wb; if (!memcg_css->parent) return &bdi->wb; rcu_read_lock(); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb) { struct cgroup_subsys_state *blkcg_css; /* see whether the blkcg association has changed */ blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) wb = NULL; css_put(blkcg_css); } rcu_read_unlock(); return wb; } /** * wb_get_create - get wb for a given memcg, create if necessary * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * @gfp: allocation mask to use * * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to * create one. See wb_get_lookup() for more details. */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct bdi_writeback *wb; might_alloc(gfp); do { wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; } static int cgwb_bdi_init(struct backing_dev_info *bdi) { int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; } return ret; } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; void **slot; struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); spin_unlock_irq(&cgwb_lock); mutex_lock(&bdi->cgwb_release_mutex); spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); mutex_unlock(&bdi->cgwb_release_mutex); } /* * cleanup_offline_cgwbs_workfn - try to release dying cgwbs * * Try to release dying cgwbs by switching attached inodes to the nearest * living ancestor's writeback. Processed wbs are placed at the end * of the list to guarantee the forward progress. */ static void cleanup_offline_cgwbs_workfn(struct work_struct *work) { struct bdi_writeback *wb; LIST_HEAD(processed); spin_lock_irq(&cgwb_lock); while (!list_empty(&offline_cgwbs)) { wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, offline_node); list_move(&wb->offline_node, &processed); /* * If wb is dirty, cleaning up the writeback by switching * attached inodes will result in an effective removal of any * bandwidth restrictions, which isn't the goal. Instead, * it can be postponed until the next time, when all io * will be likely completed. If in the meantime some inodes * will get re-dirtied, they should be eventually switched to * a new cgwb. */ if (wb_has_dirty_io(wb)) continue; if (!wb_tryget(wb)) continue; spin_unlock_irq(&cgwb_lock); while (cleanup_offline_cgwb(wb)) cond_resched(); spin_lock_irq(&cgwb_lock); wb_put(wb); } if (!list_empty(&processed)) list_splice_tail(&processed, &offline_cgwbs); spin_unlock_irq(&cgwb_lock); } /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined * * Also prevents creation of any new wb's associated with @memcg. */ void wb_memcg_offline(struct mem_cgroup *memcg) { struct list_head *memcg_cgwb_list = &memcg->cgwb_list; struct bdi_writeback *wb, *next; spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work); } /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } static void cgwb_bdi_register(struct backing_dev_info *bdi) { spin_lock_irq(&cgwb_lock); list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); spin_unlock_irq(&cgwb_lock); } static int __init cgwb_init(void) { /* * There can be many concurrent release work items overwhelming * system_wq. Put them in a separate wq and limit concurrency. * There's no point in executing many of these in parallel. */ cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); if (!cgwb_release_wq) return -ENOMEM; return 0; } subsys_initcall(cgwb_init); #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) { return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { list_del_rcu(&wb->bdi_node); } #endif /* CONFIG_CGROUP_WRITEBACK */ int bdi_init(struct backing_dev_info *bdi) { bdi->dev = NULL; kref_init(&bdi->refcnt); bdi->min_ratio = 0; bdi->max_ratio = 100 * BDI_RATIO_SCALE; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } struct backing_dev_info *bdi_alloc(int node_id) { struct backing_dev_info *bdi; bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL; if (bdi_init(bdi)) { kfree(bdi); return NULL; } bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); return bdi; } EXPORT_SYMBOL(bdi_alloc); static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) { struct rb_node **p = &bdi_tree.rb_node; struct rb_node *parent = NULL; struct backing_dev_info *bdi; lockdep_assert_held(&bdi_lock); while (*p) { parent = *p; bdi = rb_entry(parent, struct backing_dev_info, rb_node); if (bdi->id > id) p = &(*p)->rb_left; else if (bdi->id < id) p = &(*p)->rb_right; else break; } if (parentp) *parentp = parent; return p; } /** * bdi_get_by_id - lookup and get bdi from its id * @id: bdi id to lookup * * Find bdi matching @id and get it. Returns NULL if the matching bdi * doesn't exist or is already unregistered. */ struct backing_dev_info *bdi_get_by_id(u64 id) { struct backing_dev_info *bdi = NULL; struct rb_node **p; spin_lock_bh(&bdi_lock); p = bdi_lookup_rb_node(id, NULL); if (*p) { bdi = rb_entry(*p, struct backing_dev_info, rb_node); bdi_get(bdi); } spin_unlock_bh(&bdi_lock); return bdi; } int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); dev = device_create(&bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); bdi->id = ++bdi_id_cursor; p = bdi_lookup_rb_node(bdi->id, &parent); rb_link_node(&bdi->rb_node, parent, p); rb_insert_color(&bdi->rb_node, &bdi_tree); list_add_tail_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); return 0; } int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = bdi_register_va(bdi, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL(bdi_register); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) { WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner); } /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); } void bdi_unregister(struct backing_dev_info *bdi) { del_timer_sync(&bdi->laptop_mode_wb_timer); /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); /* * If this BDI's min ratio has been set, use bdi_set_min_ratio() to * update the global bdi_min_ratio. */ if (bdi->min_ratio) bdi_set_min_ratio(bdi, 0); if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; } if (bdi->owner) { put_device(bdi->owner); bdi->owner = NULL; } } EXPORT_SYMBOL(bdi_unregister); static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi); } void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } EXPORT_SYMBOL(bdi_put); struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb; if (!inode) return &noop_backing_dev_info; sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return I_BDEV(inode)->bd_disk->bdi; #endif return sb->s_bdi; } EXPORT_SYMBOL(inode_to_bdi); const char *bdi_dev_name(struct backing_dev_info *bdi) { if (!bdi || !bdi->dev) return bdi_unknown_name; return bdi->dev_name; } EXPORT_SYMBOL_GPL(bdi_dev_name); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | // SPDX-License-Identifier: GPL-2.0-only /* * Network interface table. * * Network interfaces (devices) do not have a security field, so we * maintain a table associating each interface with a SID. * * Author: James Morris <jmorris@redhat.com> * * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2007 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> */ #include <linux/init.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include "security.h" #include "objsec.h" #include "netif.h" #define SEL_NETIF_HASH_SIZE 64 #define SEL_NETIF_HASH_MAX 1024 struct sel_netif { struct list_head list; struct netif_security_struct nsec; struct rcu_head rcu_head; }; static u32 sel_netif_total; static DEFINE_SPINLOCK(sel_netif_lock); static struct list_head sel_netif_hash[SEL_NETIF_HASH_SIZE]; /** * sel_netif_hashfn - Hashing function for the interface table * @ns: the network namespace * @ifindex: the network interface * * Description: * This is the hashing function for the network interface table, it returns the * bucket number for the given interface. * */ static inline u32 sel_netif_hashfn(const struct net *ns, int ifindex) { return (((uintptr_t)ns + ifindex) & (SEL_NETIF_HASH_SIZE - 1)); } /** * sel_netif_find - Search for an interface record * @ns: the network namespace * @ifindex: the network interface * * Description: * Search the network interface table and return the record matching @ifindex. * If an entry can not be found in the table return NULL. * */ static inline struct sel_netif *sel_netif_find(const struct net *ns, int ifindex) { u32 idx = sel_netif_hashfn(ns, ifindex); struct sel_netif *netif; list_for_each_entry_rcu(netif, &sel_netif_hash[idx], list) if (net_eq(netif->nsec.ns, ns) && netif->nsec.ifindex == ifindex) return netif; return NULL; } /** * sel_netif_insert - Insert a new interface into the table * @netif: the new interface record * * Description: * Add a new interface record to the network interface hash table. Returns * zero on success, negative values on failure. * */ static int sel_netif_insert(struct sel_netif *netif) { u32 idx; if (sel_netif_total >= SEL_NETIF_HASH_MAX) return -ENOSPC; idx = sel_netif_hashfn(netif->nsec.ns, netif->nsec.ifindex); list_add_rcu(&netif->list, &sel_netif_hash[idx]); sel_netif_total++; return 0; } /** * sel_netif_destroy - Remove an interface record from the table * @netif: the existing interface record * * Description: * Remove an existing interface record from the network interface table. * */ static void sel_netif_destroy(struct sel_netif *netif) { list_del_rcu(&netif->list); sel_netif_total--; kfree_rcu(netif, rcu_head); } /** * sel_netif_sid_slow - Lookup the SID of a network interface using the policy * @ns: the network namespace * @ifindex: the network interface * @sid: interface SID * * Description: * This function determines the SID of a network interface by querying the * security policy. The result is added to the network interface table to * speedup future queries. Returns zero on success, negative values on * failure. * */ static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid) { int ret = 0; struct sel_netif *netif; struct sel_netif *new; struct net_device *dev; /* NOTE: we always use init's network namespace since we don't * currently support containers */ dev = dev_get_by_index(ns, ifindex); if (unlikely(dev == NULL)) { pr_warn("SELinux: failure in %s(), invalid network interface (%d)\n", __func__, ifindex); return -ENOENT; } spin_lock_bh(&sel_netif_lock); netif = sel_netif_find(ns, ifindex); if (netif != NULL) { *sid = netif->nsec.sid; goto out; } ret = security_netif_sid(dev->name, sid); if (ret != 0) goto out; new = kzalloc(sizeof(*new), GFP_ATOMIC); if (new) { new->nsec.ns = ns; new->nsec.ifindex = ifindex; new->nsec.sid = *sid; if (sel_netif_insert(new)) kfree(new); } out: spin_unlock_bh(&sel_netif_lock); dev_put(dev); if (unlikely(ret)) pr_warn("SELinux: failure in %s(), unable to determine network interface label (%d)\n", __func__, ifindex); return ret; } /** * sel_netif_sid - Lookup the SID of a network interface * @ns: the network namespace * @ifindex: the network interface * @sid: interface SID * * Description: * This function determines the SID of a network interface using the fastest * method possible. First the interface table is queried, but if an entry * can't be found then the policy is queried and the result is added to the * table to speedup future queries. Returns zero on success, negative values * on failure. * */ int sel_netif_sid(struct net *ns, int ifindex, u32 *sid) { struct sel_netif *netif; rcu_read_lock(); netif = sel_netif_find(ns, ifindex); if (likely(netif != NULL)) { *sid = netif->nsec.sid; rcu_read_unlock(); return 0; } rcu_read_unlock(); return sel_netif_sid_slow(ns, ifindex, sid); } /** * sel_netif_kill - Remove an entry from the network interface table * @ns: the network namespace * @ifindex: the network interface * * Description: * This function removes the entry matching @ifindex from the network interface * table if it exists. * */ static void sel_netif_kill(const struct net *ns, int ifindex) { struct sel_netif *netif; rcu_read_lock(); spin_lock_bh(&sel_netif_lock); netif = sel_netif_find(ns, ifindex); if (netif) sel_netif_destroy(netif); spin_unlock_bh(&sel_netif_lock); rcu_read_unlock(); } /** * sel_netif_flush - Flush the entire network interface table * * Description: * Remove all entries from the network interface table. * */ void sel_netif_flush(void) { int idx; struct sel_netif *netif; spin_lock_bh(&sel_netif_lock); for (idx = 0; idx < SEL_NETIF_HASH_SIZE; idx++) list_for_each_entry(netif, &sel_netif_hash[idx], list) sel_netif_destroy(netif); spin_unlock_bh(&sel_netif_lock); } static int sel_netif_netdev_notifier_handler(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_DOWN) sel_netif_kill(dev_net(dev), dev->ifindex); return NOTIFY_DONE; } static struct notifier_block sel_netif_netdev_notifier = { .notifier_call = sel_netif_netdev_notifier_handler, }; static __init int sel_netif_init(void) { int i; if (!selinux_enabled_boot) return 0; for (i = 0; i < SEL_NETIF_HASH_SIZE; i++) INIT_LIST_HEAD(&sel_netif_hash[i]); register_netdevice_notifier(&sel_netif_netdev_notifier); return 0; } __initcall(sel_netif_init); |
| 999 230 230 1109 1063 165 1113 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_FILE_REF_H #define _LINUX_FILE_REF_H #include <linux/atomic.h> #include <linux/preempt.h> #include <linux/types.h> /* * file_ref is a reference count implementation specifically for use by * files. It takes inspiration from rcuref but differs in key aspects * such as support for SLAB_TYPESAFE_BY_RCU type caches. * * FILE_REF_ONEREF FILE_REF_MAXREF * 0x0000000000000000UL 0x7FFFFFFFFFFFFFFFUL * <-------------------valid -------------------> * * FILE_REF_SATURATED * 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL * <-----------------------saturation zone----------------------> * * FILE_REF_RELEASED FILE_REF_DEAD * 0xC000000000000000UL 0xE000000000000000UL * <-------------------dead zone-------------------> * * FILE_REF_NOREF * 0xFFFFFFFFFFFFFFFFUL */ #ifdef CONFIG_64BIT #define FILE_REF_ONEREF 0x0000000000000000UL #define FILE_REF_MAXREF 0x7FFFFFFFFFFFFFFFUL #define FILE_REF_SATURATED 0xA000000000000000UL #define FILE_REF_RELEASED 0xC000000000000000UL #define FILE_REF_DEAD 0xE000000000000000UL #define FILE_REF_NOREF 0xFFFFFFFFFFFFFFFFUL #else #define FILE_REF_ONEREF 0x00000000U #define FILE_REF_MAXREF 0x7FFFFFFFU #define FILE_REF_SATURATED 0xA0000000U #define FILE_REF_RELEASED 0xC0000000U #define FILE_REF_DEAD 0xE0000000U #define FILE_REF_NOREF 0xFFFFFFFFU #endif typedef struct { #ifdef CONFIG_64BIT atomic64_t refcnt; #else atomic_t refcnt; #endif } file_ref_t; /** * file_ref_init - Initialize a file reference count * @ref: Pointer to the reference count * @cnt: The initial reference count typically '1' */ static inline void file_ref_init(file_ref_t *ref, unsigned long cnt) { atomic_long_set(&ref->refcnt, cnt - 1); } bool __file_ref_put(file_ref_t *ref, unsigned long cnt); /** * file_ref_get - Acquire one reference on a file * @ref: Pointer to the reference count * * Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF. * * Provides full memory ordering. * * Return: False if the attempt to acquire a reference failed. This happens * when the last reference has been put already. True if a reference * was successfully acquired */ static __always_inline __must_check bool file_ref_get(file_ref_t *ref) { /* * Unconditionally increase the reference count with full * ordering. The saturation and dead zones provide enough * tolerance for this. * * If this indicates negative the file in question the fail can * be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU. * Hence, unconditionally altering the file reference count to * e.g., reset the file reference count back to the middle of * the deadzone risk end up marking someone else's file as dead * behind their back. * * It would be possible to do a careful: * * cnt = atomic_long_inc_return(); * if (likely(cnt >= 0)) * return true; * * and then something like: * * if (cnt >= FILE_REF_RELEASE) * atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD), * * to set the value back to the middle of the deadzone. But it's * practically impossible to go from FILE_REF_DEAD to * FILE_REF_ONEREF. It would need 2305843009213693952/2^61 * file_ref_get()s to resurrect such a dead file. */ return !atomic_long_add_negative(1, &ref->refcnt); } /** * file_ref_inc - Acquire one reference on a file * @ref: Pointer to the reference count * * Acquire an additional reference on a file. Warns if the caller didn't * already hold a reference. */ static __always_inline void file_ref_inc(file_ref_t *ref) { long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt); WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference"); } /** * file_ref_put -- Release a file reference * @ref: Pointer to the reference count * * Provides release memory ordering, such that prior loads and stores * are done before, and provides an acquire ordering on success such * that free() must come after. * * Return: True if this was the last reference with no future references * possible. This signals the caller that it can safely release * the object which is protected by the reference counter. * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * release the protected object. */ static __always_inline __must_check bool file_ref_put(file_ref_t *ref) { long cnt; /* * While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put() * calls don't risk UAFs when a file is recyclyed, it is still * vulnerable to UAFs caused by freeing the whole slab page once * it becomes unused. Prevent file_ref_put() from being * preempted protects against this. */ guard(preempt)(); /* * Unconditionally decrease the reference count. The saturation * and dead zones provide enough tolerance for this. If this * fails then we need to handle the last reference drop and * cases inside the saturation and dead zones. */ cnt = atomic_long_dec_return(&ref->refcnt); if (cnt >= 0) return false; return __file_ref_put(ref, cnt); } /** * file_ref_read - Read the number of file references * @ref: Pointer to the reference count * * Return: The number of held references (0 ... N) */ static inline unsigned long file_ref_read(file_ref_t *ref) { unsigned long c = atomic_long_read(&ref->refcnt); /* Return 0 if within the DEAD zone. */ return c >= FILE_REF_RELEASED ? 0 : c + 1; } #endif |
| 38 38 38 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/traps.c * * Copyright (C) 1995-2009 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/bug.h> #include <linux/context_tracking.h> #include <linux/signal.h> #include <linux/kallsyms.h> #include <linux/kprobes.h> #include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kdebug.h> #include <linux/module.h> #include <linux/kexec.h> #include <linux/delay.h> #include <linux/efi.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/sizes.h> #include <linux/syscalls.h> #include <linux/mm_types.h> #include <linux/kasan.h> #include <linux/ubsan.h> #include <linux/cfi.h> #include <asm/atomic.h> #include <asm/bug.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/efi.h> #include <asm/esr.h> #include <asm/exception.h> #include <asm/extable.h> #include <asm/insn.h> #include <asm/kprobes.h> #include <asm/text-patching.h> #include <asm/traps.h> #include <asm/smp.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> #include <asm/system_misc.h> #include <asm/sysreg.h> static bool __kprobes __check_eq(unsigned long pstate) { return (pstate & PSR_Z_BIT) != 0; } static bool __kprobes __check_ne(unsigned long pstate) { return (pstate & PSR_Z_BIT) == 0; } static bool __kprobes __check_cs(unsigned long pstate) { return (pstate & PSR_C_BIT) != 0; } static bool __kprobes __check_cc(unsigned long pstate) { return (pstate & PSR_C_BIT) == 0; } static bool __kprobes __check_mi(unsigned long pstate) { return (pstate & PSR_N_BIT) != 0; } static bool __kprobes __check_pl(unsigned long pstate) { return (pstate & PSR_N_BIT) == 0; } static bool __kprobes __check_vs(unsigned long pstate) { return (pstate & PSR_V_BIT) != 0; } static bool __kprobes __check_vc(unsigned long pstate) { return (pstate & PSR_V_BIT) == 0; } static bool __kprobes __check_hi(unsigned long pstate) { pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ return (pstate & PSR_C_BIT) != 0; } static bool __kprobes __check_ls(unsigned long pstate) { pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ return (pstate & PSR_C_BIT) == 0; } static bool __kprobes __check_ge(unsigned long pstate) { pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ return (pstate & PSR_N_BIT) == 0; } static bool __kprobes __check_lt(unsigned long pstate) { pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ return (pstate & PSR_N_BIT) != 0; } static bool __kprobes __check_gt(unsigned long pstate) { /*PSR_N_BIT ^= PSR_V_BIT */ unsigned long temp = pstate ^ (pstate << 3); temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ return (temp & PSR_N_BIT) == 0; } static bool __kprobes __check_le(unsigned long pstate) { /*PSR_N_BIT ^= PSR_V_BIT */ unsigned long temp = pstate ^ (pstate << 3); temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ return (temp & PSR_N_BIT) != 0; } static bool __kprobes __check_al(unsigned long pstate) { return true; } /* * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that * it behaves identically to 0b1110 ("al"). */ pstate_check_t * const aarch32_opcode_cond_checks[16] = { __check_eq, __check_ne, __check_cs, __check_cc, __check_mi, __check_pl, __check_vs, __check_vc, __check_hi, __check_ls, __check_ge, __check_lt, __check_gt, __check_le, __check_al, __check_al }; int show_unhandled_signals = 0; static void dump_kernel_instr(const char *lvl, struct pt_regs *regs) { unsigned long addr = instruction_pointer(regs); char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str; int i; if (user_mode(regs)) return; for (i = -4; i < 1; i++) { unsigned int val, bad; bad = aarch64_insn_read(&((u32 *)addr)[i], &val); if (!bad) p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val); else p += sprintf(p, i == 0 ? "(????????) " : "???????? "); } printk("%sCode: %s\n", lvl, str); } #ifdef CONFIG_PREEMPT #define S_PREEMPT " PREEMPT" #elif defined(CONFIG_PREEMPT_RT) #define S_PREEMPT " PREEMPT_RT" #else #define S_PREEMPT "" #endif #define S_SMP " SMP" static int __die(const char *str, long err, struct pt_regs *regs) { static int die_counter; int ret; pr_emerg("Internal error: %s: %016lx [#%d]" S_PREEMPT S_SMP "\n", str, err, ++die_counter); /* trap and error numbers are mostly meaningless on ARM */ ret = notify_die(DIE_OOPS, str, regs, err, 0, SIGSEGV); if (ret == NOTIFY_STOP) return ret; print_modules(); show_regs(regs); dump_kernel_instr(KERN_EMERG, regs); return ret; } static DEFINE_RAW_SPINLOCK(die_lock); /* * This function is protected against re-entrancy. */ void die(const char *str, struct pt_regs *regs, long err) { int ret; unsigned long flags; raw_spin_lock_irqsave(&die_lock, flags); oops_enter(); console_verbose(); bust_spinlocks(1); ret = __die(str, err, regs); if (regs && kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); oops_exit(); if (in_interrupt()) panic("%s: Fatal exception in interrupt", str); if (panic_on_oops) panic("%s: Fatal exception", str); raw_spin_unlock_irqrestore(&die_lock, flags); if (ret != NOTIFY_STOP) make_task_dead(SIGSEGV); } static void arm64_show_signal(int signo, const char *str) { static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); struct task_struct *tsk = current; unsigned long esr = tsk->thread.fault_code; struct pt_regs *regs = task_pt_regs(tsk); /* Leave if the signal won't be shown */ if (!show_unhandled_signals || !unhandled_signal(tsk, signo) || !__ratelimit(&rs)) return; pr_info("%s[%d]: unhandled exception: ", tsk->comm, task_pid_nr(tsk)); if (esr) pr_cont("%s, ESR 0x%016lx, ", esr_get_class_string(esr), esr); pr_cont("%s", str); print_vma_addr(KERN_CONT " in ", regs->pc); pr_cont("\n"); __show_regs(regs); } void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str) { arm64_show_signal(signo, str); if (signo == SIGKILL) force_sig(SIGKILL); else force_sig_fault(signo, code, (void __user *)far); } void arm64_force_sig_fault_pkey(unsigned long far, const char *str, int pkey) { arm64_show_signal(SIGSEGV, str); force_sig_pkuerr((void __user *)far, pkey); } void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str) { arm64_show_signal(SIGBUS, str); force_sig_mceerr(code, (void __user *)far, lsb); } void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str) { arm64_show_signal(SIGTRAP, str); force_sig_ptrace_errno_trap(errno, (void __user *)far); } void arm64_notify_die(const char *str, struct pt_regs *regs, int signo, int sicode, unsigned long far, unsigned long err) { if (user_mode(regs)) { WARN_ON(regs != current_pt_regs()); current->thread.fault_address = 0; current->thread.fault_code = err; arm64_force_sig_fault(signo, sicode, far, str); } else { die(str, regs, err); } } #ifdef CONFIG_COMPAT #define PSTATE_IT_1_0_SHIFT 25 #define PSTATE_IT_1_0_MASK (0x3 << PSTATE_IT_1_0_SHIFT) #define PSTATE_IT_7_2_SHIFT 10 #define PSTATE_IT_7_2_MASK (0x3f << PSTATE_IT_7_2_SHIFT) static u32 compat_get_it_state(struct pt_regs *regs) { u32 it, pstate = regs->pstate; it = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT; it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2; return it; } static void compat_set_it_state(struct pt_regs *regs, u32 it) { u32 pstate_it; pstate_it = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK; pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK; regs->pstate &= ~PSR_AA32_IT_MASK; regs->pstate |= pstate_it; } static void advance_itstate(struct pt_regs *regs) { u32 it; /* ARM mode */ if (!(regs->pstate & PSR_AA32_T_BIT) || !(regs->pstate & PSR_AA32_IT_MASK)) return; it = compat_get_it_state(regs); /* * If this is the last instruction of the block, wipe the IT * state. Otherwise advance it. */ if (!(it & 7)) it = 0; else it = (it & 0xe0) | ((it << 1) & 0x1f); compat_set_it_state(regs, it); } #else static void advance_itstate(struct pt_regs *regs) { } #endif void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size) { regs->pc += size; /* * If we were single stepping, we want to get the step exception after * we return from the trap. */ if (user_mode(regs)) user_fastforward_single_step(current); if (compat_user_mode(regs)) advance_itstate(regs); else regs->pstate &= ~PSR_BTYPE_MASK; } static int user_insn_read(struct pt_regs *regs, u32 *insnp) { u32 instr; unsigned long pc = instruction_pointer(regs); if (compat_thumb_mode(regs)) { /* 16-bit Thumb instruction */ __le16 instr_le; if (get_user(instr_le, (__le16 __user *)pc)) return -EFAULT; instr = le16_to_cpu(instr_le); if (aarch32_insn_is_wide(instr)) { u32 instr2; if (get_user(instr_le, (__le16 __user *)(pc + 2))) return -EFAULT; instr2 = le16_to_cpu(instr_le); instr = (instr << 16) | instr2; } } else { /* 32-bit ARM instruction */ __le32 instr_le; if (get_user(instr_le, (__le32 __user *)pc)) return -EFAULT; instr = le32_to_cpu(instr_le); } *insnp = instr; return 0; } void force_signal_inject(int signal, int code, unsigned long address, unsigned long err) { const char *desc; struct pt_regs *regs = current_pt_regs(); if (WARN_ON(!user_mode(regs))) return; switch (signal) { case SIGILL: desc = "undefined instruction"; break; case SIGSEGV: desc = "illegal memory access"; break; default: desc = "unknown or unrecoverable error"; break; } /* Force signals we don't understand to SIGKILL */ if (WARN_ON(signal != SIGKILL && siginfo_layout(signal, code) != SIL_FAULT)) { signal = SIGKILL; } arm64_notify_die(desc, regs, signal, code, address, err); } /* * Set up process info to signal segmentation fault - called on access error. */ void arm64_notify_segfault(unsigned long addr) { int code; mmap_read_lock(current->mm); if (find_vma(current->mm, untagged_addr(addr)) == NULL) code = SEGV_MAPERR; else code = SEGV_ACCERR; mmap_read_unlock(current->mm); force_signal_inject(SIGSEGV, code, addr, 0); } void do_el0_undef(struct pt_regs *regs, unsigned long esr) { u32 insn; /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) return; if (user_insn_read(regs, &insn)) goto out_err; if (try_emulate_mrs(regs, insn)) return; if (try_emulate_armv8_deprecated(regs, insn)) return; out_err: force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } void do_el1_undef(struct pt_regs *regs, unsigned long esr) { u32 insn; if (aarch64_insn_read((void *)regs->pc, &insn)) goto out_err; if (try_emulate_el1_ssbs(regs, insn)) return; out_err: die("Oops - Undefined instruction", regs, esr); } void do_el0_bti(struct pt_regs *regs) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } void do_el1_bti(struct pt_regs *regs, unsigned long esr) { if (efi_runtime_fixup_exception(regs, "BTI violation")) { regs->pstate &= ~PSR_BTYPE_MASK; return; } die("Oops - BTI", regs, esr); } void do_el0_gcs(struct pt_regs *regs, unsigned long esr) { force_signal_inject(SIGSEGV, SEGV_CPERR, regs->pc, 0); } void do_el1_gcs(struct pt_regs *regs, unsigned long esr) { die("Oops - GCS", regs, esr); } void do_el0_fpac(struct pt_regs *regs, unsigned long esr) { force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr); } void do_el1_fpac(struct pt_regs *regs, unsigned long esr) { /* * Unexpected FPAC exception in the kernel: kill the task before it * does any more harm. */ die("Oops - FPAC", regs, esr); } void do_el0_mops(struct pt_regs *regs, unsigned long esr) { arm64_mops_reset_regs(®s->user_regs, esr); /* * If single stepping then finish the step before executing the * prologue instruction. */ user_fastforward_single_step(current); } void do_el1_mops(struct pt_regs *regs, unsigned long esr) { arm64_mops_reset_regs(®s->user_regs, esr); kernel_fastforward_single_step(regs); } #define __user_cache_maint(insn, address, res) \ if (address >= TASK_SIZE_MAX) { \ res = -EFAULT; \ } else { \ uaccess_ttbr0_enable(); \ asm volatile ( \ "1: " insn ", %1\n" \ " mov %w0, #0\n" \ "2:\n" \ _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0) \ : "=r" (res) \ : "r" (address)); \ uaccess_ttbr0_disable(); \ } static void user_cache_maint_handler(unsigned long esr, struct pt_regs *regs) { unsigned long tagged_address, address; int rt = ESR_ELx_SYS64_ISS_RT(esr); int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; int ret = 0; tagged_address = pt_regs_read_reg(regs, rt); address = untagged_addr(tagged_address); switch (crm) { case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */ __user_cache_maint("dc civac", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CVAC: /* DC CVAC, gets promoted */ __user_cache_maint("dc civac", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CVADP: /* DC CVADP */ __user_cache_maint("sys 3, c7, c13, 1", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CVAP: /* DC CVAP */ __user_cache_maint("sys 3, c7, c12, 1", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CIVAC: /* DC CIVAC */ __user_cache_maint("dc civac", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_IC_IVAU: /* IC IVAU */ __user_cache_maint("ic ivau", address, ret); break; default: force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } if (ret) arm64_notify_segfault(tagged_address); else arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } static void ctr_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = ESR_ELx_SYS64_ISS_RT(esr); unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); if (cpus_have_final_cap(ARM64_WORKAROUND_1542419)) { /* Hide DIC so that we can trap the unnecessary maintenance...*/ val &= ~BIT(CTR_EL0_DIC_SHIFT); /* ... and fake IminLine to reduce the number of traps. */ val &= ~CTR_EL0_IminLine_MASK; val |= (PAGE_SHIFT - 2) & CTR_EL0_IminLine_MASK; } pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } static void cntvct_read_handler(unsigned long esr, struct pt_regs *regs) { if (test_thread_flag(TIF_TSC_SIGSEGV)) { force_sig(SIGSEGV); } else { int rt = ESR_ELx_SYS64_ISS_RT(esr); pt_regs_write_reg(regs, rt, arch_timer_read_counter()); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } } static void cntfrq_read_handler(unsigned long esr, struct pt_regs *regs) { if (test_thread_flag(TIF_TSC_SIGSEGV)) { force_sig(SIGSEGV); } else { int rt = ESR_ELx_SYS64_ISS_RT(esr); pt_regs_write_reg(regs, rt, arch_timer_get_rate()); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } } static void mrs_handler(unsigned long esr, struct pt_regs *regs) { u32 sysreg, rt; rt = ESR_ELx_SYS64_ISS_RT(esr); sysreg = esr_sys64_to_sysreg(esr); if (do_emulate_mrs(regs, sysreg, rt) != 0) force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } static void wfi_handler(unsigned long esr, struct pt_regs *regs) { arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } struct sys64_hook { unsigned long esr_mask; unsigned long esr_val; void (*handler)(unsigned long esr, struct pt_regs *regs); }; static const struct sys64_hook sys64_hooks[] = { { .esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL, .handler = user_cache_maint_handler, }, { /* Trap read access to CTR_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ, .handler = ctr_read_handler, }, { /* Trap read access to CNTVCT_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCT, .handler = cntvct_read_handler, }, { /* Trap read access to CNTVCTSS_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCTSS, .handler = cntvct_read_handler, }, { /* Trap read access to CNTFRQ_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTFRQ, .handler = cntfrq_read_handler, }, { /* Trap read access to CPUID registers */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL, .handler = mrs_handler, }, { /* Trap WFI instructions executed in userspace */ .esr_mask = ESR_ELx_WFx_MASK, .esr_val = ESR_ELx_WFx_WFI_VAL, .handler = wfi_handler, }, {}, }; #ifdef CONFIG_COMPAT static bool cp15_cond_valid(unsigned long esr, struct pt_regs *regs) { int cond; /* Only a T32 instruction can trap without CV being set */ if (!(esr & ESR_ELx_CV)) { u32 it; it = compat_get_it_state(regs); if (!it) return true; cond = it >> 4; } else { cond = (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT; } return aarch32_opcode_cond_checks[cond](regs->pstate); } static void compat_cntfrq_read_handler(unsigned long esr, struct pt_regs *regs) { int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT; pt_regs_write_reg(regs, reg, arch_timer_get_rate()); arm64_skip_faulting_instruction(regs, 4); } static const struct sys64_hook cp15_32_hooks[] = { { .esr_mask = ESR_ELx_CP15_32_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_32_ISS_SYS_CNTFRQ, .handler = compat_cntfrq_read_handler, }, {}, }; static void compat_cntvct_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT; int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT; u64 val = arch_timer_read_counter(); pt_regs_write_reg(regs, rt, lower_32_bits(val)); pt_regs_write_reg(regs, rt2, upper_32_bits(val)); arm64_skip_faulting_instruction(regs, 4); } static const struct sys64_hook cp15_64_hooks[] = { { .esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCT, .handler = compat_cntvct_read_handler, }, { .esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCTSS, .handler = compat_cntvct_read_handler, }, {}, }; void do_el0_cp15(unsigned long esr, struct pt_regs *regs) { const struct sys64_hook *hook, *hook_base; if (!cp15_cond_valid(esr, regs)) { /* * There is no T16 variant of a CP access, so we * always advance PC by 4 bytes. */ arm64_skip_faulting_instruction(regs, 4); return; } switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_CP15_32: hook_base = cp15_32_hooks; break; case ESR_ELx_EC_CP15_64: hook_base = cp15_64_hooks; break; default: do_el0_undef(regs, esr); return; } for (hook = hook_base; hook->handler; hook++) if ((hook->esr_mask & esr) == hook->esr_val) { hook->handler(esr, regs); return; } /* * New cp15 instructions may previously have been undefined at * EL0. Fall back to our usual undefined instruction handler * so that we handle these consistently. */ do_el0_undef(regs, esr); } #endif void do_el0_sys(unsigned long esr, struct pt_regs *regs) { const struct sys64_hook *hook; for (hook = sys64_hooks; hook->handler; hook++) if ((hook->esr_mask & esr) == hook->esr_val) { hook->handler(esr, regs); return; } /* * New SYS instructions may previously have been undefined at EL0. Fall * back to our usual undefined instruction handler so that we handle * these consistently. */ do_el0_undef(regs, esr); } static const char *esr_class_str[] = { [0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC", [ESR_ELx_EC_UNKNOWN] = "Unknown/Uncategorized", [ESR_ELx_EC_WFx] = "WFI/WFE", [ESR_ELx_EC_CP15_32] = "CP15 MCR/MRC", [ESR_ELx_EC_CP15_64] = "CP15 MCRR/MRRC", [ESR_ELx_EC_CP14_MR] = "CP14 MCR/MRC", [ESR_ELx_EC_CP14_LS] = "CP14 LDC/STC", [ESR_ELx_EC_FP_ASIMD] = "ASIMD", [ESR_ELx_EC_CP10_ID] = "CP10 MRC/VMRS", [ESR_ELx_EC_PAC] = "PAC", [ESR_ELx_EC_CP14_64] = "CP14 MCRR/MRRC", [ESR_ELx_EC_BTI] = "BTI", [ESR_ELx_EC_ILL] = "PSTATE.IL", [ESR_ELx_EC_SVC32] = "SVC (AArch32)", [ESR_ELx_EC_HVC32] = "HVC (AArch32)", [ESR_ELx_EC_SMC32] = "SMC (AArch32)", [ESR_ELx_EC_SVC64] = "SVC (AArch64)", [ESR_ELx_EC_HVC64] = "HVC (AArch64)", [ESR_ELx_EC_SMC64] = "SMC (AArch64)", [ESR_ELx_EC_SYS64] = "MSR/MRS (AArch64)", [ESR_ELx_EC_SVE] = "SVE", [ESR_ELx_EC_ERET] = "ERET/ERETAA/ERETAB", [ESR_ELx_EC_FPAC] = "FPAC", [ESR_ELx_EC_SME] = "SME", [ESR_ELx_EC_IMP_DEF] = "EL3 IMP DEF", [ESR_ELx_EC_IABT_LOW] = "IABT (lower EL)", [ESR_ELx_EC_IABT_CUR] = "IABT (current EL)", [ESR_ELx_EC_PC_ALIGN] = "PC Alignment", [ESR_ELx_EC_DABT_LOW] = "DABT (lower EL)", [ESR_ELx_EC_DABT_CUR] = "DABT (current EL)", [ESR_ELx_EC_SP_ALIGN] = "SP Alignment", [ESR_ELx_EC_MOPS] = "MOPS", [ESR_ELx_EC_FP_EXC32] = "FP (AArch32)", [ESR_ELx_EC_FP_EXC64] = "FP (AArch64)", [ESR_ELx_EC_GCS] = "Guarded Control Stack", [ESR_ELx_EC_SERROR] = "SError", [ESR_ELx_EC_BREAKPT_LOW] = "Breakpoint (lower EL)", [ESR_ELx_EC_BREAKPT_CUR] = "Breakpoint (current EL)", [ESR_ELx_EC_SOFTSTP_LOW] = "Software Step (lower EL)", [ESR_ELx_EC_SOFTSTP_CUR] = "Software Step (current EL)", [ESR_ELx_EC_WATCHPT_LOW] = "Watchpoint (lower EL)", [ESR_ELx_EC_WATCHPT_CUR] = "Watchpoint (current EL)", [ESR_ELx_EC_BKPT32] = "BKPT (AArch32)", [ESR_ELx_EC_VECTOR32] = "Vector catch (AArch32)", [ESR_ELx_EC_BRK64] = "BRK (AArch64)", }; const char *esr_get_class_string(unsigned long esr) { return esr_class_str[ESR_ELx_EC(esr)]; } /* * bad_el0_sync handles unexpected, but potentially recoverable synchronous * exceptions taken from EL0. */ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr) { unsigned long pc = instruction_pointer(regs); current->thread.fault_address = 0; current->thread.fault_code = esr; arm64_force_sig_fault(SIGILL, ILL_ILLOPC, pc, "Bad EL0 synchronous exception"); } #ifdef CONFIG_VMAP_STACK DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); console_verbose(); pr_emerg("Insufficient stack space to handle exception!"); pr_emerg("ESR: 0x%016lx -- %s\n", esr, esr_get_class_string(esr)); pr_emerg("FAR: 0x%016lx\n", far); pr_emerg("Task stack: [0x%016lx..0x%016lx]\n", tsk_stk, tsk_stk + THREAD_SIZE); pr_emerg("IRQ stack: [0x%016lx..0x%016lx]\n", irq_stk, irq_stk + IRQ_STACK_SIZE); pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n", ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE); __show_regs(regs); /* * We use nmi_panic to limit the potential for recusive overflows, and * to get a better stack trace. */ nmi_panic(NULL, "kernel stack overflow"); cpu_park_loop(); } #endif void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr) { console_verbose(); pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n", smp_processor_id(), esr, esr_get_class_string(esr)); if (regs) __show_regs(regs); nmi_panic(regs, "Asynchronous SError Interrupt"); cpu_park_loop(); } bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr) { unsigned long aet = arm64_ras_serror_get_severity(esr); switch (aet) { case ESR_ELx_AET_CE: /* corrected error */ case ESR_ELx_AET_UEO: /* restartable, not yet consumed */ /* * The CPU can make progress. We may take UEO again as * a more severe error. */ return false; case ESR_ELx_AET_UEU: /* Uncorrected Unrecoverable */ case ESR_ELx_AET_UER: /* Uncorrected Recoverable */ /* * The CPU can't make progress. The exception may have * been imprecise. * * Neoverse-N1 #1349291 means a non-KVM SError reported as * Unrecoverable should be treated as Uncontainable. We * call arm64_serror_panic() in both cases. */ return true; case ESR_ELx_AET_UC: /* Uncontainable or Uncategorized error */ default: /* Error has been silently propagated */ arm64_serror_panic(regs, esr); } } void do_serror(struct pt_regs *regs, unsigned long esr) { /* non-RAS errors are not containable */ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr)) arm64_serror_panic(regs, esr); } /* GENERIC_BUG traps */ #ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long addr) { /* * bug_handler() only called for BRK #BUG_BRK_IMM. * So the answer is trivial -- any spurious instances with no * bug table entry will be rejected by report_bug() and passed * back to the debug-monitors code and handled as a fatal * unexpected debug exception. */ return 1; } #endif static int bug_handler(struct pt_regs *regs, unsigned long esr) { switch (report_bug(regs->pc, regs)) { case BUG_TRAP_TYPE_BUG: die("Oops - BUG", regs, esr); break; case BUG_TRAP_TYPE_WARN: break; default: /* unknown/unrecognised bug trap type */ return DBG_HOOK_ERROR; } /* If thread survives, skip over the BUG instruction and continue: */ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); return DBG_HOOK_HANDLED; } static struct break_hook bug_break_hook = { .fn = bug_handler, .imm = BUG_BRK_IMM, }; #ifdef CONFIG_CFI_CLANG static int cfi_handler(struct pt_regs *regs, unsigned long esr) { unsigned long target; u32 type; target = pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TARGET, esr)); type = (u32)pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TYPE, esr)); switch (report_cfi_failure(regs, regs->pc, &target, type)) { case BUG_TRAP_TYPE_BUG: die("Oops - CFI", regs, esr); break; case BUG_TRAP_TYPE_WARN: break; default: return DBG_HOOK_ERROR; } arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); return DBG_HOOK_HANDLED; } static struct break_hook cfi_break_hook = { .fn = cfi_handler, .imm = CFI_BRK_IMM_BASE, .mask = CFI_BRK_IMM_MASK, }; #endif /* CONFIG_CFI_CLANG */ static int reserved_fault_handler(struct pt_regs *regs, unsigned long esr) { pr_err("%s generated an invalid instruction at %pS!\n", "Kernel text patching", (void *)instruction_pointer(regs)); /* We cannot handle this */ return DBG_HOOK_ERROR; } static struct break_hook fault_break_hook = { .fn = reserved_fault_handler, .imm = FAULT_BRK_IMM, }; #ifdef CONFIG_KASAN_SW_TAGS #define KASAN_ESR_RECOVER 0x20 #define KASAN_ESR_WRITE 0x10 #define KASAN_ESR_SIZE_MASK 0x0f #define KASAN_ESR_SIZE(esr) (1 << ((esr) & KASAN_ESR_SIZE_MASK)) static int kasan_handler(struct pt_regs *regs, unsigned long esr) { bool recover = esr & KASAN_ESR_RECOVER; bool write = esr & KASAN_ESR_WRITE; size_t size = KASAN_ESR_SIZE(esr); void *addr = (void *)regs->regs[0]; u64 pc = regs->pc; kasan_report(addr, size, write, pc); /* * The instrumentation allows to control whether we can proceed after * a crash was detected. This is done by passing the -recover flag to * the compiler. Disabling recovery allows to generate more compact * code. * * Unfortunately disabling recovery doesn't work for the kernel right * now. KASAN reporting is disabled in some contexts (for example when * the allocator accesses slab object metadata; this is controlled by * current->kasan_depth). All these accesses are detected by the tool, * even though the reports for them are not printed. * * This is something that might be fixed at some point in the future. */ if (!recover) die("Oops - KASAN", regs, esr); /* If thread survives, skip over the brk instruction and continue: */ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); return DBG_HOOK_HANDLED; } static struct break_hook kasan_break_hook = { .fn = kasan_handler, .imm = KASAN_BRK_IMM, .mask = KASAN_BRK_MASK, }; #endif #ifdef CONFIG_UBSAN_TRAP static int ubsan_handler(struct pt_regs *regs, unsigned long esr) { die(report_ubsan_failure(regs, esr & UBSAN_BRK_MASK), regs, esr); return DBG_HOOK_HANDLED; } static struct break_hook ubsan_break_hook = { .fn = ubsan_handler, .imm = UBSAN_BRK_IMM, .mask = UBSAN_BRK_MASK, }; #endif /* * Initial handler for AArch64 BRK exceptions * This handler only used until debug_traps_init(). */ int __init early_brk64(unsigned long addr, unsigned long esr, struct pt_regs *regs) { #ifdef CONFIG_CFI_CLANG if (esr_is_cfi_brk(esr)) return cfi_handler(regs, esr) != DBG_HOOK_HANDLED; #endif #ifdef CONFIG_KASAN_SW_TAGS if ((esr_brk_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM) return kasan_handler(regs, esr) != DBG_HOOK_HANDLED; #endif #ifdef CONFIG_UBSAN_TRAP if ((esr_brk_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM) return ubsan_handler(regs, esr) != DBG_HOOK_HANDLED; #endif return bug_handler(regs, esr) != DBG_HOOK_HANDLED; } void __init trap_init(void) { register_kernel_break_hook(&bug_break_hook); #ifdef CONFIG_CFI_CLANG register_kernel_break_hook(&cfi_break_hook); #endif register_kernel_break_hook(&fault_break_hook); #ifdef CONFIG_KASAN_SW_TAGS register_kernel_break_hook(&kasan_break_hook); #endif #ifdef CONFIG_UBSAN_TRAP register_kernel_break_hook(&ubsan_break_hook); #endif debug_traps_init(); } |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A security context is a set of security attributes * associated with each subject and object controlled * by the security policy. Security contexts are * externally represented as variable-length strings * that can be interpreted by a user or application * with an understanding of the security policy. * Internally, the security server uses a simple * structure. This structure is private to the * security server and can be changed without affecting * clients of the security server. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_CONTEXT_H_ #define _SS_CONTEXT_H_ #include "ebitmap.h" #include "mls_types.h" #include "security.h" /* * A security context consists of an authenticated user * identity, a role, a type and a MLS range. */ struct context { u32 user; u32 role; u32 type; u32 len; /* length of string in bytes */ struct mls_range range; char *str; /* string representation if context cannot be mapped. */ }; static inline void mls_context_init(struct context *c) { memset(&c->range, 0, sizeof(c->range)); } static inline int mls_context_cpy(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the low level of 'src'. */ static inline int mls_context_cpy_low(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the high level of 'src'. */ static inline int mls_context_cpy_high(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[1].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } static inline int mls_context_glblub(struct context *dst, const struct context *c1, const struct context *c2) { struct mls_range *dr = &dst->range; const struct mls_range *r1 = &c1->range, *r2 = &c2->range; int rc = 0; if (r1->level[1].sens < r2->level[0].sens || r2->level[1].sens < r1->level[0].sens) /* These ranges have no common sensitivities */ return -EINVAL; /* Take the greatest of the low */ dr->level[0].sens = max(r1->level[0].sens, r2->level[0].sens); /* Take the least of the high */ dr->level[1].sens = min(r1->level[1].sens, r2->level[1].sens); rc = ebitmap_and(&dr->level[0].cat, &r1->level[0].cat, &r2->level[0].cat); if (rc) goto out; rc = ebitmap_and(&dr->level[1].cat, &r1->level[1].cat, &r2->level[1].cat); if (rc) goto out; out: return rc; } static inline int mls_context_cmp(const struct context *c1, const struct context *c2) { return ((c1->range.level[0].sens == c2->range.level[0].sens) && ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) && (c1->range.level[1].sens == c2->range.level[1].sens) && ebitmap_cmp(&c1->range.level[1].cat, &c2->range.level[1].cat)); } static inline void mls_context_destroy(struct context *c) { ebitmap_destroy(&c->range.level[0].cat); ebitmap_destroy(&c->range.level[1].cat); mls_context_init(c); } static inline void context_init(struct context *c) { memset(c, 0, sizeof(*c)); } static inline int context_cpy(struct context *dst, const struct context *src) { int rc; dst->user = src->user; dst->role = src->role; dst->type = src->type; if (src->str) { dst->str = kstrdup(src->str, GFP_ATOMIC); if (!dst->str) return -ENOMEM; dst->len = src->len; } else { dst->str = NULL; dst->len = 0; } rc = mls_context_cpy(dst, src); if (rc) { kfree(dst->str); dst->str = NULL; dst->len = 0; return rc; } return 0; } static inline void context_destroy(struct context *c) { c->user = c->role = c->type = 0; kfree(c->str); c->str = NULL; c->len = 0; mls_context_destroy(c); } static inline int context_cmp(const struct context *c1, const struct context *c2) { if (c1->len && c2->len) return (c1->len == c2->len && !strcmp(c1->str, c2->str)); if (c1->len || c2->len) return 0; return ((c1->user == c2->user) && (c1->role == c2->role) && (c1->type == c2->type) && mls_context_cmp(c1, c2)); } u32 context_compute_hash(const struct context *c); #endif /* _SS_CONTEXT_H_ */ |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILEATTR_H #define _LINUX_FILEATTR_H /* Flags shared betwen flags/xflags */ #define FS_COMMON_FL \ (FS_SYNC_FL | FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NODUMP_FL | FS_NOATIME_FL | FS_DAX_FL | \ FS_PROJINHERIT_FL) #define FS_XFLAG_COMMON \ (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND | \ FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \ FS_XFLAG_PROJINHERIT) /* * Merged interface for miscellaneous file attributes. 'flags' originates from * ext* and 'fsx_flags' from xfs. There's some overlap between the two, which * is handled by the VFS helpers, so filesystems are free to implement just one * or both of these sub-interfaces. */ struct fileattr { u32 flags; /* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */ /* struct fsxattr: */ u32 fsx_xflags; /* xflags field value (get/set) */ u32 fsx_extsize; /* extsize field value (get/set)*/ u32 fsx_nextents; /* nextents field value (get) */ u32 fsx_projid; /* project identifier (get/set) */ u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ /* selectors: */ bool flags_valid:1; bool fsx_valid:1; }; int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa); void fileattr_fill_xflags(struct fileattr *fa, u32 xflags); void fileattr_fill_flags(struct fileattr *fa, u32 flags); /** * fileattr_has_fsx - check for extended flags/attributes * @fa: fileattr pointer * * Return: true if any attributes are present that are not represented in * ->flags. */ static inline bool fileattr_has_fsx(const struct fileattr *fa) { return fa->fsx_valid && ((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 || fa->fsx_projid != 0 || fa->fsx_cowextsize != 0); } int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); #endif /* _LINUX_FILEATTR_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_device.c - IPsec device offloading code. * * Copyright (c) 2015 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/errno.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/gso.h> #include <net/xfrm.h> #include <linux/notifier.h> #ifdef CONFIG_XFRM_OFFLOAD static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); pskb_pull(skb, skb->mac_len + x->props.header_len); } static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); int phlen = 0; if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); if (x->sel.family != AF_INET6) { phlen = IPV4_BEET_PHMAXLEN; if (x->outer_mode.family == AF_INET6) phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr); } pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen)); } /* Adjust pointers into the packet when IPsec is done at layer2 */ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) { switch (x->outer_mode.encap) { case XFRM_MODE_TUNNEL: if (x->outer_mode.family == AF_INET) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_TRANSPORT: if (x->outer_mode.family == AF_INET) return __xfrm_transport_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_transport_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_BEET: if (x->outer_mode.family == AF_INET) return __xfrm_mode_beet_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_beet_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: break; } } static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) { struct xfrm_offload *xo = xfrm_offload(skb); __u32 seq = xo->seq.low; seq += skb_shinfo(skb)->gso_segs; if (unlikely(seq < xo->seq.low)) return true; return false; } struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; unsigned long flags; struct xfrm_state *x; struct softnet_data *sd; struct sk_buff *skb2, *nskb, *pskb = NULL; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct net_device *dev = skb->dev; struct sec_path *sp; if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN) return skb; /* The packet was sent to HW IPsec packet offload engine, * but to wrong device. Drop the packet, so it won't skip * XFRM stack. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } /* This skb was already validated on the upper/virtual dev */ if ((x->xso.dev != dev) && (x->xso.real_dev == dev)) return skb; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); err = !skb_queue_empty(&sd->xfrm_backlog); local_irq_restore(flags); if (err) { *again = true; return skb; } if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP); segs = skb_gso_segment(skb, esp_features); if (IS_ERR(segs)) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } else { consume_skb(skb); skb = segs; } } if (!skb->next) { esp_features |= skb->dev->gso_partial_features; xfrm_outer_mode_prep(x, skb); xo->flags |= XFRM_DEV_RESUME; err = x->type_offload->xmit(x, skb, esp_features); if (err) { if (err == -EINPROGRESS) return NULL; XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); return NULL; } skb_push(skb, skb->data - skb_mac_header(skb)); return skb; } skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; xfrm_outer_mode_prep(x, skb2); err = x->type_offload->xmit(x, skb2, esp_features); if (!err) { skb2->next = nskb; } else if (err != -EINPROGRESS) { XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); skb2->next = nskb; kfree_skb_list(skb2); return NULL; } else { if (skb == skb2) skb = nskb; else pskb->next = nskb; continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); pskb = skb2; } return skb; } EXPORT_SYMBOL_GPL(validate_xmit_xfrm); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { int err; struct dst_entry *dst; struct net_device *dev; struct xfrm_dev_offload *xso = &x->xso; xfrm_address_t *saddr; xfrm_address_t *daddr; bool is_packet_offload; if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); return -EINVAL; } if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) { NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); return -EINVAL; } is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support TFC padding. */ if (x->tfcpad) { NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { struct xfrm_dst_lookup_params params; if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { saddr = &x->props.saddr; daddr = &x->id.daddr; } else { saddr = &x->id.daddr; daddr = &x->props.saddr; } memset(¶ms, 0, sizeof(params)); params.net = net; params.saddr = saddr; params.daddr = daddr; params.mark = xfrm_smark_get(0, x); dst = __xfrm_dst_lookup(x->props.family, ¶ms); if (IS_ERR(dst)) return (is_packet_offload) ? -EINVAL : 0; dev = dst->dev; dev_hold(dev); dst_release(dst); } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { xso->dev = NULL; dev_put(dev); return (is_packet_offload) ? -EINVAL : 0; } if (!is_packet_offload && x->props.flags & XFRM_STATE_ESN && !dev->xfrmdev_ops->xdo_dev_state_advance_esn) { NL_SET_ERR_MSG(extack, "Device doesn't support offload with ESN"); xso->dev = NULL; dev_put(dev); return -EINVAL; } xso->dev = dev; netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); xso->real_dev = dev; if (xuo->flags & XFRM_OFFLOAD_INBOUND) xso->dir = XFRM_DEV_OFFLOAD_IN; else xso->dir = XFRM_DEV_OFFLOAD_OUT; if (is_packet_offload) xso->type = XFRM_DEV_OFFLOAD_PACKET; else xso->type = XFRM_DEV_OFFLOAD_CRYPTO; err = dev->xfrmdev_ops->xdo_dev_state_add(x, extack); if (err) { xso->dev = NULL; xso->dir = 0; xso->real_dev = NULL; netdev_put(dev, &xso->dev_tracker); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; /* User explicitly requested packet offload mode and configured * policy in addition to the XFRM state. So be civil to users, * and return an error instead of taking fallback path. */ if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; } } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_state_add); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { struct xfrm_dev_offload *xdo = &xp->xdo; struct net_device *dev; int err; if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) { /* We support only packet offload mode and it means * that user must set XFRM_OFFLOAD_PACKET bit. */ NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) return -EINVAL; if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) { xdo->dev = NULL; dev_put(dev); NL_SET_ERR_MSG(extack, "Policy offload is not supported"); return -EINVAL; } xdo->dev = dev; netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); xdo->real_dev = dev; xdo->type = XFRM_DEV_OFFLOAD_PACKET; switch (dir) { case XFRM_POLICY_IN: xdo->dir = XFRM_DEV_OFFLOAD_IN; break; case XFRM_POLICY_OUT: xdo->dir = XFRM_DEV_OFFLOAD_OUT; break; case XFRM_POLICY_FWD: xdo->dir = XFRM_DEV_OFFLOAD_FWD; break; default: xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack); if (err) { xdo->dev = NULL; xdo->real_dev = NULL; xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy"); return err; } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_policy_add); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { int mtu; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; if (!x->type_offload || (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || ((!dev || (dev == xfrm_dst_path(dst)->dev)) && !xdst->child->xfrm)) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } return false; ok: if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_offload_ok) return x->xso.dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x); return true; } EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); void xfrm_dev_resume(struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret = NETDEV_TX_BUSY; struct netdev_queue *txq; struct softnet_data *sd; unsigned long flags; rcu_read_lock(); txq = netdev_core_pick_tx(dev, skb, NULL); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); if (!dev_xmit_complete(ret)) { local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); skb_queue_tail(&sd->xfrm_backlog, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(xfrm_dev_resume); void xfrm_dev_backlog(struct softnet_data *sd) { struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog; struct sk_buff_head list; struct sk_buff *skb; if (skb_queue_empty(xfrm_backlog)) return; __skb_queue_head_init(&list); spin_lock(&xfrm_backlog->lock); skb_queue_splice_init(xfrm_backlog, &list); spin_unlock(&xfrm_backlog->lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); xfrm_dev_resume(skb); } } #endif static int xfrm_api_check(struct net_device *dev) { #ifdef CONFIG_XFRM_OFFLOAD if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && !(dev->features & NETIF_F_HW_ESP)) return NOTIFY_BAD; if ((dev->features & NETIF_F_HW_ESP) && (!(dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_add && dev->xfrmdev_ops->xdo_dev_state_delete))) return NOTIFY_BAD; #else if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM)) return NOTIFY_BAD; #endif return NOTIFY_DONE; } static int xfrm_dev_down(struct net_device *dev) { if (dev->features & NETIF_F_HW_ESP) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); } return NOTIFY_DONE; } static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: return xfrm_api_check(dev); case NETDEV_FEAT_CHANGE: return xfrm_api_check(dev); case NETDEV_DOWN: case NETDEV_UNREGISTER: return xfrm_dev_down(dev); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { .notifier_call = xfrm_dev_event, }; void __init xfrm_dev_init(void) { register_netdevice_notifier(&xfrm_dev_notifier); } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* raw.c - Raw sockets for protocol family CAN * * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */ #include <linux/can/skb.h> #include <linux/can/raw.h> #include <net/sock.h> #include <net/net_namespace.h> MODULE_DESCRIPTION("PF_CAN raw protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); MODULE_ALIAS("can-proto-1"); #define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) #define MASK_ALL 0 /* A raw socket has a list of can_filters attached to it, each receiving * the CAN frames matching that filter. If the filter list is empty, * no CAN frames will be received by the socket. The default after * opening the socket, is to have one filter which receives all frames. * The filter list is allocated dynamically with the exception of the * list containing only one item. This common case is optimized by * storing the single filter in dfilter, to avoid using dynamic memory. */ struct uniqframe { int skbcnt; const struct sk_buff *skb; unsigned int join_rx_count; }; struct raw_sock { struct sock sk; int bound; int ifindex; struct net_device *dev; netdevice_tracker dev_tracker; struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; int xl_frames; struct can_raw_vcid_options raw_vcid_opts; canid_t tx_vcid_shifted; canid_t rx_vcid_shifted; canid_t rx_vcid_mask_shifted; int join_filters; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ struct can_filter *filter; /* pointer to filter(s) */ can_err_mask_t err_mask; struct uniqframe __percpu *uniq; }; static LIST_HEAD(raw_notifier_list); static DEFINE_SPINLOCK(raw_notifier_lock); static struct raw_sock *raw_busy_notifier; /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. */ static inline unsigned int *raw_flags(struct sk_buff *skb) { sock_skb_cb_check_size(sizeof(struct sockaddr_can) + sizeof(unsigned int)); /* return pointer after struct sockaddr_can */ return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); } static inline struct raw_sock *raw_sk(const struct sock *sk) { return (struct raw_sock *)sk; } static void raw_rcv(struct sk_buff *oskb, void *data) { struct sock *sk = (struct sock *)data; struct raw_sock *ro = raw_sk(sk); struct sockaddr_can *addr; struct sk_buff *skb; unsigned int *pflags; /* check the received tx sock reference */ if (!ro->recv_own_msgs && oskb->sk == sk) return; /* make sure to not pass oversized frames to the socket */ if (!ro->fd_frames && can_is_canfd_skb(oskb)) return; if (can_is_canxl_skb(oskb)) { struct canxl_frame *cxl = (struct canxl_frame *)oskb->data; /* make sure to not pass oversized frames to the socket */ if (!ro->xl_frames) return; /* filter CAN XL VCID content */ if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_RX_FILTER) { /* apply VCID filter if user enabled the filter */ if ((cxl->prio & ro->rx_vcid_mask_shifted) != (ro->rx_vcid_shifted & ro->rx_vcid_mask_shifted)) return; } else { /* no filter => do not forward VCID tagged frames */ if (cxl->prio & CANXL_VCID_MASK) return; } } /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) { if (!ro->join_filters) return; this_cpu_inc(ro->uniq->join_rx_count); /* drop frame until all enabled filters matched */ if (this_cpu_ptr(ro->uniq)->join_rx_count < ro->count) return; } else { this_cpu_ptr(ro->uniq)->skb = oskb; this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt; this_cpu_ptr(ro->uniq)->join_rx_count = 1; /* drop first frame to check all enabled filters? */ if (ro->join_filters && ro->count > 1) return; } /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) return; /* Put the datagram to the queue so that raw_recvmsg() can get * it from there. We need to pass the interface index to * raw_recvmsg(). We pass a whole struct sockaddr_can in * skb->cb containing the interface index. */ sock_skb_cb_check_size(sizeof(struct sockaddr_can)); addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; /* add CAN specific message flags for raw_recvmsg() */ pflags = raw_flags(skb); *pflags = 0; if (oskb->sk) *pflags |= MSG_DONTROUTE; if (oskb->sk == sk) *pflags |= MSG_CONFIRM; if (sock_queue_rcv_skb(sk, skb) < 0) kfree_skb(skb); } static int raw_enable_filters(struct net *net, struct net_device *dev, struct sock *sk, struct can_filter *filter, int count) { int err = 0; int i; for (i = 0; i < count; i++) { err = can_rx_register(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk, "raw", sk); if (err) { /* clean up successfully registered filters */ while (--i >= 0) can_rx_unregister(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk); break; } } return err; } static int raw_enable_errfilter(struct net *net, struct net_device *dev, struct sock *sk, can_err_mask_t err_mask) { int err = 0; if (err_mask) err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk, "raw", sk); return err; } static void raw_disable_filters(struct net *net, struct net_device *dev, struct sock *sk, struct can_filter *filter, int count) { int i; for (i = 0; i < count; i++) can_rx_unregister(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk); } static inline void raw_disable_errfilter(struct net *net, struct net_device *dev, struct sock *sk, can_err_mask_t err_mask) { if (err_mask) can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk); } static inline void raw_disable_allfilters(struct net *net, struct net_device *dev, struct sock *sk) { struct raw_sock *ro = raw_sk(sk); raw_disable_filters(net, dev, sk, ro->filter, ro->count); raw_disable_errfilter(net, dev, sk, ro->err_mask); } static int raw_enable_allfilters(struct net *net, struct net_device *dev, struct sock *sk) { struct raw_sock *ro = raw_sk(sk); int err; err = raw_enable_filters(net, dev, sk, ro->filter, ro->count); if (!err) { err = raw_enable_errfilter(net, dev, sk, ro->err_mask); if (err) raw_disable_filters(net, dev, sk, ro->filter, ro->count); } return err; } static void raw_notify(struct raw_sock *ro, unsigned long msg, struct net_device *dev) { struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) return; if (ro->dev != dev) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); netdev_put(dev, &ro->dev_tracker); } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; ro->dev = NULL; ro->count = 0; release_sock(sk); sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; } } static int raw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&raw_notifier_lock); list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { spin_unlock(&raw_notifier_lock); raw_notify(raw_busy_notifier, msg, dev); spin_lock(&raw_notifier_lock); } raw_busy_notifier = NULL; spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } static int raw_init(struct sock *sk) { struct raw_sock *ro = raw_sk(sk); ro->bound = 0; ro->ifindex = 0; ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; ro->dfilter.can_mask = MASK_ALL; ro->filter = &ro->dfilter; ro->count = 1; /* set default loopback behaviour */ ro->loopback = 1; ro->recv_own_msgs = 0; ro->fd_frames = 0; ro->xl_frames = 0; ro->join_filters = 0; /* alloc_percpu provides zero'ed memory */ ro->uniq = alloc_percpu(struct uniqframe); if (unlikely(!ro->uniq)) return -ENOMEM; /* set notifier */ spin_lock(&raw_notifier_lock); list_add_tail(&ro->notifier, &raw_notifier_list); spin_unlock(&raw_notifier_lock); return 0; } static int raw_release(struct socket *sock) { struct sock *sk = sock->sk; struct raw_sock *ro; if (!sk) return 0; ro = raw_sk(sk); spin_lock(&raw_notifier_lock); while (raw_busy_notifier == ro) { spin_unlock(&raw_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&raw_notifier_lock); } list_del(&ro->notifier); spin_unlock(&raw_notifier_lock); rtnl_lock(); lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); sock_orphan(sk); sock->sk = NULL; release_sock(sk); rtnl_unlock(); sock_put(sk); return 0; } static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; if (len < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { err = -ENODEV; goto out_put_dev; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; ifindex = dev->ifindex; /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); if (err) goto out_put_dev; } else { ifindex = 0; /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), NULL, sk); } if (!err) { if (ro->bound) { /* unregister old filters */ if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); /* drop reference to old ro->dev */ netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } ro->ifindex = ifindex; ro->bound = 1; /* bind() ok -> hold a reference for new ro->dev */ ro->dev = dev; if (ro->dev) netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL); } out_put_dev: /* remove potential reference from dev_get_by_index() */ dev_put(dev); out: release_sock(sk); rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } return err; } static int raw_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); if (peer) return -EOPNOTSUPP; memset(addr, 0, RAW_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; return RAW_MIN_NAMELEN; } static int raw_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct can_filter *filter = NULL; /* dyn. alloc'ed filters */ struct can_filter sfilter; /* single filter */ struct net_device *dev = NULL; can_err_mask_t err_mask = 0; int fd_frames; int count = 0; int err = 0; if (level != SOL_CAN_RAW) return -EINVAL; switch (optname) { case CAN_RAW_FILTER: if (optlen % sizeof(struct can_filter) != 0) return -EINVAL; if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter)) return -EINVAL; count = optlen / sizeof(struct can_filter); if (count > 1) { /* filter does not fit into dfilter => alloc space */ filter = memdup_sockptr(optval, optlen); if (IS_ERR(filter)) return PTR_ERR(filter); } else if (count == 1) { if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter))) return -EFAULT; } rtnl_lock(); lock_sock(sk); dev = ro->dev; if (ro->bound && dev) { if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; goto out_fil; } } if (ro->bound) { /* (try to) register the new filters */ if (count == 1) err = raw_enable_filters(sock_net(sk), dev, sk, &sfilter, 1); else err = raw_enable_filters(sock_net(sk), dev, sk, filter, count); if (err) { if (count > 1) kfree(filter); goto out_fil; } /* remove old filter registrations */ raw_disable_filters(sock_net(sk), dev, sk, ro->filter, ro->count); } /* remove old filter space */ if (ro->count > 1) kfree(ro->filter); /* link new filters to the socket */ if (count == 1) { /* copy filter data for single filter */ ro->dfilter = sfilter; filter = &ro->dfilter; } ro->filter = filter; ro->count = count; out_fil: release_sock(sk); rtnl_unlock(); break; case CAN_RAW_ERR_FILTER: if (optlen != sizeof(err_mask)) return -EINVAL; if (copy_from_sockptr(&err_mask, optval, optlen)) return -EFAULT; err_mask &= CAN_ERR_MASK; rtnl_lock(); lock_sock(sk); dev = ro->dev; if (ro->bound && dev) { if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } } /* remove current error mask */ if (ro->bound) { /* (try to) register the new err_mask */ err = raw_enable_errfilter(sock_net(sk), dev, sk, err_mask); if (err) goto out_err; /* remove old err_mask registration */ raw_disable_errfilter(sock_net(sk), dev, sk, ro->err_mask); } /* link new err_mask to the socket */ ro->err_mask = err_mask; out_err: release_sock(sk); rtnl_unlock(); break; case CAN_RAW_LOOPBACK: if (optlen != sizeof(ro->loopback)) return -EINVAL; if (copy_from_sockptr(&ro->loopback, optval, optlen)) return -EFAULT; break; case CAN_RAW_RECV_OWN_MSGS: if (optlen != sizeof(ro->recv_own_msgs)) return -EINVAL; if (copy_from_sockptr(&ro->recv_own_msgs, optval, optlen)) return -EFAULT; break; case CAN_RAW_FD_FRAMES: if (optlen != sizeof(fd_frames)) return -EINVAL; if (copy_from_sockptr(&fd_frames, optval, optlen)) return -EFAULT; /* Enabling CAN XL includes CAN FD */ if (ro->xl_frames && !fd_frames) return -EINVAL; ro->fd_frames = fd_frames; break; case CAN_RAW_XL_FRAMES: if (optlen != sizeof(ro->xl_frames)) return -EINVAL; if (copy_from_sockptr(&ro->xl_frames, optval, optlen)) return -EFAULT; /* Enabling CAN XL includes CAN FD */ if (ro->xl_frames) ro->fd_frames = ro->xl_frames; break; case CAN_RAW_XL_VCID_OPTS: if (optlen != sizeof(ro->raw_vcid_opts)) return -EINVAL; if (copy_from_sockptr(&ro->raw_vcid_opts, optval, optlen)) return -EFAULT; /* prepare 32 bit values for handling in hot path */ ro->tx_vcid_shifted = ro->raw_vcid_opts.tx_vcid << CANXL_VCID_OFFSET; ro->rx_vcid_shifted = ro->raw_vcid_opts.rx_vcid << CANXL_VCID_OFFSET; ro->rx_vcid_mask_shifted = ro->raw_vcid_opts.rx_vcid_mask << CANXL_VCID_OFFSET; break; case CAN_RAW_JOIN_FILTERS: if (optlen != sizeof(ro->join_filters)) return -EINVAL; if (copy_from_sockptr(&ro->join_filters, optval, optlen)) return -EFAULT; break; default: return -ENOPROTOOPT; } return err; } static int raw_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); int len; void *val; if (level != SOL_CAN_RAW) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case CAN_RAW_FILTER: { int err = 0; lock_sock(sk); if (ro->count > 0) { int fsize = ro->count * sizeof(struct can_filter); /* user space buffer to small for filter list? */ if (len < fsize) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; if (put_user(fsize, optlen)) err = -EFAULT; } else { if (len > fsize) len = fsize; if (copy_to_user(optval, ro->filter, len)) err = -EFAULT; } } else { len = 0; } release_sock(sk); if (!err) err = put_user(len, optlen); return err; } case CAN_RAW_ERR_FILTER: if (len > sizeof(can_err_mask_t)) len = sizeof(can_err_mask_t); val = &ro->err_mask; break; case CAN_RAW_LOOPBACK: if (len > sizeof(int)) len = sizeof(int); val = &ro->loopback; break; case CAN_RAW_RECV_OWN_MSGS: if (len > sizeof(int)) len = sizeof(int); val = &ro->recv_own_msgs; break; case CAN_RAW_FD_FRAMES: if (len > sizeof(int)) len = sizeof(int); val = &ro->fd_frames; break; case CAN_RAW_XL_FRAMES: if (len > sizeof(int)) len = sizeof(int); val = &ro->xl_frames; break; case CAN_RAW_XL_VCID_OPTS: { int err = 0; /* user space buffer to small for VCID opts? */ if (len < sizeof(ro->raw_vcid_opts)) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; if (put_user(sizeof(ro->raw_vcid_opts), optlen)) err = -EFAULT; } else { if (len > sizeof(ro->raw_vcid_opts)) len = sizeof(ro->raw_vcid_opts); if (copy_to_user(optval, &ro->raw_vcid_opts, len)) err = -EFAULT; } if (!err) err = put_user(len, optlen); return err; } case CAN_RAW_JOIN_FILTERS: if (len > sizeof(int)) len = sizeof(int); val = &ro->join_filters; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, val, len)) return -EFAULT; return 0; } static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) { struct canxl_frame *cxl = (struct canxl_frame *)skb->data; /* sanitize non CAN XL bits */ cxl->prio &= (CANXL_PRIO_MASK | CANXL_VCID_MASK); /* clear VCID in CAN XL frame if pass through is disabled */ if (!(ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_PASS)) cxl->prio &= CANXL_PRIO_MASK; /* set VCID in CAN XL frame if enabled */ if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_SET) { cxl->prio &= CANXL_PRIO_MASK; cxl->prio |= ro->tx_vcid_shifted; } } static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) { /* Classical CAN -> no checks for flags and device capabilities */ if (can_is_can_skb(skb)) return CAN_MTU; /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ if (ro->fd_frames && can_is_canfd_skb(skb) && (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) return CANFD_MTU; /* CAN XL -> needs to be enabled and a CAN XL device */ if (ro->xl_frames && can_is_canxl_skb(skb) && can_is_canxl_dev_mtu(mtu)) return CANXL_MTU; return 0; } static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct sockcm_cookie sockc; struct sk_buff *skb; struct net_device *dev; unsigned int txmtu; int ifindex; int err = -EINVAL; /* check for valid CAN frame sizes */ if (size < CANXL_HDR_SIZE + CANXL_MIN_DLEN || size > CANXL_MTU) return -EINVAL; if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; ifindex = addr->can_ifindex; } else { ifindex = ro->ifindex; } dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) return -ENXIO; skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto put_dev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; /* fill the skb before testing for valid CAN frames */ err = memcpy_from_msg(skb_put(skb, size), msg, size); if (err < 0) goto free_skb; err = -EINVAL; /* check for valid CAN (CC/FD/XL) frame content */ txmtu = raw_check_txframe(ro, skb, dev->mtu); if (!txmtu) goto free_skb; /* only CANXL: clear/forward/set VCID value */ if (txmtu == CANXL_MTU) raw_put_canxl_vcid(ro, skb); sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto free_skb; } skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, &sockc); err = can_send(skb, ro->loopback); dev_put(dev); if (err) goto send_failed; return size; free_skb: kfree_skb(skb); put_dev: dev_put(dev); send_failed: return err; } static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int err = 0; if (flags & MSG_ERRQUEUE) return sock_recv_errqueue(sk, msg, size, SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE); skb = skb_recv_datagram(sk, flags, &err); if (!skb) return err; if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else size = skb->len; err = memcpy_to_msg(msg, skb->data, size); if (err < 0) { skb_free_datagram(sk, skb); return err; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(RAW_MIN_NAMELEN); msg->msg_namelen = RAW_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* assign the flags that have been recorded in raw_rcv() */ msg->msg_flags |= *(raw_flags(skb)); skb_free_datagram(sk, skb); return size; } static int raw_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops raw_ops = { .family = PF_CAN, .release = raw_release, .bind = raw_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, .ioctl = raw_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = raw_setsockopt, .getsockopt = raw_getsockopt, .sendmsg = raw_sendmsg, .recvmsg = raw_recvmsg, .mmap = sock_no_mmap, }; static struct proto raw_proto __read_mostly = { .name = "CAN_RAW", .owner = THIS_MODULE, .obj_size = sizeof(struct raw_sock), .init = raw_init, }; static const struct can_proto raw_can_proto = { .type = SOCK_RAW, .protocol = CAN_RAW, .ops = &raw_ops, .prot = &raw_proto, }; static struct notifier_block canraw_notifier = { .notifier_call = raw_notifier }; static __init int raw_module_init(void) { int err; pr_info("can: raw protocol\n"); err = register_netdevice_notifier(&canraw_notifier); if (err) return err; err = can_proto_register(&raw_can_proto); if (err < 0) { pr_err("can: registration of raw protocol failed\n"); goto register_proto_failed; } return 0; register_proto_failed: unregister_netdevice_notifier(&canraw_notifier); return err; } static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); module_exit(raw_module_exit); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IP multicast routing support for mrouted 3.6/3.8 * * (c) 1995 Alan Cox, <alan@lxorguk.ukuu.org.uk> * Linux Consultancy and Custom Driver Development * * Fixes: * Michael Chastain : Incorrect size of copying. * Alan Cox : Added the cache manager code * Alan Cox : Fixed the clone/copy bug and device race. * Mike McLagan : Routing by source * Malcolm Beattie : Buffer handling fixes. * Alexey Kuznetsov : Double buffer free and other fixes. * SVR Anand : Fixed several multicast bugs and problems. * Alexey Kuznetsov : Status, optimisations and more. * Brad Parker : Better behaviour on mrouted upcall * overflow. * Carlos Picoto : PIMv1 Support * Pavlin Ivanov Radoslavov: PIMv2 Registers must checksum only PIM header * Relax this requirement to work with older peers. */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/cache.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mroute.h> #include <linux/init.h> #include <linux/if_ether.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/route.h> #include <net/icmp.h> #include <net/udp.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> #include <linux/netfilter_ipv4.h> #include <linux/compat.h> #include <linux/export.h> #include <linux/rhashtable.h> #include <net/ip_tunnels.h> #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/rtnh.h> #include <net/inet_dscp.h> #include <linux/nospec.h> struct ipmr_rule { struct fib_rule common; }; struct ipmr_result { struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. * Note that the changes are semaphored via rtnl_lock. */ static DEFINE_SPINLOCK(mrt_lock); static struct net_device *vif_dev_read(const struct vif_device *vif) { return rcu_dereference(vif->dev); } /* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved * entries is changed only in process context and protected * with weak lock mrt_lock. Queue of unresolved entries is protected * with strong spinlock mfc_unres_lock. * * In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __ro_after_init; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc_cache *cache, int local); static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); static void igmpmsg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt); static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES #define ipmr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list, \ lockdep_rtnl_is_held() || \ list_empty(&net->ipv4.mr_tables)) static bool ipmr_can_free_table(struct net *net) { return !check_net(net) || !net_initialized(net); } static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { struct mr_table *ret; if (!mrt) ret = list_entry_rcu(net->ipv4.mr_tables.next, struct mr_table, list); else ret = list_entry_rcu(mrt->list.next, struct mr_table, list); if (&ret->list == &net->ipv4.mr_tables) return NULL; return ret; } static struct mr_table *__ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; ipmr_for_each_table(mrt, net) { if (mrt->id == id) return mrt; } return NULL; } static struct mr_table *ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; rcu_read_lock(); mrt = __ipmr_get_table(net, id); rcu_read_unlock(); return mrt; } static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { int err; struct ipmr_result res; struct fib_lookup_arg arg = { .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi4_to_flowi(flp4)); err = fib_rules_lookup(net->ipv4.mr_rules_ops, flowi4_to_flowi(flp4), 0, &arg); if (err < 0) return err; *mrt = res.mrt; return 0; } static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ipmr_result *res = arg->result; struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } arg->table = fib_rule_get_table(rule, arg); mrt = __ipmr_get_table(rule->fr_net, arg->table); if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; } static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { return 1; } static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { return 0; } static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { return 1; } static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { frh->dst_len = 0; frh->src_len = 0; frh->tos = 0; return 0; } static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = { .family = RTNL_FAMILY_IPMR, .rule_size = sizeof(struct ipmr_rule), .addr_size = sizeof(u32), .action = ipmr_rule_action, .match = ipmr_rule_match, .configure = ipmr_rule_configure, .compare = ipmr_rule_compare, .fill = ipmr_rule_fill, .nlgroup = RTNLGRP_IPV4_RULE, .owner = THIS_MODULE, }; static int __net_init ipmr_rules_init(struct net *net) { struct fib_rules_ops *ops; struct mr_table *mrt; int err; ops = fib_rules_register(&ipmr_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); INIT_LIST_HEAD(&net->ipv4.mr_tables); mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); if (IS_ERR(mrt)) { err = PTR_ERR(mrt); goto err1; } err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT); if (err < 0) goto err2; net->ipv4.mr_rules_ops = ops; return 0; err2: rtnl_lock(); ipmr_free_table(mrt); rtnl_unlock(); err1: fib_rules_unregister(ops); return err; } static void __net_exit ipmr_rules_exit(struct net *net) { struct mr_table *mrt, *next; ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) { list_del(&mrt->list); ipmr_free_table(mrt); } fib_rules_unregister(net->ipv4.mr_rules_ops); } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack); } static unsigned int ipmr_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, RTNL_FAMILY_IPMR); } bool ipmr_rule_default(const struct fib_rule *rule) { return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT; } EXPORT_SYMBOL(ipmr_rule_default); #else #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) static bool ipmr_can_free_table(struct net *net) { return !check_net(net); } static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { if (!mrt) return net->ipv4.mrt; return NULL; } static struct mr_table *ipmr_get_table(struct net *net, u32 id) { return net->ipv4.mrt; } #define __ipmr_get_table ipmr_get_table static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { *mrt = net->ipv4.mrt; return 0; } static int __net_init ipmr_rules_init(struct net *net) { struct mr_table *mrt; mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); if (IS_ERR(mrt)) return PTR_ERR(mrt); net->ipv4.mrt = mrt; return 0; } static void __net_exit ipmr_rules_exit(struct net *net) { ASSERT_RTNL(); ipmr_free_table(net->ipv4.mrt); net->ipv4.mrt = NULL; } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static unsigned int ipmr_rules_seq_read(const struct net *net) { return 0; } bool ipmr_rule_default(const struct fib_rule *rule) { return true; } EXPORT_SYMBOL(ipmr_rule_default); #endif static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct mfc_cache_cmp_arg *cmparg = arg->key; const struct mfc_cache *c = ptr; return cmparg->mfc_mcastgrp != c->mfc_mcastgrp || cmparg->mfc_origin != c->mfc_origin; } static const struct rhashtable_params ipmr_rht_params = { .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc_cache, cmparg), .key_len = sizeof(struct mfc_cache_cmp_arg), .nelem_hint = 3, .obj_cmpfn = ipmr_hash_cmp, .automatic_shrinking = true, }; static void ipmr_new_table_set(struct mr_table *mrt, struct net *net) { #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); #endif } static struct mfc_cache_cmp_arg ipmr_mr_table_ops_cmparg_any = { .mfc_mcastgrp = htonl(INADDR_ANY), .mfc_origin = htonl(INADDR_ANY), }; static struct mr_table_ops ipmr_mr_table_ops = { .rht_params = &ipmr_rht_params, .cmparg_any = &ipmr_mr_table_ops_cmparg_any, }; static struct mr_table *ipmr_new_table(struct net *net, u32 id) { struct mr_table *mrt; /* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (id != RT_TABLE_DEFAULT && id >= 1000000000) return ERR_PTR(-EINVAL); mrt = __ipmr_get_table(net, id); if (mrt) return mrt; return mr_table_alloc(net, id, &ipmr_mr_table_ops, ipmr_expire_process, ipmr_new_table_set); } static void ipmr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); WARN_ON_ONCE(!ipmr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC); rhltable_destroy(&mrt->mfc_hash); kfree(mrt); } /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ /* Initialize ipmr pimreg/tunnel in_device */ static bool ipmr_init_vif_indev(const struct net_device *dev) { struct in_device *in_dev; ASSERT_RTNL(); in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return false; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; return true; } static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { struct net_device *tunnel_dev, *new_dev; struct ip_tunnel_parm_kern p = { }; int err; tunnel_dev = __dev_get_by_name(net, "tunl0"); if (!tunnel_dev) goto out; p.iph.daddr = v->vifc_rmt_addr.s_addr; p.iph.saddr = v->vifc_lcl_addr.s_addr; p.iph.version = 4; p.iph.ihl = 5; p.iph.protocol = IPPROTO_IPIP; sprintf(p.name, "dvmrp%d", v->vifc_vifi); if (!tunnel_dev->netdev_ops->ndo_tunnel_ctl) goto out; err = tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, SIOCADDTUNNEL); if (err) goto out; new_dev = __dev_get_by_name(net, p.name); if (!new_dev) goto out; new_dev->flags |= IFF_MULTICAST; if (!ipmr_init_vif_indev(new_dev)) goto out_unregister; if (dev_open(new_dev, NULL)) goto out_unregister; dev_hold(new_dev); err = dev_set_allmulti(new_dev, 1); if (err) { dev_close(new_dev); tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, SIOCDELTUNNEL); dev_put(new_dev); new_dev = ERR_PTR(err); } return new_dev; out_unregister: unregister_netdevice(new_dev); out: return ERR_PTR(-ENOBUFS); } #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); struct mr_table *mrt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, .flowi4_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi4_mark = skb->mark, }; int err; err = ipmr_fib_lookup(net, &fl4, &mrt); if (err < 0) { kfree_skb(skb); return err; } DEV_STATS_ADD(dev, tx_bytes, skb->len); DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ ipmr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), IGMPMSG_WHOLEPKT); rcu_read_unlock(); kfree_skb(skb); return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) { return 0; } static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 8; dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; dev->netns_local = true; } static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; if (mrt->id == RT_TABLE_DEFAULT) sprintf(name, "pimreg"); else sprintf(name, "pimreg%u", mrt->id); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (!dev) return NULL; dev_net_set(dev, net); if (register_netdevice(dev)) { free_netdev(dev); return NULL; } if (!ipmr_init_vif_indev(dev)) goto failure; if (dev_open(dev, NULL)) goto failure; dev_hold(dev); return dev; failure: unregister_netdevice(dev); return NULL; } /* called with rcu_read_lock() */ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, unsigned int pimlen) { struct net_device *reg_dev = NULL; struct iphdr *encap; int vif_num; encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* Check that: * a. packet is really sent to a multicast group * b. packet is not a NULL-REGISTER * c. packet is not truncated */ if (!ipv4_is_multicast(encap->daddr) || encap->tot_len == 0 || ntohs(encap->tot_len) + pimlen > skb->len) return 1; /* Pairs with WRITE_ONCE() in vif_add()/vid_delete() */ vif_num = READ_ONCE(mrt->mroute_reg_vif_num); if (vif_num >= 0) reg_dev = vif_dev_read(&mrt->vif_table[vif_num]); if (!reg_dev) return 1; skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); skb->ip_summed = CHECKSUM_NONE; skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); netif_rx(skb); return NET_RX_SUCCESS; } #else static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { return NULL; } #endif static int call_ipmr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, vifi_t vif_index, u32 tb_id) { return mr_call_vif_notifiers(net, RTNL_FAMILY_IPMR, event_type, vif, vif_dev, vif_index, tb_id, &net->ipv4.ipmr_seq); } static int call_ipmr_mfc_entry_notifiers(struct net *net, enum fib_event_type event_type, struct mfc_cache *mfc, u32 tb_id) { return mr_call_mfc_notifiers(net, RTNL_FAMILY_IPMR, event_type, &mfc->_c, tb_id, &net->ipv4.ipmr_seq); } /** * vif_delete - Delete a VIF entry * @mrt: Table to delete from * @vifi: VIF identifier to delete * @notify: Set to 1, if the caller is a notifier_call * @head: if unregistering the VIF, place it on this queue */ static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct net *net = read_pnet(&mrt->net); struct vif_device *v; struct net_device *dev; struct in_device *in_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; v = &mrt->vif_table[vifi]; dev = rtnl_dereference(v->dev); if (!dev) return -EADDRNOTAVAIL; spin_lock(&mrt_lock); call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, dev, vifi, mrt->id); RCU_INIT_POINTER(v->dev, NULL); if (vifi == mrt->mroute_reg_vif_num) { /* Pairs with READ_ONCE() in ipmr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, -1); } if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } WRITE_ONCE(mrt->maxvif, tmp + 1); } spin_unlock(&mrt_lock); dev_set_allmulti(dev, -1); in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; inet_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); } if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); netdev_put(dev, &v->dev_tracker); return 0; } static void ipmr_cache_free_rcu(struct rcu_head *head) { struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); kmem_cache_free(mrt_cachep, (struct mfc_cache *)c); } static void ipmr_cache_free(struct mfc_cache *c) { call_rcu(&c->_c.rcu, ipmr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. */ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; struct nlmsgerr *e; atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); e = nlmsg_data(nlh); e->error = -ETIMEDOUT; memset(&e->msg, 0, sizeof(e->msg)); rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { kfree_skb(skb); } } ipmr_cache_free(c); } /* Timer process for the unresolved queue. */ static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); struct mr_mfc *c, *next; unsigned long expires; unsigned long now; if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10); return; } if (list_empty(&mrt->mfc_unres_queue)) goto out; now = jiffies; expires = 10*HZ; list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; continue; } list_del(&c->list); mroute_netlink_event(mrt, (struct mfc_cache *)c, RTM_DELROUTE); ipmr_destroy_unres(mrt, (struct mfc_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); out: spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under locked mrt_lock. */ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; cache->mfc_un.res.minvif = MAXVIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXVIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) cache->mfc_un.res.minvif = vifi; if (cache->mfc_un.res.maxvif <= vifi) cache->mfc_un.res.maxvif = vifi + 1; } } cache->mfc_un.res.lastuse = jiffies; } static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { struct netdev_phys_item_id ppid = { }; int vifi = vifc->vifc_vifi; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; int err; /* Is vif busy ? */ if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->vifc_flags) { case VIFF_REGISTER: if (!ipmr_pimsm_enabled()) return -EINVAL; /* Special Purpose VIF in PIM * All the packets will be sent to the daemon */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ipmr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); if (err) { unregister_netdevice(dev); dev_put(dev); return err; } break; case VIFF_TUNNEL: dev = ipmr_new_tunnel(net, vifc); if (IS_ERR(dev)) return PTR_ERR(dev); break; case VIFF_USE_IFINDEX: case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); if (dev && !__in_dev_get_rtnl(dev)) { dev_put(dev); return -EADDRNOTAVAIL; } } else { dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); } if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); if (err) { dev_put(dev); return err; } break; default: return -EINVAL; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) { dev_put(dev); return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); err = dev_get_port_parent_id(dev, &ppid, true); if (err == 0) { memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); v->dev_parent_id.id_len = ppid.id_len; } else { v->dev_parent_id.id_len = 0; } v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; /* And finish update writing critical data */ spin_lock(&mrt_lock); rcu_assign_pointer(v->dev, dev); netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); if (v->flags & VIFF_REGISTER) { /* Pairs with READ_ONCE() in ipmr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, vifi); } if (vifi+1 > mrt->maxvif) WRITE_ONCE(mrt->maxvif, vifi + 1); spin_unlock(&mrt_lock); call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, dev, vifi, mrt->id); return 0; } /* called with rcu_read_lock() */ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, __be32 origin, __be32 mcastgrp) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = origin }; return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, __be32 mcastgrp, int vifi) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = htonl(INADDR_ANY) }; if (mcastgrp == htonl(INADDR_ANY)) return mr_mfc_find_any_parent(mrt, vifi); return mr_mfc_find_any(mrt, vifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ static struct mfc_cache *ipmr_cache_find_parent(struct mr_table *mrt, __be32 origin, __be32 mcastgrp, int parent) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = origin, }; return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c) { c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->_c.mfc_un.res.minvif = MAXVIFS; c->_c.free = ipmr_cache_free_rcu; refcount_set(&c->_c.mfc_un.res.refcount, 1); } return c; } static struct mfc_cache *ipmr_cache_alloc_unres(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c) { skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; } return c; } /* A cache entry has gone into a resolved state from queued */ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc_cache *uc, struct mfc_cache *c) { struct sk_buff *skb; struct nlmsgerr *e; /* Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); if (mr_fill_mroute(mrt, skb, &c->_c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); e = nlmsg_data(nlh); e->error = -EMSGSIZE; memset(&e->msg, 0, sizeof(e->msg)); } rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { rcu_read_lock(); ip_mr_forward(net, mrt, skb->dev, skb, c, 0); rcu_read_unlock(); } } } /* Bounce a cache query up to mrouted and netlink. * * Called under rcu_read_lock(). */ static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert) { const int ihl = ip_hdrlen(pkt); struct sock *mroute_sk; struct igmphdr *igmp; struct igmpmsg *msg; struct sk_buff *skb; int ret; mroute_sk = rcu_dereference(mrt->mroute_sk); if (!mroute_sk) return -EINVAL; if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else skb = alloc_skb(128, GFP_ATOMIC); if (!skb) return -ENOBUFS; if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) { /* Ugly, but we have no choice with this interface. * Duplicate old header, fix ihl, length etc. * And all this only to mangle msg->im_msgtype and * to set msg->im_mbz to "mbz" :-) */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); skb_reset_transport_header(skb); msg = (struct igmpmsg *)skb_network_header(skb); memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); msg->im_msgtype = assert; msg->im_mbz = 0; if (assert == IGMPMSG_WRVIFWHOLE) { msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; } else { /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ int vif_num = READ_ONCE(mrt->mroute_reg_vif_num); msg->im_vif = vif_num; msg->im_vif_hi = vif_num >> 8; } ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); } else { /* Copy the IP header */ skb_set_network_header(skb, skb->len); skb_put(skb, ihl); skb_copy_to_linear_data(skb, pkt->data, ihl); /* Flag to the kernel this is a route add */ ip_hdr(skb)->protocol = 0; msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; ipv4_pktinfo_prepare(mroute_sk, pkt, false); memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); igmp->type = assert; msg->im_msgtype = assert; igmp->code = 0; ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ skb->transport_header = skb->network_header; } igmpmsg_netlink_event(mrt, skb); /* Deliver to mrouted */ ret = sock_queue_rcv_skb(mroute_sk, skb); if (ret < 0) { net_warn_ratelimited("mroute: pending queue full, dropping entries\n"); kfree_skb(skb); } return ret; } /* Queue a packet for resolution. It gets locked cache entry! */ /* Called under rcu_read_lock() */ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); struct mfc_cache *c; bool found = false; int err; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) { found = true; break; } } if (!found) { /* Create a new entry if allowable */ c = ipmr_cache_alloc_unres(); if (!c) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); return -ENOBUFS; } /* Fill in the new cache entry */ c->_c.mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; /* Reflect first query at mrouted. */ err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker */ spin_unlock_bh(&mfc_unres_lock); ipmr_cache_free(c); kfree_skb(skb); return err; } atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->_c.list, &mrt->mfc_unres_queue); mroute_netlink_event(mrt, c, RTM_NEWROUTE); if (atomic_read(&mrt->cache_resolve_queue_len) == 1) mod_timer(&mrt->ipmr_expire_timer, c->_c.mfc_un.unres.expires); } /* See if we can append the packet */ if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { if (dev) { skb->dev = dev; skb->skb_iif = dev->ifindex; } skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } spin_unlock_bh(&mfc_unres_lock); return err; } /* MFC cache manipulation by user space mroute daemon */ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { struct net *net = read_pnet(&mrt->net); struct mfc_cache *c; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr, mfc->mfcc_mcastgrp.s_addr, parent); rcu_read_unlock(); if (!c) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ipmr_rht_params); list_del_rcu(&c->_c.list); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); mr_cache_put(&c->_c); return 0; } static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, struct mfcctl *mfc, int mrtsock, int parent) { struct mfc_cache *uc, *c; struct mr_mfc *_uc; bool found; int ret; if (mfc->mfcc_parent >= MAXVIFS) return -ENFILE; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr, mfc->mfcc_mcastgrp.s_addr, parent); rcu_read_unlock(); if (c) { spin_lock(&mrt_lock); c->_c.mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; spin_unlock(&mrt_lock); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) && !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; c = ipmr_cache_alloc(); if (!c) return -ENOMEM; c->mfc_origin = mfc->mfcc_origin.s_addr; c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; c->_c.mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ipmr_rht_params); if (ret) { pr_err("ipmr: rhtable insert error %d\n", ret); ipmr_cache_free(c); return ret; } list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { uc = (struct mfc_cache *)_uc; if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } if (list_empty(&mrt->mfc_unres_queue)) del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } /* Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, int flags) { struct net *net = read_pnet(&mrt->net); struct mr_mfc *c, *tmp; struct mfc_cache *cache; LIST_HEAD(list); int i; /* Shut down all active vif entries */ if (flags & (MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC)) { for (i = 0; i < mrt->maxvif; i++) { if (((mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS_STATIC)) || (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS))) continue; vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); } /* Wipe the cache */ if (flags & (MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC)) { list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC_STATIC)) || (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC))) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); cache = (struct mfc_cache *)c; call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache, mrt->id); mroute_netlink_event(mrt, cache, RTM_DELROUTE); mr_cache_put(c); } } if (flags & MRT_FLUSH_MFC) { if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); cache = (struct mfc_cache *)c; mroute_netlink_event(mrt, cache, RTM_DELROUTE); ipmr_destroy_unres(mrt, cache); } spin_unlock_bh(&mfc_unres_lock); } } } /* called from ip_ra_control(), before an RCU grace period, * we don't need to call synchronize_rcu() here */ static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); struct mr_table *mrt; rtnl_lock(); ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); RCU_INIT_POINTER(mrt->mroute_sk, NULL); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_MFC); } } rtnl_unlock(); } /* Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately * that's how BSD mrouted happens to think. Maybe one day with a proper * MOSPF/PIM router set up we can clean this up. */ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { struct net *net = sock_net(sk); int val, ret = 0, parent = 0; struct mr_table *mrt; struct vifctl vif; struct mfcctl mfc; bool do_wrvifwhole; u32 uval; /* There's one exception to the lock - MRT_DONE which needs to unlock */ rtnl_lock(); if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_IGMP) { ret = -EOPNOTSUPP; goto out_unlock; } mrt = __ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) { ret = -ENOENT; goto out_unlock; } if (optname != MRT_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) { ret = -EACCES; goto out_unlock; } } switch (optname) { case MRT_INIT: if (optlen != sizeof(int)) { ret = -EINVAL; break; } if (rtnl_dereference(mrt->mroute_sk)) { ret = -EADDRINUSE; break; } ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); } break; case MRT_DONE: if (sk != rcu_access_pointer(mrt->mroute_sk)) { ret = -EACCES; } else { /* We need to unlock here because mrtsock_destruct takes * care of rtnl itself and we can't change that due to * the IP_ROUTER_ALERT setsockopt which runs without it. */ rtnl_unlock(); ret = ip_ra_control(sk, 0, NULL); goto out; } break; case MRT_ADD_VIF: case MRT_DEL_VIF: if (optlen != sizeof(vif)) { ret = -EINVAL; break; } if (copy_from_sockptr(&vif, optval, sizeof(vif))) { ret = -EFAULT; break; } if (vif.vifc_vifi >= MAXVIFS) { ret = -ENFILE; break; } if (optname == MRT_ADD_VIF) { ret = vif_add(net, mrt, &vif, sk == rtnl_dereference(mrt->mroute_sk)); } else { ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } break; /* Manipulate the forwarding caches. These live * in a sort of kernel/user symbiosis. */ case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; fallthrough; case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { ret = -EINVAL; break; } if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) { ret = -EFAULT; break; } if (parent == 0) parent = mfc.mfcc_parent; if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, sk == rtnl_dereference(mrt->mroute_sk), parent); break; case MRT_FLUSH: if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } mroute_clean_tables(mrt, val); break; /* Control PIM assert. */ case MRT_ASSERT: if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } mrt->mroute_do_assert = val; break; case MRT_PIM: if (!ipmr_pimsm_enabled()) { ret = -ENOPROTOOPT; break; } if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE); val = !!val; if (val != mrt->mroute_do_pim) { mrt->mroute_do_pim = val; mrt->mroute_do_assert = val; mrt->mroute_do_wrvifwhole = do_wrvifwhole; } break; case MRT_TABLE: if (!IS_BUILTIN(CONFIG_IP_MROUTE_MULTIPLE_TABLES)) { ret = -ENOPROTOOPT; break; } if (optlen != sizeof(uval)) { ret = -EINVAL; break; } if (copy_from_sockptr(&uval, optval, sizeof(uval))) { ret = -EFAULT; break; } if (sk == rtnl_dereference(mrt->mroute_sk)) { ret = -EBUSY; } else { mrt = ipmr_new_table(net, uval); if (IS_ERR(mrt)) ret = PTR_ERR(mrt); else raw_sk(sk)->ipmr_table = uval; } break; /* Spurious command, or MRT_VERSION which you cannot set. */ default: ret = -ENOPROTOOPT; } out_unlock: rtnl_unlock(); out: return ret; } /* Execute if this ioctl is a special mroute ioctl */ int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { switch (cmd) { /* These userspace buffers will be consumed by ipmr_ioctl() */ case SIOCGETVIFCNT: { struct sioc_vif_req buffer; return sock_ioctl_inout(sk, cmd, arg, &buffer, sizeof(buffer)); } case SIOCGETSGCNT: { struct sioc_sg_req buffer; return sock_ioctl_inout(sk, cmd, arg, &buffer, sizeof(buffer)); } } /* return code > 0 means that the ioctl was not executed */ return 1; } /* Getsock opt support for the multicast routing system. */ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, sockptr_t optlen) { int olr; int val; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_IGMP) return -EOPNOTSUPP; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (optname) { case MRT_VERSION: val = 0x0305; break; case MRT_PIM: if (!ipmr_pimsm_enabled()) return -ENOPROTOOPT; val = mrt->mroute_do_pim; break; case MRT_ASSERT: val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; } if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; if (olr < 0) return -EINVAL; olr = min_t(unsigned int, olr, sizeof(int)); if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } /* The IP multicast ioctl support routines. */ int ipmr_ioctl(struct sock *sk, int cmd, void *arg) { struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); struct sioc_vif_req *vr; struct sioc_sg_req *sr; struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: vr = (struct sioc_vif_req *)arg; if (vr->vifi >= mrt->maxvif) return -EINVAL; vr->vifi = array_index_nospec(vr->vifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr->vifi]; if (VIF_EXISTS(mrt, vr->vifi)) { vr->icount = READ_ONCE(vif->pkt_in); vr->ocount = READ_ONCE(vif->pkt_out); vr->ibytes = READ_ONCE(vif->bytes_in); vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT: sr = (struct sioc_sg_req *)arg; rcu_read_lock(); c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr); if (c) { sr->pktcnt = c->_c.mfc_un.res.pkt; sr->bytecnt = c->_c.mfc_un.res.bytes; sr->wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #ifdef CONFIG_COMPAT struct compat_sioc_sg_req { struct in_addr src; struct in_addr grp; compat_ulong_t pktcnt; compat_ulong_t bytecnt; compat_ulong_t wrong_if; }; struct compat_sioc_vif_req { vifi_t vifi; /* Which iface */ compat_ulong_t icount; compat_ulong_t ocount; compat_ulong_t ibytes; compat_ulong_t obytes; }; int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req sr; struct compat_sioc_vif_req vr; struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { vr.icount = READ_ONCE(vif->pkt_in); vr.ocount = READ_ONCE(vif->pkt_out); vr.ibytes = READ_ONCE(vif->bytes_in); vr.obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT: if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { sr.pktcnt = c->_c.mfc_un.res.pkt; sr.bytecnt = c->_c.mfc_un.res.bytes; sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #endif static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ipmr_for_each_table(mrt, net) { v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (rcu_access_pointer(v->dev) == dev) vif_delete(mrt, ct, 1, NULL); } } return NOTIFY_DONE; } static struct notifier_block ip_mr_notifier = { .notifier_call = ipmr_device_event, }; /* Encapsulate a packet by attaching a valid IPIP header to it. * This avoids tunnel drivers and other mess and gives us the speed so * important for multicast video. */ static void ip_encap(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph; const struct iphdr *old_iph = ip_hdr(skb); skb_push(skb, sizeof(struct iphdr)); skb->transport_header = skb->network_header; skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->tos = old_iph->tos; iph->ttl = old_iph->ttl; iph->frag_off = 0; iph->daddr = daddr; iph->saddr = saddr; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); ip_select_ident(net, skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); nf_reset_ct(skb); } static inline int ipmr_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); if (unlikely(opt->optlen)) ip_forward_options(skb); return dst_output(net, sk, skb); } #ifdef CONFIG_NET_SWITCHDEV static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, int in_vifi, int out_vifi) { struct vif_device *out_vif = &mrt->vif_table[out_vifi]; struct vif_device *in_vif = &mrt->vif_table[in_vifi]; if (!skb->offload_l3_fwd_mark) return false; if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len) return false; return netdev_phys_item_id_same(&out_vif->dev_parent_id, &in_vif->dev_parent_id); } #else static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, int in_vifi, int out_vifi) { return false; } #endif /* Processing handlers for ipmr_forward, under rcu_read_lock() */ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, int in_vifi, struct sk_buff *skb, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; struct net_device *dev; struct rtable *rt; struct flowi4 fl4; int encap = 0; vif_dev = vif_dev_read(vif); if (!vif_dev) goto out_free; if (vif->flags & VIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) goto out_free; if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, 0, 0, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; encap = sizeof(struct iphdr); } else { rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0, 0, 0, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; } dev = rt->dst.dev; if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not * allow to send ICMP, so that packets will disappear * to blackhole. */ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); goto out_free; } encap += LL_RESERVED_SPACE(dev) + rt->dst.header_len; if (skb_cow(skb, encap)) { ip_rt_put(rt); goto out_free; } WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. * What do we do with netfilter? -- RR */ if (vif->flags & VIFF_TUNNEL) { ip_encap(net, skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ DEV_STATS_INC(vif_dev, tx_packets); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); } IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output * interfaces. It is clear, if mrouter runs a multicasting * program, it should receive packets not depending to what interface * program is joined. * If we will not make it, the program will have to join on all * interfaces. On the other hand, multihoming host (or router, but * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, net, NULL, skb, skb->dev, dev, ipmr_forward_finish); return; out_free: kfree_skb(skb); } /* Called with mrt_lock or rcu_read_lock() */ static int ipmr_find_vif(const struct mr_table *mrt, struct net_device *dev) { int ct; /* Pairs with WRITE_ONCE() in vif_delete()/vif_add() */ for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) { if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev) break; } return ct; } /* "local" means that we should preserve one skb (for local delivery) */ /* Called uner rcu_read_lock() */ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc_cache *c, int local) { int true_vifi = ipmr_find_vif(mrt, dev); int psend = -1; int vif, ct; vif = c->_c.mfc_parent; c->_c.mfc_un.res.pkt++; c->_c.mfc_un.res.bytes += skb->len; c->_c.mfc_un.res.lastuse = jiffies; if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } /* Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... * * The best workaround until routing daemons will be * fixed is not to redistribute packet, if it was * send through wrong interface. It means, that * multicast applications WILL NOT work for * (S,G), which have default multicast route pointing * to wrong oif. In any case, it is not a good * idea to use multicasting applications on router. */ goto dont_forward; } c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, * so that we cannot check that packet arrived on an oif. * It is bad, but otherwise we would need to move pretty * large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, c->_c.mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); if (mrt->mroute_do_wrvifwhole) ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRVIFWHOLE); } goto dont_forward; } forward: WRITE_ONCE(mrt->vif_table[vif].pkt_in, mrt->vif_table[vif].pkt_in + 1); WRITE_ONCE(mrt->vif_table[vif].bytes_in, mrt->vif_table[vif].bytes_in + skb->len); /* Forward the frame */ if (c->mfc_origin == htonl(INADDR_ANY) && c->mfc_mcastgrp == htonl(INADDR_ANY)) { if (true_vifi >= 0 && true_vifi != c->_c.mfc_parent && ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } for (ct = c->_c.mfc_un.res.maxvif - 1; ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ if ((c->mfc_origin != htonl(INADDR_ANY) || ct != true_vifi) && ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, psend); } psend = ct; } } last_forward: if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, psend); } else { ipmr_queue_xmit(net, mrt, true_vifi, skb, psend); return; } } dont_forward: if (!local) kfree_skb(skb); } static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? LOOPBACK_IFINDEX : skb->dev->ifindex), .flowi4_mark = skb->mark, }; struct mr_table *mrt; int err; err = ipmr_fib_lookup(net, &fl4, &mrt); if (err) return ERR_PTR(err); return mrt; } /* Multicast packets for forwarding arrive here * Called with rcu_read_lock(); */ int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; struct net *net = dev_net(skb->dev); int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; struct mr_table *mrt; struct net_device *dev; /* skb->dev passed in is the loX master dev for vrfs. * As there are no vifs associated with loopback devices, * get the proper interface that does have a vif associated with it. */ dev = skb->dev; if (netif_is_l3_master(skb->dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) { kfree_skb(skb); return -ENODEV; } } /* Packet is looped back after forward, it should not be * forwarded second time, but still can be delivered locally. */ if (IPCB(skb)->flags & IPSKB_FORWARDED) goto dont_forward; mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) { kfree_skb(skb); return PTR_ERR(mrt); } if (!local) { if (IPCB(skb)->opt.router_alert) { if (ip_call_ra_chain(skb)) return 0; } else if (ip_hdr(skb)->protocol == IPPROTO_IGMP) { /* IGMPv1 (and broken IGMPv2 implementations sort of * Cisco IOS <= 11.2(8)) do not put router alert * option to IGMP packets destined to routable * groups. It is very bad, because it means * that we can forward NO IGMP messages. */ struct sock *mroute_sk; mroute_sk = rcu_dereference(mrt->mroute_sk); if (mroute_sk) { nf_reset_ct(skb); raw_rcv(mroute_sk, skb); return 0; } } } /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); if (!cache) { int vif = ipmr_find_vif(mrt, dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, vif); } /* No usable cache entry */ if (!cache) { int vif; if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); ip_local_deliver(skb); if (!skb2) return -ENOBUFS; skb = skb2; } vif = ipmr_find_vif(mrt, dev); if (vif >= 0) return ipmr_cache_unresolved(mrt, vif, skb, dev); kfree_skb(skb); return -ENODEV; } ip_mr_forward(net, mrt, dev, skb, cache, local); if (local) return ip_local_deliver(skb); return 0; dont_forward: if (local) return ip_local_deliver(skb); kfree_skb(skb); return 0; } #ifdef CONFIG_IP_PIMSM_V1 /* Handle IGMP messages of PIMv1 */ int pim_rcv_v1(struct sk_buff *skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = igmp_hdr(skb); mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (!mrt->mroute_do_pim || pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) goto drop; if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } return 0; } #endif #ifdef CONFIG_IP_PIMSM_V2 static int pim_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct net *net = dev_net(skb->dev); struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); if (pim->type != ((PIM_VERSION << 4) | (PIM_TYPE_REGISTER)) || (pim->flags & PIM_NULL_REGISTER) || (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } return 0; } #endif int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid) { struct mfc_cache *cache; struct mr_table *mrt; int err; rcu_read_lock(); mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) { rcu_read_unlock(); return -ENOENT; } cache = ipmr_cache_find(mrt, saddr, daddr); if (!cache && skb->dev) { int vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, daddr, vif); } if (!cache) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; int vif = -1; dev = skb->dev; if (dev) vif = ipmr_find_vif(mrt, dev); if (vif < 0) { rcu_read_unlock(); return -ENODEV; } skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { rcu_read_unlock(); return -ENOMEM; } NETLINK_CB(skb2).portid = portid; skb_push(skb2, sizeof(struct iphdr)); skb_reset_network_header(skb2); iph = ip_hdr(skb2); iph->ihl = sizeof(struct iphdr) >> 2; iph->saddr = saddr; iph->daddr = daddr; iph->version = 0; err = ipmr_cache_unresolved(mrt, vif, skb2, dev); rcu_read_unlock(); return err; } err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); rcu_read_unlock(); return err; } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc_cache *c, int cmd, int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = RTNL_FAMILY_IPMR; rtm->rtm_dst_len = 32; rtm->rtm_src_len = 32; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) || nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int _ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags) { return ipmr_fill_mroute(mrt, skb, portid, seq, (struct mfc_cache *)c, cmd, flags); } static size_t mroute_msgsize(bool unresolved, int maxvif) { size_t len = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_SRC */ + nla_total_size(4) /* RTA_DST */ ; if (!unresolved) len = len + nla_total_size(4) /* RTA_IIF */ + nla_total_size(0) /* RTA_MULTIPATH */ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) /* RTA_MFC_STATS */ + nla_total_size_64bit(sizeof(struct rta_mfc_stats)) ; return len; } static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE, NULL, GFP_ATOMIC); return; errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } static size_t igmpmsg_netlink_msgsize(size_t payloadlen) { size_t len = NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(1) /* IPMRA_CREPORT_MSGTYPE */ + nla_total_size(4) /* IPMRA_CREPORT_VIF_ID */ + nla_total_size(4) /* IPMRA_CREPORT_SRC_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_DST_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_TABLE */ /* IPMRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; return len; } static void igmpmsg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; struct rtgenmsg *rtgenm; struct igmpmsg *msg; struct sk_buff *skb; struct nlattr *nla; int payloadlen; payloadlen = pkt->len - sizeof(struct igmpmsg); msg = (struct igmpmsg *)skb_network_header(pkt); skb = nlmsg_new(igmpmsg_netlink_msgsize(payloadlen), GFP_ATOMIC); if (!skb) goto errout; nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, sizeof(struct rtgenmsg), 0); if (!nlh) goto errout; rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IPMR; if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) || nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif | (msg->im_vif_hi << 8)) || nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR, msg->im_src.s_addr) || nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR, msg->im_dst.s_addr) || nla_put_u32(skb, IPMRA_CREPORT_TABLE, mrt->id)) goto nla_put_failure; nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen); if (!nla || skb_copy_bits(pkt, sizeof(struct igmpmsg), nla_data(nla), payloadlen)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE_R, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_cancel(skb, nlh); errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE_R, -ENOBUFS); } static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for multicast route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for multicast route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_TABLE: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in multicast route get request"); return -EINVAL; } } return 0; } static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX + 1]; struct sk_buff *skb = NULL; struct mfc_cache *cache; struct mr_table *mrt; __be32 src, grp; u32 tableid; int err; err = ipmr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; src = nla_get_in_addr_default(tb[RTA_SRC], 0); grp = nla_get_in_addr_default(tb[RTA_DST], 0); tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = __ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); if (!mrt) { err = -ENOENT; goto errout_free; } /* entries are added/deleted only under RTNL */ rcu_read_lock(); cache = ipmr_cache_find(mrt, src, grp); rcu_read_unlock(); if (!cache) { err = -ENOENT; goto errout_free; } skb = nlmsg_new(mroute_msgsize(false, mrt->maxvif), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout_free; } err = ipmr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0); if (err < 0) goto errout_free; err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; errout_free: kfree_skb(skb); goto errout; } static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .rtnl_held = true, }; int err; if (cb->strict_check) { err = ip_valid_fib_dump_req(sock_net(skb->sk), cb->nlh, &filter, cb); if (err < 0) return err; } if (filter.table_id) { struct mr_table *mrt; mrt = __ipmr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist"); return -ENOENT; } err = mr_table_dump(mrt, skb, cb, _ipmr_fill_mroute, &mfc_unres_lock, &filter); return skb->len ? : err; } return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter, _ipmr_fill_mroute, &mfc_unres_lock, &filter); } static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = { [RTA_SRC] = { .type = NLA_U32 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, }; static bool ipmr_rtm_validate_proto(unsigned char rtm_protocol) { switch (rtm_protocol) { case RTPROT_STATIC: case RTPROT_MROUTED: return true; } return false; } static int ipmr_nla_get_ttls(const struct nlattr *nla, struct mfcctl *mfcc) { struct rtnexthop *rtnh = nla_data(nla); int remaining = nla_len(nla), vifi = 0; while (rtnh_ok(rtnh, remaining)) { mfcc->mfcc_ttls[vifi] = rtnh->rtnh_hops; if (++vifi == MAXVIFS) break; rtnh = rtnh_next(rtnh, &remaining); } return remaining > 0 ? -EINVAL : vifi; } /* returns < 0 on error, 0 for ADD_MFC and 1 for ADD_MFC_PROXY */ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh, struct mfcctl *mfcc, int *mrtsock, struct mr_table **mrtret, struct netlink_ext_ack *extack) { struct net_device *dev = NULL; u32 tblid = RT_TABLE_DEFAULT; struct mr_table *mrt; struct nlattr *attr; struct rtmsg *rtm; int ret, rem; ret = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy, extack); if (ret < 0) goto out; rtm = nlmsg_data(nlh); ret = -EINVAL; if (rtm->rtm_family != RTNL_FAMILY_IPMR || rtm->rtm_dst_len != 32 || rtm->rtm_type != RTN_MULTICAST || rtm->rtm_scope != RT_SCOPE_UNIVERSE || !ipmr_rtm_validate_proto(rtm->rtm_protocol)) goto out; memset(mfcc, 0, sizeof(*mfcc)); mfcc->mfcc_parent = -1; ret = 0; nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), rem) { switch (nla_type(attr)) { case RTA_SRC: mfcc->mfcc_origin.s_addr = nla_get_be32(attr); break; case RTA_DST: mfcc->mfcc_mcastgrp.s_addr = nla_get_be32(attr); break; case RTA_IIF: dev = __dev_get_by_index(net, nla_get_u32(attr)); if (!dev) { ret = -ENODEV; goto out; } break; case RTA_MULTIPATH: if (ipmr_nla_get_ttls(attr, mfcc) < 0) { ret = -EINVAL; goto out; } break; case RTA_PREFSRC: ret = 1; break; case RTA_TABLE: tblid = nla_get_u32(attr); break; } } mrt = __ipmr_get_table(net, tblid); if (!mrt) { ret = -ENOENT; goto out; } *mrtret = mrt; *mrtsock = rtm->rtm_protocol == RTPROT_MROUTED ? 1 : 0; if (dev) mfcc->mfcc_parent = ipmr_find_vif(mrt, dev); out: return ret; } /* takes care of both newroute and delroute */ static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); int ret, mrtsock, parent; struct mr_table *tbl; struct mfcctl mfcc; mrtsock = 0; tbl = NULL; ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl, extack); if (ret < 0) return ret; parent = ret ? mfcc.mfcc_parent : -1; if (nlh->nlmsg_type == RTM_NEWROUTE) return ipmr_mfc_add(net, tbl, &mfcc, mrtsock, parent); else return ipmr_mfc_delete(tbl, &mfcc, parent); } static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb) { u32 queue_len = atomic_read(&mrt->cache_resolve_queue_len); if (nla_put_u32(skb, IPMRA_TABLE_ID, mrt->id) || nla_put_u32(skb, IPMRA_TABLE_CACHE_RES_QUEUE_LEN, queue_len) || nla_put_s32(skb, IPMRA_TABLE_MROUTE_REG_VIF_NUM, mrt->mroute_reg_vif_num) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT, mrt->mroute_do_assert) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE, mrt->mroute_do_wrvifwhole)) return false; return true; } static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb) { struct net_device *vif_dev; struct nlattr *vif_nest; struct vif_device *vif; vif = &mrt->vif_table[vifid]; vif_dev = rtnl_dereference(vif->dev); /* if the VIF doesn't exist just continue */ if (!vif_dev) return true; vif_nest = nla_nest_start_noflag(skb, IPMRA_VIF); if (!vif_nest) return false; if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif_dev->ifindex) || nla_put_u32(skb, IPMRA_VIFA_VIF_ID, vifid) || nla_put_u16(skb, IPMRA_VIFA_FLAGS, vif->flags) || nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_IN, vif->bytes_in, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_OUT, vif->bytes_out, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_IN, vif->pkt_in, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_OUT, vif->pkt_out, IPMRA_VIFA_PAD) || nla_put_be32(skb, IPMRA_VIFA_LOCAL_ADDR, vif->local) || nla_put_be32(skb, IPMRA_VIFA_REMOTE_ADDR, vif->remote)) { nla_nest_cancel(skb, vif_nest); return false; } nla_nest_end(skb, vif_nest); return true; } static int ipmr_valid_dumplink(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ifinfomsg *ifm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for ipmr link dump"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "Invalid data after header in ipmr link dump"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags || ifm->ifi_change || ifm->ifi_index) { NL_SET_ERR_MSG(extack, "Invalid values in header for ipmr link dump request"); return -EINVAL; } return 0; } static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nlmsghdr *nlh = NULL; unsigned int t = 0, s_t; unsigned int e = 0, s_e; struct mr_table *mrt; if (cb->strict_check) { int err = ipmr_valid_dumplink(cb->nlh, cb->extack); if (err < 0) return err; } s_t = cb->args[0]; s_e = cb->args[1]; ipmr_for_each_table(mrt, net) { struct nlattr *vifs, *af; struct ifinfomsg *hdr; u32 i; if (t < s_t) goto skip_table; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, sizeof(*hdr), NLM_F_MULTI); if (!nlh) break; hdr = nlmsg_data(nlh); memset(hdr, 0, sizeof(*hdr)); hdr->ifi_family = RTNL_FAMILY_IPMR; af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) { nlmsg_cancel(skb, nlh); goto out; } if (!ipmr_fill_table(mrt, skb)) { nlmsg_cancel(skb, nlh); goto out; } vifs = nla_nest_start_noflag(skb, IPMRA_TABLE_VIFS); if (!vifs) { nla_nest_end(skb, af); nlmsg_end(skb, nlh); goto out; } for (i = 0; i < mrt->maxvif; i++) { if (e < s_e) goto skip_entry; if (!ipmr_fill_vif(mrt, i, skb)) { nla_nest_end(skb, vifs); nla_nest_end(skb, af); nlmsg_end(skb, nlh); goto out; } skip_entry: e++; } s_e = 0; e = 0; nla_nest_end(skb, vifs); nla_nest_end(skb, af); nlmsg_end(skb, nlh); skip_table: t++; } out: cb->args[1] = e; cb->args[0] = t; return skb->len; } #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing : * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; rcu_read_lock(); mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) { rcu_read_unlock(); return ERR_PTR(-ENOENT); } iter->mrt = mrt; return mr_vif_seq_start(seq, pos); } static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags Local Remote\n"); } else { const struct vif_device *vif = v; const struct net_device *vif_dev; const char *name; vif_dev = vif_dev_read(vif); name = vif_dev ? vif_dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n", vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags, vif->local, vif->remote); } return 0; } static const struct seq_operations ipmr_vif_seq_ops = { .start = ipmr_vif_seq_start, .next = mr_vif_seq_next, .stop = ipmr_vif_seq_stop, .show = ipmr_vif_seq_show, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct mr_table *mrt; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) return ERR_PTR(-ENOENT); return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Group Origin Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc_cache *mfc = v; const struct mr_mfc_iter *it = seq->private; const struct mr_table *mrt = it->mrt; seq_printf(seq, "%08X %08X %-3hd", (__force u32) mfc->mfc_mcastgrp, (__force u32) mfc->mfc_origin, mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->_c.mfc_un.res.pkt, mfc->_c.mfc_un.res.bytes, mfc->_c.mfc_un.res.wrong_if); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain * pkt, bytes and wrong_if values */ seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = mr_mfc_seq_next, .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; #endif #ifdef CONFIG_IP_PIMSM_V2 static const struct net_protocol pim_protocol = { .handler = pim_rcv, }; #endif static unsigned int ipmr_seq_read(const struct net *net) { return READ_ONCE(net->ipv4.ipmr_seq) + ipmr_rules_seq_read(net); } static int ipmr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump, ipmr_mr_table_iter, extack); } static const struct fib_notifier_ops ipmr_notifier_ops_template = { .family = RTNL_FAMILY_IPMR, .fib_seq_read = ipmr_seq_read, .fib_dump = ipmr_dump, .owner = THIS_MODULE, }; static int __net_init ipmr_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv4.ipmr_seq = 0; ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv4.ipmr_notifier_ops = ops; return 0; } static void __net_exit ipmr_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops); net->ipv4.ipmr_notifier_ops = NULL; } /* Setup for IP multicast routing */ static int __net_init ipmr_net_init(struct net *net) { int err; err = ipmr_notifier_init(net); if (err) goto ipmr_notifier_fail; err = ipmr_rules_init(net); if (err < 0) goto ipmr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; if (!proc_create_net("ip_mr_vif", 0, net->proc_net, &ipmr_vif_seq_ops, sizeof(struct mr_vif_iter))) goto proc_vif_fail; if (!proc_create_net("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops, sizeof(struct mr_mfc_iter))) goto proc_cache_fail; #endif return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: remove_proc_entry("ip_mr_vif", net->proc_net); proc_vif_fail: rtnl_lock(); ipmr_rules_exit(net); rtnl_unlock(); #endif ipmr_rules_fail: ipmr_notifier_exit(net); ipmr_notifier_fail: return err; } static void __net_exit ipmr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ip_mr_cache", net->proc_net); remove_proc_entry("ip_mr_vif", net->proc_net); #endif ipmr_notifier_exit(net); } static void __net_exit ipmr_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ipmr_rules_exit(net); rtnl_unlock(); } static struct pernet_operations ipmr_net_ops = { .init = ipmr_net_init, .exit = ipmr_net_exit, .exit_batch = ipmr_net_exit_batch, }; static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = { {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETLINK, .dumpit = ipmr_rtm_dumplink}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_NEWROUTE, .doit = ipmr_rtm_route}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_DELROUTE, .doit = ipmr_rtm_route}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETROUTE, .doit = ipmr_rtm_getroute, .dumpit = ipmr_rtm_dumproute}, }; int __init ip_mr_init(void) { int err; mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = register_pernet_subsys(&ipmr_net_ops); if (err) goto reg_pernet_fail; err = register_netdevice_notifier(&ip_mr_notifier); if (err) goto reg_notif_fail; #ifdef CONFIG_IP_PIMSM_V2 if (inet_add_protocol(&pim_protocol, IPPROTO_PIM) < 0) { pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } #endif rtnl_register_many(ipmr_rtnl_msg_handlers); return 0; #ifdef CONFIG_IP_PIMSM_V2 add_proto_fail: unregister_netdevice_notifier(&ip_mr_notifier); #endif reg_notif_fail: unregister_pernet_subsys(&ipmr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); return err; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { struct ns_common ns; struct mount * root; struct rb_root mounts; /* Protected by namespace_sem */ struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ union { struct rb_node mnt_node; /* Under ns->mounts */ struct list_head mnt_list; }; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { refcount_inc(&ns->ns.count); } extern seqlock_t mount_lock; struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); mnt->mnt.mnt_flags &= ~MNT_ONRB; rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *lookup_next_mnt_ns(struct mnt_namespace *mntns) { return __lookup_next_mnt_ns(mntns, false); } static inline struct mnt_namespace *lookup_prev_mnt_ns(struct mnt_namespace *mntns) { return __lookup_next_mnt_ns(mntns, true); } static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } |
| 173 173 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal schedule timeout and sleeping functions */ #include <linux/delay.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include "tick-internal.h" /* * Since schedule_timeout()'s timer is defined on the stack, it must store * the target task on the stack as well. */ struct process_timer { struct timer_list timer; struct task_struct *task; }; static void process_timeout(struct timer_list *t) { struct process_timer *timeout = from_timer(timeout, t, timer); wake_up_process(timeout->task); } /** * schedule_timeout - sleep until timeout * @timeout: timeout value in jiffies * * Make the current task sleep until @timeout jiffies have elapsed. * The function behavior depends on the current task state * (see also set_current_state() description): * * %TASK_RUNNING - the scheduler is called, but the task does not sleep * at all. That happens because sched_submit_work() does nothing for * tasks in %TASK_RUNNING state. * * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be %TASK_RUNNING when this * routine returns. * * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule * the CPU away without a bound on the timeout. In this case the return * value will be %MAX_SCHEDULE_TIMEOUT. * * Returns: 0 when the timer has expired otherwise the remaining time in * jiffies will be returned. In all cases the return value is guaranteed * to be non-negative. */ signed long __sched schedule_timeout(signed long timeout) { struct process_timer timer; unsigned long expire; switch (timeout) { case MAX_SCHEDULE_TIMEOUT: /* * These two special cases are useful to be comfortable * in the caller. Nothing more. We could take * MAX_SCHEDULE_TIMEOUT from one of the negative value * but I' d like to return a valid offset (>=0) to allow * the caller to do everything it want with the retval. */ schedule(); goto out; default: /* * Another bit of PARANOID. Note that the retval will be * 0 since no piece of kernel is supposed to do a check * for a negative retval of schedule_timeout() (since it * should never happens anyway). You just have the printk() * that will tell you if something is gone wrong and where. */ if (timeout < 0) { pr_err("%s: wrong timeout value %lx\n", __func__, timeout); dump_stack(); __set_current_state(TASK_RUNNING); goto out; } } expire = timeout + jiffies; timer.task = current; timer_setup_on_stack(&timer.timer, process_timeout, 0); timer.timer.expires = expire; add_timer(&timer.timer); schedule(); del_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer.timer); timeout = expire - jiffies; out: return timeout < 0 ? 0 : timeout; } EXPORT_SYMBOL(schedule_timeout); /* * __set_current_state() can be used in schedule_timeout_*() functions, because * schedule_timeout() calls schedule() unconditionally. */ /** * schedule_timeout_interruptible - sleep until timeout (interruptible) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_INTERRUPTIBLE before starting the timeout. */ signed long __sched schedule_timeout_interruptible(signed long timeout) { __set_current_state(TASK_INTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_interruptible); /** * schedule_timeout_killable - sleep until timeout (killable) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_KILLABLE before starting the timeout. */ signed long __sched schedule_timeout_killable(signed long timeout) { __set_current_state(TASK_KILLABLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_killable); /** * schedule_timeout_uninterruptible - sleep until timeout (uninterruptible) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_UNINTERRUPTIBLE before starting the timeout. */ signed long __sched schedule_timeout_uninterruptible(signed long timeout) { __set_current_state(TASK_UNINTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_uninterruptible); /** * schedule_timeout_idle - sleep until timeout (idle) * @timeout: timeout value in jiffies * * See schedule_timeout() for details. * * Task state is set to TASK_IDLE before starting the timeout. It is similar to * schedule_timeout_uninterruptible(), except this task will not contribute to * load average. */ signed long __sched schedule_timeout_idle(signed long timeout) { __set_current_state(TASK_IDLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_idle); /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * @clock_id: timer clock to be used * * Details are explained in schedule_hrtimeout_range() function description as * this function is commonly used. */ int __sched schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id) { struct hrtimer_sleeper t; /* * Optimize when a zero timeout value is given. It does not * matter whether this is an absolute or a relative time. */ if (expires && *expires == 0) { __set_current_state(TASK_RUNNING); return 0; } /* * A NULL parameter means "infinite" */ if (!expires) { schedule(); return -EINTR; } hrtimer_setup_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); if (likely(t.task)) schedule(); hrtimer_cancel(&t.timer); destroy_hrtimer_on_stack(&t.timer); __set_current_state(TASK_RUNNING); return !t.task ? 0 : -EINTR; } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * * Make the current task sleep until the given expiry time has * elapsed. The routine will return immediately unless * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the * actual wakeup to a time that is both power and performance friendly * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * * You can set the task state as follows - * * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be TASK_RUNNING when this * routine returns. * * Returns: 0 when the timer has expired. If the task was woken before the * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or * by an explicit wakeup, it returns -EINTR. */ int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode) { return schedule_hrtimeout_range_clock(expires, delta, mode, CLOCK_MONOTONIC); } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); /** * schedule_hrtimeout - sleep until timeout * @expires: timeout value (ktime_t) * @mode: timer mode * * See schedule_hrtimeout_range() for details. @delta argument of * schedule_hrtimeout_range() is set to 0 and has therefore no impact. */ int __sched schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode) { return schedule_hrtimeout_range(expires, 0, mode); } EXPORT_SYMBOL_GPL(schedule_hrtimeout); /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Requested sleep duration in milliseconds * * msleep() uses jiffy based timeouts for the sleep duration. Because of the * design of the timer wheel, the maximum additional percentage delay (slack) is * 12.5%. This is only valid for timers which will end up in level 1 or a higher * level of the timer wheel. For explanation of those 12.5% please check the * detailed description about the basics of the timer wheel. * * The slack of timers which will end up in level 0 depends on sleep duration * (msecs) and HZ configuration and can be calculated in the following way (with * the timer wheel design restriction that the slack is not less than 12.5%): * * ``slack = MSECS_PER_TICK / msecs`` * * When the allowed slack of the callsite is known, the calculation could be * turned around to find the minimal allowed sleep duration to meet the * constraints. For example: * * * ``HZ=1000`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 1 / (1/4) = 4``: * all sleep durations greater or equal 4ms will meet the constraints. * * ``HZ=1000`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 1 / (1/8) = 8``: * all sleep durations greater or equal 8ms will meet the constraints. * * ``HZ=250`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 4 / (1/4) = 16``: * all sleep durations greater or equal 16ms will meet the constraints. * * ``HZ=250`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 4 / (1/8) = 32``: * all sleep durations greater or equal 32ms will meet the constraints. * * See also the signal aware variant msleep_interruptible(). */ void msleep(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs); while (timeout) timeout = schedule_timeout_uninterruptible(timeout); } EXPORT_SYMBOL(msleep); /** * msleep_interruptible - sleep waiting for signals * @msecs: Requested sleep duration in milliseconds * * See msleep() for some basic information. * * The difference between msleep() and msleep_interruptible() is that the sleep * could be interrupted by a signal delivery and then returns early. * * Returns: The remaining time of the sleep duration transformed to msecs (see * schedule_timeout() for details). */ unsigned long msleep_interruptible(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs); while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); return jiffies_to_msecs(timeout); } EXPORT_SYMBOL(msleep_interruptible); /** * usleep_range_state - Sleep for an approximate time in a given state * @min: Minimum time in usecs to sleep * @max: Maximum time in usecs to sleep * @state: State of the current task that will be while sleeping * * usleep_range_state() sleeps at least for the minimum specified time but not * longer than the maximum specified amount of time. The range might reduce * power usage by allowing hrtimers to coalesce an already scheduled interrupt * with this hrtimer. In the worst case, an interrupt is scheduled for the upper * bound. * * The sleeping task is set to the specified state before starting the sleep. * * In non-atomic context where the exact wakeup time is flexible, use * usleep_range() or its variants instead of udelay(). The sleep improves * responsiveness by avoiding the CPU-hogging busy-wait of udelay(). */ void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; if (WARN_ON_ONCE(max < min)) delta = 0; for (;;) { __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } EXPORT_SYMBOL(usleep_range_state); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Generic netlink support functions to configure an SMC-R PNET table * * Copyright IBM Corp. 2016 * * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> */ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> #include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> #include <uapi/linux/if.h> #include <uapi/linux/smc.h> #include <rdma/ib_verbs.h> #include <net/netns/generic.h> #include "smc_netns.h" #include "smc_pnet.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_core.h" static struct net_device *__pnet_find_base_ndev(struct net_device *ndev); static struct net_device *pnet_find_base_ndev(struct net_device *ndev); static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [SMC_PNETID_IBNAME] = { .type = NLA_NUL_STRING, .len = IB_DEVICE_NAME_MAX - 1 }, [SMC_PNETID_IBPORT] = { .type = NLA_U8 } }; static struct genl_family smc_pnet_nl_family; enum smc_pnet_nametype { SMC_PNET_ETH = 1, SMC_PNET_IB = 2, }; /* pnet entry stored in pnet table */ struct smc_pnetentry { struct list_head list; char pnet_name[SMC_MAX_PNETID_LEN + 1]; enum smc_pnet_nametype type; union { struct { char eth_name[IFNAMSIZ + 1]; struct net_device *ndev; netdevice_tracker dev_tracker; }; struct { char ib_name[IB_DEVICE_NAME_MAX + 1]; u8 ib_port; }; }; }; /* Check if the pnetid is set */ bool smc_pnet_is_pnetid_set(u8 *pnetid) { if (pnetid[0] == 0 || pnetid[0] == _S) return false; return true; } /* Check if two given pnetids match */ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2) { int i; for (i = 0; i < SMC_MAX_PNETID_LEN; i++) { if ((pnetid1[i] == 0 || pnetid1[i] == _S) && (pnetid2[i] == 0 || pnetid2[i] == _S)) break; if (pnetid1[i] != pnetid2[i]) return false; } return true; } /* Remove a pnetid from the pnet table. */ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct smc_ib_device *ibdev; struct smcd_dev *smcd; struct smc_net *sn; int rc = -ENOENT; int ibport; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* remove table entry */ mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || smc_pnet_match(pnetelem->pnet_name, pnet_name)) { list_del(&pnetelem->list); if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pr_warn_ratelimited("smc: net device %s " "erased user defined " "pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); } kfree(pnetelem); rc = 0; } } mutex_unlock(&pnettable->lock); /* if this is not the initial namespace, stop here */ if (net != &init_net) return rc; /* remove ib devices */ mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && (!pnet_name || smc_pnet_match(pnet_name, ibdev->pnetid[ibport]))) { pr_warn_ratelimited("smc: ib device %s ibport " "%d erased user defined " "pnetid %.16s\n", ibdev->ibdev->name, ibport + 1, ibdev->pnetid[ibport]); memset(ibdev->pnetid[ibport], 0, SMC_MAX_PNETID_LEN); ibdev->pnetid_by_user[ibport] = false; rc = 0; } } } mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->pnetid_by_user && (!pnet_name || smc_pnet_match(pnet_name, smcd->pnetid))) { pr_warn_ratelimited("smc: smcd device %s " "erased user defined pnetid " "%.16s\n", dev_name(smcd->ops->get_dev(smcd)), smcd->pnetid); memset(smcd->pnetid, 0, SMC_MAX_PNETID_LEN); smcd->pnetid_by_user = false; rc = 0; } } mutex_unlock(&smcd_dev_list.mutex); return rc; } /* Add the reference to a given network device to the pnet table. */ static int smc_pnet_add_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { netdev_hold(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); pnetelem->ndev = ndev; rc = 0; pr_warn_ratelimited("smc: adding net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Remove the reference to a given network device from the pnet table. */ static int smc_pnet_remove_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pnetelem->ndev = NULL; rc = 0; pr_warn_ratelimited("smc: removing net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Apply pnetid to ib device when no pnetid is set. */ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, char *pnet_name) { bool applied = false; mutex_lock(&smc_ib_devices.mutex); if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } mutex_unlock(&smc_ib_devices.mutex); return applied; } /* Apply pnetid to smcd device when no pnetid is set. */ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) { bool applied = false; mutex_lock(&smcd_dev_list.mutex); if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } mutex_unlock(&smcd_dev_list.mutex); return applied; } /* The limit for pnetid is 16 characters. * Valid characters should be (single-byte character set) a-z, A-Z, 0-9. * Lower case letters are converted to upper case. * Interior blanks should not be used. */ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) { char *bf = skip_spaces(pnet_name); size_t len = strlen(bf); char *end = bf + len; if (!len) return false; while (--end >= bf && isspace(*end)) ; if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) return false; *pnetid++ = islower(*bf) ? toupper(*bf) : *bf; bf++; } *pnetid = '\0'; return true; } /* Find an infiniband device by a given name. The device might not exist. */ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || (ibdev->ibdev->dev.parent && !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, IB_DEVICE_NAME_MAX - 1))) { goto out; } } ibdev = NULL; out: mutex_unlock(&smc_ib_devices.mutex); return ibdev; } /* Find an smcd device by a given name. The device might not exist. */ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(smcd_dev->ops->get_dev(smcd_dev)), smcd_name, IB_DEVICE_NAME_MAX - 1)) goto out; } smcd_dev = NULL; out: mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, char *eth_name, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct net_device *ndev, *base_ndev; u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; bool new_netdev; int rc; /* check if (base) netdev already has a pnetid. If there is one, we do * not want to add a pnet table entry */ rc = -EEXIST; ndev = dev_get_by_name(net, eth_name); /* dev_hold() */ if (ndev) { base_ndev = pnet_find_base_ndev(ndev); if (!smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid)) goto out_put; } /* add a new netdev entry to the pnet table if there isn't one */ rc = -ENOMEM; new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) goto out_put; new_pe->type = SMC_PNET_ETH; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->eth_name, eth_name, IFNAMSIZ); rc = -EEXIST; new_netdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { new_netdev = false; break; } } if (new_netdev) { if (ndev) { new_pe->ndev = ndev; netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_ATOMIC); } list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } if (ndev) pr_warn_ratelimited("smc: net device %s " "applied user defined pnetid %.16s\n", new_pe->eth_name, new_pe->pnet_name); return 0; out_put: dev_put(ndev); return rc; } static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, u8 ib_port, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct smc_ib_device *ib_dev; bool smcddev_applied = true; bool ibdev_applied = true; struct smcd_dev *smcd; struct device *dev; bool new_ibdev; /* try to apply the pnetid to active devices */ ib_dev = smc_pnet_find_ib(ib_name); if (ib_dev) { ibdev_applied = smc_pnet_apply_ib(ib_dev, ib_port, pnet_name); if (ibdev_applied) pr_warn_ratelimited("smc: ib device %s ibport %d " "applied user defined pnetid " "%.16s\n", ib_dev->ibdev->name, ib_port, ib_dev->pnetid[ib_port - 1]); } smcd = smc_pnet_find_smcd(ib_name); if (smcd) { smcddev_applied = smc_pnet_apply_smcd(smcd, pnet_name); if (smcddev_applied) { dev = smcd->ops->get_dev(smcd); pr_warn_ratelimited("smc: smcd device %s " "applied user defined pnetid " "%.16s\n", dev_name(dev), smcd->pnetid); } } /* Apply fails when a device has a hardware-defined pnetid set, do not * add a pnet table entry in that case. */ if (!ibdev_applied || !smcddev_applied) return -EEXIST; /* add a new ib entry to the pnet table if there isn't one */ new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) return -ENOMEM; new_pe->type = SMC_PNET_IB; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX); new_pe->ib_port = ib_port; new_ibdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { new_ibdev = false; break; } } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; } /* Append a pnetid to the end of the pnet table if not already on this list. */ static int smc_pnet_enter(struct net *net, struct nlattr *tb[]) { char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct smc_pnettable *pnettable; bool new_netdev = false; bool new_ibdev = false; struct smc_net *sn; u8 ibport = 1; char *string; int rc; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; rc = -EINVAL; if (!tb[SMC_PNETID_NAME]) goto error; string = (char *)nla_data(tb[SMC_PNETID_NAME]); if (!smc_pnetid_valid(string, pnet_name)) goto error; if (tb[SMC_PNETID_ETHNAME]) { string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); rc = smc_pnet_add_eth(pnettable, net, string, pnet_name); if (!rc) new_netdev = true; else if (rc != -EEXIST) goto error; } /* if this is not the initial namespace, stop here */ if (net != &init_net) return new_netdev ? 0 : -EEXIST; rc = -EINVAL; if (tb[SMC_PNETID_IBNAME]) { string = (char *)nla_data(tb[SMC_PNETID_IBNAME]); string = strim(string); if (tb[SMC_PNETID_IBPORT]) { ibport = nla_get_u8(tb[SMC_PNETID_IBPORT]); if (ibport < 1 || ibport > SMC_MAX_PORTS) goto error; } rc = smc_pnet_add_ib(pnettable, string, ibport, pnet_name); if (!rc) new_ibdev = true; else if (rc != -EEXIST) goto error; } return (new_netdev || new_ibdev) ? 0 : -EEXIST; error: return rc; } /* Convert an smc_pnetentry to a netlink attribute sequence */ static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem) { if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name)) return -1; if (pnetelem->type == SMC_PNET_ETH) { if (nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->eth_name)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a")) return -1; } if (pnetelem->type == SMC_PNET_IB) { if (nla_put_string(msg, SMC_PNETID_IBNAME, pnetelem->ib_name) || nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") || nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff)) return -1; } return 0; } static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); return smc_pnet_enter(net, info->attrs); } static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; return smc_pnet_remove_by_pnetid(net, (char *)nla_data(info->attrs[SMC_PNETID_NAME])); } static int smc_pnet_dump_start(struct netlink_callback *cb) { cb->args[0] = 0; return 0; } static int smc_pnet_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, u32 flags, struct smc_pnetentry *pnetelem) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family, flags, SMC_PNETID_GET); if (!hdr) return -ENOMEM; if (smc_pnet_set_nla(skb, pnetelem) < 0) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; } genlmsg_end(skb, hdr); return 0; } static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid, int start_idx) { struct smc_pnettable *pnettable; struct smc_pnetentry *pnetelem; struct smc_net *sn; int idx = 0; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* dump pnettable entries */ mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; if (idx++ < start_idx) continue; /* if this is not the initial namespace, dump only netdev */ if (net != &init_net && pnetelem->type != SMC_PNET_ETH) continue; if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI, pnetelem)) { --idx; break; } } mutex_unlock(&pnettable->lock); return idx; } static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx; idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NULL, cb->args[0]); cb->args[0] = idx; return skb->len; } /* Retrieve one PNETID entry */ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct sk_buff *msg; void *hdr; if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; _smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq, nla_data(info->attrs[SMC_PNETID_NAME]), 0); /* finish multi part message and send it */ hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, NLM_F_MULTI); if (!hdr) { nlmsg_free(msg); return -EMSGSIZE; } return genlmsg_reply(msg, info); } /* Remove and delete all pnetids from pnet table. */ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); smc_pnet_remove_by_pnetid(net, NULL); return 0; } /* SMC_PNETID generic netlink operation definition */ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start }, { .cmd = SMC_PNETID_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_flush } }; /* SMC_PNETID family definition */ static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, .policy = smc_pnet_policy, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, .n_ops = ARRAY_SIZE(smc_pnet_ops), .resv_start_op = SMC_PNETID_FLUSH + 1, }; bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe; bool rc = false; read_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pe, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { rc = true; goto unlock; } } unlock: read_unlock(&sn->pnetids_ndev.lock); return rc; } static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pi; pe = kzalloc(sizeof(*pe), GFP_KERNEL); if (!pe) return -ENOMEM; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pi->pnetid)) { refcount_inc(&pi->refcnt); kfree(pe); goto unlock; } } refcount_set(&pe->refcnt, 1); memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN); list_add_tail(&pe->list, &sn->pnetids_ndev.list); unlock: write_unlock(&sn->pnetids_ndev.lock); return 0; } static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pe2; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { if (refcount_dec_and_test(&pe->refcnt)) { list_del(&pe->list); kfree(pe); } break; } } write_unlock(&sn->pnetids_ndev.lock); } static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev, u8 *ndev_pnetid) { struct net_device *base_dev; base_dev = __pnet_find_base_ndev(dev); if (base_dev->flags & IFF_UP && !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port, ndev_pnetid)) { /* add to PNETIDs list */ smc_pnet_add_pnetid(net, ndev_pnetid); } } /* create initial list of netdevice pnetids */ static void smc_pnet_create_pnetids_list(struct net *net) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; /* Newly created netns do not have devices. * Do not even acquire rtnl. */ if (list_empty(&net->dev_base_head)) return; /* Note: This might not be needed, because smc_pnet_netdev_event() * is also calling smc_pnet_add_base_pnetid() when handling * NETDEV_UP event. */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); rtnl_unlock(); } /* clean up list of netdevice pnetids */ static void smc_pnet_destroy_pnetids_list(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *temp_pe; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) { list_del(&pe->list); kfree(pe); } write_unlock(&sn->pnetids_ndev.lock); } static int smc_pnet_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(event_dev); u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; switch (event) { case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_REGISTER: smc_pnet_add_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_UP: smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid); return NOTIFY_OK; case NETDEV_DOWN: event_dev = __pnet_find_base_ndev(event_dev); if (!smc_pnetid_by_dev_port(event_dev->dev.parent, event_dev->dev_port, ndev_pnetid)) { /* remove from PNETIDs list */ smc_pnet_remove_pnetid(net, ndev_pnetid); } return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block smc_netdev_notifier = { .notifier_call = smc_pnet_netdev_event }; /* init network namespace */ int smc_pnet_net_init(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnettable *pnettable = &sn->pnettable; struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock); smc_pnet_create_pnetids_list(net); return 0; } int __init smc_pnet_init(void) { int rc; rc = genl_register_family(&smc_pnet_nl_family); if (rc) return rc; rc = register_netdevice_notifier(&smc_netdev_notifier); if (rc) genl_unregister_family(&smc_pnet_nl_family); return rc; } /* exit network namespace */ void smc_pnet_net_exit(struct net *net) { /* flush pnet table */ smc_pnet_remove_by_pnetid(net, NULL); smc_pnet_destroy_pnetids_list(net); } void smc_pnet_exit(void) { unregister_netdevice_notifier(&smc_netdev_notifier); genl_unregister_family(&smc_pnet_nl_family); } static struct net_device *__pnet_find_base_ndev(struct net_device *ndev) { int i, nest_lvl; ASSERT_RTNL(); nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; if (list_empty(lower)) break; lower = lower->next; ndev = netdev_lower_get_next(ndev, &lower); } return ndev; } /* Determine one base device for stacked net devices. * If the lower device level contains more than one devices * (for instance with bonding slaves), just the first device * is used to reach a base device. */ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { rtnl_lock(); ndev = __pnet_find_base_ndev(ndev); rtnl_unlock(); return ndev; } static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, u8 *pnetid) { struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_pnetentry *pnetelem; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, struct smc_init_info *ini) { if (!ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, NULL)) { ini->ib_dev = ibdev; ini->ib_port = i; return 0; } if (ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, NULL, &ini->smcrv2)) { ini->smcrv2.ib_dev_v2 = ibdev; ini->smcrv2.ib_port_v2 = i; return 0; } return -ENODEV; } /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, struct smc_ib_device *known_dev, struct net *net) { struct smc_ib_device *ibdev; int i; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev || !rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) goto out; } } } out: mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id, vlan_id and net namespace */ void smc_pnet_find_alt_roce(struct smc_link_group *lgr, struct smc_init_info *ini, struct smc_ib_device *known_dev) { struct net *net = lgr->net; _smc_pnet_find_roce_by_pnetid(lgr->pnet_id, ini, known_dev, net); } /* if handshake network device belongs to a roce device, return its * IB device and port */ static void smc_pnet_find_rdma_dev(struct net_device *netdev, struct smc_init_info *ini) { struct net *net = dev_net(netdev); struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; /* check rdma net namespace */ if (!rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; ndev = ib_device_get_netdev(ibdev->ibdev, i); if (!ndev) continue; dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) break; } } } mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. * Searching stops at the first matching active IB device port with vlan_id * configured. * If nothing found, check pnetid table. * If nothing found, try to use handshake device */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net *net; ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { smc_pnet_find_rdma_dev(ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); } static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct smcd_dev *ismdev; ndev = pnet_find_base_ndev(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away && (!ini->ism_peer_gid[0].gid || !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id, ismdev))) { ini->ism_dev[0] = ismdev; break; } } mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: * determine ib_device and port belonging to used internal TCP socket * ethernet interface. */ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_roce_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); ini->ism_dev[0] = NULL; if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_ism_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } /* Lookup and apply a pnet table entry to the given ib device. */ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) { char *ib_name = smcibdev->ibdev->name; struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && tmp_pe->ib_port == ib_port) { smc_pnet_apply_ib(smcibdev, ib_port, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } /* Lookup and apply a pnet table entry to the given smcd device. */ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) { const char *ib_name = dev_name(smcddev->ops->get_dev(smcddev)); struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { smc_pnet_apply_smcd(smcddev, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #include <linux/ethtool.h> #include "ipvlan.h" static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan; unsigned int flags; int err; ASSERT_RTNL(); if (port->mode != nval) { list_for_each_entry(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) { err = dev_change_flags(ipvlan->dev, flags | IFF_NOARP, extack); } else { err = dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, extack); } if (unlikely(err)) goto fail; } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ err = ipvlan_l3s_register(port); if (err) goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ ipvlan_l3s_unregister(port); } port->mode = nval; } return 0; fail: /* Undo the flags changes that have been done so far. */ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (port->mode == IPVLAN_MODE_L3 || port->mode == IPVLAN_MODE_L3S) dev_change_flags(ipvlan->dev, flags | IFF_NOARP, NULL); else dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, NULL); } return err; } static int ipvlan_port_create(struct net_device *dev) { struct ipvl_port *port; int err, idx; port = kzalloc(sizeof(struct ipvl_port), GFP_KERNEL); if (!port) return -ENOMEM; write_pnet(&port->pnet, dev_net(dev)); port->dev = dev; port->mode = IPVLAN_MODE_L3; INIT_LIST_HEAD(&port->ipvlans); for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++) INIT_HLIST_HEAD(&port->hlhead[idx]); skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); port->dev_id_start = 1; err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port); if (err) goto err; netdev_hold(dev, &port->dev_tracker, GFP_KERNEL); return 0; err: kfree(port); return err; } static void ipvlan_port_destroy(struct net_device *dev) { struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; netdev_put(dev, &port->dev_tracker); if (port->mode == IPVLAN_MODE_L3S) ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); cancel_work_sync(&port->wq); while ((skb = __skb_dequeue(&port->backlog)) != NULL) { dev_put(skb->dev); kfree_skb(skb); } ida_destroy(&port->ida); kfree(port); } #define IPVLAN_ALWAYS_ON_OFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) #define IPVLAN_ALWAYS_ON \ (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_VLAN_CHALLENGED) #define IPVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \ NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */ #define IPVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static int ipvlan_init(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; int err; dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; dev->features |= IPVLAN_ALWAYS_ON; dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; dev->lltx = true; netif_inherit_tso_max(dev, phy_dev); dev->hard_header_len = phy_dev->hard_header_len; netdev_lockdep_set_classes(dev); ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats); if (!ipvlan->pcpu_stats) return -ENOMEM; if (!netif_is_ipvlan_port(phy_dev)) { err = ipvlan_port_create(phy_dev); if (err < 0) { free_percpu(ipvlan->pcpu_stats); return err; } } port = ipvlan_port_get_rtnl(phy_dev); port->count += 1; return 0; } static void ipvlan_uninit(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; free_percpu(ipvlan->pcpu_stats); port = ipvlan_port_get_rtnl(phy_dev); port->count -= 1; if (!port->count) ipvlan_port_destroy(port->dev); } static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || ipvlan->port->mode == IPVLAN_MODE_L3S) dev->flags |= IFF_NOARP; else dev->flags &= ~IFF_NOARP; rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); rcu_read_unlock(); return 0; } static int ipvlan_stop(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); rcu_read_unlock(); return 0; } static netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); int skblen = skb->len; int ret; ret = ipvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct ipvl_pcpu_stats *pcptr; pcptr = this_cpu_ptr(ipvlan->pcpu_stats); u64_stats_update_begin(&pcptr->syncp); u64_stats_inc(&pcptr->tx_pkts); u64_stats_add(&pcptr->tx_bytes, skblen); u64_stats_update_end(&pcptr->syncp); } else { this_cpu_inc(ipvlan->pcpu_stats->tx_drps); } return ret; } static netdev_features_t ipvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct ipvl_dev *ipvlan = netdev_priv(dev); features |= NETIF_F_ALL_FOR_ALL; features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES); features = netdev_increment_features(ipvlan->phy_dev->features, features, features); features |= IPVLAN_ALWAYS_ON; features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON); return features; } static void ipvlan_change_rx_flags(struct net_device *dev, int change) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; if (change & IFF_ALLMULTI) dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1); } static void ipvlan_set_multicast_mac_filter(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(ipvlan->mac_filters, IPVLAN_MAC_FILTER_SIZE); } else { struct netdev_hw_addr *ha; DECLARE_BITMAP(mc_filters, IPVLAN_MAC_FILTER_SIZE); bitmap_zero(mc_filters, IPVLAN_MAC_FILTER_SIZE); netdev_for_each_mc_addr(ha, dev) __set_bit(ipvlan_mac_hash(ha->addr), mc_filters); /* Turn-on broadcast bit irrespective of address family, * since broadcast is deferred to a work-queue, hence no * impact on fast-path processing. */ __set_bit(ipvlan_mac_hash(dev->broadcast), mc_filters); bitmap_copy(ipvlan->mac_filters, mc_filters, IPVLAN_MAC_FILTER_SIZE); } dev_uc_sync(ipvlan->phy_dev, dev); dev_mc_sync(ipvlan->phy_dev, dev); } static void ipvlan_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (ipvlan->pcpu_stats) { struct ipvl_pcpu_stats *pcptr; u64 rx_pkts, rx_bytes, rx_mcast, tx_pkts, tx_bytes; u32 rx_errs = 0, tx_drps = 0; u32 strt; int idx; for_each_possible_cpu(idx) { pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx); do { strt = u64_stats_fetch_begin(&pcptr->syncp); rx_pkts = u64_stats_read(&pcptr->rx_pkts); rx_bytes = u64_stats_read(&pcptr->rx_bytes); rx_mcast = u64_stats_read(&pcptr->rx_mcast); tx_pkts = u64_stats_read(&pcptr->tx_pkts); tx_bytes = u64_stats_read(&pcptr->tx_bytes); } while (u64_stats_fetch_retry(&pcptr->syncp, strt)); s->rx_packets += rx_pkts; s->rx_bytes += rx_bytes; s->multicast += rx_mcast; s->tx_packets += tx_pkts; s->tx_bytes += tx_bytes; /* u32 values are updated without syncp protection. */ rx_errs += READ_ONCE(pcptr->rx_errs); tx_drps += READ_ONCE(pcptr->tx_drps); } s->rx_errors = rx_errs; s->rx_dropped = rx_errs; s->tx_dropped = tx_drps; } s->tx_errors = DEV_STATS_READ(dev, tx_errors); } static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; return vlan_vid_add(phy_dev, proto, vid); } static int ipvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; vlan_vid_del(phy_dev, proto, vid); return 0; } static int ipvlan_get_iflink(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return READ_ONCE(ipvlan->phy_dev->ifindex); } static const struct net_device_ops ipvlan_netdev_ops = { .ndo_init = ipvlan_init, .ndo_uninit = ipvlan_uninit, .ndo_open = ipvlan_open, .ndo_stop = ipvlan_stop, .ndo_start_xmit = ipvlan_start_xmit, .ndo_fix_features = ipvlan_fix_features, .ndo_change_rx_flags = ipvlan_change_rx_flags, .ndo_set_rx_mode = ipvlan_set_multicast_mac_filter, .ndo_get_stats64 = ipvlan_get_stats64, .ndo_vlan_rx_add_vid = ipvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ipvlan_vlan_rx_kill_vid, .ndo_get_iflink = ipvlan_get_iflink, }; static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; /* TODO Probably use a different field than dev_addr so that the * mac-address on the virtual device is portable and can be carried * while the packets use the mac-addr on the physical device. */ return dev_hard_header(skb, phy_dev, type, daddr, saddr ? : phy_dev->dev_addr, len); } static const struct header_ops ipvlan_header_ops = { .create = ipvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) { ipvlan->dev->mtu = dev->mtu; } static bool netif_is_ipvlan(const struct net_device *dev) { /* both ipvlan and ipvtap devices use the same netdev_ops */ return dev->netdev_ops == &ipvlan_netdev_ops; } static int ipvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return __ethtool_get_link_ksettings(ipvlan->phy_dev, cmd); } static void ipvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, IPVLAN_DRV, sizeof(drvinfo->driver)); strscpy(drvinfo->version, IPV_DRV_VER, sizeof(drvinfo->version)); } static u32 ipvlan_ethtool_get_msglevel(struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return ipvlan->msg_enable; } static void ipvlan_ethtool_set_msglevel(struct net_device *dev, u32 value) { struct ipvl_dev *ipvlan = netdev_priv(dev); ipvlan->msg_enable = value; } static const struct ethtool_ops ipvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = ipvlan_ethtool_get_link_ksettings, .get_drvinfo = ipvlan_ethtool_get_drvinfo, .get_msglevel = ipvlan_ethtool_get_msglevel, .set_msglevel = ipvlan_ethtool_set_msglevel, }; static int ipvlan_nl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int err = 0; if (!data) return 0; if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, nmode, extack); } if (!err && data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (flags & IPVLAN_F_PRIVATE) ipvlan_mark_private(port); else ipvlan_clear_private(port); if (flags & IPVLAN_F_VEPA) ipvlan_mark_vepa(port); else ipvlan_clear_vepa(port); } return err; } static size_t ipvlan_nl_getsize(const struct net_device *dev) { return (0 + nla_total_size(2) /* IFLA_IPVLAN_MODE */ + nla_total_size(2) /* IFLA_IPVLAN_FLAGS */ ); } static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return 0; if (data[IFLA_IPVLAN_MODE]) { u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); if (mode >= IPVLAN_MODE_MAX) return -EINVAL; } if (data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); /* Only two bits are used at this moment. */ if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; /* Also both flags can't be active at the same time. */ if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) == (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; } return 0; } static int ipvlan_nl_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int ret = -EINVAL; if (!port) goto err; ret = -EMSGSIZE; if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode)) goto err; if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags)) goto err; return 0; err: return ret; } int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port; struct net_device *phy_dev; int err; u16 mode = IPVLAN_MODE_L3; if (!tb[IFLA_LINK]) return -EINVAL; phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!phy_dev) return -ENODEV; if (netif_is_ipvlan(phy_dev)) { struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { /* Exit early if the underlying link is invalid or busy */ if (phy_dev->type != ARPHRD_ETHER || phy_dev->flags & IFF_LOOPBACK) { netdev_err(phy_dev, "Master is either lo or non-ether device\n"); return -EINVAL; } if (netdev_is_rx_handler_busy(phy_dev)) { netdev_err(phy_dev, "Device is already in use.\n"); return -EBUSY; } } ipvlan->phy_dev = phy_dev; ipvlan->dev = dev; ipvlan->sfeatures = IPVLAN_FEATURES; if (!tb[IFLA_MTU]) ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing * packets. */ eth_hw_addr_set(dev, phy_dev->dev_addr); dev->priv_flags |= IFF_NO_RX_HANDLER; err = register_netdevice(dev); if (err < 0) return err; /* ipvlan_init() would have created the port, if required */ port = ipvlan_port_get_rtnl(phy_dev); ipvlan->port = port; /* If the port-id base is at the MAX value, then wrap it around and * begin from 0x1 again. This may be due to a busy system where lots * of slaves are getting created and deleted. */ if (port->dev_id_start == 0xFFFE) port->dev_id_start = 0x1; /* Since L2 address is shared among all IPvlan slaves including * master, use unique 16 bit dev-ids to differentiate among them. * Assign IDs between 0x1 and 0xFFFE (used by the master) to each * slave link [see addrconf_ifid_eui48()]. */ err = ida_alloc_range(&port->ida, port->dev_id_start, 0xFFFD, GFP_KERNEL); if (err < 0) err = ida_alloc_range(&port->ida, 0x1, port->dev_id_start - 1, GFP_KERNEL); if (err < 0) goto unregister_netdev; dev->dev_id = err; /* Increment id-base to the next slot for the future assignment */ port->dev_id_start = err + 1; err = netdev_upper_dev_link(phy_dev, dev, extack); if (err) goto remove_ida; /* Flags are per port and latest update overrides. User has * to be consistent in setting it just like the mode attribute. */ if (data && data[IFLA_IPVLAN_FLAGS]) port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (data && data[IFLA_IPVLAN_MODE]) mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, mode, extack); if (err) goto unlink_netdev; list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); netif_stacked_transfer_operstate(phy_dev, dev); return 0; unlink_netdev: netdev_upper_dev_unlink(phy_dev, dev); remove_ida: ida_free(&port->ida, dev->dev_id); unregister_netdev: unregister_netdevice(dev); return err; } EXPORT_SYMBOL_GPL(ipvlan_link_new); void ipvlan_link_delete(struct net_device *dev, struct list_head *head) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; spin_lock_bh(&ipvlan->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } spin_unlock_bh(&ipvlan->addrs_lock); ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(ipvlan->phy_dev, dev); } EXPORT_SYMBOL_GPL(ipvlan_link_delete); void ipvlan_link_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE; dev->netdev_ops = &ipvlan_netdev_ops; dev->needs_free_netdev = true; dev->header_ops = &ipvlan_header_ops; dev->ethtool_ops = &ipvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(ipvlan_link_setup); static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = { [IFLA_IPVLAN_MODE] = { .type = NLA_U16 }, [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; static struct net *ipvlan_get_link_net(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return dev_net(ipvlan->phy_dev); } static struct rtnl_link_ops ipvlan_link_ops = { .kind = "ipvlan", .priv_size = sizeof(struct ipvl_dev), .setup = ipvlan_link_setup, .newlink = ipvlan_link_new, .dellink = ipvlan_link_delete, .get_link_net = ipvlan_get_link_net, }; int ipvlan_link_register(struct rtnl_link_ops *ops) { ops->get_size = ipvlan_nl_getsize; ops->policy = ipvlan_nl_policy; ops->validate = ipvlan_nl_validate; ops->fill_info = ipvlan_nl_fillinfo; ops->changelink = ipvlan_nl_changelink; ops->maxtype = IFLA_IPVLAN_MAX; return rtnl_link_register(ops); } EXPORT_SYMBOL_GPL(ipvlan_link_register); static int ipvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct netdev_notifier_pre_changeaddr_info *prechaddr_info; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvl_dev *ipvlan, *next; struct ipvl_port *port; LIST_HEAD(lst_kill); int err; if (!netif_is_ipvlan_port(dev)) return NOTIFY_DONE; port = ipvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) netif_stacked_transfer_operstate(ipvlan->phy_dev, ipvlan->dev); break; case NETDEV_REGISTER: { struct net *oldnet, *newnet = dev_net(dev); oldnet = read_pnet(&port->pnet); if (net_eq(newnet, oldnet)) break; write_pnet(&port->pnet, newnet); if (port->mode == IPVLAN_MODE_L3S) ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev, &lst_kill); unregister_netdevice_many(&lst_kill); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { netif_inherit_tso_max(ipvlan->dev, dev); netdev_update_features(ipvlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(ipvlan, &port->ipvlans, pnode) ipvlan_adjust_mtu(ipvlan, dev); break; case NETDEV_PRE_CHANGEADDR: prechaddr_info = ptr; list_for_each_entry(ipvlan, &port->ipvlans, pnode) { err = dev_pre_changeaddr_notify(ipvlan->dev, prechaddr_info->dev_addr, extack); if (err) return notifier_from_errno(err); } break; case NETDEV_CHANGEADDR: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { eth_hw_addr_set(ipvlan->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev); } break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; } return NOTIFY_DONE; } /* the caller must held the addrs lock */ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC); if (!addr) return -ENOMEM; addr->master = ipvlan; if (!is_v6) { memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr)); addr->atype = IPVL_IPV4; #if IS_ENABLED(CONFIG_IPV6) } else { memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); addr->atype = IPVL_IPV6; #endif } list_add_tail_rcu(&addr->anode, &ipvlan->addrs); /* If the interface is not up, the address will be added to the hash * list by ipvlan_open. */ if (netif_running(ipvlan->dev)) ipvlan_ht_addr_add(ipvlan, addr); return 0; } static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; spin_lock_bh(&ipvlan->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); if (!addr) { spin_unlock_bh(&ipvlan->addrs_lock); return; } ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); spin_unlock_bh(&ipvlan->addrs_lock); kfree_rcu(addr, rcu); } static bool ipvlan_is_valid_dev(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (!netif_is_ipvlan(dev)) return false; if (!ipvlan || !ipvlan->port) return false; return true; } #if IS_ENABLED(CONFIG_IPV6) static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip6_addr, true); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { return ipvlan_del_addr(ipvlan, ip6_addr, true); } static int ipvlan_addr6_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct inet6_ifaddr *if6 = (struct inet6_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if6->idev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_add_addr6(ipvlan, &if6->addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ipvlan_del_addr6(ipvlan, &if6->addr); break; } return NOTIFY_OK; } static int ipvlan_addr6_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { NL_SET_ERR_MSG(i6vi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } #endif static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip4_addr, false); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { return ipvlan_del_addr(ipvlan, ip4_addr, false); } static int ipvlan_addr4_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_ifaddr *if4 = (struct in_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if4->ifa_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); struct in_addr ip4_addr; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: ip4_addr.s_addr = if4->ifa_address; if (ipvlan_add_addr4(ipvlan, &ip4_addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ip4_addr.s_addr = if4->ifa_address; ipvlan_del_addr4(ipvlan, &ip4_addr); break; } return NOTIFY_OK; } static int ipvlan_addr4_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_validator_info *ivi = (struct in_validator_info *)ptr; struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { NL_SET_ERR_MSG(ivi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_event, }; static struct notifier_block ipvlan_addr4_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_validator_event, }; static struct notifier_block ipvlan_notifier_block __read_mostly = { .notifier_call = ipvlan_device_event, }; #if IS_ENABLED(CONFIG_IPV6) static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_event, }; static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_validator_event, }; #endif static int __init ipvlan_init_module(void) { int err; ipvlan_init_secret(); register_netdevice_notifier(&ipvlan_notifier_block); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&ipvlan_addr6_notifier_block); register_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); err = ipvlan_l3s_init(); if (err < 0) goto error; err = ipvlan_link_register(&ipvlan_link_ops); if (err < 0) { ipvlan_l3s_cleanup(); goto error; } return 0; error: unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif unregister_netdevice_notifier(&ipvlan_notifier_block); return err; } static void __exit ipvlan_cleanup_module(void) { rtnl_link_unregister(&ipvlan_link_ops); ipvlan_l3s_cleanup(); unregister_netdevice_notifier(&ipvlan_notifier_block); unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif } module_init(ipvlan_init_module); module_exit(ipvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs"); MODULE_ALIAS_RTNL_LINK("ipvlan"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 | /* SPDX-License-Identifier: GPL-2.0-only */ /* include/net/xdp.h * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ #include <linux/bitfield.h> #include <linux/filter.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* skb_shared_info */ /** * DOC: XDP RX-queue information * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how * the driver has configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. * * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally needs to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, MEM_TYPE_XSK_BUFF_POOL, MEM_TYPE_MAX, }; /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; }; struct page_pool; struct xdp_rxq_info { struct net_device *dev; u32 queue_index; u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; enum xdp_buff_flags { XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under * pressure */ }; struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; xdp->flags = 0; } static __always_inline void xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, int headroom, int data_len, const bool meta_valid) { unsigned char *data = hard_start + headroom; xdp->data_hard_start = hard_start; xdp->data = data; xdp->data_end = data + data_len; xdp->data_meta = meta_valid ? data : data + 1; } /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the * XDP/BPF data access to data_hard_end. Notice same area (and size) * is used for XDP_PASS, when constructing the SKB via build_skb(). */ #define xdp_data_hard_end(xdp) \ ((xdp)->data_hard_start + (xdp)->frame_sz - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * xdp_get_shared_info_from_buff(struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); len += sinfo->xdp_frags_size; out: return len; } struct xdp_frame { void *data; u16 len; u16 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem info is valid on remote CPU. */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; void *xa; void *q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { /* bq->count will be zero'ed when bq->xa gets updated */ bq->xa = NULL; } static inline struct skb_shared_info * xdp_get_shared_info_from_frame(struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); return (struct skb_shared_info *)(data_hard_start + frame->frame_sz - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); } struct xdp_cpumap_stats { unsigned int redirect; unsigned int pass; unsigned int drop; }; /* Clear kernel pointers in xdp_frame */ static inline void xdp_scrub_frame(struct xdp_frame *frame) { frame->data = NULL; frame->dev_rx = NULL; } static inline void xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, bool pfmemalloc) { skb_shinfo(skb)->nr_frags = nr_frags; skb->len += size; skb->data_len += size; skb->truesize += truesize; skb->pfmemalloc |= pfmemalloc; } /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; xdp->flags = frame->flags; } static inline int xdp_update_frame_from_buff(struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) return -ENOSPC; /* Catch if driver didn't reserve tailroom for skb_shared_info */ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { XDP_WARN("Driver BUG: missing reserved tailroom"); return -ENOSPC; } xdp_frame->data = xdp->data; xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; xdp_frame->flags = xdp->flags; return 0; } /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) { struct xdp_frame *xdp_frame; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) return xdp_convert_zc_to_xdp_frame(xdp); /* Store info in top of packet */ xdp_frame = xdp->data_hard_start; if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ xdp_frame->mem = xdp->rxq->mem; return xdp_frame; } void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); len += sinfo->xdp_frags_size; out: return len; } int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size); static inline int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id) { return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. */ static __always_inline void xdp_set_data_meta_invalid(struct xdp_buff *xdp) { xdp->data_meta = xdp->data + 1; } static __always_inline bool xdp_data_meta_unsupported(const struct xdp_buff *xdp) { return unlikely(xdp->data_meta > xdp->data); } static inline bool xdp_metalen_invalid(unsigned long metalen) { unsigned long meta_max; meta_max = type_max(typeof_member(struct skb_shared_info, meta_len)); BUILD_BUG_ON(!__builtin_constant_p(meta_max)); return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max; } struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; }; struct netdev_bpf; void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE /* Define the relationship between xdp-rx-metadata kfunc and * various other entities: * - xdp_rx_metadata enum * - netdev netlink enum (Documentation/netlink/specs/netdev.yaml) * - kfunc name * - xdp_metadata_ops field */ #define XDP_METADATA_KFUNC_xxx \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \ NETDEV_XDP_RX_METADATA_TIMESTAMP, \ bpf_xdp_metadata_rx_timestamp, \ xmo_rx_timestamp) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \ NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \ NETDEV_XDP_RX_METADATA_VLAN_TAG, \ bpf_xdp_metadata_rx_vlan_tag, \ xmo_rx_vlan_tag) \ enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC MAX_XDP_METADATA_KFUNC, }; enum xdp_rss_hash_type { /* First part: Individual bits for L3/L4 types */ XDP_RSS_L3_IPV4 = BIT(0), XDP_RSS_L3_IPV6 = BIT(1), /* The fixed (L3) IPv4 and IPv6 headers can both be followed by * variable/dynamic headers, IPv4 called Options and IPv6 called * Extension Headers. HW RSS type can contain this info. */ XDP_RSS_L3_DYNHDR = BIT(2), /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in * addition to the protocol specific bit. This ease interaction with * SKBs and avoids reserving a fixed mask for future L4 protocol bits. */ XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */ XDP_RSS_L4_TCP = BIT(4), XDP_RSS_L4_UDP = BIT(5), XDP_RSS_L4_SCTP = BIT(6), XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ XDP_RSS_L4_ICMP = BIT(8), /* Second part: RSS hash type combinations used for driver HW mapping */ XDP_RSS_TYPE_NONE = 0, XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE, XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4, XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6, XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4, XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV4_ICMP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV6_ICMP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, }; struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type); int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci); }; #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg); void xdp_features_clear_redirect_target(struct net_device *dev); #else static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; } static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; } static inline void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { } static inline void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { } static inline void xdp_features_clear_redirect_target(struct net_device *dev) { } #endif static inline void xdp_clear_features_flag(struct net_device *dev) { xdp_set_features_flag(dev, 0); } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus * under local_bh_disable(), which provides the needed RCU protection * for accessing map entries. */ u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) act = xdp_master_redirect(xdp); } return act; } #endif /* __LINUX_NET_XDP_H__ */ |
| 87 | 1 2 3 4 5 6 7 8 9 10 11 12 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <asm/kvm_hyp.h> void __kvm_timer_set_cntvoff(u64 cntvoff) { write_sysreg(cntvoff, cntvoff_el2); } |
| 406 283 247 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_BL_H #define _LINUX_RCULIST_BL_H /* * RCU-protected bl list version. See include/linux/list_bl.h. */ #include <linux/list_bl.h> #include <linux/rcupdate.h> static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); rcu_assign_pointer(h->first, (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry(). */ static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) { __hlist_bl_del(n); n->pprev = LIST_POISON2; } /** * hlist_bl_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_bl, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first; /* don't need hlist_bl_first_rcu because we're under lock */ first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; /* need _rcu because we can have concurrent lock free readers */ hlist_bl_set_first_rcu(h, n); } /** * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_bl_node within the struct. * */ #define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = hlist_bl_first_rcu(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) #endif |
| 33 33 33 33 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/mmu.c * * Copyright (C) 1995-2005 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/cache.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/kexec.h> #include <linux/libfdt.h> #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/memblock.h> #include <linux/memremap.h> #include <linux/memory.h> #include <linux/fs.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/set_memory.h> #include <linux/kfence.h> #include <linux/pkeys.h> #include <asm/barrier.h> #include <asm/cputype.h> #include <asm/fixmap.h> #include <asm/kasan.h> #include <asm/kernel-pgtable.h> #include <asm/sections.h> #include <asm/setup.h> #include <linux/sizes.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #include <asm/ptdump.h> #include <asm/tlbflush.h> #include <asm/pgalloc.h> #include <asm/kfence.h> #define NO_BLOCK_MAPPINGS BIT(0) #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); u32 __boot_cpu_mode[] = { BOOT_CPU_MODE_EL2, BOOT_CPU_MODE_EL1 }; static bool rodata_is_rw __ro_after_init = true; /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. */ long __section(".mmuoff.data.write") __early_cpu_boot_status; /* * Empty_zero_page is a special page that is used for zero-initialized data * and COW. */ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); static DEFINE_SPINLOCK(swapper_pgdir_lock); static DEFINE_MUTEX(fixmap_lock); void noinstr set_swapper_pgd(pgd_t *pgdp, pgd_t pgd) { pgd_t *fixmap_pgdp; /* * Don't bother with the fixmap if swapper_pg_dir is still mapped * writable in the kernel mapping. */ if (rodata_is_rw) { WRITE_ONCE(*pgdp, pgd); dsb(ishst); isb(); return; } spin_lock(&swapper_pgdir_lock); fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp)); WRITE_ONCE(*fixmap_pgdp, pgd); /* * We need dsb(ishst) here to ensure the page-table-walker sees * our new entry before set_p?d() returns. The fixmap's * flush_tlb_kernel_range() via clear_fixmap() does this for us. */ pgd_clear_fixmap(); spin_unlock(&swapper_pgdir_lock); } pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { if (!pfn_is_map_memory(pfn)) return pgprot_noncached(vma_prot); else if (file->f_flags & O_SYNC) return pgprot_writecombine(vma_prot); return vma_prot; } EXPORT_SYMBOL(phys_mem_access_prot); static phys_addr_t __init early_pgtable_alloc(int shift) { phys_addr_t phys; phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0, MEMBLOCK_ALLOC_NOLEAKTRACE); if (!phys) panic("Failed to allocate page table page\n"); return phys; } bool pgattr_change_is_safe(pteval_t old, pteval_t new) { /* * The following mapping attributes may be updated in live * kernel mappings without the need for break-before-make. */ pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG | PTE_SWBITS_MASK; /* creating or taking down mappings is always safe */ if (!pte_valid(__pte(old)) || !pte_valid(__pte(new))) return true; /* A live entry's pfn should not change */ if (pte_pfn(__pte(old)) != pte_pfn(__pte(new))) return false; /* live contiguous mappings may not be manipulated at all */ if ((old | new) & PTE_CONT) return false; /* Transitioning from Non-Global to Global is unsafe */ if (old & ~new & PTE_NG) return false; /* * Changing the memory type between Normal and Normal-Tagged is safe * since Tagged is considered a permission attribute from the * mismatched attribute aliases perspective. */ if (((old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) || (old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)) && ((new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) || (new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED))) mask |= PTE_ATTRINDX_MASK; return ((old ^ new) & ~mask) == 0; } static void init_clear_pgtable(void *table) { clear_page(table); /* Ensure the zeroing is observed by page table walks. */ dsb(ishst); } static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot) { do { pte_t old_pte = __ptep_get(ptep); /* * Required barriers to make this visible to the table walker * are deferred to the end of alloc_init_cont_pte(). */ __set_pte_nosync(ptep, pfn_pte(__phys_to_pfn(phys), prot)); /* * After the PTE entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(__ptep_get(ptep)))); phys += PAGE_SIZE; } while (ptep++, addr += PAGE_SIZE, addr != end); } static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long next; pmd_t pmd = READ_ONCE(*pmdp); pte_t *ptep; BUG_ON(pmd_sect(pmd)); if (pmd_none(pmd)) { pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF; phys_addr_t pte_phys; if (flags & NO_EXEC_MAPPINGS) pmdval |= PMD_TABLE_PXN; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(PAGE_SHIFT); ptep = pte_set_fixmap(pte_phys); init_clear_pgtable(ptep); ptep += pte_index(addr); __pmd_populate(pmdp, pte_phys, pmdval); } else { BUG_ON(pmd_bad(pmd)); ptep = pte_set_fixmap_offset(pmdp, addr); } do { pgprot_t __prot = prot; next = pte_cont_addr_end(addr, end); /* use a contiguous mapping if the range is suitably aligned */ if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) && (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); init_pte(ptep, addr, next, phys, __prot); ptep += pte_index(next) - pte_index(addr); phys += next - addr; } while (addr = next, addr != end); /* * Note: barriers and maintenance necessary to clear the fixmap slot * ensure that all previous pgtable writes are visible to the table * walker. */ pte_clear_fixmap(); } static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long next; do { pmd_t old_pmd = READ_ONCE(*pmdp); next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~PMD_MASK) == 0 && (flags & NO_BLOCK_MAPPINGS) == 0) { pmd_set_huge(pmdp, phys, prot); /* * After the PMD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), READ_ONCE(pmd_val(*pmdp)))); } else { alloc_init_cont_pte(pmdp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pmd_val(old_pmd) != 0 && pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp))); } phys += next - addr; } while (pmdp++, addr = next, addr != end); } static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; /* * Check for initial section mappings in the pgd/pud. */ BUG_ON(pud_sect(pud)); if (pud_none(pud)) { pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF; phys_addr_t pmd_phys; if (flags & NO_EXEC_MAPPINGS) pudval |= PUD_TABLE_PXN; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(PMD_SHIFT); pmdp = pmd_set_fixmap(pmd_phys); init_clear_pgtable(pmdp); pmdp += pmd_index(addr); __pud_populate(pudp, pmd_phys, pudval); } else { BUG_ON(pud_bad(pud)); pmdp = pmd_set_fixmap_offset(pudp, addr); } do { pgprot_t __prot = prot; next = pmd_cont_addr_end(addr, end); /* use a contiguous mapping if the range is suitably aligned */ if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) && (flags & NO_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); pmdp += pmd_index(next) - pmd_index(addr); phys += next - addr; } while (addr = next, addr != end); pmd_clear_fixmap(); } static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long next; p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; if (p4d_none(p4d)) { p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN | P4D_TABLE_AF; phys_addr_t pud_phys; if (flags & NO_EXEC_MAPPINGS) p4dval |= P4D_TABLE_PXN; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(PUD_SHIFT); pudp = pud_set_fixmap(pud_phys); init_clear_pgtable(pudp); pudp += pud_index(addr); __p4d_populate(p4dp, pud_phys, p4dval); } else { BUG_ON(p4d_bad(p4d)); pudp = pud_set_fixmap_offset(p4dp, addr); } do { pud_t old_pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); /* * For 4K granule only, attempt to put down a 1GB block */ if (pud_sect_supported() && ((addr | next | phys) & ~PUD_MASK) == 0 && (flags & NO_BLOCK_MAPPINGS) == 0) { pud_set_huge(pudp, phys, prot); /* * After the PUD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), READ_ONCE(pud_val(*pudp)))); } else { alloc_init_cont_pmd(pudp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(pud_val(old_pud) != 0 && pud_val(old_pud) != READ_ONCE(pud_val(*pudp))); } phys += next - addr; } while (pudp++, addr = next, addr != end); pud_clear_fixmap(); } static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long next; pgd_t pgd = READ_ONCE(*pgdp); p4d_t *p4dp; if (pgd_none(pgd)) { pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN | PGD_TABLE_AF; phys_addr_t p4d_phys; if (flags & NO_EXEC_MAPPINGS) pgdval |= PGD_TABLE_PXN; BUG_ON(!pgtable_alloc); p4d_phys = pgtable_alloc(P4D_SHIFT); p4dp = p4d_set_fixmap(p4d_phys); init_clear_pgtable(p4dp); p4dp += p4d_index(addr); __pgd_populate(pgdp, p4d_phys, pgdval); } else { BUG_ON(pgd_bad(pgd)); p4dp = p4d_set_fixmap_offset(pgdp, addr); } do { p4d_t old_p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); alloc_init_pud(p4dp, addr, next, phys, prot, pgtable_alloc, flags); BUG_ON(p4d_val(old_p4d) != 0 && p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp))); phys += next - addr; } while (p4dp++, addr = next, addr != end); p4d_clear_fixmap(); } static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_pgd(pgdir, virt); /* * If the virtual and physical address don't have the same offset * within a page, we cannot map the region as the caller expects. */ if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) return; phys &= PAGE_MASK; addr = virt & PAGE_MASK; end = PAGE_ALIGN(virt + size); do { next = pgd_addr_end(addr, end); alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, flags); phys += next - addr; } while (pgdp++, addr = next, addr != end); } static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { mutex_lock(&fixmap_lock); __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, pgtable_alloc, flags); mutex_unlock(&fixmap_lock); } #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 extern __alias(__create_pgd_mapping_locked) void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags); #endif static phys_addr_t __pgd_pgtable_alloc(int shift) { /* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */ void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL & ~__GFP_ZERO); BUG_ON(!ptr); return __pa(ptr); } static phys_addr_t pgd_pgtable_alloc(int shift) { phys_addr_t pa = __pgd_pgtable_alloc(shift); struct ptdesc *ptdesc = page_ptdesc(phys_to_page(pa)); /* * Call proper page table ctor in case later we need to * call core mm functions like apply_to_page_range() on * this pre-allocated page table. * * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is * folded, and if so pagetable_pte_ctor() becomes nop. */ if (shift == PAGE_SHIFT) BUG_ON(!pagetable_pte_ctor(ptdesc)); else if (shift == PMD_SHIFT) BUG_ON(!pagetable_pmd_ctor(ptdesc)); return pa; } /* * This function can only be used to modify existing table entries, * without allocating new levels of table. Note that this permits the * creation of new section or page entries. */ void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { if (virt < PAGE_OFFSET) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; } __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, NO_CONT_MAPPINGS); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only) { int flags = 0; BUG_ON(mm == &init_mm); if (page_mappings_only) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; __create_pgd_mapping(mm->pgd, phys, virt, size, prot, pgd_pgtable_alloc, flags); } static void update_mapping_prot(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { if (virt < PAGE_OFFSET) { pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; } __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, NO_CONT_MAPPINGS); /* flush the TLBs after updating live kernel mappings */ flush_tlb_kernel_range(virt, virt + size); } static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start, phys_addr_t end, pgprot_t prot, int flags) { __create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start, prot, early_pgtable_alloc, flags); } void __init mark_linear_text_alias_ro(void) { /* * Remove the write permissions from the linear alias of .text/.rodata */ update_mapping_prot(__pa_symbol(_stext), (unsigned long)lm_alias(_stext), (unsigned long)__init_begin - (unsigned long)_stext, PAGE_KERNEL_RO); } #ifdef CONFIG_KFENCE bool __ro_after_init kfence_early_init = !!CONFIG_KFENCE_SAMPLE_INTERVAL; /* early_param() will be parsed before map_mem() below. */ static int __init parse_kfence_early_init(char *arg) { int val; if (get_option(&arg, &val)) kfence_early_init = !!val; return 0; } early_param("kfence.sample_interval", parse_kfence_early_init); static phys_addr_t __init arm64_kfence_alloc_pool(void) { phys_addr_t kfence_pool; if (!kfence_early_init) return 0; kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE); if (!kfence_pool) { pr_err("failed to allocate kfence pool\n"); kfence_early_init = false; return 0; } /* Temporarily mark as NOMAP. */ memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE); return kfence_pool; } static void __init arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { if (!kfence_pool) return; /* KFENCE pool needs page-level mapping. */ __map_memblock(pgdp, kfence_pool, kfence_pool + KFENCE_POOL_SIZE, pgprot_tagged(PAGE_KERNEL), NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS); memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE); __kfence_pool = phys_to_virt(kfence_pool); } #else /* CONFIG_KFENCE */ static inline phys_addr_t arm64_kfence_alloc_pool(void) { return 0; } static inline void arm64_kfence_map_pool(phys_addr_t kfence_pool, pgd_t *pgdp) { } #endif /* CONFIG_KFENCE */ static void __init map_mem(pgd_t *pgdp) { static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN); phys_addr_t kernel_start = __pa_symbol(_stext); phys_addr_t kernel_end = __pa_symbol(__init_begin); phys_addr_t start, end; phys_addr_t early_kfence_pool; int flags = NO_EXEC_MAPPINGS; u64 i; /* * Setting hierarchical PXNTable attributes on table entries covering * the linear region is only possible if it is guaranteed that no table * entries at any level are being shared between the linear region and * the vmalloc region. Check whether this is true for the PGD level, in * which case it is guaranteed to be true for all other levels as well. * (Unless we are running with support for LPA2, in which case the * entire reduced VA space is covered by a single pgd_t which will have * been populated without the PXNTable attribute by the time we get here.) */ BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end) && pgd_index(_PAGE_OFFSET(VA_BITS_MIN)) != PTRS_PER_PGD - 1); early_kfence_pool = arm64_kfence_alloc_pool(); if (can_set_direct_map()) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* * Take care not to create a writable alias for the * read-only text and rodata sections of the kernel image. * So temporarily mark them as NOMAP to skip mappings in * the following for-loop */ memblock_mark_nomap(kernel_start, kernel_end - kernel_start); /* map all the memory banks */ for_each_mem_range(i, &start, &end) { if (start >= end) break; /* * The linear map must allow allocation tags reading/writing * if MTE is present. Otherwise, it has the same attributes as * PAGE_KERNEL. */ __map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL), flags); } /* * Map the linear alias of the [_stext, __init_begin) interval * as non-executable now, and remove the write permission in * mark_linear_text_alias_ro() below (which will be called after * alternative patching has completed). This makes the contents * of the region accessible to subsystems such as hibernate, * but protects it from inadvertent modification or execution. * Note that contiguous mappings cannot be remapped in this way, * so we should avoid them here. */ __map_memblock(pgdp, kernel_start, kernel_end, PAGE_KERNEL, NO_CONT_MAPPINGS); memblock_clear_nomap(kernel_start, kernel_end - kernel_start); arm64_kfence_map_pool(early_kfence_pool, pgdp); } void mark_rodata_ro(void) { unsigned long section_size; /* * mark .rodata as read only. Use __init_begin rather than __end_rodata * to cover NOTES and EXCEPTION_TABLE. */ section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata; WRITE_ONCE(rodata_is_rw, false); update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata, section_size, PAGE_KERNEL_RO); } static void __init declare_vma(struct vm_struct *vma, void *va_start, void *va_end, unsigned long vm_flags) { phys_addr_t pa_start = __pa_symbol(va_start); unsigned long size = va_end - va_start; BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); if (!(vm_flags & VM_NO_GUARD)) size += PAGE_SIZE; vma->addr = va_start; vma->phys_addr = pa_start; vma->size = size; vma->flags = VM_MAP | vm_flags; vma->caller = __builtin_return_address(0); vm_area_add_early(vma); } #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static pgprot_t kernel_exec_prot(void) { return rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; } static int __init map_entry_trampoline(void) { int i; if (!arm64_kernel_unmapped_at_el0()) return 0; pgprot_t prot = kernel_exec_prot(); phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start); /* The trampoline is always mapped and can therefore be global */ pgprot_val(prot) &= ~PTE_NG; /* Map only the text into the trampoline page table */ memset(tramp_pg_dir, 0, PGD_SIZE); __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, entry_tramp_text_size(), prot, __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS); /* Map both the text and data into the kernel page table */ for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++) __set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i, pa_start + i * PAGE_SIZE, prot); if (IS_ENABLED(CONFIG_RELOCATABLE)) __set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i, pa_start + i * PAGE_SIZE, PAGE_KERNEL_RO); return 0; } core_initcall(map_entry_trampoline); #endif /* * Declare the VMA areas for the kernel */ static void __init declare_kernel_vmas(void) { static struct vm_struct vmlinux_seg[KERNEL_SEGMENT_COUNT]; declare_vma(&vmlinux_seg[0], _stext, _etext, VM_NO_GUARD); declare_vma(&vmlinux_seg[1], __start_rodata, __inittext_begin, VM_NO_GUARD); declare_vma(&vmlinux_seg[2], __inittext_begin, __inittext_end, VM_NO_GUARD); declare_vma(&vmlinux_seg[3], __initdata_begin, __initdata_end, VM_NO_GUARD); declare_vma(&vmlinux_seg[4], _data, _end, 0); } void __pi_map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, int level, pte_t *tbl, bool may_use_cont, u64 va_offset); static u8 idmap_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init, kpti_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init; static void __init create_idmap(void) { u64 start = __pa_symbol(__idmap_text_start); u64 end = __pa_symbol(__idmap_text_end); u64 ptep = __pa_symbol(idmap_ptes); __pi_map_range(&ptep, start, end, start, PAGE_KERNEL_ROX, IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, __phys_to_virt(ptep) - ptep); if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && !arm64_use_ng_mappings) { extern u32 __idmap_kpti_flag; u64 pa = __pa_symbol(&__idmap_kpti_flag); /* * The KPTI G-to-nG conversion code needs a read-write mapping * of its synchronization flag in the ID map. */ ptep = __pa_symbol(kpti_ptes); __pi_map_range(&ptep, pa, pa + sizeof(u32), pa, PAGE_KERNEL, IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, __phys_to_virt(ptep) - ptep); } } void __init paging_init(void) { map_mem(swapper_pg_dir); memblock_allow_resize(); create_idmap(); declare_kernel_vmas(); } #ifdef CONFIG_MEMORY_HOTPLUG static void free_hotplug_page_range(struct page *page, size_t size, struct vmem_altmap *altmap) { if (altmap) { vmem_altmap_free(altmap, size >> PAGE_SHIFT); } else { WARN_ON(PageReserved(page)); free_pages((unsigned long)page_address(page), get_order(size)); } } static void free_hotplug_pgtable_page(struct page *page) { free_hotplug_page_range(page, PAGE_SIZE, NULL); } static bool pgtable_range_aligned(unsigned long start, unsigned long end, unsigned long floor, unsigned long ceiling, unsigned long mask) { start &= mask; if (start < floor) return false; if (ceiling) { ceiling &= mask; if (!ceiling) return false; } if (end - 1 > ceiling - 1) return false; return true; } static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr, unsigned long end, bool free_mapped, struct vmem_altmap *altmap) { pte_t *ptep, pte; do { ptep = pte_offset_kernel(pmdp, addr); pte = __ptep_get(ptep); if (pte_none(pte)) continue; WARN_ON(!pte_present(pte)); __pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); if (free_mapped) free_hotplug_page_range(pte_page(pte), PAGE_SIZE, altmap); } while (addr += PAGE_SIZE, addr < end); } static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr, unsigned long end, bool free_mapped, struct vmem_altmap *altmap) { unsigned long next; pmd_t *pmdp, pmd; do { next = pmd_addr_end(addr, end); pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); if (pmd_none(pmd)) continue; WARN_ON(!pmd_present(pmd)); if (pmd_sect(pmd)) { pmd_clear(pmdp); /* * One TLBI should be sufficient here as the PMD_SIZE * range is mapped with a single block entry. */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE); if (free_mapped) free_hotplug_page_range(pmd_page(pmd), PMD_SIZE, altmap); continue; } WARN_ON(!pmd_table(pmd)); unmap_hotplug_pte_range(pmdp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr, unsigned long end, bool free_mapped, struct vmem_altmap *altmap) { unsigned long next; pud_t *pudp, pud; do { next = pud_addr_end(addr, end); pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); if (pud_none(pud)) continue; WARN_ON(!pud_present(pud)); if (pud_sect(pud)) { pud_clear(pudp); /* * One TLBI should be sufficient here as the PUD_SIZE * range is mapped with a single block entry. */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE); if (free_mapped) free_hotplug_page_range(pud_page(pud), PUD_SIZE, altmap); continue; } WARN_ON(!pud_table(pud)); unmap_hotplug_pmd_range(pudp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr, unsigned long end, bool free_mapped, struct vmem_altmap *altmap) { unsigned long next; p4d_t *p4dp, p4d; do { next = p4d_addr_end(addr, end); p4dp = p4d_offset(pgdp, addr); p4d = READ_ONCE(*p4dp); if (p4d_none(p4d)) continue; WARN_ON(!p4d_present(p4d)); unmap_hotplug_pud_range(p4dp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } static void unmap_hotplug_range(unsigned long addr, unsigned long end, bool free_mapped, struct vmem_altmap *altmap) { unsigned long next; pgd_t *pgdp, pgd; /* * altmap can only be used as vmemmap mapping backing memory. * In case the backing memory itself is not being freed, then * altmap is irrelevant. Warn about this inconsistency when * encountered. */ WARN_ON(!free_mapped && altmap); do { next = pgd_addr_end(addr, end); pgdp = pgd_offset_k(addr); pgd = READ_ONCE(*pgdp); if (pgd_none(pgd)) continue; WARN_ON(!pgd_present(pgd)); unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pte_t *ptep, pte; unsigned long i, start = addr; do { ptep = pte_offset_kernel(pmdp, addr); pte = __ptep_get(ptep); /* * This is just a sanity check here which verifies that * pte clearing has been done by earlier unmap loops. */ WARN_ON(!pte_none(pte)); } while (addr += PAGE_SIZE, addr < end); if (!pgtable_range_aligned(start, end, floor, ceiling, PMD_MASK)) return; /* * Check whether we can free the pte page if the rest of the * entries are empty. Overlap with other regions have been * handled by the floor/ceiling check. */ ptep = pte_offset_kernel(pmdp, 0UL); for (i = 0; i < PTRS_PER_PTE; i++) { if (!pte_none(__ptep_get(&ptep[i]))) return; } pmd_clear(pmdp); __flush_tlb_kernel_pgtable(start); free_hotplug_pgtable_page(virt_to_page(ptep)); } static void free_empty_pmd_table(pud_t *pudp, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmdp, pmd; unsigned long i, next, start = addr; do { next = pmd_addr_end(addr, end); pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); if (pmd_none(pmd)) continue; WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd)); free_empty_pte_table(pmdp, addr, next, floor, ceiling); } while (addr = next, addr < end); if (CONFIG_PGTABLE_LEVELS <= 2) return; if (!pgtable_range_aligned(start, end, floor, ceiling, PUD_MASK)) return; /* * Check whether we can free the pmd page if the rest of the * entries are empty. Overlap with other regions have been * handled by the floor/ceiling check. */ pmdp = pmd_offset(pudp, 0UL); for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_none(READ_ONCE(pmdp[i]))) return; } pud_clear(pudp); __flush_tlb_kernel_pgtable(start); free_hotplug_pgtable_page(virt_to_page(pmdp)); } static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pudp, pud; unsigned long i, next, start = addr; do { next = pud_addr_end(addr, end); pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); if (pud_none(pud)) continue; WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud)); free_empty_pmd_table(pudp, addr, next, floor, ceiling); } while (addr = next, addr < end); if (!pgtable_l4_enabled()) return; if (!pgtable_range_aligned(start, end, floor, ceiling, P4D_MASK)) return; /* * Check whether we can free the pud page if the rest of the * entries are empty. Overlap with other regions have been * handled by the floor/ceiling check. */ pudp = pud_offset(p4dp, 0UL); for (i = 0; i < PTRS_PER_PUD; i++) { if (!pud_none(READ_ONCE(pudp[i]))) return; } p4d_clear(p4dp); __flush_tlb_kernel_pgtable(start); free_hotplug_pgtable_page(virt_to_page(pudp)); } static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4dp, p4d; unsigned long i, next, start = addr; do { next = p4d_addr_end(addr, end); p4dp = p4d_offset(pgdp, addr); p4d = READ_ONCE(*p4dp); if (p4d_none(p4d)) continue; WARN_ON(!p4d_present(p4d)); free_empty_pud_table(p4dp, addr, next, floor, ceiling); } while (addr = next, addr < end); if (!pgtable_l5_enabled()) return; if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK)) return; /* * Check whether we can free the p4d page if the rest of the * entries are empty. Overlap with other regions have been * handled by the floor/ceiling check. */ p4dp = p4d_offset(pgdp, 0UL); for (i = 0; i < PTRS_PER_P4D; i++) { if (!p4d_none(READ_ONCE(p4dp[i]))) return; } pgd_clear(pgdp); __flush_tlb_kernel_pgtable(start); free_hotplug_pgtable_page(virt_to_page(p4dp)); } static void free_empty_tables(unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { unsigned long next; pgd_t *pgdp, pgd; do { next = pgd_addr_end(addr, end); pgdp = pgd_offset_k(addr); pgd = READ_ONCE(*pgdp); if (pgd_none(pgd)) continue; WARN_ON(!pgd_present(pgd)); free_empty_p4d_table(pgdp, addr, next, floor, ceiling); } while (addr = next, addr < end); } #endif void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node, unsigned long addr, unsigned long next) { pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); } int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, unsigned long addr, unsigned long next) { vmemmap_verify((pte_t *)pmdp, node, addr, next); return 1; } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES)) return vmemmap_populate_basepages(start, end, node, altmap); else return vmemmap_populate_hugepages(start, end, node, altmap); } #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); unmap_hotplug_range(start, end, true, altmap); free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END); } #endif /* CONFIG_MEMORY_HOTPLUG */ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot)); /* Only allow permission changes for now */ if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)), pud_val(new_pud))) return 0; VM_BUG_ON(phys & ~PUD_MASK); set_pud(pudp, new_pud); return 1; } int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot)); /* Only allow permission changes for now */ if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)), pmd_val(new_pmd))) return 0; VM_BUG_ON(phys & ~PMD_MASK); set_pmd(pmdp, new_pmd); return 1; } #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_huge(p4d_t *p4dp) { } #endif int pud_clear_huge(pud_t *pudp) { if (!pud_sect(READ_ONCE(*pudp))) return 0; pud_clear(pudp); return 1; } int pmd_clear_huge(pmd_t *pmdp) { if (!pmd_sect(READ_ONCE(*pmdp))) return 0; pmd_clear(pmdp); return 1; } int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) { pte_t *table; pmd_t pmd; pmd = READ_ONCE(*pmdp); if (!pmd_table(pmd)) { VM_WARN_ON(1); return 1; } table = pte_offset_kernel(pmdp, addr); pmd_clear(pmdp); __flush_tlb_kernel_pgtable(addr); pte_free_kernel(NULL, table); return 1; } int pud_free_pmd_page(pud_t *pudp, unsigned long addr) { pmd_t *table; pmd_t *pmdp; pud_t pud; unsigned long next, end; pud = READ_ONCE(*pudp); if (!pud_table(pud)) { VM_WARN_ON(1); return 1; } table = pmd_offset(pudp, addr); pmdp = table; next = addr; end = addr + PUD_SIZE; do { pmd_free_pte_page(pmdp, next); } while (pmdp++, next += PMD_SIZE, next != end); pud_clear(pudp); __flush_tlb_kernel_pgtable(addr); pmd_free(NULL, table); return 1; } #ifdef CONFIG_MEMORY_HOTPLUG static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) { unsigned long end = start + size; WARN_ON(pgdir != init_mm.pgd); WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END)); unmap_hotplug_range(start, end, false, NULL); free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); } struct range arch_get_mappable_range(void) { struct range mhp_range; u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual)); u64 end_linear_pa = __pa(PAGE_END - 1); if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { /* * Check for a wrap, it is possible because of randomized linear * mapping the start physical address is actually bigger than * the end physical address. In this case set start to zero * because [0, end_linear_pa] range must still be able to cover * all addressable physical addresses. */ if (start_linear_pa > end_linear_pa) start_linear_pa = 0; } WARN_ON(start_linear_pa > end_linear_pa); /* * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] * accommodating both its ends but excluding PAGE_END. Max physical * range which can be mapped inside this linear mapping range, must * also be derived from its end points. */ mhp_range.start = start_linear_pa; mhp_range.end = end_linear_pa; return mhp_range; } int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { int ret, flags = NO_EXEC_MAPPINGS; VM_BUG_ON(!mhp_range_allowed(start, size, true)); if (can_set_direct_map()) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), size, params->pgprot, __pgd_pgtable_alloc, flags); memblock_clear_nomap(start, size); ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, params); if (ret) __remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size); else { max_pfn = PFN_UP(start + size); max_low_pfn = max_pfn; } return ret; } void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; __remove_pages(start_pfn, nr_pages, altmap); __remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size); } /* * This memory hotplug notifier helps prevent boot memory from being * inadvertently removed as it blocks pfn range offlining process in * __offline_pages(). Hence this prevents both offlining as well as * removal process for boot memory which is initially always online. * In future if and when boot memory could be removed, this notifier * should be dropped and free_hotplug_page_range() should handle any * reserved pages allocated during boot. */ static int prevent_bootmem_remove_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct mem_section *ms; struct memory_notify *arg = data; unsigned long end_pfn = arg->start_pfn + arg->nr_pages; unsigned long pfn = arg->start_pfn; if ((action != MEM_GOING_OFFLINE) && (action != MEM_OFFLINE)) return NOTIFY_OK; for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { unsigned long start = PFN_PHYS(pfn); unsigned long end = start + (1UL << PA_SECTION_SHIFT); ms = __pfn_to_section(pfn); if (!early_section(ms)) continue; if (action == MEM_GOING_OFFLINE) { /* * Boot memory removal is not supported. Prevent * it via blocking any attempted offline request * for the boot memory and just report it. */ pr_warn("Boot memory [%lx %lx] offlining attempted\n", start, end); return NOTIFY_BAD; } else if (action == MEM_OFFLINE) { /* * This should have never happened. Boot memory * offlining should have been prevented by this * very notifier. Probably some memory removal * procedure might have changed which would then * require further debug. */ pr_err("Boot memory [%lx %lx] offlined\n", start, end); /* * Core memory hotplug does not process a return * code from the notifier for MEM_OFFLINE events. * The error condition has been reported. Return * from here as if ignored. */ return NOTIFY_DONE; } } return NOTIFY_OK; } static struct notifier_block prevent_bootmem_remove_nb = { .notifier_call = prevent_bootmem_remove_notifier, }; /* * This ensures that boot memory sections on the platform are online * from early boot. Memory sections could not be prevented from being * offlined, unless for some reason they are not online to begin with. * This helps validate the basic assumption on which the above memory * event notifier works to prevent boot memory section offlining and * its possible removal. */ static void validate_bootmem_online(void) { phys_addr_t start, end, addr; struct mem_section *ms; u64 i; /* * Scanning across all memblock might be expensive * on some big memory systems. Hence enable this * validation only with DEBUG_VM. */ if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; for_each_mem_range(i, &start, &end) { for (addr = start; addr < end; addr += (1UL << PA_SECTION_SHIFT)) { ms = __pfn_to_section(PHYS_PFN(addr)); /* * All memory ranges in the system at this point * should have been marked as early sections. */ WARN_ON(!early_section(ms)); /* * Memory notifier mechanism here to prevent boot * memory offlining depends on the fact that each * early section memory on the system is initially * online. Otherwise a given memory section which * is already offline will be overlooked and can * be removed completely. Call out such sections. */ if (!online_section(ms)) pr_err("Boot memory [%llx %llx] is offline, can be removed\n", addr, addr + (1UL << PA_SECTION_SHIFT)); } } } static int __init prevent_bootmem_remove_init(void) { int ret = 0; if (!IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) return ret; validate_bootmem_online(); ret = register_memory_notifier(&prevent_bootmem_remove_nb); if (ret) pr_err("%s: Notifier registration failed %d\n", __func__, ret); return ret; } early_initcall(prevent_bootmem_remove_init); #endif pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable * in cases where cpu is affected with errata #2645198. */ if (pte_user_exec(ptep_get(ptep))) return ptep_clear_flush(vma, addr, ptep); } return ptep_get_and_clear(vma->vm_mm, addr, ptep); } void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { set_pte_at(vma->vm_mm, addr, ptep, pte); } /* * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; ttbr_replace_func *replace_phys; unsigned long daif; /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */ phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp)); if (cnp) ttbr1 |= TTBR_CNP_BIT; replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); cpu_install_idmap(); /* * We really don't want to take *any* exceptions while TTBR1 is * in the process of being replaced so mask everything. */ daif = local_daif_save(); replace_phys(ttbr1); local_daif_restore(daif); cpu_uninstall_idmap(); } #ifdef CONFIG_ARCH_HAS_PKEYS int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { u64 new_por = POE_RXW; u64 old_por; u64 pkey_shift; if (!system_supports_poe()) return -ENOSPC; /* * This code should only be called with valid 'pkey' * values originating from in-kernel users. Complain * if a bad value is observed. */ if (WARN_ON_ONCE(pkey >= arch_max_pkey())) return -EINVAL; /* Set the bits we need in POR: */ new_por = POE_RXW; if (init_val & PKEY_DISABLE_WRITE) new_por &= ~POE_W; if (init_val & PKEY_DISABLE_ACCESS) new_por &= ~POE_RW; if (init_val & PKEY_DISABLE_READ) new_por &= ~POE_R; if (init_val & PKEY_DISABLE_EXECUTE) new_por &= ~POE_X; /* Shift the bits in to the correct place in POR for pkey: */ pkey_shift = pkey * POR_BITS_PER_PKEY; new_por <<= pkey_shift; /* Get old POR and mask off any old bits in place: */ old_por = read_sysreg_s(SYS_POR_EL0); old_por &= ~(POE_MASK << pkey_shift); /* Write old part along with new part: */ write_sysreg_s(old_por | new_por, SYS_POR_EL0); return 0; } #endif |
| 108 591 217 217 218 218 222 223 580 584 63 63 556 557 551 228 229 166 166 165 516 519 288 288 287 326 326 78 78 107 107 52 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * iw_table is the sysfs-set interleave weight table, a value of 0 denotes * system-default value should be used. A NULL iw_table also denotes that * system-default values should be used. Until the system-default table * is implemented, the system-default is always 1. * * iw_table is RCU protected */ static u8 __rcu *iw_table; static DEFINE_MUTEX(iw_table_lock); static u8 get_il_weight(int node) { u8 *table; u8 weight; rcu_read_lock(); table = rcu_dereference(iw_table); /* if no iw_table, use system default */ weight = table ? table[node] : 1; /* if value in iw_table is 0, use system default */ weight = weight ? weight : 1; rcu_read_unlock(); return weight; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(is_pmd_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { if (is_migration_entry(pte_to_swp_entry(ptent))) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed++; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; goto unlock; } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table; unsigned int weight_total = 0; u8 weight; int nid; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); table = rcu_dereference(iw_table); /* calculate the total weight */ for_each_node_mask(nid, nodemask) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; weight_total += weight; } /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_pages_node_noprof(nid, gfp | __GFP_THISNODE | __GFP_NORETRY, order); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { return page_rmappable_folio(alloc_pages_mpol_noprof(gfp | __GFP_COMP, order, pol, ilx, nid)); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of alloc_pages_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, NULL, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, NULL, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *table, *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); table = rcu_dereference(iw_table); if (table) memcpy(weights, table, nr_node_ids); rcu_read_unlock(); /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) { if (!weights[node]) weights[node] = 1; weight_total += weights[node]; } /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, NULL, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, NULL, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_array_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_array_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_array_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, NULL, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct iw_node_attr *node_attr; u8 *new; u8 *old; u8 weight = 0; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "")) weight = 0; else if (kstrtou8(buf, 0, &weight)) return -EINVAL; new = kzalloc(nr_node_ids, GFP_KERNEL); if (!new) return -ENOMEM; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); if (old) memcpy(new, old, nr_node_ids); new[node_attr->nid] = weight; rcu_assign_pointer(iw_table, new); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); return count; } static struct iw_node_attr **node_attrs; static void sysfs_wi_node_release(struct iw_node_attr *node_attr, struct kobject *parent) { if (!node_attr) return; sysfs_remove_file(parent, &node_attr->kobj_attr.attr); kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); } static void sysfs_wi_release(struct kobject *wi_kobj) { int i; for (i = 0; i < nr_node_ids; i++) sysfs_wi_node_release(node_attrs[i], wi_kobj); kobject_put(wi_kobj); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = sysfs_wi_release, }; static int add_weight_node(int nid, struct kobject *wi_kobj) { struct iw_node_attr *node_attr; char *name; node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL); if (!node_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(node_attr); return -ENOMEM; } sysfs_attr_init(&node_attr->kobj_attr.attr); node_attr->kobj_attr.attr.name = name; node_attr->kobj_attr.attr.mode = 0644; node_attr->kobj_attr.show = node_show; node_attr->kobj_attr.store = node_store; node_attr->nid = nid; if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) { kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); pr_err("failed to add attribute to weighted_interleave\n"); return -ENOMEM; } node_attrs[nid] = node_attr; return 0; } static int add_weighted_interleave_group(struct kobject *root_kobj) { struct kobject *wi_kobj; int nid, err; wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (!wi_kobj) return -ENOMEM; err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj, "weighted_interleave"); if (err) { kfree(wi_kobj); return err; } for_each_node_state(nid, N_POSSIBLE) { err = add_weight_node(nid, wi_kobj); if (err) { pr_err("failed to add sysfs [node%d]\n", nid); break; } } if (err) kobject_put(wi_kobj); return 0; } static void mempolicy_kobj_release(struct kobject *kobj) { u8 *old; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); rcu_assign_pointer(iw_table, NULL); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); kfree(node_attrs); kfree(kobj); } static const struct kobj_type mempolicy_ktype = { .release = mempolicy_kobj_release }; static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL); if (!mempolicy_kobj) { err = -ENOMEM; goto err_out; } node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *), GFP_KERNEL); if (!node_attrs) { err = -ENOMEM; goto mempol_out; } err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj, "mempolicy"); if (err) goto node_out; err = add_weighted_interleave_group(mempolicy_kobj); if (err) { pr_err("mempolicy sysfs structure failed to initialize\n"); kobject_put(mempolicy_kobj); return err; } return err; node_out: kfree(node_attrs); mempol_out: kfree(mempolicy_kobj); err_out: pr_err("failed to add mempolicy kobject to the system\n"); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 88 88 86 87 4 4 4 87 87 86 87 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013-2017 ARM Limited, All Rights Reserved. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #define pr_fmt(fmt) "GICv3: " fmt #include <linux/acpi.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/kstrtox.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/percpu.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/iopoll.h> #include <linux/irqchip.h> #include <linux/irqchip/arm-gic-common.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/irqchip/arm-gic-v3-prio.h> #include <linux/irqchip/irq-partition-percpu.h> #include <linux/bitfield.h> #include <linux/bits.h> #include <linux/arm-smccc.h> #include <asm/cputype.h> #include <asm/exception.h> #include <asm/smp_plat.h> #include <asm/virt.h> #include "irq-gic-common.h" static u8 dist_prio_irq __ro_after_init = GICV3_PRIO_IRQ; static u8 dist_prio_nmi __ro_after_init = GICV3_PRIO_NMI; #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) #define FLAGS_WORKAROUND_ASR_ERRATUM_8601001 (1ULL << 2) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) static struct cpumask broken_rdists __read_mostly __maybe_unused; struct redist_region { void __iomem *redist_base; phys_addr_t phys_base; bool single_redist; }; struct gic_chip_data { struct fwnode_handle *fwnode; phys_addr_t dist_phys_base; void __iomem *dist_base; struct redist_region *redist_regions; struct rdists rdists; struct irq_domain *domain; u64 redist_stride; u32 nr_redist_regions; u64 flags; bool has_rss; unsigned int ppi_nr; struct partition_desc **ppi_descs; }; #define T241_CHIPS_MAX 4 static void __iomem *t241_dist_base_alias[T241_CHIPS_MAX] __read_mostly; static DEFINE_STATIC_KEY_FALSE(gic_nvidia_t241_erratum); static DEFINE_STATIC_KEY_FALSE(gic_arm64_2941627_erratum); static struct gic_chip_data gic_data __read_mostly; static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); #define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer)) #define GIC_LINE_NR min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U) #define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer) /* * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs * are potentially stolen by the secure side. Some code, especially code dealing * with hwirq IDs, is simplified by accounting for all 16. */ #define SGI_NR 16 /* * The behaviours of RPR and PMR registers differ depending on the value of * SCR_EL3.FIQ, and the behaviour of non-secure priority registers of the * distributor and redistributors depends on whether security is enabled in the * GIC. * * When security is enabled, non-secure priority values from the (re)distributor * are presented to the GIC CPUIF as follow: * (GIC_(R)DIST_PRI[irq] >> 1) | 0x80; * * If SCR_EL3.FIQ == 1, the values written to/read from PMR and RPR at non-secure * EL1 are subject to a similar operation thus matching the priorities presented * from the (re)distributor when security is enabled. When SCR_EL3.FIQ == 0, * these values are unchanged by the GIC. * * see GICv3/GICv4 Architecture Specification (IHI0069D): * - section 4.8.1 Non-secure accesses to register fields for Secure interrupt * priorities. * - Figure 4-7 Secure read of the priority field for a Non-secure Group 1 * interrupt. */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); static u32 gic_get_pribits(void) { u32 pribits; pribits = gic_read_ctlr(); pribits &= ICC_CTLR_EL1_PRI_BITS_MASK; pribits >>= ICC_CTLR_EL1_PRI_BITS_SHIFT; pribits++; return pribits; } static bool gic_has_group0(void) { u32 val; u32 old_pmr; old_pmr = gic_read_pmr(); /* * Let's find out if Group0 is under control of EL3 or not by * setting the highest possible, non-zero priority in PMR. * * If SCR_EL3.FIQ is set, the priority gets shifted down in * order for the CPU interface to set bit 7, and keep the * actual priority in the non-secure range. In the process, it * looses the least significant bit and the actual priority * becomes 0x80. Reading it back returns 0, indicating that * we're don't have access to Group0. */ gic_write_pmr(BIT(8 - gic_get_pribits())); val = gic_read_pmr(); gic_write_pmr(old_pmr); return val != 0; } static inline bool gic_dist_security_disabled(void) { return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS; } static bool cpus_have_security_disabled __ro_after_init; static bool cpus_have_group0 __ro_after_init; static void __init gic_prio_init(void) { bool ds; ds = gic_dist_security_disabled(); if (!ds) { u32 val; val = readl_relaxed(gic_data.dist_base + GICD_CTLR); val |= GICD_CTLR_DS; writel_relaxed(val, gic_data.dist_base + GICD_CTLR); ds = gic_dist_security_disabled(); if (ds) pr_warn("Broken GIC integration, security disabled"); } cpus_have_security_disabled = ds; cpus_have_group0 = gic_has_group0(); /* * How priority values are used by the GIC depends on two things: * the security state of the GIC (controlled by the GICD_CTRL.DS bit) * and if Group 0 interrupts can be delivered to Linux in the non-secure * world as FIQs (controlled by the SCR_EL3.FIQ bit). These affect the * way priorities are presented in ICC_PMR_EL1 and in the distributor: * * GICD_CTRL.DS | SCR_EL3.FIQ | ICC_PMR_EL1 | Distributor * ------------------------------------------------------- * 1 | - | unchanged | unchanged * ------------------------------------------------------- * 0 | 1 | non-secure | non-secure * ------------------------------------------------------- * 0 | 0 | unchanged | non-secure * * In the non-secure view reads and writes are modified: * * - A value written is right-shifted by one and the MSB is set, * forcing the priority into the non-secure range. * * - A value read is left-shifted by one. * * In the first two cases, where ICC_PMR_EL1 and the interrupt priority * are both either modified or unchanged, we can use the same set of * priorities. * * In the last case, where only the interrupt priorities are modified to * be in the non-secure range, we program the non-secure values into * the distributor to match the PMR values we want. */ if (cpus_have_group0 & !cpus_have_security_disabled) { dist_prio_irq = __gicv3_prio_to_ns(dist_prio_irq); dist_prio_nmi = __gicv3_prio_to_ns(dist_prio_nmi); } pr_info("GICD_CTRL.DS=%d, SCR_EL3.FIQ=%d\n", cpus_have_security_disabled, !cpus_have_group0); } /* rdist_nmi_refs[n] == number of cpus having the rdist interrupt n set as NMI */ static refcount_t *rdist_nmi_refs; static struct gic_kvm_info gic_v3_kvm_info __initdata; static DEFINE_PER_CPU(bool, has_rss); #define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4) #define gic_data_rdist() (this_cpu_ptr(gic_data.rdists.rdist)) #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K) /* Our default, arbitrary priority value. Linux only uses one anyway. */ #define DEFAULT_PMR_VALUE 0xf0 enum gic_intid_range { SGI_RANGE, PPI_RANGE, SPI_RANGE, EPPI_RANGE, ESPI_RANGE, LPI_RANGE, __INVALID_RANGE__ }; static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq) { switch (hwirq) { case 0 ... 15: return SGI_RANGE; case 16 ... 31: return PPI_RANGE; case 32 ... 1019: return SPI_RANGE; case EPPI_BASE_INTID ... (EPPI_BASE_INTID + 63): return EPPI_RANGE; case ESPI_BASE_INTID ... (ESPI_BASE_INTID + 1023): return ESPI_RANGE; case 8192 ... GENMASK(23, 0): return LPI_RANGE; default: return __INVALID_RANGE__; } } static enum gic_intid_range get_intid_range(struct irq_data *d) { return __get_intid_range(d->hwirq); } static inline bool gic_irq_in_rdist(struct irq_data *d) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: return true; default: return false; } } static inline void __iomem *gic_dist_base_alias(struct irq_data *d) { if (static_branch_unlikely(&gic_nvidia_t241_erratum)) { irq_hw_number_t hwirq = irqd_to_hwirq(d); u32 chip; /* * For the erratum T241-FABRIC-4, read accesses to GICD_In{E} * registers are directed to the chip that owns the SPI. The * the alias region can also be used for writes to the * GICD_In{E} except GICD_ICENABLERn. Each chip has support * for 320 {E}SPIs. Mappings for all 4 chips: * Chip0 = 32-351 * Chip1 = 352-671 * Chip2 = 672-991 * Chip3 = 4096-4415 */ switch (__get_intid_range(hwirq)) { case SPI_RANGE: chip = (hwirq - 32) / 320; break; case ESPI_RANGE: chip = 3; break; default: unreachable(); } return t241_dist_base_alias[chip]; } return gic_data.dist_base; } static inline void __iomem *gic_dist_base(struct irq_data *d) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: /* SGI+PPI -> SGI_base for this CPU */ return gic_data_rdist_sgi_base(); case SPI_RANGE: case ESPI_RANGE: /* SPI -> dist_base */ return gic_data.dist_base; default: return NULL; } } static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 val; int ret; ret = readl_relaxed_poll_timeout_atomic(base + GICD_CTLR, val, !(val & bit), 1, USEC_PER_SEC); if (ret == -ETIMEDOUT) pr_err_ratelimited("RWP timeout, gone fishing\n"); } /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP); } /* Wait for completion of a redistributor change */ static void gic_redist_wait_for_rwp(void) { gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } static void gic_enable_redist(bool enable) { void __iomem *rbase; u32 val; int ret; if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996) return; rbase = gic_data_rdist_rd_base(); val = readl_relaxed(rbase + GICR_WAKER); if (enable) /* Wake up this CPU redistributor */ val &= ~GICR_WAKER_ProcessorSleep; else val |= GICR_WAKER_ProcessorSleep; writel_relaxed(val, rbase + GICR_WAKER); if (!enable) { /* Check that GICR_WAKER is writeable */ val = readl_relaxed(rbase + GICR_WAKER); if (!(val & GICR_WAKER_ProcessorSleep)) return; /* No PM support in this redistributor */ } ret = readl_relaxed_poll_timeout_atomic(rbase + GICR_WAKER, val, enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep), 1, USEC_PER_SEC); if (ret == -ETIMEDOUT) { pr_err_ratelimited("redistributor failed to %s...\n", enable ? "wakeup" : "sleep"); } } /* * Routines to disable, enable, EOI and route interrupts */ static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case SPI_RANGE: *index = d->hwirq; return offset; case EPPI_RANGE: /* * Contrary to the ESPI range, the EPPI range is contiguous * to the PPI range in the registers, so let's adjust the * displacement accordingly. Consistency is overrated. */ *index = d->hwirq - EPPI_BASE_INTID + 32; return offset; case ESPI_RANGE: *index = d->hwirq - ESPI_BASE_INTID; switch (offset) { case GICD_ISENABLER: return GICD_ISENABLERnE; case GICD_ICENABLER: return GICD_ICENABLERnE; case GICD_ISPENDR: return GICD_ISPENDRnE; case GICD_ICPENDR: return GICD_ICPENDRnE; case GICD_ISACTIVER: return GICD_ISACTIVERnE; case GICD_ICACTIVER: return GICD_ICACTIVERnE; case GICD_IPRIORITYR: return GICD_IPRIORITYRnE; case GICD_ICFGR: return GICD_ICFGRnE; case GICD_IROUTER: return GICD_IROUTERnE; default: break; } break; default: break; } WARN_ON(1); *index = d->hwirq; return offset; } static int gic_peek_irq(struct irq_data *d, u32 offset) { void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_dist_base_alias(d); return !!(readl_relaxed(base + offset + (index / 32) * 4) & mask); } static void gic_poke_irq(struct irq_data *d, u32 offset) { void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_data.dist_base; writel_relaxed(mask, base + offset + (index / 32) * 4); } static void gic_mask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ICENABLER); if (gic_irq_in_rdist(d)) gic_redist_wait_for_rwp(); else gic_dist_wait_for_rwp(); } static void gic_eoimode1_mask_irq(struct irq_data *d) { gic_mask_irq(d); /* * When masking a forwarded interrupt, make sure it is * deactivated as well. * * This ensures that an interrupt that is getting * disabled/masked will not get "stuck", because there is * noone to deactivate it (guest is being terminated). */ if (irqd_is_forwarded_to_vcpu(d)) gic_poke_irq(d, GICD_ICACTIVER); } static void gic_unmask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ISENABLER); } static inline bool gic_supports_nmi(void) { return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && static_branch_likely(&supports_pseudo_nmis); } static int gic_irq_set_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool val) { u32 reg; if (d->hwirq >= 8192) /* SGI/PPI/SPI only */ return -EINVAL; switch (which) { case IRQCHIP_STATE_PENDING: reg = val ? GICD_ISPENDR : GICD_ICPENDR; break; case IRQCHIP_STATE_ACTIVE: reg = val ? GICD_ISACTIVER : GICD_ICACTIVER; break; case IRQCHIP_STATE_MASKED: if (val) { gic_mask_irq(d); return 0; } reg = GICD_ISENABLER; break; default: return -EINVAL; } gic_poke_irq(d, reg); /* * Force read-back to guarantee that the active state has taken * effect, and won't race with a guest-driven deactivation. */ if (reg == GICD_ISACTIVER) gic_peek_irq(d, reg); return 0; } static int gic_irq_get_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool *val) { if (d->hwirq >= 8192) /* PPI/SPI only */ return -EINVAL; switch (which) { case IRQCHIP_STATE_PENDING: *val = gic_peek_irq(d, GICD_ISPENDR); break; case IRQCHIP_STATE_ACTIVE: *val = gic_peek_irq(d, GICD_ISACTIVER); break; case IRQCHIP_STATE_MASKED: *val = !gic_peek_irq(d, GICD_ISENABLER); break; default: return -EINVAL; } return 0; } static void gic_irq_set_prio(struct irq_data *d, u8 prio) { void __iomem *base = gic_dist_base(d); u32 offset, index; offset = convert_offset_index(d, GICD_IPRIORITYR, &index); writeb_relaxed(prio, base + offset + index); } static u32 __gic_get_ppi_index(irq_hw_number_t hwirq) { switch (__get_intid_range(hwirq)) { case PPI_RANGE: return hwirq - 16; case EPPI_RANGE: return hwirq - EPPI_BASE_INTID + 16; default: unreachable(); } } static u32 __gic_get_rdist_index(irq_hw_number_t hwirq) { switch (__get_intid_range(hwirq)) { case SGI_RANGE: case PPI_RANGE: return hwirq; case EPPI_RANGE: return hwirq - EPPI_BASE_INTID + 32; default: unreachable(); } } static u32 gic_get_rdist_index(struct irq_data *d) { return __gic_get_rdist_index(d->hwirq); } static int gic_irq_nmi_setup(struct irq_data *d) { struct irq_desc *desc = irq_to_desc(d->irq); if (!gic_supports_nmi()) return -EINVAL; if (gic_peek_irq(d, GICD_ISENABLER)) { pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq); return -EINVAL; } /* * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return -EINVAL; /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { u32 idx = gic_get_rdist_index(d); /* * Setting up a percpu interrupt as NMI, only switch handler * for first NMI */ if (!refcount_inc_not_zero(&rdist_nmi_refs[idx])) { refcount_set(&rdist_nmi_refs[idx], 1); desc->handle_irq = handle_percpu_devid_fasteoi_nmi; } } else { desc->handle_irq = handle_fasteoi_nmi; } gic_irq_set_prio(d, dist_prio_nmi); return 0; } static void gic_irq_nmi_teardown(struct irq_data *d) { struct irq_desc *desc = irq_to_desc(d->irq); if (WARN_ON(!gic_supports_nmi())) return; if (gic_peek_irq(d, GICD_ISENABLER)) { pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq); return; } /* * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return; /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { u32 idx = gic_get_rdist_index(d); /* Tearing down NMI, only switch handler for last NMI */ if (refcount_dec_and_test(&rdist_nmi_refs[idx])) desc->handle_irq = handle_percpu_devid_irq; } else { desc->handle_irq = handle_fasteoi_irq; } gic_irq_set_prio(d, dist_prio_irq); } static bool gic_arm64_erratum_2941627_needed(struct irq_data *d) { enum gic_intid_range range; if (!static_branch_unlikely(&gic_arm64_2941627_erratum)) return false; range = get_intid_range(d); /* * The workaround is needed if the IRQ is an SPI and * the target cpu is different from the one we are * executing on. */ return (range == SPI_RANGE || range == ESPI_RANGE) && !cpumask_test_cpu(raw_smp_processor_id(), irq_data_get_effective_affinity_mask(d)); } static void gic_eoi_irq(struct irq_data *d) { write_gicreg(irqd_to_hwirq(d), ICC_EOIR1_EL1); isb(); if (gic_arm64_erratum_2941627_needed(d)) { /* * Make sure the GIC stream deactivate packet * issued by ICC_EOIR1_EL1 has completed before * deactivating through GICD_IACTIVER. */ dsb(sy); gic_poke_irq(d, GICD_ICACTIVER); } } static void gic_eoimode1_eoi_irq(struct irq_data *d) { /* * No need to deactivate an LPI, or an interrupt that * is is getting forwarded to a vcpu. */ if (irqd_to_hwirq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d)) return; if (!gic_arm64_erratum_2941627_needed(d)) gic_write_dir(irqd_to_hwirq(d)); else gic_poke_irq(d, GICD_ICACTIVER); } static int gic_set_type(struct irq_data *d, unsigned int type) { irq_hw_number_t irq = irqd_to_hwirq(d); enum gic_intid_range range; void __iomem *base; u32 offset, index; int ret; range = get_intid_range(d); /* Interrupt configuration for SGIs can't be changed */ if (range == SGI_RANGE) return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0; /* SPIs have restrictions on the supported types */ if ((range == SPI_RANGE || range == ESPI_RANGE) && type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING) return -EINVAL; if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_dist_base_alias(d); offset = convert_offset_index(d, GICD_ICFGR, &index); ret = gic_configure_irq(index, type, base + offset); if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) { /* Misconfigured PPIs are usually not fatal */ pr_warn("GIC: PPI INTID%ld is secure or misconfigured\n", irq); ret = 0; } return ret; } static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) { if (get_intid_range(d) == SGI_RANGE) return -EINVAL; if (vcpu) irqd_set_forwarded_to_vcpu(d); else irqd_clr_forwarded_to_vcpu(d); return 0; } static u64 gic_cpu_to_affinity(int cpu) { u64 mpidr = cpu_logical_map(cpu); u64 aff; /* ASR8601 needs to have its affinities shifted down... */ if (unlikely(gic_data.flags & FLAGS_WORKAROUND_ASR_ERRATUM_8601001)) mpidr = (MPIDR_AFFINITY_LEVEL(mpidr, 1) | (MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8)); aff = ((u64)MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | MPIDR_AFFINITY_LEVEL(mpidr, 0)); return aff; } static void gic_deactivate_unhandled(u32 irqnr) { if (static_branch_likely(&supports_deactivate_key)) { if (irqnr < 8192) gic_write_dir(irqnr); } else { write_gicreg(irqnr, ICC_EOIR1_EL1); isb(); } } /* * Follow a read of the IAR with any HW maintenance that needs to happen prior * to invoking the relevant IRQ handler. We must do two things: * * (1) Ensure instruction ordering between a read of IAR and subsequent * instructions in the IRQ handler using an ISB. * * It is possible for the IAR to report an IRQ which was signalled *after* * the CPU took an IRQ exception as multiple interrupts can race to be * recognized by the GIC, earlier interrupts could be withdrawn, and/or * later interrupts could be prioritized by the GIC. * * For devices which are tightly coupled to the CPU, such as PMUs, a * context synchronization event is necessary to ensure that system * register state is not stale, as these may have been indirectly written * *after* exception entry. * * (2) Execute an interrupt priority drop when EOI mode 1 is in use. */ static inline void gic_complete_ack(u32 irqnr) { if (static_branch_likely(&supports_deactivate_key)) write_gicreg(irqnr, ICC_EOIR1_EL1); isb(); } static bool gic_rpr_is_nmi_prio(void) { if (!gic_supports_nmi()) return false; return unlikely(gic_read_rpr() == GICV3_PRIO_NMI); } static bool gic_irqnr_is_special(u32 irqnr) { return irqnr >= 1020 && irqnr <= 1023; } static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs) { if (gic_irqnr_is_special(irqnr)) return; gic_complete_ack(irqnr); if (generic_handle_domain_irq(gic_data.domain, irqnr)) { WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr); gic_deactivate_unhandled(irqnr); } } static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs) { if (gic_irqnr_is_special(irqnr)) return; gic_complete_ack(irqnr); if (generic_handle_domain_nmi(gic_data.domain, irqnr)) { WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr); gic_deactivate_unhandled(irqnr); } } /* * An exception has been taken from a context with IRQs enabled, and this could * be an IRQ or an NMI. * * The entry code called us with DAIF.IF set to keep NMIs masked. We must clear * DAIF.IF (and update ICC_PMR_EL1 to mask regular IRQs) prior to returning, * after handling any NMI but before handling any IRQ. * * The entry code has performed IRQ entry, and if an NMI is detected we must * perform NMI entry/exit around invoking the handler. */ static void __gic_handle_irq_from_irqson(struct pt_regs *regs) { bool is_nmi; u32 irqnr; irqnr = gic_read_iar(); is_nmi = gic_rpr_is_nmi_prio(); if (is_nmi) { nmi_enter(); __gic_handle_nmi(irqnr, regs); nmi_exit(); } if (gic_prio_masking_enabled()) { gic_pmr_mask_irqs(); gic_arch_enable_irqs(); } if (!is_nmi) __gic_handle_irq(irqnr, regs); } /* * An exception has been taken from a context with IRQs disabled, which can only * be an NMI. * * The entry code called us with DAIF.IF set to keep NMIs masked. We must leave * DAIF.IF (and ICC_PMR_EL1) unchanged. * * The entry code has performed NMI entry. */ static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs) { u64 pmr; u32 irqnr; /* * We were in a context with IRQs disabled. However, the * entry code has set PMR to a value that allows any * interrupt to be acknowledged, and not just NMIs. This can * lead to surprising effects if the NMI has been retired in * the meantime, and that there is an IRQ pending. The IRQ * would then be taken in NMI context, something that nobody * wants to debug twice. * * Until we sort this, drop PMR again to a level that will * actually only allow NMIs before reading IAR, and then * restore it to what it was. */ pmr = gic_read_pmr(); gic_pmr_mask_irqs(); isb(); irqnr = gic_read_iar(); gic_write_pmr(pmr); __gic_handle_nmi(irqnr, regs); } static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) { if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs))) __gic_handle_irq_from_irqsoff(regs); else __gic_handle_irq_from_irqson(regs); } static void __init gic_dist_init(void) { unsigned int i; u64 affinity; void __iomem *base = gic_data.dist_base; u32 val; /* Disable the distributor */ writel_relaxed(0, base + GICD_CTLR); gic_dist_wait_for_rwp(); /* * Configure SPIs as non-secure Group-1. This will only matter * if the GIC only has a single security state. This will not * do the right thing if the kernel is running in secure mode, * but that's not the intended use case anyway. */ for (i = 32; i < GIC_LINE_NR; i += 32) writel_relaxed(~0, base + GICD_IGROUPR + i / 8); /* Extended SPI range, not handled by the GICv2/GICv3 common code */ for (i = 0; i < GIC_ESPI_NR; i += 32) { writel_relaxed(~0U, base + GICD_ICENABLERnE + i / 8); writel_relaxed(~0U, base + GICD_ICACTIVERnE + i / 8); } for (i = 0; i < GIC_ESPI_NR; i += 32) writel_relaxed(~0U, base + GICD_IGROUPRnE + i / 8); for (i = 0; i < GIC_ESPI_NR; i += 16) writel_relaxed(0, base + GICD_ICFGRnE + i / 4); for (i = 0; i < GIC_ESPI_NR; i += 4) writel_relaxed(REPEAT_BYTE_U32(dist_prio_irq), base + GICD_IPRIORITYRnE + i); /* Now do the common stuff */ gic_dist_config(base, GIC_LINE_NR, dist_prio_irq); val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1; if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) { pr_info("Enabling SGIs without active state\n"); val |= GICD_CTLR_nASSGIreq; } /* Enable distributor with ARE, Group1, and wait for it to drain */ writel_relaxed(val, base + GICD_CTLR); gic_dist_wait_for_rwp(); /* * Set all global interrupts to the boot CPU only. ARE must be * enabled. */ affinity = gic_cpu_to_affinity(smp_processor_id()); for (i = 32; i < GIC_LINE_NR; i++) gic_write_irouter(affinity, base + GICD_IROUTER + i * 8); for (i = 0; i < GIC_ESPI_NR; i++) gic_write_irouter(affinity, base + GICD_IROUTERnE + i * 8); } static int gic_iterate_rdists(int (*fn)(struct redist_region *, void __iomem *)) { int ret = -ENODEV; int i; for (i = 0; i < gic_data.nr_redist_regions; i++) { void __iomem *ptr = gic_data.redist_regions[i].redist_base; u64 typer; u32 reg; reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK; if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */ pr_warn("No redistributor present @%p\n", ptr); break; } do { typer = gic_read_typer(ptr + GICR_TYPER); ret = fn(gic_data.redist_regions + i, ptr); if (!ret) return 0; if (gic_data.redist_regions[i].single_redist) break; if (gic_data.redist_stride) { ptr += gic_data.redist_stride; } else { ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */ if (typer & GICR_TYPER_VLPIS) ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */ } } while (!(typer & GICR_TYPER_LAST)); } return ret ? -ENODEV : 0; } static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr) { unsigned long mpidr; u64 typer; u32 aff; /* * Convert affinity to a 32bit value that can be matched to * GICR_TYPER bits [63:32]. */ mpidr = gic_cpu_to_affinity(smp_processor_id()); aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | MPIDR_AFFINITY_LEVEL(mpidr, 0)); typer = gic_read_typer(ptr + GICR_TYPER); if ((typer >> 32) == aff) { u64 offset = ptr - region->redist_base; raw_spin_lock_init(&gic_data_rdist()->rd_lock); gic_data_rdist_rd_base() = ptr; gic_data_rdist()->phys_base = region->phys_base + offset; pr_info("CPU%d: found redistributor %lx region %d:%pa\n", smp_processor_id(), mpidr, (int)(region - gic_data.redist_regions), &gic_data_rdist()->phys_base); return 0; } /* Try next one */ return 1; } static int gic_populate_rdist(void) { if (gic_iterate_rdists(__gic_populate_rdist) == 0) return 0; /* We couldn't even deal with ourselves... */ WARN(true, "CPU%d: mpidr %lx has no re-distributor!\n", smp_processor_id(), (unsigned long)cpu_logical_map(smp_processor_id())); return -ENODEV; } static int __gic_update_rdist_properties(struct redist_region *region, void __iomem *ptr) { u64 typer = gic_read_typer(ptr + GICR_TYPER); u32 ctlr = readl_relaxed(ptr + GICR_CTLR); /* Boot-time cleanup */ if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) { u64 val; /* Deactivate any present vPE */ val = gicr_read_vpendbaser(ptr + SZ_128K + GICR_VPENDBASER); if (val & GICR_VPENDBASER_Valid) gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast, ptr + SZ_128K + GICR_VPENDBASER); /* Mark the VPE table as invalid */ val = gicr_read_vpropbaser(ptr + SZ_128K + GICR_VPROPBASER); val &= ~GICR_VPROPBASER_4_1_VALID; gicr_write_vpropbaser(val, ptr + SZ_128K + GICR_VPROPBASER); } gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS); /* * TYPER.RVPEID implies some form of DirectLPI, no matter what the * doc says... :-/ And CTLR.IR implies another subset of DirectLPI * that the ITS driver can make use of for LPIs (and not VLPIs). * * These are 3 different ways to express the same thing, depending * on the revision of the architecture and its relaxations over * time. Just group them under the 'direct_lpi' banner. */ gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID); gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) | !!(ctlr & GICR_CTLR_IR) | gic_data.rdists.has_rvpeid); gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY); /* Detect non-sensical configurations */ if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) { gic_data.rdists.has_direct_lpi = false; gic_data.rdists.has_vlpis = false; gic_data.rdists.has_rvpeid = false; } gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr); return 1; } static void gic_update_rdist_properties(void) { gic_data.ppi_nr = UINT_MAX; gic_iterate_rdists(__gic_update_rdist_properties); if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; pr_info("GICv3 features: %d PPIs%s%s\n", gic_data.ppi_nr, gic_data.has_rss ? ", RSS" : "", gic_data.rdists.has_direct_lpi ? ", DirectLPI" : ""); if (gic_data.rdists.has_vlpis) pr_info("GICv4 features: %s%s%s\n", gic_data.rdists.has_direct_lpi ? "DirectLPI " : "", gic_data.rdists.has_rvpeid ? "RVPEID " : "", gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : ""); } static void gic_cpu_sys_reg_enable(void) { /* * Need to check that the SRE bit has actually been set. If * not, it means that SRE is disabled at EL2. We're going to * die painfully, and there is nothing we can do about it. * * Kindly inform the luser. */ if (!gic_enable_sre()) pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n"); } static void gic_cpu_sys_reg_init(void) { int i, cpu = smp_processor_id(); u64 mpidr = gic_cpu_to_affinity(cpu); u64 need_rss = MPIDR_RS(mpidr); bool group0; u32 pribits; pribits = gic_get_pribits(); group0 = gic_has_group0(); /* Set priority mask register */ if (!gic_prio_masking_enabled()) { write_gicreg(DEFAULT_PMR_VALUE, ICC_PMR_EL1); } else if (gic_supports_nmi()) { /* * Check that all CPUs use the same priority space. * * If there's a mismatch with the boot CPU, the system is * likely to die as interrupt masking will not work properly on * all CPUs. */ WARN_ON(group0 != cpus_have_group0); WARN_ON(gic_dist_security_disabled() != cpus_have_security_disabled); } /* * Some firmwares hand over to the kernel with the BPR changed from * its reset value (and with a value large enough to prevent * any pre-emptive interrupts from working at all). Writing a zero * to BPR restores is reset value. */ gic_write_bpr1(0); if (static_branch_likely(&supports_deactivate_key)) { /* EOI drops priority only (mode 1) */ gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop); } else { /* EOI deactivates interrupt too (mode 0) */ gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir); } /* Always whack Group0 before Group1 */ if (group0) { switch(pribits) { case 8: case 7: write_gicreg(0, ICC_AP0R3_EL1); write_gicreg(0, ICC_AP0R2_EL1); fallthrough; case 6: write_gicreg(0, ICC_AP0R1_EL1); fallthrough; case 5: case 4: write_gicreg(0, ICC_AP0R0_EL1); } isb(); } switch(pribits) { case 8: case 7: write_gicreg(0, ICC_AP1R3_EL1); write_gicreg(0, ICC_AP1R2_EL1); fallthrough; case 6: write_gicreg(0, ICC_AP1R1_EL1); fallthrough; case 5: case 4: write_gicreg(0, ICC_AP1R0_EL1); } isb(); /* ... and let's hit the road... */ gic_write_grpen1(1); /* Keep the RSS capability status in per_cpu variable */ per_cpu(has_rss, cpu) = !!(gic_read_ctlr() & ICC_CTLR_EL1_RSS); /* Check all the CPUs have capable of sending SGIs to other CPUs */ for_each_online_cpu(i) { bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu); need_rss |= MPIDR_RS(gic_cpu_to_affinity(i)); if (need_rss && (!have_rss)) pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n", cpu, (unsigned long)mpidr, i, (unsigned long)gic_cpu_to_affinity(i)); } /** * GIC spec says, when ICC_CTLR_EL1.RSS==1 and GICD_TYPER.RSS==0, * writing ICC_ASGI1R_EL1 register with RS != 0 is a CONSTRAINED * UNPREDICTABLE choice of : * - The write is ignored. * - The RS field is treated as 0. */ if (need_rss && (!gic_data.has_rss)) pr_crit_once("RSS is required but GICD doesn't support it\n"); } static bool gicv3_nolpi; static int __init gicv3_nolpi_cfg(char *buf) { return kstrtobool(buf, &gicv3_nolpi); } early_param("irqchip.gicv3_nolpi", gicv3_nolpi_cfg); static int gic_dist_supports_lpis(void) { return (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && !!(readl_relaxed(gic_data.dist_base + GICD_TYPER) & GICD_TYPER_LPIS) && !gicv3_nolpi); } static void gic_cpu_init(void) { void __iomem *rbase; int i; /* Register ourselves with the rest of the world */ if (gic_populate_rdist()) return; gic_enable_redist(true); WARN((gic_data.ppi_nr > 16 || GIC_ESPI_NR != 0) && !(gic_read_ctlr() & ICC_CTLR_EL1_ExtRange), "Distributor has extended ranges, but CPU%d doesn't\n", smp_processor_id()); rbase = gic_data_rdist_sgi_base(); /* Configure SGIs/PPIs as non-secure Group-1 */ for (i = 0; i < gic_data.ppi_nr + SGI_NR; i += 32) writel_relaxed(~0, rbase + GICR_IGROUPR0 + i / 8); gic_cpu_config(rbase, gic_data.ppi_nr + SGI_NR, dist_prio_irq); gic_redist_wait_for_rwp(); /* initialise system registers */ gic_cpu_sys_reg_init(); } #ifdef CONFIG_SMP #define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT) #define MPIDR_TO_SGI_CLUSTER_ID(mpidr) ((mpidr) & ~0xFUL) /* * gic_starting_cpu() is called after the last point where cpuhp is allowed * to fail. So pre check for problems earlier. */ static int gic_check_rdist(unsigned int cpu) { if (cpumask_test_cpu(cpu, &broken_rdists)) return -EINVAL; return 0; } static int gic_starting_cpu(unsigned int cpu) { gic_cpu_sys_reg_enable(); gic_cpu_init(); if (gic_dist_supports_lpis()) its_cpu_init(); return 0; } static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, unsigned long cluster_id) { int next_cpu, cpu = *base_cpu; unsigned long mpidr; u16 tlist = 0; mpidr = gic_cpu_to_affinity(cpu); while (cpu < nr_cpu_ids) { tlist |= 1 << (mpidr & 0xf); next_cpu = cpumask_next(cpu, mask); if (next_cpu >= nr_cpu_ids) goto out; cpu = next_cpu; mpidr = gic_cpu_to_affinity(cpu); if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) { cpu--; goto out; } } out: *base_cpu = cpu; return tlist; } #define MPIDR_TO_SGI_AFFINITY(cluster_id, level) \ (MPIDR_AFFINITY_LEVEL(cluster_id, level) \ << ICC_SGI1R_AFFINITY_## level ##_SHIFT) static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq) { u64 val; val = (MPIDR_TO_SGI_AFFINITY(cluster_id, 3) | MPIDR_TO_SGI_AFFINITY(cluster_id, 2) | irq << ICC_SGI1R_SGI_ID_SHIFT | MPIDR_TO_SGI_AFFINITY(cluster_id, 1) | MPIDR_TO_SGI_RS(cluster_id) | tlist << ICC_SGI1R_TARGET_LIST_SHIFT); pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); gic_write_sgi1r(val); } static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask) { int cpu; if (WARN_ON(d->hwirq >= 16)) return; /* * Ensure that stores to Normal memory are visible to the * other CPUs before issuing the IPI. */ dsb(ishst); for_each_cpu(cpu, mask) { u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(gic_cpu_to_affinity(cpu)); u16 tlist; tlist = gic_compute_target_list(&cpu, mask, cluster_id); gic_send_sgi(cluster_id, tlist, d->hwirq); } /* Force the above writes to ICC_SGI1R_EL1 to be executed */ isb(); } static void __init gic_smp_init(void) { struct irq_fwspec sgi_fwspec = { .fwnode = gic_data.fwnode, .param_count = 1, }; int base_sgi; cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN, "irqchip/arm/gicv3:checkrdist", gic_check_rdist, NULL); cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING, "irqchip/arm/gicv3:starting", gic_starting_cpu, NULL); /* Register all 8 non-secure SGIs */ base_sgi = irq_domain_alloc_irqs(gic_data.domain, 8, NUMA_NO_NODE, &sgi_fwspec); if (WARN_ON(base_sgi <= 0)) return; set_smp_ipi_range(base_sgi, 8); } static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { unsigned int cpu; u32 offset, index; void __iomem *reg; int enabled; u64 val; if (force) cpu = cpumask_first(mask_val); else cpu = cpumask_any_and(mask_val, cpu_online_mask); if (cpu >= nr_cpu_ids) return -EINVAL; if (gic_irq_in_rdist(d)) return -EINVAL; /* If interrupt was enabled, disable it first */ enabled = gic_peek_irq(d, GICD_ISENABLER); if (enabled) gic_mask_irq(d); offset = convert_offset_index(d, GICD_IROUTER, &index); reg = gic_dist_base(d) + offset + (index * 8); val = gic_cpu_to_affinity(cpu); gic_write_irouter(val, reg); /* * If the interrupt was enabled, enabled it again. Otherwise, * just wait for the distributor to have digested our changes. */ if (enabled) gic_unmask_irq(d); irq_data_update_effective_affinity(d, cpumask_of(cpu)); return IRQ_SET_MASK_OK_DONE; } #else #define gic_set_affinity NULL #define gic_ipi_send_mask NULL #define gic_smp_init() do { } while(0) #endif static int gic_retrigger(struct irq_data *data) { return !gic_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING, true); } #ifdef CONFIG_CPU_PM static int gic_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { if (cmd == CPU_PM_EXIT) { if (gic_dist_security_disabled()) gic_enable_redist(true); gic_cpu_sys_reg_enable(); gic_cpu_sys_reg_init(); } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) { gic_write_grpen1(0); gic_enable_redist(false); } return NOTIFY_OK; } static struct notifier_block gic_cpu_pm_notifier_block = { .notifier_call = gic_cpu_pm_notifier, }; static void gic_cpu_pm_init(void) { cpu_pm_register_notifier(&gic_cpu_pm_notifier_block); } #else static inline void gic_cpu_pm_init(void) { } #endif /* CONFIG_CPU_PM */ static struct irq_chip gic_chip = { .name = "GICv3", .irq_mask = gic_mask_irq, .irq_unmask = gic_unmask_irq, .irq_eoi = gic_eoi_irq, .irq_set_type = gic_set_type, .irq_set_affinity = gic_set_affinity, .irq_retrigger = gic_retrigger, .irq_get_irqchip_state = gic_irq_get_irqchip_state, .irq_set_irqchip_state = gic_irq_set_irqchip_state, .irq_nmi_setup = gic_irq_nmi_setup, .irq_nmi_teardown = gic_irq_nmi_teardown, .ipi_send_mask = gic_ipi_send_mask, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, }; static struct irq_chip gic_eoimode1_chip = { .name = "GICv3", .irq_mask = gic_eoimode1_mask_irq, .irq_unmask = gic_unmask_irq, .irq_eoi = gic_eoimode1_eoi_irq, .irq_set_type = gic_set_type, .irq_set_affinity = gic_set_affinity, .irq_retrigger = gic_retrigger, .irq_get_irqchip_state = gic_irq_get_irqchip_state, .irq_set_irqchip_state = gic_irq_set_irqchip_state, .irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity, .irq_nmi_setup = gic_irq_nmi_setup, .irq_nmi_teardown = gic_irq_nmi_teardown, .ipi_send_mask = gic_ipi_send_mask, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, }; static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { struct irq_chip *chip = &gic_chip; struct irq_data *irqd = irq_desc_get_irq_data(irq_to_desc(irq)); if (static_branch_likely(&supports_deactivate_key)) chip = &gic_eoimode1_chip; switch (__get_intid_range(hw)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: irq_set_percpu_devid(irq); irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_percpu_devid_irq, NULL, NULL); break; case SPI_RANGE: case ESPI_RANGE: irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_fasteoi_irq, NULL, NULL); irq_set_probe(irq); irqd_set_single_target(irqd); break; case LPI_RANGE: if (!gic_dist_supports_lpis()) return -EPERM; irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_fasteoi_irq, NULL, NULL); break; default: return -EPERM; } /* Prevents SW retriggers which mess up the ACK/EOI ordering */ irqd_set_handle_enforce_irqctx(irqd); return 0; } static int gic_irq_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { if (fwspec->param_count == 1 && fwspec->param[0] < 16) { *hwirq = fwspec->param[0]; *type = IRQ_TYPE_EDGE_RISING; return 0; } if (is_of_node(fwspec->fwnode)) { if (fwspec->param_count < 3) return -EINVAL; switch (fwspec->param[0]) { case 0: /* SPI */ *hwirq = fwspec->param[1] + 32; break; case 1: /* PPI */ *hwirq = fwspec->param[1] + 16; break; case 2: /* ESPI */ *hwirq = fwspec->param[1] + ESPI_BASE_INTID; break; case 3: /* EPPI */ *hwirq = fwspec->param[1] + EPPI_BASE_INTID; break; case GIC_IRQ_TYPE_LPI: /* LPI */ *hwirq = fwspec->param[1]; break; case GIC_IRQ_TYPE_PARTITION: *hwirq = fwspec->param[1]; if (fwspec->param[1] >= 16) *hwirq += EPPI_BASE_INTID - 16; else *hwirq += 16; break; default: return -EINVAL; } *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; /* * Make it clear that broken DTs are... broken. * Partitioned PPIs are an unfortunate exception. */ WARN_ON(*type == IRQ_TYPE_NONE && fwspec->param[0] != GIC_IRQ_TYPE_PARTITION); return 0; } if (is_fwnode_irqchip(fwspec->fwnode)) { if(fwspec->param_count != 2) return -EINVAL; if (fwspec->param[0] < 16) { pr_err(FW_BUG "Illegal GSI%d translation request\n", fwspec->param[0]); return -EINVAL; } *hwirq = fwspec->param[0]; *type = fwspec->param[1]; WARN_ON(*type == IRQ_TYPE_NONE); return 0; } return -EINVAL; } static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { int i, ret; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; struct irq_fwspec *fwspec = arg; ret = gic_irq_domain_translate(domain, fwspec, &hwirq, &type); if (ret) return ret; for (i = 0; i < nr_irqs; i++) { ret = gic_irq_domain_map(domain, virq + i, hwirq + i); if (ret) return ret; } return 0; } static void gic_irq_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { int i; for (i = 0; i < nr_irqs; i++) { struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); irq_set_handler(virq + i, NULL); irq_domain_reset_irq_data(d); } } static bool fwspec_is_partitioned_ppi(struct irq_fwspec *fwspec, irq_hw_number_t hwirq) { enum gic_intid_range range; if (!gic_data.ppi_descs) return false; if (!is_of_node(fwspec->fwnode)) return false; if (fwspec->param_count < 4 || !fwspec->param[3]) return false; range = __get_intid_range(hwirq); if (range != PPI_RANGE && range != EPPI_RANGE) return false; return true; } static int gic_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token) { unsigned int type, ret, ppi_idx; irq_hw_number_t hwirq; /* Not for us */ if (fwspec->fwnode != d->fwnode) return 0; /* Handle pure domain searches */ if (!fwspec->param_count) return d->bus_token == bus_token; /* If this is not DT, then we have a single domain */ if (!is_of_node(fwspec->fwnode)) return 1; ret = gic_irq_domain_translate(d, fwspec, &hwirq, &type); if (WARN_ON_ONCE(ret)) return 0; if (!fwspec_is_partitioned_ppi(fwspec, hwirq)) return d == gic_data.domain; /* * If this is a PPI and we have a 4th (non-null) parameter, * then we need to match the partition domain. */ ppi_idx = __gic_get_ppi_index(hwirq); return d == partition_get_domain(gic_data.ppi_descs[ppi_idx]); } static const struct irq_domain_ops gic_irq_domain_ops = { .translate = gic_irq_domain_translate, .alloc = gic_irq_domain_alloc, .free = gic_irq_domain_free, .select = gic_irq_domain_select, }; static int partition_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { unsigned long ppi_intid; struct device_node *np; unsigned int ppi_idx; int ret; if (!gic_data.ppi_descs) return -ENOMEM; np = of_find_node_by_phandle(fwspec->param[3]); if (WARN_ON(!np)) return -EINVAL; ret = gic_irq_domain_translate(d, fwspec, &ppi_intid, type); if (WARN_ON_ONCE(ret)) return 0; ppi_idx = __gic_get_ppi_index(ppi_intid); ret = partition_translate_id(gic_data.ppi_descs[ppi_idx], of_node_to_fwnode(np)); if (ret < 0) return ret; *hwirq = ret; *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; return 0; } static const struct irq_domain_ops partition_domain_ops = { .translate = partition_domain_translate, .select = gic_irq_domain_select, }; static bool gic_enable_quirk_msm8996(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_GICR_WAKER_MSM8996; return true; } static bool gic_enable_quirk_cavium_38539(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539; return true; } static bool gic_enable_quirk_hip06_07(void *data) { struct gic_chip_data *d = data; /* * HIP06 GICD_IIDR clashes with GIC-600 product number (despite * not being an actual ARM implementation). The saving grace is * that GIC-600 doesn't have ESPI, so nothing to do in that case. * HIP07 doesn't even have a proper IIDR, and still pretends to * have ESPI. In both cases, put them right. */ if (d->rdists.gicd_typer & GICD_TYPER_ESPI) { /* Zero both ESPI and the RES0 field next to it... */ d->rdists.gicd_typer &= ~GENMASK(9, 8); return true; } return false; } #define T241_CHIPN_MASK GENMASK_ULL(45, 44) #define T241_CHIP_GICDA_OFFSET 0x1580000 #define SMCCC_SOC_ID_T241 0x036b0241 static bool gic_enable_quirk_nvidia_t241(void *data) { s32 soc_id = arm_smccc_get_soc_id_version(); unsigned long chip_bmask = 0; phys_addr_t phys; u32 i; /* Check JEP106 code for NVIDIA T241 chip (036b:0241) */ if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241)) return false; /* Find the chips based on GICR regions PHYS addr */ for (i = 0; i < gic_data.nr_redist_regions; i++) { chip_bmask |= BIT(FIELD_GET(T241_CHIPN_MASK, (u64)gic_data.redist_regions[i].phys_base)); } if (hweight32(chip_bmask) < 3) return false; /* Setup GICD alias regions */ for (i = 0; i < ARRAY_SIZE(t241_dist_base_alias); i++) { if (chip_bmask & BIT(i)) { phys = gic_data.dist_phys_base + T241_CHIP_GICDA_OFFSET; phys |= FIELD_PREP(T241_CHIPN_MASK, i); t241_dist_base_alias[i] = ioremap(phys, SZ_64K); WARN_ON_ONCE(!t241_dist_base_alias[i]); } } static_branch_enable(&gic_nvidia_t241_erratum); return true; } static bool gic_enable_quirk_asr8601(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_ASR_ERRATUM_8601001; return true; } static bool gic_enable_quirk_arm64_2941627(void *data) { static_branch_enable(&gic_arm64_2941627_erratum); return true; } static bool rd_set_non_coherent(void *data) { struct gic_chip_data *d = data; d->rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE; return true; } static const struct gic_quirk gic_quirks[] = { { .desc = "GICv3: Qualcomm MSM8996 broken firmware", .compatible = "qcom,msm8996-gic-v3", .init = gic_enable_quirk_msm8996, }, { .desc = "GICv3: ASR erratum 8601001", .compatible = "asr,asr8601-gic-v3", .init = gic_enable_quirk_asr8601, }, { .desc = "GICv3: HIP06 erratum 161010803", .iidr = 0x0204043b, .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, { .desc = "GICv3: HIP07 erratum 161010803", .iidr = 0x00000000, .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, { /* * Reserved register accesses generate a Synchronous * External Abort. This erratum applies to: * - ThunderX: CN88xx * - OCTEON TX: CN83xx, CN81xx * - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* */ .desc = "GICv3: Cavium erratum 38539", .iidr = 0xa000034c, .mask = 0xe8f00fff, .init = gic_enable_quirk_cavium_38539, }, { .desc = "GICv3: NVIDIA erratum T241-FABRIC-4", .iidr = 0x0402043b, .mask = 0xffffffff, .init = gic_enable_quirk_nvidia_t241, }, { /* * GIC-700: 2941627 workaround - IP variant [0,1] * */ .desc = "GICv3: ARM64 erratum 2941627", .iidr = 0x0400043b, .mask = 0xff0e0fff, .init = gic_enable_quirk_arm64_2941627, }, { /* * GIC-700: 2941627 workaround - IP variant [2] */ .desc = "GICv3: ARM64 erratum 2941627", .iidr = 0x0402043b, .mask = 0xff0f0fff, .init = gic_enable_quirk_arm64_2941627, }, { .desc = "GICv3: non-coherent attribute", .property = "dma-noncoherent", .init = rd_set_non_coherent, }, { } }; static void gic_enable_nmi_support(void) { int i; if (!gic_prio_masking_enabled()) return; rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR, sizeof(*rdist_nmi_refs), GFP_KERNEL); if (!rdist_nmi_refs) return; for (i = 0; i < gic_data.ppi_nr + SGI_NR; i++) refcount_set(&rdist_nmi_refs[i], 0); pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n", gic_has_relaxed_pmr_sync() ? "relaxed" : "forced"); static_branch_enable(&supports_pseudo_nmis); if (static_branch_likely(&supports_deactivate_key)) gic_eoimode1_chip.flags |= IRQCHIP_SUPPORTS_NMI; else gic_chip.flags |= IRQCHIP_SUPPORTS_NMI; } static int __init gic_init_bases(phys_addr_t dist_phys_base, void __iomem *dist_base, struct redist_region *rdist_regs, u32 nr_redist_regions, u64 redist_stride, struct fwnode_handle *handle) { u32 typer; int err; if (!is_hyp_mode_available()) static_branch_disable(&supports_deactivate_key); if (static_branch_likely(&supports_deactivate_key)) pr_info("GIC: Using split EOI/Deactivate mode\n"); gic_data.fwnode = handle; gic_data.dist_phys_base = dist_phys_base; gic_data.dist_base = dist_base; gic_data.redist_regions = rdist_regs; gic_data.nr_redist_regions = nr_redist_regions; gic_data.redist_stride = redist_stride; /* * Find out how many interrupts are supported. */ typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); gic_data.rdists.gicd_typer = typer; gic_enable_quirks(readl_relaxed(gic_data.dist_base + GICD_IIDR), gic_quirks, &gic_data); pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32); pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR); /* * ThunderX1 explodes on reading GICD_TYPER2, in violation of the * architecture spec (which says that reserved registers are RES0). */ if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539)) gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, &gic_data); gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist)); if (!static_branch_unlikely(&gic_nvidia_t241_erratum)) { /* Disable GICv4.x features for the erratum T241-FABRIC-4 */ gic_data.rdists.has_rvpeid = true; gic_data.rdists.has_vlpis = true; gic_data.rdists.has_direct_lpi = true; gic_data.rdists.has_vpend_valid_dirty = true; } if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { err = -ENOMEM; goto out_free; } irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); gic_data.has_rss = !!(typer & GICD_TYPER_RSS); if (typer & GICD_TYPER_MBIS) { err = mbi_init(handle, gic_data.domain); if (err) pr_err("Failed to initialize MBIs\n"); } set_handle_irq(gic_handle_irq); gic_update_rdist_properties(); gic_cpu_sys_reg_enable(); gic_prio_init(); gic_dist_init(); gic_cpu_init(); gic_enable_nmi_support(); gic_smp_init(); gic_cpu_pm_init(); if (gic_dist_supports_lpis()) { its_init(handle, &gic_data.rdists, gic_data.domain, dist_prio_irq); its_cpu_init(); its_lpi_memreserve_init(); } else { if (IS_ENABLED(CONFIG_ARM_GIC_V2M)) gicv2m_init(handle, gic_data.domain); } return 0; out_free: if (gic_data.domain) irq_domain_remove(gic_data.domain); free_percpu(gic_data.rdists.rdist); return err; } static int __init gic_validate_dist_version(void __iomem *dist_base) { u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) return -ENODEV; return 0; } /* Create all possible partitions at boot time */ static void __init gic_populate_ppi_partitions(struct device_node *gic_node) { struct device_node *parts_node, *child_part; int part_idx = 0, i; int nr_parts; struct partition_affinity *parts; parts_node = of_get_child_by_name(gic_node, "ppi-partitions"); if (!parts_node) return; gic_data.ppi_descs = kcalloc(gic_data.ppi_nr, sizeof(*gic_data.ppi_descs), GFP_KERNEL); if (!gic_data.ppi_descs) goto out_put_node; nr_parts = of_get_child_count(parts_node); if (!nr_parts) goto out_put_node; parts = kcalloc(nr_parts, sizeof(*parts), GFP_KERNEL); if (WARN_ON(!parts)) goto out_put_node; for_each_child_of_node(parts_node, child_part) { struct partition_affinity *part; int n; part = &parts[part_idx]; part->partition_id = of_node_to_fwnode(child_part); pr_info("GIC: PPI partition %pOFn[%d] { ", child_part, part_idx); n = of_property_count_elems_of_size(child_part, "affinity", sizeof(u32)); WARN_ON(n <= 0); for (i = 0; i < n; i++) { int err, cpu; u32 cpu_phandle; struct device_node *cpu_node; err = of_property_read_u32_index(child_part, "affinity", i, &cpu_phandle); if (WARN_ON(err)) continue; cpu_node = of_find_node_by_phandle(cpu_phandle); if (WARN_ON(!cpu_node)) continue; cpu = of_cpu_node_to_id(cpu_node); if (WARN_ON(cpu < 0)) { of_node_put(cpu_node); continue; } pr_cont("%pOF[%d] ", cpu_node, cpu); cpumask_set_cpu(cpu, &part->mask); of_node_put(cpu_node); } pr_cont("}\n"); part_idx++; } for (i = 0; i < gic_data.ppi_nr; i++) { unsigned int irq; struct partition_desc *desc; struct irq_fwspec ppi_fwspec = { .fwnode = gic_data.fwnode, .param_count = 3, .param = { [0] = GIC_IRQ_TYPE_PARTITION, [1] = i, [2] = IRQ_TYPE_NONE, }, }; irq = irq_create_fwspec_mapping(&ppi_fwspec); if (WARN_ON(!irq)) continue; desc = partition_create_desc(gic_data.fwnode, parts, nr_parts, irq, &partition_domain_ops); if (WARN_ON(!desc)) continue; gic_data.ppi_descs[i] = desc; } out_put_node: of_node_put(parts_node); } static void __init gic_of_setup_kvm_info(struct device_node *node, u32 nr_redist_regions) { int ret; struct resource r; gic_v3_kvm_info.type = GIC_V3; gic_v3_kvm_info.maint_irq = irq_of_parse_and_map(node, 0); if (!gic_v3_kvm_info.maint_irq) return; /* Also skip GICD, GICC, GICH */ ret = of_address_to_resource(node, nr_redist_regions + 3, &r); if (!ret) gic_v3_kvm_info.vcpu = r; gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; vgic_set_kvm_info(&gic_v3_kvm_info); } static void gic_request_region(resource_size_t base, resource_size_t size, const char *name) { if (!request_mem_region(base, size, name)) pr_warn_once(FW_BUG "%s region %pa has overlapping address\n", name, &base); } static void __iomem *gic_of_iomap(struct device_node *node, int idx, const char *name, struct resource *res) { void __iomem *base; int ret; ret = of_address_to_resource(node, idx, res); if (ret) return IOMEM_ERR_PTR(ret); gic_request_region(res->start, resource_size(res), name); base = of_iomap(node, idx); return base ?: IOMEM_ERR_PTR(-ENOMEM); } static int __init gic_of_init(struct device_node *node, struct device_node *parent) { phys_addr_t dist_phys_base; void __iomem *dist_base; struct redist_region *rdist_regs; struct resource res; u64 redist_stride; u32 nr_redist_regions; int err, i; dist_base = gic_of_iomap(node, 0, "GICD", &res); if (IS_ERR(dist_base)) { pr_err("%pOF: unable to map gic dist registers\n", node); return PTR_ERR(dist_base); } dist_phys_base = res.start; err = gic_validate_dist_version(dist_base); if (err) { pr_err("%pOF: no distributor detected, giving up\n", node); goto out_unmap_dist; } if (of_property_read_u32(node, "#redistributor-regions", &nr_redist_regions)) nr_redist_regions = 1; rdist_regs = kcalloc(nr_redist_regions, sizeof(*rdist_regs), GFP_KERNEL); if (!rdist_regs) { err = -ENOMEM; goto out_unmap_dist; } for (i = 0; i < nr_redist_regions; i++) { rdist_regs[i].redist_base = gic_of_iomap(node, 1 + i, "GICR", &res); if (IS_ERR(rdist_regs[i].redist_base)) { pr_err("%pOF: couldn't map region %d\n", node, i); err = -ENODEV; goto out_unmap_rdist; } rdist_regs[i].phys_base = res.start; } if (of_property_read_u64(node, "redistributor-stride", &redist_stride)) redist_stride = 0; gic_enable_of_quirks(node, gic_quirks, &gic_data); err = gic_init_bases(dist_phys_base, dist_base, rdist_regs, nr_redist_regions, redist_stride, &node->fwnode); if (err) goto out_unmap_rdist; gic_populate_ppi_partitions(node); if (static_branch_likely(&supports_deactivate_key)) gic_of_setup_kvm_info(node, nr_redist_regions); return 0; out_unmap_rdist: for (i = 0; i < nr_redist_regions; i++) if (rdist_regs[i].redist_base && !IS_ERR(rdist_regs[i].redist_base)) iounmap(rdist_regs[i].redist_base); kfree(rdist_regs); out_unmap_dist: iounmap(dist_base); return err; } IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init); #ifdef CONFIG_ACPI static struct { void __iomem *dist_base; struct redist_region *redist_regs; u32 nr_redist_regions; bool single_redist; int enabled_rdists; u32 maint_irq; int maint_irq_mode; phys_addr_t vcpu_base; } acpi_data __initdata; static void __init gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base) { static int count = 0; acpi_data.redist_regs[count].phys_base = phys_base; acpi_data.redist_regs[count].redist_base = redist_base; acpi_data.redist_regs[count].single_redist = acpi_data.single_redist; count++; } static int __init gic_acpi_parse_madt_redist(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_redistributor *redist = (struct acpi_madt_generic_redistributor *)header; void __iomem *redist_base; redist_base = ioremap(redist->base_address, redist->length); if (!redist_base) { pr_err("Couldn't map GICR region @%llx\n", redist->base_address); return -ENOMEM; } if (acpi_get_madt_revision() >= 7 && (redist->flags & ACPI_MADT_GICR_NON_COHERENT)) gic_data.rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE; gic_request_region(redist->base_address, redist->length, "GICR"); gic_acpi_register_redist(redist->base_address, redist_base); return 0; } static int __init gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; u32 reg = readl_relaxed(acpi_data.dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2; void __iomem *redist_base; /* Neither enabled or online capable means it doesn't exist, skip it */ if (!(gicc->flags & (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) return 0; /* * Capable but disabled CPUs can be brought online later. What about * the redistributor? ACPI doesn't want to say! * Virtual hotplug systems can use the MADT's "always-on" GICR entries. * Otherwise, prevent such CPUs from being brought online. */ if (!(gicc->flags & ACPI_MADT_ENABLED)) { int cpu = get_cpu_for_acpi_id(gicc->uid); pr_warn("CPU %u's redistributor is inaccessible: this CPU can't be brought online\n", cpu); if (cpu >= 0) cpumask_set_cpu(cpu, &broken_rdists); return 0; } redist_base = ioremap(gicc->gicr_base_address, size); if (!redist_base) return -ENOMEM; gic_request_region(gicc->gicr_base_address, size, "GICR"); if (acpi_get_madt_revision() >= 7 && (gicc->flags & ACPI_MADT_GICC_NON_COHERENT)) gic_data.rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE; gic_acpi_register_redist(gicc->gicr_base_address, redist_base); return 0; } static int __init gic_acpi_collect_gicr_base(void) { acpi_tbl_entry_handler redist_parser; enum acpi_madt_type type; if (acpi_data.single_redist) { type = ACPI_MADT_TYPE_GENERIC_INTERRUPT; redist_parser = gic_acpi_parse_madt_gicc; } else { type = ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR; redist_parser = gic_acpi_parse_madt_redist; } /* Collect redistributor base addresses in GICR entries */ if (acpi_table_parse_madt(type, redist_parser, 0) > 0) return 0; pr_info("No valid GICR entries exist\n"); return -ENODEV; } static int __init gic_acpi_match_gicr(union acpi_subtable_headers *header, const unsigned long end) { /* Subtable presence means that redist exists, that's it */ return 0; } static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; /* * If GICC is enabled and has valid gicr base address, then it means * GICR base is presented via GICC. The redistributor is only known to * be accessible if the GICC is marked as enabled. If this bit is not * set, we'd need to add the redistributor at runtime, which isn't * supported. */ if (gicc->flags & ACPI_MADT_ENABLED && gicc->gicr_base_address) acpi_data.enabled_rdists++; return 0; } static int __init gic_acpi_count_gicr_regions(void) { int count; /* * Count how many redistributor regions we have. It is not allowed * to mix redistributor description, GICR and GICC subtables have to be * mutually exclusive. */ count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR, gic_acpi_match_gicr, 0); if (count > 0) { acpi_data.single_redist = false; return count; } count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, gic_acpi_match_gicc, 0); if (count > 0) { acpi_data.single_redist = true; count = acpi_data.enabled_rdists; } return count; } static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header, struct acpi_probe_entry *ape) { struct acpi_madt_generic_distributor *dist; int count; dist = (struct acpi_madt_generic_distributor *)header; if (dist->version != ape->driver_data) return false; /* We need to do that exercise anyway, the sooner the better */ count = gic_acpi_count_gicr_regions(); if (count <= 0) return false; acpi_data.nr_redist_regions = count; return true; } static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; int maint_irq_mode; static int first_madt = true; if (!(gicc->flags & (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) return 0; maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ? ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE; if (first_madt) { first_madt = false; acpi_data.maint_irq = gicc->vgic_interrupt; acpi_data.maint_irq_mode = maint_irq_mode; acpi_data.vcpu_base = gicc->gicv_base_address; return 0; } /* * The maintenance interrupt and GICV should be the same for every CPU */ if ((acpi_data.maint_irq != gicc->vgic_interrupt) || (acpi_data.maint_irq_mode != maint_irq_mode) || (acpi_data.vcpu_base != gicc->gicv_base_address)) return -EINVAL; return 0; } static bool __init gic_acpi_collect_virt_info(void) { int count; count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, gic_acpi_parse_virt_madt_gicc, 0); return (count > 0); } #define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K) #define ACPI_GICV2_VCTRL_MEM_SIZE (SZ_4K) #define ACPI_GICV2_VCPU_MEM_SIZE (SZ_8K) static void __init gic_acpi_setup_kvm_info(void) { int irq; if (!gic_acpi_collect_virt_info()) { pr_warn("Unable to get hardware information used for virtualization\n"); return; } gic_v3_kvm_info.type = GIC_V3; irq = acpi_register_gsi(NULL, acpi_data.maint_irq, acpi_data.maint_irq_mode, ACPI_ACTIVE_HIGH); if (irq <= 0) return; gic_v3_kvm_info.maint_irq = irq; if (acpi_data.vcpu_base) { struct resource *vcpu = &gic_v3_kvm_info.vcpu; vcpu->flags = IORESOURCE_MEM; vcpu->start = acpi_data.vcpu_base; vcpu->end = vcpu->start + ACPI_GICV2_VCPU_MEM_SIZE - 1; } gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; vgic_set_kvm_info(&gic_v3_kvm_info); } static struct fwnode_handle *gsi_domain_handle; static struct fwnode_handle *gic_v3_get_gsi_domain_id(u32 gsi) { return gsi_domain_handle; } static int __init gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_distributor *dist; size_t size; int i, err; /* Get distributor base address */ dist = (struct acpi_madt_generic_distributor *)header; acpi_data.dist_base = ioremap(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE); if (!acpi_data.dist_base) { pr_err("Unable to map GICD registers\n"); return -ENOMEM; } gic_request_region(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE, "GICD"); err = gic_validate_dist_version(acpi_data.dist_base); if (err) { pr_err("No distributor detected at @%p, giving up\n", acpi_data.dist_base); goto out_dist_unmap; } size = sizeof(*acpi_data.redist_regs) * acpi_data.nr_redist_regions; acpi_data.redist_regs = kzalloc(size, GFP_KERNEL); if (!acpi_data.redist_regs) { err = -ENOMEM; goto out_dist_unmap; } err = gic_acpi_collect_gicr_base(); if (err) goto out_redist_unmap; gsi_domain_handle = irq_domain_alloc_fwnode(&dist->base_address); if (!gsi_domain_handle) { err = -ENOMEM; goto out_redist_unmap; } err = gic_init_bases(dist->base_address, acpi_data.dist_base, acpi_data.redist_regs, acpi_data.nr_redist_regions, 0, gsi_domain_handle); if (err) goto out_fwhandle_free; acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, gic_v3_get_gsi_domain_id); if (static_branch_likely(&supports_deactivate_key)) gic_acpi_setup_kvm_info(); return 0; out_fwhandle_free: irq_domain_free_fwnode(gsi_domain_handle); out_redist_unmap: for (i = 0; i < acpi_data.nr_redist_regions; i++) if (acpi_data.redist_regs[i].redist_base) iounmap(acpi_data.redist_regs[i].redist_base); kfree(acpi_data.redist_regs); out_dist_unmap: iounmap(acpi_data.dist_base); return err; } IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V3, gic_acpi_init); IRQCHIP_ACPI_DECLARE(gic_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V4, gic_acpi_init); IRQCHIP_ACPI_DECLARE(gic_v3_or_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_NONE, gic_acpi_init); #endif |
| 534 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/mempool.h> #include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ /* * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify * which does not support FS_ERROR. */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; }; /* * fsnotify group priorities. * Events are sent in order from highest priority to lowest priority. */ enum fsnotify_group_prio { FSNOTIFY_PRIO_NORMAL = 0, /* normal notifiers, no permissions */ FSNOTIFY_PRIO_CONTENT, /* fanotify permission events */ FSNOTIFY_PRIO_PRE_CONTENT, /* fanotify pre-content events */ __FSNOTIFY_PRIO_NUM }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ enum fsnotify_group_prio priority; /* priority for sending events */ bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* Hash table of events for merge */ struct hlist_head *merge_hash; /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* * These helpers are used to prevent deadlock when reclaiming inodes with * evictable marks of the same group that is allocating a new mark. */ static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, FSNOTIFY_EVENT_ERROR, }; struct fs_error_report { int error; struct inode *inode; struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_DENTRY: return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: return NULL; } } static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_DENTRY: /* Non const is needed for dget() */ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; default: return NULL; } } static inline struct super_block *fsnotify_data_sb(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return ((struct inode *)data)->i_sb; case FSNOTIFY_EVENT_DENTRY: return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: return NULL; } } static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_ERROR: return (struct fs_error_report *) data; default: return NULL; } } /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not * the other way around, because an event can match different watched objects * of the same object type. * For example, both parent and child are watching an object of type inode. */ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_INODE, FSNOTIFY_ITER_TYPE_VFSMOUNT, FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, FSNOTIFY_ITER_TYPE_COUNT }; /* The type of object that a mark is attached to */ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { iter_info->report_mask |= (1U << iter_type); } static inline struct fsnotify_mark *fsnotify_iter_mark( struct fsnotify_iter_info *iter_info, int iter_type) { if (fsnotify_iter_should_report_type(iter_info, iter_type)) return iter_info->marks[iter_type]; return NULL; } static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, struct fsnotify_mark **markp) { while (type < FSNOTIFY_ITER_TYPE_COUNT) { *markp = fsnotify_iter_mark(iter, type); if (*markp) break; type++; } return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) #define fsnotify_foreach_iter_mark_type(iter, mark, type) \ for (type = 0; \ type = fsnotify_iter_step(iter, type, &mark), \ type < FSNOTIFY_ITER_TYPE_COUNT; \ type++) /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned char type; /* Type of object [lock] */ unsigned char prio; /* Highest priority group */ #define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ union { /* Object pointer [lock] */ void *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; /* * Container for per-sb fsnotify state (sb marks and more). * Attached lazily on first marked object on the sb and freed when killing sb. */ struct fsnotify_sb_info { struct fsnotify_mark_connector __rcu *sb_marks; /* * Number of inode/mount/sb objects that are being watched in this sb. * Note that inodes objects are currently double-accounted. * * The value in watched_objects[prio] is the number of objects that are * watched by groups of priority >= prio, so watched_objects[0] is the * total number of watched objects in this sb. */ atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM]; }; static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb) { #ifdef CONFIG_FSNOTIFY return READ_ONCE(sb->s_fsnotify_info); #else return NULL; #endif } static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb) { return &fsnotify_sb_info(sb)->watched_objects[0]; } /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ __u32 ignore_mask; /* General fsnotify mark flags */ #define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 /* inotify mark flags */ #define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 #define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 #define FSNOTIFY_MARK_FLAG_HAS_FSID 0x0800 #define FSNOTIFY_MARK_FLAG_WEAK_FSID 0x1000 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask); /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(parent_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return parent_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following fsnotify_set_children_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)); static inline int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *)) { return fsnotify_insert_event(group, event, merge, NULL); } /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) { return mask & FS_Q_OVERFLOW; } static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); return list_empty(&group->notification_list); } extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* * Canonical "ignore mask" including event flags. * * Note the subtle semantic difference from the legacy ->ignored_mask. * ->ignored_mask traditionally only meant which events should be ignored, * while ->ignore_mask also includes flags regarding the type of objects on * which events should be ignored. */ static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) { __u32 ignore_mask = mark->ignore_mask; /* The event flags in ignore mask take effect */ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) return ignore_mask; /* * Legacy behavior: * - Always ignore events on dir * - Ignore events on child if parent is watching children */ ignore_mask |= FS_ISDIR; ignore_mask &= ~FS_EVENT_ON_CHILD; ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; return ignore_mask; } /* Legacy ignored_mask - only event types to ignore */ static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) { return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; } /* * Check if mask (or ignore mask) should be applied depending if victim is a * directory and whether it is reported to a watching parent. */ static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, int iter_type) { /* Should mask be applied to a directory? */ if (is_dir && !(mask & FS_ISDIR)) return false; /* Should mask be applied to a child? */ if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && !(mask & FS_EVENT_ON_CHILD)) return false; return true; } /* * Effective ignore mask taking into account if event victim is a * directory and whether it is reported to a watching parent. */ static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, bool is_dir, int iter_type) { __u32 ignore_mask = fsnotify_ignored_events(mark); if (!ignore_mask) return 0; /* For non-dir and non-child, no need to consult the event flags */ if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) return ignore_mask; ignore_mask = fsnotify_ignore_mask(mark); if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) return 0; return ignore_mask & ALL_FSNOTIFY_EVENTS; } /* Get mask for calculating object interest taking ignore mask into account */ static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) { __u32 mask = mark->mask; if (!fsnotify_ignored_events(mark)) return mask; /* Interest in FS_MODIFY may be needed for clearing ignore mask */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mask |= FS_MODIFY; /* * If mark is interested in ignoring events on children, the object must * show interest in those events for fsnotify_parent() to notice it. */ return mask | mark->ignore_mask; } /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, struct fsnotify_group *group); /* attach the mark to the object */ int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline struct fsnotify_mark *fsnotify_find_inode_mark( struct inode *inode, struct fsnotify_group *group) { return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* Clear all of the marks of a group attached to a given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } #else static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void fsnotify_sb_free(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_H */ |
| 414 508 373 375 193 194 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 | // 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 */ int lockref_get_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_not_zero - Decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count would become zero */ int lockref_put_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count--; if (old.count <= 1) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 1) { lockref->count--; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_put_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 an error. */ 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 */ int lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return 0; lockref->count--; spin_unlock(&lockref->lock); return 1; } 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 */ int lockref_get_not_dead(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count < 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count >= 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 279 263 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 43 43 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2022 Linutronix GmbH, John Ogness // Copyright (C) 2022 Intel, Thomas Gleixner #include <linux/atomic.h> #include <linux/bug.h> #include <linux/console.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/init.h> #include <linux/irqflags.h> #include <linux/kthread.h> #include <linux/minmax.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/slab.h> #include <linux/smp.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include "internal.h" #include "printk_ringbuffer.h" /* * Printk console printing implementation for consoles which does not depend * on the legacy style console_lock mechanism. * * The state of the console is maintained in the "nbcon_state" atomic * variable. * * The console is locked when: * * - The 'prio' field contains the priority of the context that owns the * console. Only higher priority contexts are allowed to take over the * lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked. * * - The 'cpu' field denotes on which CPU the console is locked. It is used * to prevent busy waiting on the same CPU. Also it informs the lock owner * that it has lost the lock in a more complex scenario when the lock was * taken over by a higher priority context, released, and taken on another * CPU with the same priority as the interrupted owner. * * The acquire mechanism uses a few more fields: * * - The 'req_prio' field is used by the handover approach to make the * current owner aware that there is a context with a higher priority * waiting for the friendly handover. * * - The 'unsafe' field allows to take over the console in a safe way in the * middle of emitting a message. The field is set only when accessing some * shared resources or when the console device is manipulated. It can be * cleared, for example, after emitting one character when the console * device is in a consistent state. * * - The 'unsafe_takeover' field is set when a hostile takeover took the * console in an unsafe state. The console will stay in the unsafe state * until re-initialized. * * The acquire mechanism uses three approaches: * * 1) Direct acquire when the console is not owned or is owned by a lower * priority context and is in a safe state. * * 2) Friendly handover mechanism uses a request/grant handshake. It is used * when the current owner has lower priority and the console is in an * unsafe state. * * The requesting context: * * a) Sets its priority into the 'req_prio' field. * * b) Waits (with a timeout) for the owning context to unlock the * console. * * c) Takes the lock and clears the 'req_prio' field. * * The owning context: * * a) Observes the 'req_prio' field set on exit from the unsafe * console state. * * b) Gives up console ownership by clearing the 'prio' field. * * 3) Unsafe hostile takeover allows to take over the lock even when the * console is an unsafe state. It is used only in panic() by the final * attempt to flush consoles in a try and hope mode. * * Note that separate record buffers are used in panic(). As a result, * the messages can be read and formatted without any risk even after * using the hostile takeover in unsafe state. * * The release function simply clears the 'prio' field. * * All operations on @console::nbcon_state are atomic cmpxchg based to * handle concurrency. * * The acquire/release functions implement only minimal policies: * * - Preference for higher priority contexts. * - Protection of the panic CPU. * * All other policy decisions must be made at the call sites: * * - What is marked as an unsafe section. * - Whether to spin-wait if there is already an owner and the console is * in an unsafe state. * - Whether to attempt an unsafe hostile takeover. * * The design allows to implement the well known: * * acquire() * output_one_printk_record() * release() * * The output of one printk record might be interrupted with a higher priority * context. The new owner is supposed to reprint the entire interrupted record * from scratch. */ /** * nbcon_state_set - Helper function to set the console state * @con: Console to update * @new: The new state to write * * Only to be used when the console is not yet or no longer visible in the * system. Otherwise use nbcon_state_try_cmpxchg(). */ static inline void nbcon_state_set(struct console *con, struct nbcon_state *new) { atomic_set(&ACCESS_PRIVATE(con, nbcon_state), new->atom); } /** * nbcon_state_read - Helper function to read the console state * @con: Console to read * @state: The state to store the result */ static inline void nbcon_state_read(struct console *con, struct nbcon_state *state) { state->atom = atomic_read(&ACCESS_PRIVATE(con, nbcon_state)); } /** * nbcon_state_try_cmpxchg() - Helper function for atomic_try_cmpxchg() on console state * @con: Console to update * @cur: Old/expected state * @new: New state * * Return: True on success. False on fail and @cur is updated. */ static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_state *cur, struct nbcon_state *new) { return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom); } /** * nbcon_seq_read - Read the current console sequence * @con: Console to read the sequence of * * Return: Sequence number of the next record to print on @con. */ u64 nbcon_seq_read(struct console *con) { unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq)); return __ulseq_to_u64seq(prb, nbcon_seq); } /** * nbcon_seq_force - Force console sequence to a specific value * @con: Console to work on * @seq: Sequence number value to set * * Only to be used during init (before registration) or in extreme situations * (such as panic with CONSOLE_REPLAY_ALL). */ void nbcon_seq_force(struct console *con, u64 seq) { /* * If the specified record no longer exists, the oldest available record * is chosen. This is especially important on 32bit systems because only * the lower 32 bits of the sequence number are stored. The upper 32 bits * are derived from the sequence numbers available in the ringbuffer. */ u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb)); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq)); } /** * nbcon_seq_try_update - Try to update the console sequence number * @ctxt: Pointer to an acquire context that contains * all information about the acquire mode * @new_seq: The new sequence number to set * * @ctxt->seq is updated to the new value of @con::nbcon_seq (expanded to * the 64bit value). This could be a different value than @new_seq if * nbcon_seq_force() was used or the current context no longer owns the * console. In the later case, it will stop printing anyway. */ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq) { unsigned long nbcon_seq = __u64seq_to_ulseq(ctxt->seq); struct console *con = ctxt->console; if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq, __u64seq_to_ulseq(new_seq))) { ctxt->seq = new_seq; } else { ctxt->seq = nbcon_seq_read(con); } } /** * nbcon_context_try_acquire_direct - Try to acquire directly * @ctxt: The context of the caller * @cur: The current console state * * Acquire the console when it is released. Also acquire the console when * the current owner has a lower priority and the console is in a safe state. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU. * Or the current owner or waiter has the same or higher * priority. No acquire method can be successful in * this case. * * -EBUSY: The current owner has a lower priority but the console * in an unsafe state. The caller should try using * the handover acquire method. */ static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; do { /* * Panic does not imply that the console is owned. However, it * is critical that non-panic CPUs during panic are unable to * acquire ownership in order to satisfy the assumptions of * nbcon_waiter_matches(). In particular, the assumption that * lower priorities are ignored during panic. */ if (other_cpu_in_panic()) return -EPERM; if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio) return -EPERM; if (cur->unsafe) return -EBUSY; /* * The console should never be safe for a direct acquire * if an unsafe hostile takeover has ever happened. */ WARN_ON_ONCE(cur->unsafe_takeover); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio) { /* * The request context is well defined by the @req_prio because: * * - Only a context with a priority higher than the owner can become * a waiter. * - Only a context with a priority higher than the waiter can * directly take over the request. * - There are only three priorities. * - Only one CPU is allowed to request PANIC priority. * - Lower priorities are ignored during panic() until reboot. * * As a result, the following scenario is *not* possible: * * 1. This context is currently a waiter. * 2. Another context with a higher priority than this context * directly takes ownership. * 3. The higher priority context releases the ownership. * 4. Another lower priority context takes the ownership. * 5. Another context with the same priority as this context * creates a request and starts waiting. * * Event #1 implies this context is EMERGENCY. * Event #2 implies the new context is PANIC. * Event #3 occurs when panic() has flushed the console. * Events #4 and #5 are not possible due to the other_cpu_in_panic() * check in nbcon_context_try_acquire_direct(). */ return (cur->req_prio == expected_prio); } /** * nbcon_context_try_acquire_requested - Try to acquire after having * requested a handover * @ctxt: The context of the caller * @cur: The current console state * * This is a helper function for nbcon_context_try_acquire_handover(). * It is called when the console is in an unsafe state. The current * owner will release the console on exit from the unsafe region. * * Return: 0 on success and @cur is updated to the new console state. * Otherwise an error code on failure. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU * or this context is no longer the waiter. * * -EBUSY: The console is still locked. The caller should * continue waiting. * * Note: The caller must still remove the request when an error has occurred * except when this context is no longer the waiter. */ static int nbcon_context_try_acquire_requested(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; /* Note that the caller must still remove the request! */ if (other_cpu_in_panic()) return -EPERM; /* * Note that the waiter will also change if there was an unsafe * hostile takeover. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* If still locked, caller should continue waiting. */ if (cur->prio != NBCON_PRIO_NONE) return -EBUSY; /* * The previous owner should have never released ownership * in an unsafe region. */ WARN_ON_ONCE(cur->unsafe); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; if (!nbcon_state_try_cmpxchg(con, cur, &new)) { /* * The acquire could fail only when it has been taken * over by a higher priority context. */ WARN_ON_ONCE(nbcon_waiter_matches(cur, ctxt->prio)); return -EPERM; } /* Handover success. This context now owns the console. */ return 0; } /** * nbcon_context_try_acquire_handover - Try to acquire via handover * @ctxt: The context of the caller * @cur: The current console state * * The function must be called only when the context has higher priority * than the current owner and the console is in an unsafe state. * It is the case when nbcon_context_try_acquire_direct() returns -EBUSY. * * The function sets "req_prio" field to make the current owner aware of * the request. Then it waits until the current owner releases the console, * or an even higher context takes over the request, or timeout expires. * * The current owner checks the "req_prio" field on exit from the unsafe * region and releases the console. It does not touch the "req_prio" field * so that the console stays reserved for the waiter. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU. * Or a higher priority context has taken over the * console or the handover request. * * -EBUSY: The current owner is on the same CPU so that the hand * shake could not work. Or the current owner is not * willing to wait (zero timeout). Or the console does * not enter the safe state before timeout passed. The * caller might still use the unsafe hostile takeover * when allowed. * * -EAGAIN: @cur has changed when creating the handover request. * The caller should retry with direct acquire. */ static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; int timeout; int request_err = -EBUSY; /* * Check that the handover is called when the direct acquire failed * with -EBUSY. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(!cur->unsafe); /* Handover is not possible on the same CPU. */ if (cur->cpu == cpu) return -EBUSY; /* * Console stays unsafe after an unsafe takeover until re-initialized. * Waiting is not going to help in this case. */ if (cur->unsafe_takeover) return -EBUSY; /* Is the caller willing to wait? */ if (ctxt->spinwait_max_us == 0) return -EBUSY; /* * Setup a request for the handover. The caller should try to acquire * the console directly when the current state has been modified. */ new.atom = cur->atom; new.req_prio = ctxt->prio; if (!nbcon_state_try_cmpxchg(con, cur, &new)) return -EAGAIN; cur->atom = new.atom; /* Wait until there is no owner and then acquire the console. */ for (timeout = ctxt->spinwait_max_us; timeout >= 0; timeout--) { /* On successful acquire, this request is cleared. */ request_err = nbcon_context_try_acquire_requested(ctxt, cur); if (!request_err) return 0; /* * If the acquire should be aborted, it must be ensured * that the request is removed before returning to caller. */ if (request_err == -EPERM) break; udelay(1); /* Re-read the state because some time has passed. */ nbcon_state_read(con, cur); } /* Timed out or aborted. Carefully remove handover request. */ do { /* * No need to remove request if there is a new waiter. This * can only happen if a higher priority context has taken over * the console or the handover request. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* Unset request for handover. */ new.atom = cur->atom; new.req_prio = NBCON_PRIO_NONE; if (nbcon_state_try_cmpxchg(con, cur, &new)) { /* * Request successfully unset. Report failure of * acquiring via handover. */ cur->atom = new.atom; return request_err; } /* * Unable to remove request. Try to acquire in case * the owner has released the lock. */ } while (nbcon_context_try_acquire_requested(ctxt, cur)); /* Lucky timing. The acquire succeeded while removing the request. */ return 0; } /** * nbcon_context_try_acquire_hostile - Acquire via unsafe hostile takeover * @ctxt: The context of the caller * @cur: The current console state * * Acquire the console even in the unsafe state. * * It can be permitted by setting the 'allow_unsafe_takeover' field only * by the final attempt to flush messages in panic(). * * Return: 0 on success. -EPERM when not allowed by the context. */ static int nbcon_context_try_acquire_hostile(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; if (!ctxt->allow_unsafe_takeover) return -EPERM; /* Ensure caller is allowed to perform unsafe hostile takeovers. */ if (WARN_ON_ONCE(ctxt->prio != NBCON_PRIO_PANIC)) return -EPERM; /* * Check that try_acquire_direct() and try_acquire_handover() returned * -EBUSY in the right situation. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(cur->unsafe != true); do { new.atom = cur->atom; new.cpu = cpu; new.prio = ctxt->prio; new.unsafe |= cur->unsafe_takeover; new.unsafe_takeover |= cur->unsafe; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static struct printk_buffers panic_nbcon_pbufs; /** * nbcon_context_try_acquire - Try to acquire nbcon console * @ctxt: The context of the caller * * Context: Under @ctxt->con->device_lock() or local_irq_save(). * Return: True if the console was acquired. False otherwise. * * If the caller allowed an unsafe hostile takeover, on success the * caller should check the current console state to see if it is * in an unsafe state. Otherwise, on success the caller may assume * the console is not in an unsafe state. */ static bool nbcon_context_try_acquire(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state cur; int err; nbcon_state_read(con, &cur); try_again: err = nbcon_context_try_acquire_direct(ctxt, &cur); if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_handover(ctxt, &cur); if (err == -EAGAIN) goto try_again; if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_hostile(ctxt, &cur); out: if (err) return false; /* Acquire succeeded. */ /* Assign the appropriate buffer for this context. */ if (atomic_read(&panic_cpu) == cpu) ctxt->pbufs = &panic_nbcon_pbufs; else ctxt->pbufs = con->pbufs; /* Set the record sequence for this context to print. */ ctxt->seq = nbcon_seq_read(ctxt->console); return true; } static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu, int expected_prio) { /* * A similar function, nbcon_waiter_matches(), only deals with * EMERGENCY and PANIC priorities. However, this function must also * deal with the NORMAL priority, which requires additional checks * and constraints. * * For the case where preemption and interrupts are disabled, it is * enough to also verify that the owning CPU has not changed. * * For the case where preemption or interrupts are enabled, an * external synchronization method *must* be used. In particular, * the driver-specific locking mechanism used in device_lock() * (including disabling migration) should be used. It prevents * scenarios such as: * * 1. [Task A] owns a context with NBCON_PRIO_NORMAL on [CPU X] and * is scheduled out. * 2. Another context takes over the lock with NBCON_PRIO_EMERGENCY * and releases it. * 3. [Task B] acquires a context with NBCON_PRIO_NORMAL on [CPU X] * and is scheduled out. * 4. [Task A] gets running on [CPU X] and sees that the console is * still owned by a task on [CPU X] with NBON_PRIO_NORMAL. Thus * [Task A] thinks it is the owner when it is not. */ if (cur->prio != expected_prio) return false; if (cur->cpu != expected_cpu) return false; return true; } /** * nbcon_context_release - Release the console * @ctxt: The nbcon context from nbcon_context_try_acquire() */ static void nbcon_context_release(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { if (!nbcon_owner_matches(&cur, cpu, ctxt->prio)) break; new.atom = cur.atom; new.prio = NBCON_PRIO_NONE; /* * If @unsafe_takeover is set, it is kept set so that * the state remains permanently unsafe. */ new.unsafe |= cur.unsafe_takeover; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); ctxt->pbufs = NULL; } /** * nbcon_context_can_proceed - Check whether ownership can proceed * @ctxt: The nbcon context from nbcon_context_try_acquire() * @cur: The current console state * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * Must be invoked when entering the unsafe state to make sure that it still * owns the lock. Also must be invoked when exiting the unsafe context * to eventually free the lock for a higher priority context which asked * for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe * state. * * Also it can be called in the safe context before doing an expensive * safe operation. It does not make sense to do the operation when * a higher priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ static bool nbcon_context_can_proceed(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); /* Make sure this context still owns the console. */ if (!nbcon_owner_matches(cur, cpu, ctxt->prio)) return false; /* The console owner can proceed if there is no waiter. */ if (cur->req_prio == NBCON_PRIO_NONE) return true; /* * A console owner within an unsafe region is always allowed to * proceed, even if there are waiters. It can perform a handover * when exiting the unsafe region. Otherwise the waiter will * need to perform an unsafe hostile takeover. */ if (cur->unsafe) return true; /* Waiters always have higher priorities than owners. */ WARN_ON_ONCE(cur->req_prio <= cur->prio); /* * Having a safe point for take over and eventually a few * duplicated characters or a full line is way better than a * hostile takeover. Post processing can take care of the garbage. * Release and hand over. */ nbcon_context_release(ctxt); /* * It is not clear whether the waiter really took over ownership. The * outermost callsite must make the final decision whether console * ownership is needed for it to proceed. If yes, it must reacquire * ownership (possibly hostile) before carefully proceeding. * * The calling context no longer owns the console so go back all the * way instead of trying to implement reacquire heuristics in tons of * places. */ return false; } /** * nbcon_can_proceed - Check whether ownership can proceed * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * It is used in nbcon_enter_unsafe() to make sure that it still owns the * lock. Also it is used in nbcon_exit_unsafe() to eventually free the lock * for a higher priority context which asked for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe state. * * Also it can be called in the safe context before doing an expensive safe * operation. It does not make sense to do the operation when a higher * priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; nbcon_state_read(con, &cur); return nbcon_context_can_proceed(ctxt, &cur); } EXPORT_SYMBOL_GPL(nbcon_can_proceed); #define nbcon_context_enter_unsafe(c) __nbcon_context_update_unsafe(c, true) #define nbcon_context_exit_unsafe(c) __nbcon_context_update_unsafe(c, false) /** * __nbcon_context_update_unsafe - Update the unsafe bit in @con->nbcon_state * @ctxt: The nbcon context from nbcon_context_try_acquire() * @unsafe: The new value for the unsafe bit * * Return: True if the unsafe state was updated and this context still * owns the console. Otherwise false if ownership was handed * over or taken. * * This function allows console owners to modify the unsafe status of the * console. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. * * Internal helper to avoid duplicated code. */ static bool __nbcon_context_update_unsafe(struct nbcon_context *ctxt, bool unsafe) { struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { /* * The unsafe bit must not be cleared if an * unsafe hostile takeover has occurred. */ if (!unsafe && cur.unsafe_takeover) goto out; if (!nbcon_context_can_proceed(ctxt, &cur)) return false; new.atom = cur.atom; new.unsafe = unsafe; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); cur.atom = new.atom; out: return nbcon_context_can_proceed(ctxt, &cur); } static void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, char *buf, unsigned int len) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; wctxt->outbuf = buf; wctxt->len = len; nbcon_state_read(con, &cur); wctxt->unsafe_takeover = cur.unsafe_takeover; } /** * nbcon_enter_unsafe - Enter an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool is_owner; is_owner = nbcon_context_enter_unsafe(ctxt); if (!is_owner) nbcon_write_context_set_buf(wctxt, NULL, 0); return is_owner; } EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); /** * nbcon_exit_unsafe - Exit an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool ret; ret = nbcon_context_exit_unsafe(ctxt); if (!ret) nbcon_write_context_set_buf(wctxt, NULL, 0); return ret; } EXPORT_SYMBOL_GPL(nbcon_exit_unsafe); /** * nbcon_reacquire_nobuf - Reacquire a console after losing ownership * while printing * @wctxt: The write context that was handed to the write callback * * Since ownership can be lost at any time due to handover or takeover, a * printing context _must_ be prepared to back out immediately and * carefully. However, there are scenarios where the printing context must * reacquire ownership in order to finalize or revert hardware changes. * * This function allows a printing context to reacquire ownership using the * same priority as its previous ownership. * * Note that after a successful reacquire the printing context will have no * output buffer because that has been lost. This function cannot be used to * resume printing. */ void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); while (!nbcon_context_try_acquire(ctxt)) cpu_relax(); nbcon_write_context_set_buf(wctxt, NULL, 0); } EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf); /** * nbcon_emit_next_record - Emit a record in the acquired context * @wctxt: The write context that will be handed to the write function * @use_atomic: True if the write_atomic() callback is to be used * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. If the caller * wants to do more it must reacquire the console first. * * When true is returned, @wctxt->ctxt.backlog indicates whether there are * still records pending in the ringbuffer, */ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; struct printk_message pmsg = { .pbufs = ctxt->pbufs, }; unsigned long con_dropped; struct nbcon_state cur; unsigned long dropped; unsigned long ulseq; /* * This function should never be called for consoles that have not * implemented the necessary callback for writing: i.e. legacy * consoles and, when atomic, nbcon consoles with no write_atomic(). * Handle it as if ownership was lost and try to continue. * * Note that for nbcon consoles the write_thread() callback is * mandatory and was already checked in nbcon_alloc(). */ if (WARN_ON_ONCE((use_atomic && !con->write_atomic) || !(console_srcu_read_flags(con) & CON_NBCON))) { nbcon_context_release(ctxt); return false; } /* * The printk buffers are filled within an unsafe section. This * prevents NBCON_PRIO_NORMAL and NBCON_PRIO_EMERGENCY from * clobbering each other. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; ctxt->backlog = printk_get_next_message(&pmsg, ctxt->seq, is_extended, true); if (!ctxt->backlog) return nbcon_context_exit_unsafe(ctxt); /* * @con->dropped is not protected in case of an unsafe hostile * takeover. In that situation the update can be racy so * annotate it accordingly. */ con_dropped = data_race(READ_ONCE(con->dropped)); dropped = con_dropped + pmsg.dropped; if (dropped && !is_extended) console_prepend_dropped(&pmsg, dropped); /* * If the previous owner was assigned the same record, this context * has taken over ownership and is replaying the record. Prepend a * message to let the user know the record is replayed. */ ulseq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_prev_seq)); if (__ulseq_to_u64seq(prb, ulseq) == pmsg.seq) { console_prepend_replay(&pmsg); } else { /* * Ensure this context is still the owner before trying to * update @nbcon_prev_seq. Otherwise the value in @ulseq may * not be from the previous owner and instead be some later * value from the context that took over ownership. */ nbcon_state_read(con, &cur); if (!nbcon_context_can_proceed(ctxt, &cur)) return false; atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_prev_seq), &ulseq, __u64seq_to_ulseq(pmsg.seq)); } if (!nbcon_context_exit_unsafe(ctxt)) return false; /* For skipped records just update seq/dropped in @con. */ if (pmsg.outbuf_len == 0) goto update_con; /* Initialize the write context for driver callbacks. */ nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len); if (use_atomic) con->write_atomic(con, wctxt); else con->write_thread(con, wctxt); if (!wctxt->outbuf) { /* * Ownership was lost and reacquired by the driver. Handle it * as if ownership was lost. */ nbcon_context_release(ctxt); return false; } /* * Ownership may have been lost but _not_ reacquired by the driver. * This case is detected and handled when entering unsafe to update * dropped/seq values. */ /* * Since any dropped message was successfully output, reset the * dropped count for the console. */ dropped = 0; update_con: /* * The dropped count and the sequence number are updated within an * unsafe section. This limits update races to the panic context and * allows the panic context to win. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; if (dropped != con_dropped) { /* Counterpart to the READ_ONCE() above. */ WRITE_ONCE(con->dropped, dropped); } nbcon_seq_try_update(ctxt, pmsg.seq + 1); return nbcon_context_exit_unsafe(ctxt); } /* * nbcon_emit_one - Print one record for an nbcon console using the * specified callback * @wctxt: An initialized write context struct to use for this context * @use_atomic: True if the write_atomic() callback is to be used * * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This is an internal helper to handle the locking of the console before * calling nbcon_emit_next_record(). */ static bool nbcon_emit_one(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; unsigned long flags; bool ret = false; if (!use_atomic) { con->device_lock(con, &flags); /* * Ensure this stays on the CPU to make handover and * takeover possible. */ cant_migrate(); } if (!nbcon_context_try_acquire(ctxt)) goto out; /* * nbcon_emit_next_record() returns false when the console was * handed over or taken over. In both cases the context is no * longer valid. * * The higher priority printing context takes over responsibility * to print the pending records. */ if (!nbcon_emit_next_record(wctxt, use_atomic)) goto out; nbcon_context_release(ctxt); ret = ctxt->backlog; out: if (!use_atomic) con->device_unlock(con, flags); return ret; } /** * nbcon_kthread_should_wakeup - Check whether a printer thread should wakeup * @con: Console to operate on * @ctxt: The nbcon context from nbcon_context_try_acquire() * * Return: True if the thread should shutdown or if the console is * allowed to print and a record is available. False otherwise. * * After the thread wakes up, it must first check if it should shutdown before * attempting any printing. */ static bool nbcon_kthread_should_wakeup(struct console *con, struct nbcon_context *ctxt) { bool ret = false; short flags; int cookie; if (kthread_should_stop()) return true; cookie = console_srcu_read_lock(); flags = console_srcu_read_flags(con); if (console_is_usable(con, flags, false)) { /* Bring the sequence in @ctxt up to date */ ctxt->seq = nbcon_seq_read(con); ret = prb_read_valid(prb, ctxt->seq, NULL); } console_srcu_read_unlock(cookie); return ret; } /** * nbcon_kthread_func - The printer thread function * @__console: Console to operate on * * Return: 0 */ static int nbcon_kthread_func(void *__console) { struct console *con = __console; struct nbcon_write_context wctxt = { .ctxt.console = con, .ctxt.prio = NBCON_PRIO_NORMAL, }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); short con_flags; bool backlog; int cookie; wait_for_event: /* * Guarantee this task is visible on the rcuwait before * checking the wake condition. * * The full memory barrier within set_current_state() of * ___rcuwait_wait_event() pairs with the full memory * barrier within rcuwait_has_sleeper(). * * This pairs with rcuwait_has_sleeper:A and nbcon_kthread_wake:A. */ rcuwait_wait_event(&con->rcuwait, nbcon_kthread_should_wakeup(con, ctxt), TASK_INTERRUPTIBLE); /* LMM(nbcon_kthread_func:A) */ do { if (kthread_should_stop()) return 0; backlog = false; /* * Keep the srcu read lock around the entire operation so that * synchronize_srcu() can guarantee that the kthread stopped * or suspended printing. */ cookie = console_srcu_read_lock(); con_flags = console_srcu_read_flags(con); if (console_is_usable(con, con_flags, false)) backlog = nbcon_emit_one(&wctxt, false); console_srcu_read_unlock(cookie); cond_resched(); } while (backlog); goto wait_for_event; } /** * nbcon_irq_work - irq work to wake console printer thread * @irq_work: The irq work to operate on */ static void nbcon_irq_work(struct irq_work *irq_work) { struct console *con = container_of(irq_work, struct console, irq_work); nbcon_kthread_wake(con); } static inline bool rcuwait_has_sleeper(struct rcuwait *w) { /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the rcuwait is empty. * * This full memory barrier pairs with the full memory barrier within * set_current_state() of ___rcuwait_wait_event(), which is called * after prepare_to_rcuwait() adds the waiter but before it has * checked the wait condition. * * This pairs with nbcon_kthread_func:A. */ smp_mb(); /* LMM(rcuwait_has_sleeper:A) */ return rcuwait_active(w); } /** * nbcon_kthreads_wake - Wake up printing threads using irq_work */ void nbcon_kthreads_wake(void) { struct console *con; int cookie; if (!printk_kthreads_running) return; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { if (!(console_srcu_read_flags(con) & CON_NBCON)) continue; /* * Only schedule irq_work if the printing thread is * actively waiting. If not waiting, the thread will * notice by itself that it has work to do. */ if (rcuwait_has_sleeper(&con->rcuwait)) irq_work_queue(&con->irq_work); } console_srcu_read_unlock(cookie); } /* * nbcon_kthread_stop - Stop a console printer thread * @con: Console to operate on */ void nbcon_kthread_stop(struct console *con) { lockdep_assert_console_list_lock_held(); if (!con->kthread) return; kthread_stop(con->kthread); con->kthread = NULL; } /** * nbcon_kthread_create - Create a console printer thread * @con: Console to operate on * * Return: True if the kthread was started or already exists. * Otherwise false and @con must not be registered. * * This function is called when it will be expected that nbcon consoles are * flushed using the kthread. The messages printed with NBCON_PRIO_NORMAL * will be no longer flushed by the legacy loop. This is why failure must * be fatal for console registration. * * If @con was already registered and this function fails, @con must be * unregistered before the global state variable @printk_kthreads_running * can be set. */ bool nbcon_kthread_create(struct console *con) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); if (con->kthread) return true; kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); if (WARN_ON(IS_ERR(kt))) { con_printk(KERN_ERR, con, "failed to start printing thread\n"); return false; } con->kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(con->kthread, -20); return true; } /* Track the nbcon emergency nesting per CPU. */ static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting); static unsigned int early_nbcon_pcpu_emergency_nesting __initdata; /** * nbcon_get_cpu_emergency_nesting - Get the per CPU emergency nesting pointer * * Context: For reading, any context. For writing, any context which could * not be migrated to another CPU. * Return: Either a pointer to the per CPU emergency nesting counter of * the current CPU or to the init data during early boot. * * The function is safe for reading per-CPU variables in any context because * preemption is disabled if the current CPU is in the emergency state. See * also nbcon_cpu_emergency_enter(). */ static __ref unsigned int *nbcon_get_cpu_emergency_nesting(void) { /* * The value of __printk_percpu_data_ready gets set in normal * context and before SMP initialization. As a result it could * never change while inside an nbcon emergency section. */ if (!printk_percpu_data_ready()) return &early_nbcon_pcpu_emergency_nesting; return raw_cpu_ptr(&nbcon_pcpu_emergency_nesting); } /** * nbcon_get_default_prio - The appropriate nbcon priority to use for nbcon * printing on the current CPU * * Context: Any context. * Return: The nbcon_prio to use for acquiring an nbcon console in this * context for printing. * * The function is safe for reading per-CPU data in any context because * preemption is disabled if the current CPU is in the emergency or panic * state. */ enum nbcon_prio nbcon_get_default_prio(void) { unsigned int *cpu_emergency_nesting; if (this_cpu_in_panic()) return NBCON_PRIO_PANIC; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (*cpu_emergency_nesting) return NBCON_PRIO_EMERGENCY; return NBCON_PRIO_NORMAL; } /** * nbcon_legacy_emit_next_record - Print one record for an nbcon console * in legacy contexts * @con: The console to print on * @handover: Will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding * both the console_lock and the SRCU read lock. Otherwise it * is set to false. * @cookie: The cookie from the SRCU read lock. * @use_atomic: Set true when called in an atomic or unknown context. * It affects which nbcon callback will be used: write_atomic() * or write_thread(). * * When false, the write_thread() callback is used and would be * called in a preemtible context unless disabled by the * device_lock. The legacy handover is not allowed in this mode. * * Context: Any context except NMI. * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This function is meant to be called by console_flush_all() to print records * on nbcon consoles from legacy context (printing via console unlocking). * Essentially it is the nbcon version of console_emit_next_record(). */ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); unsigned long flags; bool progress; ctxt->console = con; ctxt->prio = nbcon_get_default_prio(); if (use_atomic) { /* * In an atomic or unknown context, use the same procedure as * in console_emit_next_record(). It allows to handover. */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); stop_critical_timings(); } progress = nbcon_emit_one(&wctxt, use_atomic); if (use_atomic) { start_critical_timings(); *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } else { /* Non-atomic does not perform legacy spinning handovers. */ *handover = false; } return progress; } /** * __nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * Return: 0 if @con was flushed up to @stop_seq Otherwise, error code on * failure. * * Errors: * * -EPERM: Unable to acquire console ownership. * * -EAGAIN: Another context took over ownership while printing. * * -ENOENT: A record before @stop_seq is not available. * * If flushing up to @stop_seq was not successful, it only makes sense for the * caller to try again when -EAGAIN was returned. When -EPERM is returned, * this context is not allowed to acquire the console. When -ENOENT is * returned, it cannot be expected that the unfinalized record will become * available. */ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, bool allow_unsafe_takeover) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); int err = 0; ctxt->console = con; ctxt->spinwait_max_us = 2000; ctxt->prio = nbcon_get_default_prio(); ctxt->allow_unsafe_takeover = allow_unsafe_takeover; if (!nbcon_context_try_acquire(ctxt)) return -EPERM; while (nbcon_seq_read(con) < stop_seq) { /* * nbcon_emit_next_record() returns false when the console was * handed over or taken over. In both cases the context is no * longer valid. */ if (!nbcon_emit_next_record(&wctxt, true)) return -EAGAIN; if (!ctxt->backlog) { /* Are there reserved but not yet finalized records? */ if (nbcon_seq_read(con) < stop_seq) err = -ENOENT; break; } } nbcon_context_release(ctxt); return err; } /** * nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * This will stop flushing before @stop_seq if another context has ownership. * That context is then responsible for the flushing. Likewise, if new records * are added while this context was flushing and there is no other context * to handle the printing, this context must also flush those records. */ static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, bool allow_unsafe_takeover) { struct console_flush_type ft; unsigned long flags; int err; again: /* * Atomic flushing does not use console driver synchronization (i.e. * it does not hold the port lock for uart consoles). Therefore IRQs * must be disabled to avoid being interrupted and then calling into * a driver that will deadlock trying to acquire console ownership. */ local_irq_save(flags); err = __nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); local_irq_restore(flags); /* * If there was a new owner (-EPERM, -EAGAIN), that context is * responsible for completing. * * Do not wait for records not yet finalized (-ENOENT) to avoid a * possible deadlock. They will either get flushed by the writer or * eventually skipped on panic CPU. */ if (err) return; /* * If flushing was successful but more records are available, this * context must flush those remaining records if the printer thread * is not available do it. */ printk_get_console_flush_type(&ft); if (!ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { stop_seq = prb_next_reserve_seq(prb); goto again; } } /** * __nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers */ static void __nbcon_atomic_flush_pending(u64 stop_seq, bool allow_unsafe_takeover) { struct console *con; int cookie; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); if (!(flags & CON_NBCON)) continue; if (!console_is_usable(con, flags, true)) continue; if (nbcon_seq_read(con) >= stop_seq) continue; nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); } console_srcu_read_unlock(cookie); } /** * nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * * Flush the backlog up through the currently newest record. Any new * records added while flushing will not be flushed if there is another * context available to handle the flushing. This is to avoid one CPU * printing unbounded because other CPUs continue to add records. */ void nbcon_atomic_flush_pending(void) { __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), false); } /** * nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their * write_atomic() callback and allowing unsafe hostile takeovers * * Flush the backlog up through the currently newest record. Unsafe hostile * takeovers will be performed, if necessary. */ void nbcon_atomic_flush_unsafe(void) { __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true); } /** * nbcon_cpu_emergency_enter - Enter an emergency section where printk() * messages for that CPU are flushed directly * * Context: Any context. Disables preemption. * * When within an emergency section, printk() calls will attempt to flush any * pending messages in the ringbuffer. */ void nbcon_cpu_emergency_enter(void) { unsigned int *cpu_emergency_nesting; preempt_disable(); cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); (*cpu_emergency_nesting)++; } /** * nbcon_cpu_emergency_exit - Exit an emergency section * * Context: Within an emergency section. Enables preemption. */ void nbcon_cpu_emergency_exit(void) { unsigned int *cpu_emergency_nesting; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (!WARN_ON_ONCE(*cpu_emergency_nesting == 0)) (*cpu_emergency_nesting)--; preempt_enable(); } /** * nbcon_alloc - Allocate and init the nbcon console specific data * @con: Console to initialize * * Return: True if the console was fully allocated and initialized. * Otherwise @con must not be registered. * * When allocation and init was successful, the console must be properly * freed using nbcon_free() once it is no longer needed. */ bool nbcon_alloc(struct console *con) { struct nbcon_state state = { }; /* The write_thread() callback is mandatory. */ if (WARN_ON(!con->write_thread)) return false; rcuwait_init(&con->rcuwait); init_irq_work(&con->irq_work, nbcon_irq_work); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); nbcon_state_set(con, &state); /* * Initialize @nbcon_seq to the highest possible sequence number so * that practically speaking it will have nothing to print until a * desired initial sequence number has been set via nbcon_seq_force(). */ atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), ULSEQ_MAX(prb)); if (con->flags & CON_BOOT) { /* * Boot console printing is synchronized with legacy console * printing, so boot consoles can share the same global printk * buffers. */ con->pbufs = &printk_shared_pbufs; } else { con->pbufs = kmalloc(sizeof(*con->pbufs), GFP_KERNEL); if (!con->pbufs) { con_printk(KERN_ERR, con, "failed to allocate printing buffer\n"); return false; } if (printk_kthreads_running) { if (!nbcon_kthread_create(con)) { kfree(con->pbufs); con->pbufs = NULL; return false; } } } return true; } /** * nbcon_free - Free and cleanup the nbcon console specific data * @con: Console to free/cleanup nbcon data */ void nbcon_free(struct console *con) { struct nbcon_state state = { }; if (printk_kthreads_running) nbcon_kthread_stop(con); nbcon_state_set(con, &state); /* Boot consoles share global printk buffers. */ if (!(con->flags & CON_BOOT)) kfree(con->pbufs); con->pbufs = NULL; } /** * nbcon_device_try_acquire - Try to acquire nbcon console and enter unsafe * section * @con: The nbcon console to acquire * * Context: Under the locking mechanism implemented in * @con->device_lock() including disabling migration. * Return: True if the console was acquired. False otherwise. * * Console drivers will usually use their own internal synchronization * mechasism to synchronize between console printing and non-printing * activities (such as setting baud rates). However, nbcon console drivers * supporting atomic consoles may also want to mark unsafe sections when * performing non-printing activities in order to synchronize against their * atomic_write() callback. * * This function acquires the nbcon console using priority NBCON_PRIO_NORMAL * and marks it unsafe for handover/takeover. */ bool nbcon_device_try_acquire(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); cant_migrate(); memset(ctxt, 0, sizeof(*ctxt)); ctxt->console = con; ctxt->prio = NBCON_PRIO_NORMAL; if (!nbcon_context_try_acquire(ctxt)) return false; if (!nbcon_context_enter_unsafe(ctxt)) return false; return true; } EXPORT_SYMBOL_GPL(nbcon_device_try_acquire); /** * nbcon_device_release - Exit unsafe section and release the nbcon console * @con: The nbcon console acquired in nbcon_device_try_acquire() */ void nbcon_device_release(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); struct console_flush_type ft; int cookie; if (!nbcon_context_exit_unsafe(ctxt)) return; nbcon_context_release(ctxt); /* * This context must flush any new records added while the console * was locked if the printer thread is not available to do it. The * console_srcu_read_lock must be taken to ensure the console is * usable throughout flushing. */ cookie = console_srcu_read_lock(); printk_get_console_flush_type(&ft); if (console_is_usable(con, console_srcu_read_flags(con), true) && !ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { /* * If nbcon_atomic flushing is not available, fallback to * using the legacy loop. */ if (ft.nbcon_atomic) { __nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false); } else if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } else if (ft.legacy_offload) { printk_trigger_flush(); } } console_srcu_read_unlock(cookie); } EXPORT_SYMBOL_GPL(nbcon_device_release); |
| 474 475 475 474 475 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LOCAL_LOCK_H # error "Do not include directly, include linux/local_lock.h" #endif #include <linux/percpu-defs.h> #include <linux/lockdep.h> #ifndef CONFIG_PREEMPT_RT typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ .lock_type = LD_LOCK_PERCPU, \ }, \ .owner = NULL, static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_lock_release(local_lock_t *l) { DEBUG_LOCKS_WARN_ON(l->owner != current); l->owner = NULL; lock_map_release(&l->dep_map); } static inline void local_lock_debug_init(local_lock_t *l) { l->owner = NULL; } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ local_lock_debug_init(lock); \ } while (0) #define __spinlock_nested_bh_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_NORMAL); \ local_lock_debug_init(lock); \ } while (0) #define __local_lock(lock) \ do { \ preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0) #define __local_lock_nested_bh(lock) \ do { \ lockdep_assert_in_softirq(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock_nested_bh(lock) \ local_lock_release(this_cpu_ptr(lock)) #else /* !CONFIG_PREEMPT_RT */ /* * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the * critical section while staying preemptible. */ typedef spinlock_t local_lock_t; #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define __local_lock_init(l) \ do { \ local_spin_lock_init((l)); \ } while (0) #define __local_lock(__lock) \ do { \ migrate_disable(); \ spin_lock(this_cpu_ptr((__lock))); \ } while (0) #define __local_lock_irq(lock) __local_lock(lock) #define __local_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = 0; \ __local_lock(lock); \ } while (0) #define __local_unlock(__lock) \ do { \ spin_unlock(this_cpu_ptr((__lock))); \ migrate_enable(); \ } while (0) #define __local_unlock_irq(lock) __local_unlock(lock) #define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) #define __local_lock_nested_bh(lock) \ do { \ lockdep_assert_in_softirq_func(); \ spin_lock(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock_nested_bh(lock) \ do { \ spin_unlock(this_cpu_ptr((lock))); \ } while (0) #endif /* CONFIG_PREEMPT_RT */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NetLabel Unlabeled Support * * This file defines functions for dealing with unlabeled packets for the * NetLabel system. The NetLabel system manages static and dynamic label * mappings for network protocols such as CIPSO and RIPSO. * * Author: Paul Moore <paul@paul-moore.com> */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 - 2008 */ #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/audit.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/security.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <asm/bug.h> #include <linux/atomic.h> #include "netlabel_user.h" #include "netlabel_addrlist.h" #include "netlabel_domainhash.h" #include "netlabel_unlabeled.h" #include "netlabel_mgmt.h" /* NOTE: at present we always use init's network namespace since we don't * presently support different namespaces even though the majority of * the functions in this file are "namespace safe" */ /* The unlabeled connection hash table which we use to map network interfaces * and addresses of unlabeled packets to a user specified secid value for the * LSM. The hash table is used to lookup the network interface entry * (struct netlbl_unlhsh_iface) and then the interface entry is used to * lookup an IP address match from an ordered list. If a network interface * match can not be found in the hash table then the default entry * (netlbl_unlhsh_def) is used. The IP address entry list * (struct netlbl_unlhsh_addr) is ordered such that the entries with a * larger netmask come first. */ struct netlbl_unlhsh_tbl { struct list_head *tbl; u32 size; }; #define netlbl_unlhsh_addr4_entry(iter) \ container_of(iter, struct netlbl_unlhsh_addr4, list) struct netlbl_unlhsh_addr4 { u32 secid; struct netlbl_af4list list; struct rcu_head rcu; }; #define netlbl_unlhsh_addr6_entry(iter) \ container_of(iter, struct netlbl_unlhsh_addr6, list) struct netlbl_unlhsh_addr6 { u32 secid; struct netlbl_af6list list; struct rcu_head rcu; }; struct netlbl_unlhsh_iface { int ifindex; struct list_head addr4_list; struct list_head addr6_list; u32 valid; struct list_head list; struct rcu_head rcu; }; /* Argument struct for netlbl_unlhsh_walk() */ struct netlbl_unlhsh_walk_arg { struct netlink_callback *nl_cb; struct sk_buff *skb; u32 seq; }; /* Unlabeled connection hash table */ /* updates should be so rare that having one spinlock for the entire * hash table should be okay */ static DEFINE_SPINLOCK(netlbl_unlhsh_lock); #define netlbl_unlhsh_rcu_deref(p) \ rcu_dereference_check(p, lockdep_is_held(&netlbl_unlhsh_lock)) static struct netlbl_unlhsh_tbl __rcu *netlbl_unlhsh; static struct netlbl_unlhsh_iface __rcu *netlbl_unlhsh_def; /* Accept unlabeled packets flag */ static u8 netlabel_unlabel_acceptflg; /* NetLabel Generic NETLINK unlabeled family */ static struct genl_family netlbl_unlabel_gnl_family; /* NetLabel Netlink attribute policy */ static const struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1] = { [NLBL_UNLABEL_A_ACPTFLG] = { .type = NLA_U8 }, [NLBL_UNLABEL_A_IPV6ADDR] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [NLBL_UNLABEL_A_IPV6MASK] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [NLBL_UNLABEL_A_IPV4ADDR] = { .type = NLA_BINARY, .len = sizeof(struct in_addr) }, [NLBL_UNLABEL_A_IPV4MASK] = { .type = NLA_BINARY, .len = sizeof(struct in_addr) }, [NLBL_UNLABEL_A_IFACE] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [NLBL_UNLABEL_A_SECCTX] = { .type = NLA_BINARY } }; /* * Unlabeled Connection Hash Table Functions */ /** * netlbl_unlhsh_free_iface - Frees an interface entry from the hash table * @entry: the entry's RCU field * * Description: * This function is designed to be used as a callback to the call_rcu() * function so that memory allocated to a hash table interface entry can be * released safely. It is important to note that this function does not free * the IPv4 and IPv6 address lists contained as part of an interface entry. It * is up to the rest of the code to make sure an interface entry is only freed * once it's address lists are empty. * */ static void netlbl_unlhsh_free_iface(struct rcu_head *entry) { struct netlbl_unlhsh_iface *iface; struct netlbl_af4list *iter4; struct netlbl_af4list *tmp4; #if IS_ENABLED(CONFIG_IPV6) struct netlbl_af6list *iter6; struct netlbl_af6list *tmp6; #endif /* IPv6 */ iface = container_of(entry, struct netlbl_unlhsh_iface, rcu); /* no need for locks here since we are the only one with access to this * structure */ netlbl_af4list_foreach_safe(iter4, tmp4, &iface->addr4_list) { netlbl_af4list_remove_entry(iter4); kfree(netlbl_unlhsh_addr4_entry(iter4)); } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_safe(iter6, tmp6, &iface->addr6_list) { netlbl_af6list_remove_entry(iter6); kfree(netlbl_unlhsh_addr6_entry(iter6)); } #endif /* IPv6 */ kfree(iface); } /** * netlbl_unlhsh_hash - Hashing function for the hash table * @ifindex: the network interface/device to hash * * Description: * This is the hashing function for the unlabeled hash table, it returns the * bucket number for the given device/interface. The caller is responsible for * ensuring that the hash table is protected with either a RCU read lock or * the hash table lock. * */ static u32 netlbl_unlhsh_hash(int ifindex) { return ifindex & (netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->size - 1); } /** * netlbl_unlhsh_search_iface - Search for a matching interface entry * @ifindex: the network interface * * Description: * Searches the unlabeled connection hash table and returns a pointer to the * interface entry which matches @ifindex, otherwise NULL is returned. The * caller is responsible for ensuring that the hash table is protected with * either a RCU read lock or the hash table lock. * */ static struct netlbl_unlhsh_iface *netlbl_unlhsh_search_iface(int ifindex) { u32 bkt; struct list_head *bkt_list; struct netlbl_unlhsh_iface *iter; bkt = netlbl_unlhsh_hash(ifindex); bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]; list_for_each_entry_rcu(iter, bkt_list, list, lockdep_is_held(&netlbl_unlhsh_lock)) if (iter->valid && iter->ifindex == ifindex) return iter; return NULL; } /** * netlbl_unlhsh_add_addr4 - Add a new IPv4 address entry to the hash table * @iface: the associated interface entry * @addr: IPv4 address in network byte order * @mask: IPv4 address mask in network byte order * @secid: LSM secid value for entry * * Description: * Add a new address entry into the unlabeled connection hash table using the * interface entry specified by @iface. On success zero is returned, otherwise * a negative value is returned. * */ static int netlbl_unlhsh_add_addr4(struct netlbl_unlhsh_iface *iface, const struct in_addr *addr, const struct in_addr *mask, u32 secid) { int ret_val; struct netlbl_unlhsh_addr4 *entry; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) return -ENOMEM; entry->list.addr = addr->s_addr & mask->s_addr; entry->list.mask = mask->s_addr; entry->list.valid = 1; entry->secid = secid; spin_lock(&netlbl_unlhsh_lock); ret_val = netlbl_af4list_add(&entry->list, &iface->addr4_list); spin_unlock(&netlbl_unlhsh_lock); if (ret_val != 0) kfree(entry); return ret_val; } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_unlhsh_add_addr6 - Add a new IPv6 address entry to the hash table * @iface: the associated interface entry * @addr: IPv6 address in network byte order * @mask: IPv6 address mask in network byte order * @secid: LSM secid value for entry * * Description: * Add a new address entry into the unlabeled connection hash table using the * interface entry specified by @iface. On success zero is returned, otherwise * a negative value is returned. * */ static int netlbl_unlhsh_add_addr6(struct netlbl_unlhsh_iface *iface, const struct in6_addr *addr, const struct in6_addr *mask, u32 secid) { int ret_val; struct netlbl_unlhsh_addr6 *entry; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) return -ENOMEM; entry->list.addr = *addr; entry->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; entry->list.addr.s6_addr32[1] &= mask->s6_addr32[1]; entry->list.addr.s6_addr32[2] &= mask->s6_addr32[2]; entry->list.addr.s6_addr32[3] &= mask->s6_addr32[3]; entry->list.mask = *mask; entry->list.valid = 1; entry->secid = secid; spin_lock(&netlbl_unlhsh_lock); ret_val = netlbl_af6list_add(&entry->list, &iface->addr6_list); spin_unlock(&netlbl_unlhsh_lock); if (ret_val != 0) kfree(entry); return 0; } #endif /* IPv6 */ /** * netlbl_unlhsh_add_iface - Adds a new interface entry to the hash table * @ifindex: network interface * * Description: * Add a new, empty, interface entry into the unlabeled connection hash table. * On success a pointer to the new interface entry is returned, on failure NULL * is returned. * */ static struct netlbl_unlhsh_iface *netlbl_unlhsh_add_iface(int ifindex) { u32 bkt; struct netlbl_unlhsh_iface *iface; iface = kzalloc(sizeof(*iface), GFP_ATOMIC); if (iface == NULL) return NULL; iface->ifindex = ifindex; INIT_LIST_HEAD(&iface->addr4_list); INIT_LIST_HEAD(&iface->addr6_list); iface->valid = 1; spin_lock(&netlbl_unlhsh_lock); if (ifindex > 0) { bkt = netlbl_unlhsh_hash(ifindex); if (netlbl_unlhsh_search_iface(ifindex) != NULL) goto add_iface_failure; list_add_tail_rcu(&iface->list, &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]); } else { INIT_LIST_HEAD(&iface->list); if (netlbl_unlhsh_rcu_deref(netlbl_unlhsh_def) != NULL) goto add_iface_failure; rcu_assign_pointer(netlbl_unlhsh_def, iface); } spin_unlock(&netlbl_unlhsh_lock); return iface; add_iface_failure: spin_unlock(&netlbl_unlhsh_lock); kfree(iface); return NULL; } /** * netlbl_unlhsh_add - Adds a new entry to the unlabeled connection hash table * @net: network namespace * @dev_name: interface name * @addr: IP address in network byte order * @mask: address mask in network byte order * @addr_len: length of address/mask (4 for IPv4, 16 for IPv6) * @secid: LSM secid value for the entry * @audit_info: NetLabel audit information * * Description: * Adds a new entry to the unlabeled connection hash table. Returns zero on * success, negative values on failure. * */ int netlbl_unlhsh_add(struct net *net, const char *dev_name, const void *addr, const void *mask, u32 addr_len, u32 secid, struct netlbl_audit *audit_info) { int ret_val; int ifindex; struct net_device *dev; struct netlbl_unlhsh_iface *iface; struct audit_buffer *audit_buf = NULL; char *secctx = NULL; u32 secctx_len; if (addr_len != sizeof(struct in_addr) && addr_len != sizeof(struct in6_addr)) return -EINVAL; rcu_read_lock(); if (dev_name != NULL) { dev = dev_get_by_name_rcu(net, dev_name); if (dev == NULL) { ret_val = -ENODEV; goto unlhsh_add_return; } ifindex = dev->ifindex; iface = netlbl_unlhsh_search_iface(ifindex); } else { ifindex = 0; iface = rcu_dereference(netlbl_unlhsh_def); } if (iface == NULL) { iface = netlbl_unlhsh_add_iface(ifindex); if (iface == NULL) { ret_val = -ENOMEM; goto unlhsh_add_return; } } audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCADD, audit_info); switch (addr_len) { case sizeof(struct in_addr): { const struct in_addr *addr4 = addr; const struct in_addr *mask4 = mask; ret_val = netlbl_unlhsh_add_addr4(iface, addr4, mask4, secid); if (audit_buf != NULL) netlbl_af4list_audit_addr(audit_buf, 1, dev_name, addr4->s_addr, mask4->s_addr); break; } #if IS_ENABLED(CONFIG_IPV6) case sizeof(struct in6_addr): { const struct in6_addr *addr6 = addr; const struct in6_addr *mask6 = mask; ret_val = netlbl_unlhsh_add_addr6(iface, addr6, mask6, secid); if (audit_buf != NULL) netlbl_af6list_audit_addr(audit_buf, 1, dev_name, addr6, mask6); break; } #endif /* IPv6 */ default: ret_val = -EINVAL; } if (ret_val == 0) atomic_inc(&netlabel_mgmt_protocount); unlhsh_add_return: rcu_read_unlock(); if (audit_buf != NULL) { if (security_secid_to_secctx(secid, &secctx, &secctx_len) == 0) { audit_log_format(audit_buf, " sec_obj=%s", secctx); security_release_secctx(secctx, secctx_len); } audit_log_format(audit_buf, " res=%u", ret_val == 0 ? 1 : 0); audit_log_end(audit_buf); } return ret_val; } /** * netlbl_unlhsh_remove_addr4 - Remove an IPv4 address entry * @net: network namespace * @iface: interface entry * @addr: IP address * @mask: IP address mask * @audit_info: NetLabel audit information * * Description: * Remove an IP address entry from the unlabeled connection hash table. * Returns zero on success, negative values on failure. * */ static int netlbl_unlhsh_remove_addr4(struct net *net, struct netlbl_unlhsh_iface *iface, const struct in_addr *addr, const struct in_addr *mask, struct netlbl_audit *audit_info) { struct netlbl_af4list *list_entry; struct netlbl_unlhsh_addr4 *entry; struct audit_buffer *audit_buf; struct net_device *dev; char *secctx; u32 secctx_len; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af4list_remove(addr->s_addr, mask->s_addr, &iface->addr4_list); spin_unlock(&netlbl_unlhsh_lock); if (list_entry != NULL) entry = netlbl_unlhsh_addr4_entry(list_entry); else entry = NULL; audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL, audit_info); if (audit_buf != NULL) { dev = dev_get_by_index(net, iface->ifindex); netlbl_af4list_audit_addr(audit_buf, 1, (dev != NULL ? dev->name : NULL), addr->s_addr, mask->s_addr); dev_put(dev); if (entry != NULL && security_secid_to_secctx(entry->secid, &secctx, &secctx_len) == 0) { audit_log_format(audit_buf, " sec_obj=%s", secctx); security_release_secctx(secctx, secctx_len); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); } if (entry == NULL) return -ENOENT; kfree_rcu(entry, rcu); return 0; } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_unlhsh_remove_addr6 - Remove an IPv6 address entry * @net: network namespace * @iface: interface entry * @addr: IP address * @mask: IP address mask * @audit_info: NetLabel audit information * * Description: * Remove an IP address entry from the unlabeled connection hash table. * Returns zero on success, negative values on failure. * */ static int netlbl_unlhsh_remove_addr6(struct net *net, struct netlbl_unlhsh_iface *iface, const struct in6_addr *addr, const struct in6_addr *mask, struct netlbl_audit *audit_info) { struct netlbl_af6list *list_entry; struct netlbl_unlhsh_addr6 *entry; struct audit_buffer *audit_buf; struct net_device *dev; char *secctx; u32 secctx_len; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af6list_remove(addr, mask, &iface->addr6_list); spin_unlock(&netlbl_unlhsh_lock); if (list_entry != NULL) entry = netlbl_unlhsh_addr6_entry(list_entry); else entry = NULL; audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL, audit_info); if (audit_buf != NULL) { dev = dev_get_by_index(net, iface->ifindex); netlbl_af6list_audit_addr(audit_buf, 1, (dev != NULL ? dev->name : NULL), addr, mask); dev_put(dev); if (entry != NULL && security_secid_to_secctx(entry->secid, &secctx, &secctx_len) == 0) { audit_log_format(audit_buf, " sec_obj=%s", secctx); security_release_secctx(secctx, secctx_len); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); } if (entry == NULL) return -ENOENT; kfree_rcu(entry, rcu); return 0; } #endif /* IPv6 */ /** * netlbl_unlhsh_condremove_iface - Remove an interface entry * @iface: the interface entry * * Description: * Remove an interface entry from the unlabeled connection hash table if it is * empty. An interface entry is considered to be empty if there are no * address entries assigned to it. * */ static void netlbl_unlhsh_condremove_iface(struct netlbl_unlhsh_iface *iface) { struct netlbl_af4list *iter4; #if IS_ENABLED(CONFIG_IPV6) struct netlbl_af6list *iter6; #endif /* IPv6 */ spin_lock(&netlbl_unlhsh_lock); netlbl_af4list_foreach_rcu(iter4, &iface->addr4_list) goto unlhsh_condremove_failure; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(iter6, &iface->addr6_list) goto unlhsh_condremove_failure; #endif /* IPv6 */ iface->valid = 0; if (iface->ifindex > 0) list_del_rcu(&iface->list); else RCU_INIT_POINTER(netlbl_unlhsh_def, NULL); spin_unlock(&netlbl_unlhsh_lock); call_rcu(&iface->rcu, netlbl_unlhsh_free_iface); return; unlhsh_condremove_failure: spin_unlock(&netlbl_unlhsh_lock); } /** * netlbl_unlhsh_remove - Remove an entry from the unlabeled hash table * @net: network namespace * @dev_name: interface name * @addr: IP address in network byte order * @mask: address mask in network byte order * @addr_len: length of address/mask (4 for IPv4, 16 for IPv6) * @audit_info: NetLabel audit information * * Description: * Removes and existing entry from the unlabeled connection hash table. * Returns zero on success, negative values on failure. * */ int netlbl_unlhsh_remove(struct net *net, const char *dev_name, const void *addr, const void *mask, u32 addr_len, struct netlbl_audit *audit_info) { int ret_val; struct net_device *dev; struct netlbl_unlhsh_iface *iface; if (addr_len != sizeof(struct in_addr) && addr_len != sizeof(struct in6_addr)) return -EINVAL; rcu_read_lock(); if (dev_name != NULL) { dev = dev_get_by_name_rcu(net, dev_name); if (dev == NULL) { ret_val = -ENODEV; goto unlhsh_remove_return; } iface = netlbl_unlhsh_search_iface(dev->ifindex); } else iface = rcu_dereference(netlbl_unlhsh_def); if (iface == NULL) { ret_val = -ENOENT; goto unlhsh_remove_return; } switch (addr_len) { case sizeof(struct in_addr): ret_val = netlbl_unlhsh_remove_addr4(net, iface, addr, mask, audit_info); break; #if IS_ENABLED(CONFIG_IPV6) case sizeof(struct in6_addr): ret_val = netlbl_unlhsh_remove_addr6(net, iface, addr, mask, audit_info); break; #endif /* IPv6 */ default: ret_val = -EINVAL; } if (ret_val == 0) { netlbl_unlhsh_condremove_iface(iface); atomic_dec(&netlabel_mgmt_protocount); } unlhsh_remove_return: rcu_read_unlock(); return ret_val; } /* * General Helper Functions */ /** * netlbl_unlhsh_netdev_handler - Network device notification handler * @this: notifier block * @event: the event * @ptr: the netdevice notifier info (cast to void) * * Description: * Handle network device events, although at present all we care about is a * network device going away. In the case of a device going away we clear any * related entries from the unlabeled connection hash table. * */ static int netlbl_unlhsh_netdev_handler(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netlbl_unlhsh_iface *iface = NULL; if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; /* XXX - should this be a check for NETDEV_DOWN or _UNREGISTER? */ if (event == NETDEV_DOWN) { spin_lock(&netlbl_unlhsh_lock); iface = netlbl_unlhsh_search_iface(dev->ifindex); if (iface != NULL && iface->valid) { iface->valid = 0; list_del_rcu(&iface->list); } else iface = NULL; spin_unlock(&netlbl_unlhsh_lock); } if (iface != NULL) call_rcu(&iface->rcu, netlbl_unlhsh_free_iface); return NOTIFY_DONE; } /** * netlbl_unlabel_acceptflg_set - Set the unlabeled accept flag * @value: desired value * @audit_info: NetLabel audit information * * Description: * Set the value of the unlabeled accept flag to @value. * */ static void netlbl_unlabel_acceptflg_set(u8 value, struct netlbl_audit *audit_info) { struct audit_buffer *audit_buf; u8 old_val; old_val = netlabel_unlabel_acceptflg; netlabel_unlabel_acceptflg = value; audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_ALLOW, audit_info); if (audit_buf != NULL) { audit_log_format(audit_buf, " unlbl_accept=%u old=%u", value, old_val); audit_log_end(audit_buf); } } /** * netlbl_unlabel_addrinfo_get - Get the IPv4/6 address information * @info: the Generic NETLINK info block * @addr: the IP address * @mask: the IP address mask * @len: the address length * * Description: * Examine the Generic NETLINK message and extract the IP address information. * Returns zero on success, negative values on failure. * */ static int netlbl_unlabel_addrinfo_get(struct genl_info *info, void **addr, void **mask, u32 *len) { u32 addr_len; if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR] && info->attrs[NLBL_UNLABEL_A_IPV4MASK]) { addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]); if (addr_len != sizeof(struct in_addr) && addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV4MASK])) return -EINVAL; *len = addr_len; *addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]); *mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4MASK]); return 0; } else if (info->attrs[NLBL_UNLABEL_A_IPV6ADDR]) { addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]); if (addr_len != sizeof(struct in6_addr) && addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV6MASK])) return -EINVAL; *len = addr_len; *addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]); *mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6MASK]); return 0; } return -EINVAL; } /* * NetLabel Command Handlers */ /** * netlbl_unlabel_accept - Handle an ACCEPT message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated ACCEPT message and set the accept flag accordingly. * Returns zero on success, negative values on failure. * */ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info) { u8 value; struct netlbl_audit audit_info; if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) { value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]); if (value == 1 || value == 0) { netlbl_netlink_auditinfo(&audit_info); netlbl_unlabel_acceptflg_set(value, &audit_info); return 0; } } return -EINVAL; } /** * netlbl_unlabel_list - Handle a LIST message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated LIST message and respond with the current status. * Returns zero on success, negative values on failure. * */ static int netlbl_unlabel_list(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct sk_buff *ans_skb; void *data; ans_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (ans_skb == NULL) goto list_failure; data = genlmsg_put_reply(ans_skb, info, &netlbl_unlabel_gnl_family, 0, NLBL_UNLABEL_C_LIST); if (data == NULL) { ret_val = -ENOMEM; goto list_failure; } ret_val = nla_put_u8(ans_skb, NLBL_UNLABEL_A_ACPTFLG, netlabel_unlabel_acceptflg); if (ret_val != 0) goto list_failure; genlmsg_end(ans_skb, data); return genlmsg_reply(ans_skb, info); list_failure: kfree_skb(ans_skb); return ret_val; } /** * netlbl_unlabel_staticadd - Handle a STATICADD message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICADD message and add a new unlabeled * connection entry to the hash table. Returns zero on success, negative * values on failure. * */ static int netlbl_unlabel_staticadd(struct sk_buff *skb, struct genl_info *info) { int ret_val; char *dev_name; void *addr; void *mask; u32 addr_len; u32 secid; struct netlbl_audit audit_info; /* Don't allow users to add both IPv4 and IPv6 addresses for a * single entry. However, allow users to create two entries, one each * for IPv4 and IPv6, with the same LSM security context which should * achieve the same result. */ if (!info->attrs[NLBL_UNLABEL_A_SECCTX] || !info->attrs[NLBL_UNLABEL_A_IFACE] || !((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; dev_name = nla_data(info->attrs[NLBL_UNLABEL_A_IFACE]); ret_val = security_secctx_to_secid( nla_data(info->attrs[NLBL_UNLABEL_A_SECCTX]), nla_len(info->attrs[NLBL_UNLABEL_A_SECCTX]), &secid); if (ret_val != 0) return ret_val; return netlbl_unlhsh_add(&init_net, dev_name, addr, mask, addr_len, secid, &audit_info); } /** * netlbl_unlabel_staticadddef - Handle a STATICADDDEF message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICADDDEF message and add a new default * unlabeled connection entry. Returns zero on success, negative values on * failure. * */ static int netlbl_unlabel_staticadddef(struct sk_buff *skb, struct genl_info *info) { int ret_val; void *addr; void *mask; u32 addr_len; u32 secid; struct netlbl_audit audit_info; /* Don't allow users to add both IPv4 and IPv6 addresses for a * single entry. However, allow users to create two entries, one each * for IPv4 and IPv6, with the same LSM security context which should * achieve the same result. */ if (!info->attrs[NLBL_UNLABEL_A_SECCTX] || !((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; ret_val = security_secctx_to_secid( nla_data(info->attrs[NLBL_UNLABEL_A_SECCTX]), nla_len(info->attrs[NLBL_UNLABEL_A_SECCTX]), &secid); if (ret_val != 0) return ret_val; return netlbl_unlhsh_add(&init_net, NULL, addr, mask, addr_len, secid, &audit_info); } /** * netlbl_unlabel_staticremove - Handle a STATICREMOVE message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICREMOVE message and remove the specified * unlabeled connection entry. Returns zero on success, negative values on * failure. * */ static int netlbl_unlabel_staticremove(struct sk_buff *skb, struct genl_info *info) { int ret_val; char *dev_name; void *addr; void *mask; u32 addr_len; struct netlbl_audit audit_info; /* See the note in netlbl_unlabel_staticadd() about not allowing both * IPv4 and IPv6 in the same entry. */ if (!info->attrs[NLBL_UNLABEL_A_IFACE] || !((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; dev_name = nla_data(info->attrs[NLBL_UNLABEL_A_IFACE]); return netlbl_unlhsh_remove(&init_net, dev_name, addr, mask, addr_len, &audit_info); } /** * netlbl_unlabel_staticremovedef - Handle a STATICREMOVEDEF message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICREMOVEDEF message and remove the default * unlabeled connection entry. Returns zero on success, negative values on * failure. * */ static int netlbl_unlabel_staticremovedef(struct sk_buff *skb, struct genl_info *info) { int ret_val; void *addr; void *mask; u32 addr_len; struct netlbl_audit audit_info; /* See the note in netlbl_unlabel_staticadd() about not allowing both * IPv4 and IPv6 in the same entry. */ if (!((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; return netlbl_unlhsh_remove(&init_net, NULL, addr, mask, addr_len, &audit_info); } /** * netlbl_unlabel_staticlist_gen - Generate messages for STATICLIST[DEF] * @cmd: command/message * @iface: the interface entry * @addr4: the IPv4 address entry * @addr6: the IPv6 address entry * @arg: the netlbl_unlhsh_walk_arg structure * * Description: * This function is designed to be used to generate a response for a * STATICLIST or STATICLISTDEF message. When called either @addr4 or @addr6 * can be specified, not both, the other unspecified entry should be set to * NULL by the caller. Returns the size of the message on success, negative * values on failure. * */ static int netlbl_unlabel_staticlist_gen(u32 cmd, const struct netlbl_unlhsh_iface *iface, const struct netlbl_unlhsh_addr4 *addr4, const struct netlbl_unlhsh_addr6 *addr6, void *arg) { int ret_val = -ENOMEM; struct netlbl_unlhsh_walk_arg *cb_arg = arg; struct net_device *dev; void *data; u32 secid; char *secctx; u32 secctx_len; data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_unlabel_gnl_family, NLM_F_MULTI, cmd); if (data == NULL) goto list_cb_failure; if (iface->ifindex > 0) { dev = dev_get_by_index(&init_net, iface->ifindex); if (!dev) { ret_val = -ENODEV; goto list_cb_failure; } ret_val = nla_put_string(cb_arg->skb, NLBL_UNLABEL_A_IFACE, dev->name); dev_put(dev); if (ret_val != 0) goto list_cb_failure; } if (addr4) { struct in_addr addr_struct; addr_struct.s_addr = addr4->list.addr; ret_val = nla_put_in_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV4ADDR, addr_struct.s_addr); if (ret_val != 0) goto list_cb_failure; addr_struct.s_addr = addr4->list.mask; ret_val = nla_put_in_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV4MASK, addr_struct.s_addr); if (ret_val != 0) goto list_cb_failure; secid = addr4->secid; } else { ret_val = nla_put_in6_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV6ADDR, &addr6->list.addr); if (ret_val != 0) goto list_cb_failure; ret_val = nla_put_in6_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV6MASK, &addr6->list.mask); if (ret_val != 0) goto list_cb_failure; secid = addr6->secid; } ret_val = security_secid_to_secctx(secid, &secctx, &secctx_len); if (ret_val != 0) goto list_cb_failure; ret_val = nla_put(cb_arg->skb, NLBL_UNLABEL_A_SECCTX, secctx_len, secctx); security_release_secctx(secctx, secctx_len); if (ret_val != 0) goto list_cb_failure; cb_arg->seq++; genlmsg_end(cb_arg->skb, data); return 0; list_cb_failure: genlmsg_cancel(cb_arg->skb, data); return ret_val; } /** * netlbl_unlabel_staticlist - Handle a STATICLIST message * @skb: the NETLINK buffer * @cb: the NETLINK callback * * Description: * Process a user generated STATICLIST message and dump the unlabeled * connection hash table in a form suitable for use in a kernel generated * STATICLIST message. Returns the length of @skb. * */ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlink_callback *cb) { struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; u32 skip_addr4 = cb->args[2]; u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; struct list_head *iter_list; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) u32 skip_addr6 = cb->args[3]; struct netlbl_af6list *addr6; #endif cb_arg.nl_cb = cb; cb_arg.skb = skb; cb_arg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); for (iter_bkt = skip_bkt; iter_bkt < rcu_dereference(netlbl_unlhsh)->size; iter_bkt++) { iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt]; list_for_each_entry_rcu(iface, iter_list, list) { if (!iface->valid || iter_chain++ < skip_chain) continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { if (iter_addr4++ < skip_addr4) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, iface, netlbl_unlhsh_addr4_entry(addr4), NULL, &cb_arg) < 0) { iter_addr4--; iter_chain--; goto unlabel_staticlist_return; } } iter_addr4 = 0; skip_addr4 = 0; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { if (iter_addr6++ < skip_addr6) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, iface, NULL, netlbl_unlhsh_addr6_entry(addr6), &cb_arg) < 0) { iter_addr6--; iter_chain--; goto unlabel_staticlist_return; } } iter_addr6 = 0; skip_addr6 = 0; #endif /* IPv6 */ } iter_chain = 0; skip_chain = 0; } unlabel_staticlist_return: rcu_read_unlock(); cb->args[0] = iter_bkt; cb->args[1] = iter_chain; cb->args[2] = iter_addr4; cb->args[3] = iter_addr6; return skb->len; } /** * netlbl_unlabel_staticlistdef - Handle a STATICLISTDEF message * @skb: the NETLINK buffer * @cb: the NETLINK callback * * Description: * Process a user generated STATICLISTDEF message and dump the default * unlabeled connection entry in a form suitable for use in a kernel generated * STATICLISTDEF message. Returns the length of @skb. * */ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, struct netlink_callback *cb) { struct netlbl_unlhsh_walk_arg cb_arg; struct netlbl_unlhsh_iface *iface; u32 iter_addr4 = 0, iter_addr6 = 0; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) struct netlbl_af6list *addr6; #endif cb_arg.nl_cb = cb; cb_arg.skb = skb; cb_arg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); iface = rcu_dereference(netlbl_unlhsh_def); if (iface == NULL || !iface->valid) goto unlabel_staticlistdef_return; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { if (iter_addr4++ < cb->args[0]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, netlbl_unlhsh_addr4_entry(addr4), NULL, &cb_arg) < 0) { iter_addr4--; goto unlabel_staticlistdef_return; } } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { if (iter_addr6++ < cb->args[1]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, NULL, netlbl_unlhsh_addr6_entry(addr6), &cb_arg) < 0) { iter_addr6--; goto unlabel_staticlistdef_return; } } #endif /* IPv6 */ unlabel_staticlistdef_return: rcu_read_unlock(); cb->args[0] = iter_addr4; cb->args[1] = iter_addr6; return skb->len; } /* * NetLabel Generic NETLINK Command Definitions */ static const struct genl_small_ops netlbl_unlabel_genl_ops[] = { { .cmd = NLBL_UNLABEL_C_STATICADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticadd, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICREMOVE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticremove, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICLIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = NULL, .dumpit = netlbl_unlabel_staticlist, }, { .cmd = NLBL_UNLABEL_C_STATICADDDEF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticadddef, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICREMOVEDEF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticremovedef, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICLISTDEF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = NULL, .dumpit = netlbl_unlabel_staticlistdef, }, { .cmd = NLBL_UNLABEL_C_ACCEPT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_accept, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_LIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = netlbl_unlabel_list, .dumpit = NULL, }, }; static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = { .hdrsize = 0, .name = NETLBL_NLTYPE_UNLABELED_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_UNLABEL_A_MAX, .policy = netlbl_unlabel_genl_policy, .module = THIS_MODULE, .small_ops = netlbl_unlabel_genl_ops, .n_small_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops), .resv_start_op = NLBL_UNLABEL_C_STATICLISTDEF + 1, }; /* * NetLabel Generic NETLINK Protocol Functions */ /** * netlbl_unlabel_genl_init - Register the Unlabeled NetLabel component * * Description: * Register the unlabeled packet NetLabel component with the Generic NETLINK * mechanism. Returns zero on success, negative values on failure. * */ int __init netlbl_unlabel_genl_init(void) { return genl_register_family(&netlbl_unlabel_gnl_family); } /* * NetLabel KAPI Hooks */ static struct notifier_block netlbl_unlhsh_netdev_notifier = { .notifier_call = netlbl_unlhsh_netdev_handler, }; /** * netlbl_unlabel_init - Initialize the unlabeled connection hash table * @size: the number of bits to use for the hash buckets * * Description: * Initializes the unlabeled connection hash table and registers a network * device notification handler. This function should only be called by the * NetLabel subsystem itself during initialization. Returns zero on success, * non-zero values on error. * */ int __init netlbl_unlabel_init(u32 size) { u32 iter; struct netlbl_unlhsh_tbl *hsh_tbl; if (size == 0) return -EINVAL; hsh_tbl = kmalloc(sizeof(*hsh_tbl), GFP_KERNEL); if (hsh_tbl == NULL) return -ENOMEM; hsh_tbl->size = 1 << size; hsh_tbl->tbl = kcalloc(hsh_tbl->size, sizeof(struct list_head), GFP_KERNEL); if (hsh_tbl->tbl == NULL) { kfree(hsh_tbl); return -ENOMEM; } for (iter = 0; iter < hsh_tbl->size; iter++) INIT_LIST_HEAD(&hsh_tbl->tbl[iter]); spin_lock(&netlbl_unlhsh_lock); rcu_assign_pointer(netlbl_unlhsh, hsh_tbl); spin_unlock(&netlbl_unlhsh_lock); register_netdevice_notifier(&netlbl_unlhsh_netdev_notifier); return 0; } /** * netlbl_unlabel_getattr - Get the security attributes for an unlabled packet * @skb: the packet * @family: protocol family * @secattr: the security attributes * * Description: * Determine the security attributes, if any, for an unlabled packet and return * them in @secattr. Returns zero on success and negative values on failure. * */ int netlbl_unlabel_getattr(const struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr) { struct netlbl_unlhsh_iface *iface; rcu_read_lock(); iface = netlbl_unlhsh_search_iface(skb->skb_iif); if (iface == NULL) iface = rcu_dereference(netlbl_unlhsh_def); if (iface == NULL || !iface->valid) goto unlabel_getattr_nolabel; #if IS_ENABLED(CONFIG_IPV6) /* When resolving a fallback label, check the sk_buff version as * it is possible (e.g. SCTP) to have family = PF_INET6 while * receiving ip_hdr(skb)->version = 4. */ if (family == PF_INET6 && ip_hdr(skb)->version == 4) family = PF_INET; #endif /* IPv6 */ switch (family) { case PF_INET: { struct iphdr *hdr4; struct netlbl_af4list *addr4; hdr4 = ip_hdr(skb); addr4 = netlbl_af4list_search(hdr4->saddr, &iface->addr4_list); if (addr4 == NULL) goto unlabel_getattr_nolabel; secattr->attr.secid = netlbl_unlhsh_addr4_entry(addr4)->secid; break; } #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: { struct ipv6hdr *hdr6; struct netlbl_af6list *addr6; hdr6 = ipv6_hdr(skb); addr6 = netlbl_af6list_search(&hdr6->saddr, &iface->addr6_list); if (addr6 == NULL) goto unlabel_getattr_nolabel; secattr->attr.secid = netlbl_unlhsh_addr6_entry(addr6)->secid; break; } #endif /* IPv6 */ default: goto unlabel_getattr_nolabel; } rcu_read_unlock(); secattr->flags |= NETLBL_SECATTR_SECID; secattr->type = NETLBL_NLTYPE_UNLABELED; return 0; unlabel_getattr_nolabel: rcu_read_unlock(); if (netlabel_unlabel_acceptflg == 0) return -ENOMSG; secattr->type = NETLBL_NLTYPE_UNLABELED; return 0; } /** * netlbl_unlabel_defconf - Set the default config to allow unlabeled packets * * Description: * Set the default NetLabel configuration to allow incoming unlabeled packets * and to send unlabeled network traffic by default. * */ int __init netlbl_unlabel_defconf(void) { int ret_val; struct netlbl_dom_map *entry; struct netlbl_audit audit_info; /* Only the kernel is allowed to call this function and the only time * it is called is at bootup before the audit subsystem is reporting * messages so don't worry to much about these values. */ security_current_getlsmprop_subj(&audit_info.prop); audit_info.loginuid = GLOBAL_ROOT_UID; audit_info.sessionid = 0; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) return -ENOMEM; entry->family = AF_UNSPEC; entry->def.type = NETLBL_NLTYPE_UNLABELED; ret_val = netlbl_domhsh_add_default(entry, &audit_info); if (ret_val != 0) return ret_val; netlbl_unlabel_acceptflg_set(1, &audit_info); return 0; } |
| 248 43 2 41 289 289 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @bucket_expiry: the bucket expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long bucket_expiry), TP_ARGS(timer, bucket_expiry), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, bucket_expiry ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = timer->expires; __entry->bucket_expiry = bucket_expiry; __entry->now = jiffies; __entry->flags = timer->flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] bucket_expiry=%lu cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->bucket_expiry, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); TRACE_EVENT(timer_base_idle, TP_PROTO(bool is_idle, unsigned int cpu), TP_ARGS(is_idle, cpu), TP_STRUCT__entry( __field( bool, is_idle ) __field( unsigned int, cpu ) ), TP_fast_assign( __entry->is_idle = is_idle; __entry->cpu = cpu; ), TP_printk("is_idle=%d cpu=%d", __entry->is_idle, __entry->cpu) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_init - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_init, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = hrtimer->function; __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = hrtimer->function; ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name(RCU) \ tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 215 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash func */ int (*cmp)(const void *key1, const void *key2); /* comparison func */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; u64 chain2_len_sum; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig, int (*copy)(struct hashtab_node *new, const struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); #ifdef CONFIG_SECURITY_SELINUX_DEBUG /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #else static inline void hashtab_stat(struct hashtab *h, struct hashtab_info *info) { return; } #endif #endif /* _SS_HASHTAB_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #ifndef __LINUX_NEXTHOP_H #define __LINUX_NEXTHOP_H #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/route.h> #include <linux/types.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/netlink.h> #define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK struct nexthop; struct nh_config { u32 nh_id; u8 nh_family; u8 nh_protocol; u8 nh_blackhole; u8 nh_fdb; u32 nh_flags; int nh_ifindex; struct net_device *dev; union { __be32 ipv4; struct in6_addr ipv6; } gw; struct nlattr *nh_grp; u16 nh_grp_type; u16 nh_grp_res_num_buckets; unsigned long nh_grp_res_idle_timer; unsigned long nh_grp_res_unbalanced_timer; bool nh_grp_res_has_num_buckets; bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; bool nh_hw_stats; struct nlattr *nh_encap; u16 nh_encap_type; u32 nlflags; struct nl_info nlinfo; }; struct nh_info { struct hlist_node dev_hash; /* entry on netns devhash */ struct nexthop *nh_parent; u8 family; bool reject_nh; bool fdb_nh; union { struct fib_nh_common fib_nhc; struct fib_nh fib_nh; struct fib6_nh fib6_nh; }; }; struct nh_res_bucket { struct nh_grp_entry __rcu *nh_entry; atomic_long_t used_time; unsigned long migrated_time; bool occupied; u8 nh_flags; }; struct nh_res_table { struct net *net; u32 nhg_id; struct delayed_work upkeep_dw; /* List of NHGEs that have too few buckets ("uw" for underweight). * Reclaimed buckets will be given to entries in this list. */ struct list_head uw_nh_entries; unsigned long unbalanced_since; u32 idle_timer; u32 unbalanced_timer; u16 num_nh_buckets; struct nh_res_bucket nh_buckets[] __counted_by(num_nh_buckets); }; struct nh_grp_entry_stats { u64_stats_t packets; struct u64_stats_sync syncp; }; struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; u16 weight; union { struct { atomic_t upper_bound; } hthr; struct { /* Member on uw_nh_entries. */ struct list_head uw_nh_entry; u16 count_buckets; u16 wants_buckets; } res; }; struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ u64 packets_hw; }; struct nh_group { struct nh_group *spare; /* spare group for removals */ u16 num_nh; bool is_multipath; bool hash_threshold; bool resilient; bool fdb_nh; bool has_v4; bool hw_stats; struct nh_res_table __rcu *res_table; struct nh_grp_entry nh_entries[] __counted_by(num_nh); }; struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ struct list_head fi_list; /* v4 entries using nh */ struct list_head f6i_list; /* v6 entries using nh */ struct list_head fdb_list; /* fdb entries using this nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; u32 id; u8 protocol; /* app managing this nh */ u8 nh_flags; bool is_group; refcount_t refcnt; struct rcu_head rcu; union { struct nh_info __rcu *nh_info; struct nh_group __rcu *nh_grp; }; }; enum nexthop_event_type { NEXTHOP_EVENT_DEL, NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_SINGLE, NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { struct net_device *dev; u8 gw_family; union { __be32 ipv4; struct in6_addr ipv6; }; u32 id; u8 is_reject:1, is_fdb:1, has_encap:1; }; struct nh_notifier_grp_entry_info { u16 weight; struct nh_notifier_single_info nh; }; struct nh_notifier_grp_info { u16 num_nh; bool is_fdb; bool hw_stats; struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh); }; struct nh_notifier_res_bucket_info { u16 bucket_index; unsigned int idle_timer_ms; bool force; struct nh_notifier_single_info old_nh; struct nh_notifier_single_info new_nh; }; struct nh_notifier_res_table_info { u16 num_nh_buckets; bool hw_stats; struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; struct nh_notifier_grp_hw_stats_entry_info { u32 id; u64 packets; }; struct nh_notifier_grp_hw_stats_info { u16 num_nh; bool hw_stats_used; struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); }; struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; u32 id; enum nh_notifier_info_type type; union { struct nh_notifier_single_info *nh; struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; int register_nexthop_notifier(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap); void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, unsigned int nh_idx, u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); void nexthop_free_rcu(struct rcu_head *head); static inline bool nexthop_get(struct nexthop *nh) { return refcount_inc_not_zero(&nh->refcnt); } static inline void nexthop_put(struct nexthop *nh) { if (refcount_dec_and_test(&nh->refcnt)) call_rcu_hurry(&nh->rcu, nexthop_free_rcu); } static inline bool nexthop_cmp(const struct nexthop *nh1, const struct nexthop *nh2) { return nh1 == nh2; } static inline bool nexthop_is_fdb(const struct nexthop *nh) { if (nh->is_group) { const struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->fdb_nh; } else { const struct nh_info *nhi; nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->fdb_nh; } } static inline bool nexthop_has_v4(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->has_v4; } return false; } static inline bool nexthop_is_multipath(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->is_multipath; } return false; } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash); static inline unsigned int nexthop_num_path(const struct nexthop *nh) { unsigned int rc = 1; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) rc = nh_grp->num_nh; } return rc; } static inline struct nexthop *nexthop_mpath_select(const struct nh_group *nhg, int nhsel) { /* for_nexthops macros in fib_semantics.c grabs a pointer to * the nexthop before checking nhsel */ if (nhsel >= nhg->num_nh) return NULL; return nhg->nh_entries[nhsel].nh; } static inline int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, u8 rt_family) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info); struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } return 0; } /* called with rcu lock */ static inline bool nexthop_is_blackhole(const struct nexthop *nh) { const struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->num_nh > 1) return false; nh = nh_grp->nh_entries[0].nh; } nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->reject_nh; } static inline void nexthop_path_fib_result(struct fib_result *res, int hash) { struct nh_info *nhi; struct nexthop *nh; nh = nexthop_select_path(res->fi->nh, hash); nhi = rcu_dereference(nh->nh_info); res->nhc = &nhi->fib_nhc; } /* called with rcu read lock or rtnl held */ static inline struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel) { struct nh_info *nhi; BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0); BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0); if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) { nh = nexthop_mpath_select(nh_grp, nhsel); if (!nh) return NULL; } } nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } /* called from fib_table_lookup with rcu_lock */ static inline struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh, int fib_flags, const struct flowi4 *flp, int *nhsel) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = i; return &nhi->fib_nhc; } } } else { nhi = rcu_dereference(nh->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = 0; return &nhi->fib_nhc; } } return NULL; } static inline bool nexthop_uses_dev(const struct nexthop *nh, const struct net_device *dev) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } } else { nhi = rcu_dereference(nh->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } return false; } static inline unsigned int fib_info_num_path(const struct fib_info *fi) { if (unlikely(fi->nh)) return nexthop_num_path(fi->nh); return fi->fib_nhs; } int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack); static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) { if (unlikely(fi->nh)) return nexthop_fib_nhc(fi->nh, nhsel); return &fi->fib_nh[nhsel].nh_common; } /* only used when fib_nh is built into fib_info */ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) { WARN_ON(fi->nh); return &fi->fib_nh[nhsel]; } /* * IPv6 variants */ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack); /* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); nh = nexthop_mpath_select(nh_grp, 0); if (!nh) return NULL; } nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->family == AF_INET6) return &nhi->fib6_nh; return NULL; } static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh; return fib6_nh->fib_nh_dev; } static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) { struct nexthop *nh = res->f6i->nh; struct nh_info *nhi; nh = nexthop_select_path(nh, hash); nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->reject_nh) { res->fib6_type = RTN_BLACKHOLE; res->fib6_flags |= RTF_REJECT; res->nh = nexthop_fib6_nh(nh); } else { res->nh = &nhi->fib6_nh; } } int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg); static inline int nexthop_get_family(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->family; } static inline struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh, int hash) { struct nh_info *nhi; struct nexthop *nhp; nhp = nexthop_select_path(nh, hash); if (unlikely(!nhp)) return NULL; nhi = rcu_dereference(nhp->nh_info); return &nhi->fib_nhc; } #endif |
| 228 229 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, unsigned int nr_pages); static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset); static void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 /* Reclaim directly, bypass the slot cache and don't touch device lock */ #define TTRS_DIRECT 0x8 static bool swap_is_has_cache(struct swap_info_struct *si, unsigned long offset, int nr_pages) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; do { VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); if (*map != SWAP_HAS_CACHE) return false; } while (++map < map_end); return true; } static bool swap_is_last_map(struct swap_info_struct *si, unsigned long offset, int nr_pages, bool *has_cache) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; unsigned char count = *map; if (swap_count(count) != 1) return false; while (++map < map_end) { if (*map != count) return false; } *has_cache = !!(count & SWAP_HAS_CACHE); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct address_space *address_space = swap_address_space(entry); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; folio = filemap_get_folio(address_space, swap_cache_index(entry)); if (IS_ERR(folio)) return 0; nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (!folio_trylock(folio)) goto out; /* offset could point to the middle of a large folio */ entry = folio->swap; offset = swp_offset(entry); need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio's * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = lock_cluster_or_swap_info(si, offset); need_reclaim = swap_is_has_cache(si, offset, nr_pages); unlock_cluster_or_swap_info(si, ci); if (!need_reclaim) goto out_unlock; if (!(flags & TTRS_DIRECT)) { /* Free through slot cache */ delete_from_swap_cache(folio); folio_set_dirty(folio); ret = nr_pages; goto out_unlock; } xa_lock_irq(&address_space->i_pages); __delete_from_swap_cache(folio, entry, NULL); xa_unlock_irq(&address_space->i_pages); folio_ref_sub(folio, nr_pages); folio_set_dirty(folio); spin_lock(&si->lock); /* Only sinple page folio can be backed by zswap */ if (nr_pages == 1) zswap_invalidate(entry); swap_entry_range_free(si, entry, nr_pages); spin_unlock(&si->lock); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = swp_swap_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_order() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_order(order) 0 #endif #define LATENCY_LIMIT 256 static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { unsigned int idx = cluster_index(si, ci); /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); list_move_tail(&ci->list, &si->discard_clusters); ci->flags = 0; schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); if (ci->flags) list_move_tail(&ci->list, &si->free_clusters); else list_add_tail(&ci->list, &si->free_clusters); ci->flags = CLUSTER_FLAG_FREE; ci->order = 0; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; unsigned int idx; while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); spin_lock(&ci->lock); __free_cluster(si, ci); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); spin_unlock(&ci->lock); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. * Only used for initialization. */ static void inc_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; if (!cluster_info) return; ci = cluster_info + idx; ci->count++; VM_BUG_ON(ci->count > SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags); } /* * The cluster ci decreases @nr_pages usage. If the usage counter becomes 0, * which means no page in the cluster is in use, we can optionally discard * the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *ci, int nr_pages) { if (!si->cluster_info) return; VM_BUG_ON(ci->count < nr_pages); VM_BUG_ON(cluster_is_free(ci)); lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); ci->count -= nr_pages; if (!ci->count) { free_cluster(si, ci); return; } if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; list_move_tail(&ci->list, &si->nonfull_clusters[ci->order]); ci->flags = CLUSTER_FLAG_NONFULL; } } static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; unsigned long offset; spin_unlock(&ci->lock); spin_unlock(&si->lock); for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0) continue; goto out; default: goto out; } } out: spin_lock(&si->lock); spin_lock(&ci->lock); /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) if (READ_ONCE(map[offset])) return false; return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int nr_pages) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; bool need_reclaim = false; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; need_reclaim = true; continue; default: return false; } } if (need_reclaim) return cluster_reclaim_range(si, ci, start, end); return true; } static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order; if (!(si->flags & SWP_WRITEOK)) return false; if (cluster_is_free(ci)) { if (nr_pages < SWAPFILE_CLUSTER) { list_move_tail(&ci->list, &si->nonfull_clusters[order]); ci->flags = CLUSTER_FLAG_NONFULL; } ci->order = order; } memset(si->swap_map + start, usage, nr_pages); swap_range_alloc(si, start, nr_pages); ci->count += nr_pages; if (ci->count == SWAPFILE_CLUSTER) { VM_BUG_ON(!(ci->flags & (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG))); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; list_move_tail(&ci->list, &si->full_clusters); ci->flags = CLUSTER_FLAG_FULL; } return true; } static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset, unsigned int *foundp, unsigned int order, unsigned char usage) { unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; struct swap_cluster_info *ci; if (end < nr_pages) return SWAP_NEXT_INVALID; end -= nr_pages; ci = lock_cluster(si, offset); if (ci->count + nr_pages > SWAPFILE_CLUSTER) { offset = SWAP_NEXT_INVALID; goto done; } while (offset <= end) { if (cluster_scan_range(si, ci, offset, nr_pages)) { if (!cluster_alloc_range(si, ci, offset, usage, order)) { offset = SWAP_NEXT_INVALID; goto done; } *foundp = offset; if (ci->count == SWAPFILE_CLUSTER) { offset = SWAP_NEXT_INVALID; goto done; } offset += nr_pages; break; } offset += nr_pages; } if (offset > end) offset = SWAP_NEXT_INVALID; done: unlock_cluster(ci); return offset; } /* Return true if reclaimed a whole cluster */ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; int nr_reclaim; if (force) to_scan = si->inuse_pages / SWAPFILE_CLUSTER; while (!list_empty(&si->full_clusters)) { ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list); list_move_tail(&ci->list, &si->full_clusters); offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; spin_unlock(&si->lock); while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); if (nr_reclaim) { offset += abs(nr_reclaim); continue; } } offset++; } spin_lock(&si->lock); if (to_scan <= 0) break; } } static void swap_reclaim_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, reclaim_work); spin_lock(&si->lock); swap_reclaim_full_clusters(si, true); spin_unlock(&si->lock); } /* * Try to get swap entries with specified order from current cpu's swap entry * pool (a cluster). This might involve allocating a new cluster for current CPU * too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned int offset, found = 0; new_cluster: lockdep_assert_held(&si->lock); cluster = this_cpu_ptr(si->percpu_cluster); offset = cluster->next[order]; if (offset) { offset = alloc_swap_scan_cluster(si, offset, &found, order, usage); if (found) goto done; } if (!list_empty(&si->free_clusters)) { ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); /* * Either we didn't touch the cluster due to swapoff, * or the allocation must success. */ VM_BUG_ON((si->flags & SWP_WRITEOK) && !found); goto done; } /* Try reclaim from full clusters if free clusters list is drained */ if (vm_swap_full()) swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { unsigned int frags = 0; while (!list_empty(&si->nonfull_clusters[order])) { ci = list_first_entry(&si->nonfull_clusters[order], struct swap_cluster_info, list); list_move_tail(&ci->list, &si->frag_clusters[order]); ci->flags = CLUSTER_FLAG_FRAG; si->frag_cluster_nr[order]++; offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); frags++; if (found) break; } if (!found) { /* * Nonfull clusters are moved to frag tail if we reached * here, count them too, don't over scan the frag list. */ while (frags < si->frag_cluster_nr[order]) { ci = list_first_entry(&si->frag_clusters[order], struct swap_cluster_info, list); /* * Rotate the frag list to iterate, they were all failing * high order allocation or moved here due to per-CPU usage, * this help keeping usable cluster ahead. */ list_move_tail(&ci->list, &si->frag_clusters[order]); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); frags++; if (found) break; } } } if (found) goto done; if (!list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); goto new_cluster; } if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ while (!list_empty(&si->frag_clusters[o])) { ci = list_first_entry(&si->frag_clusters[o], struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, 0, usage); if (found) goto done; } while (!list_empty(&si->nonfull_clusters[o])) { ci = list_first_entry(&si->nonfull_clusters[o], struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, 0, usage); if (found) goto done; } } done: cluster->next[order] = offset; return found; } static void __del_from_avail_list(struct swap_info_struct *si) { int nid; assert_spin_locked(&si->lock); for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *si) { spin_lock(&swap_avail_lock); __del_from_avail_list(si); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); if (si->cluster_info && vm_swap_full()) schedule_work(&si->reclaim_work); } } static void add_to_avail_list(struct swap_info_struct *si) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) clear_bit(offset + i, si->zeromap); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = get_random_u32_inclusive(si->lowest_bit, si->highest_bit); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static bool swap_offset_available_and_locked(struct swap_info_struct *si, unsigned long offset) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); return true; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); return true; } return false; } static int cluster_alloc_swap(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { int n_ret = 0; VM_BUG_ON(!si->cluster_info); si->flags += SWP_SCANNING; while (n_ret < nr) { unsigned long offset = cluster_alloc_swap_entry(si, order, usage); if (!offset) break; slots[n_ret++] = swp_entry(si->type, offset); } si->flags -= SWP_SCANNING; return n_ret; } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; unsigned int nr_pages = 1 << order; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ if (order > 0) { /* * Should not even be attempting large allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP) || nr_pages > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return 0; } /* * Swapfile is not block device or not using clusters so unable * to allocate large entries. */ if (!(si->flags & SWP_BLKDEV) || !si->cluster_info) return 0; } if (si->cluster_info) return cluster_alloc_swap(si, usage, nr, slots, order); si->flags += SWP_SCANNING; /* For HDD, sequential access is more important. */ scan_base = si->cluster_next; offset = scan_base; if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed > 0) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { if (!n_ret) goto scan; else goto done; } memset(si->swap_map + offset, usage, nr_pages); swap_range_alloc(si, offset, nr_pages); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: if (order == 0) set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: VM_WARN_ON(order > 0); spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; } offset = si->lowest_bit; while (offset < scan_base) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order) { int order = swap_entry_order(entry_order); unsigned long size = 1 << order; struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries, order); spin_unlock(&si->lock); if (n_ret || size > 1) goto check_out; cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= si->max) goto bad_offset; if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; return si; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *si, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = si->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(si->swap_map[offset], usage); else WRITE_ONCE(si->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(si, offset); usage = __swap_entry_free_locked(si, offset, 1); unlock_cluster_or_swap_info(si, ci); if (!usage) free_swap_slot(entry); return usage; } static bool __swap_entries_free(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); unsigned int type = swp_type(entry); struct swap_cluster_info *ci; bool has_cache = false; unsigned char count; int i; if (nr <= 1 || swap_count(data_race(si->swap_map[offset])) != 1) goto fallback; /* cross into another cluster */ if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER) goto fallback; ci = lock_cluster_or_swap_info(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { unlock_cluster_or_swap_info(si, ci); goto fallback; } for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); unlock_cluster_or_swap_info(si, ci); if (!has_cache) { for (i = 0; i < nr; i++) zswap_invalidate(swp_entry(si->type, offset + i)); spin_lock(&si->lock); swap_entry_range_free(si, entry, nr); spin_unlock(&si->lock); } return has_cache; fallback: for (i = 0; i < nr; i++) { if (data_race(si->swap_map[offset + i])) { count = __swap_entry_free(si, swp_entry(type, offset + i)); if (count == SWAP_HAS_CACHE) has_cache = true; } else { WARN_ON_ONCE(1); } } return has_cache; } /* * Drop the last HAS_CACHE flag of swap entries, caller have to * ensure all entries belong to the same cgroup. */ static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); do { VM_BUG_ON(*map != SWAP_HAS_CACHE); *map = 0; } while (++map < map_end); dec_cluster_info_page(si, ci, nr_pages); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); } static void cluster_swap_free_nr(struct swap_info_struct *si, unsigned long offset, int nr_pages, unsigned char usage) { struct swap_cluster_info *ci; DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 }; int i, nr; ci = lock_cluster_or_swap_info(si, offset); while (nr_pages) { nr = min(BITS_PER_LONG, nr_pages); for (i = 0; i < nr; i++) { if (!__swap_entry_free_locked(si, offset + i, usage)) bitmap_set(to_free, i, 1); } if (!bitmap_empty(to_free, BITS_PER_LONG)) { unlock_cluster_or_swap_info(si, ci); for_each_set_bit(i, to_free, BITS_PER_LONG) free_swap_slot(swp_entry(si->type, offset + i)); if (nr == nr_pages) return; bitmap_clear(to_free, 0, BITS_PER_LONG); ci = lock_cluster_or_swap_info(si, offset); } offset += nr; nr_pages -= nr; } unlock_cluster_or_swap_info(si, ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); cluster_swap_free_nr(sis, offset, nr, 1); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; struct swap_info_struct *si; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size > 1 && swap_is_has_cache(si, offset, size)) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); swap_entry_range_free(si, entry, size); spin_unlock(&si->lock); return; } for (int i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_range_free(p, entries[i], 1); prev = p; } if (p) spin_unlock(&p->lock); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; si = _swap_info_get(entry); if (!si) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(si, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_swapped(folio)) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; if (non_swap_entry(entry)) return; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ any_only_cache = __swap_entries_free(si, entry, nr); /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. This is * more efficient for large folios because we will only try to reclaim * the swap once per folio in the common case. If we do * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the * latter will get a reference and lock the folio for every individual * page but will only succeed once the swap slot for every subpage is * zero. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry)); if (IS_ERR(folio)) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writepage() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *si) { struct block_device *bdev; if (si->bdev) bdev = si->bdev; else bdev = si->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { int i; if (prio >= 0) si->prio = prio; else si->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->list.prio = -si->prio; for_each_node(i) { if (si->prio >= 0) si->avail_lists[i].prio = -si->prio; else { if (swap_node(si) == i) si->avail_lists[i].prio = 1; else si->avail_lists[i].prio = -si->prio; } } si->swap_map = swap_map; si->cluster_info = cluster_info; si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) { si->flags |= SWP_WRITEOK; atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&si->list, &swap_active_head); /* add to available list iff swap device is not full */ if (si->highest_bit) add_to_avail_list(si); } static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } bool has_usable_swap(void) { bool ret; spin_lock(&swap_lock); ret = __has_usable_swap(); spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); flush_work(&p->reclaim_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; zeromap = p->zeromap; p->zeromap = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(READ_ONCE(si->inuse_pages)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } si->lowest_bit = 1; si->cluster_next = 1; si->cluster_nr = 0; maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } si->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *si, union swap_header *swap_header, unsigned char *swap_map, unsigned long maxpages, sector_t *span) { unsigned int nr_good_pages; unsigned long i; int nr_extents; nr_good_pages = maxpages - 1; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; } } if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; si->max = maxpages; si->pages = nr_good_pages; nr_extents = setup_swap_extents(si, span); if (nr_extents < 0) return nr_extents; nr_good_pages = si->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } return nr_extents; } static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = si->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; struct swap_cluster_info *cluster_info; unsigned long i, j, k, idx; int cpu, err = -ENOMEM; cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); si->cluster_next_cpu = alloc_percpu(unsigned int); if (!si->cluster_next_cpu) goto err_free; /* Random start position to help with wear leveling */ for_each_possible_cpu(cpu) per_cpu(*si->cluster_next_cpu, cpu) = get_random_u32_inclusive(1, si->highest_bit); si->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!si->percpu_cluster) goto err_free; for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(si->percpu_cluster, cpu); for (i = 0; i < SWAP_NR_ORDERS; i++) cluster->next[i] = SWAP_NEXT_INVALID; } /* * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * * See setup_swap_map_and_extents(): header page, bad pages, * and the EOF part of the last cluster. */ inc_cluster_info_page(si, cluster_info, 0); for (i = 0; i < swap_header->info.nr_badpages; i++) inc_cluster_info_page(si, cluster_info, swap_header->info.badpages[i]); for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(si, cluster_info, i); INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); si->frag_cluster_nr[i] = 0; } /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { struct swap_cluster_info *ci; idx = i * SWAP_CLUSTER_COLS + j; ci = cluster_info + idx; if (idx >= nr_clusters) continue; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); continue; } ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } return cluster_info; err_free: kvfree(cluster_info); err: return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } si->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; cluster_info = setup_clusters(si, swap_header, maxpages); if (IS_ERR(cluster_info)) { error = PTR_ERR(cluster_info); cluster_info = NULL; goto bad_swap_unlock_inode; } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = init_swap_address_space(si->type, maxpages); if (error) goto bad_swap_unlock_inode; error = zswap_swapon(si->type, maxpages); if (error) goto free_swap_address_space; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); free_swap_address_space: exit_swap_address_space(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(si->percpu_cluster); si->percpu_cluster = NULL; free_percpu(si->cluster_next_cpu); si->cluster_next_cpu = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); si->swap_file = NULL; si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err, i; si = swp_swap_info(entry); offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); ci = lock_cluster_or_swap_info(si, offset); err = 0; for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (!count && !has_cache) { err = -ENOENT; } else if (usage == SWAP_HAS_CACHE) { if (has_cache) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; } if (err) goto unlock_out; } for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) has_cache = SWAP_HAS_CACHE; else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; else { /* * Don't need to rollback changes, because if * usage == 1, there must be nr == 1. */ err = -ENOMEM; goto unlock_out; } WRITE_ONCE(si->swap_map[offset + i], count | has_cache); } unlock_out: unlock_cluster_or_swap_info(si, ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry, int nr) { __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: first swap entry from which we allocate nr swap cache. * * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry, int nr) { return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } /* * out-of-line methods to avoid include hell. */ struct address_space *swapcache_mapping(struct folio *folio) { return swp_swap_info(folio->swap)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __folio_swap_cache_index(struct folio *folio) { return swap_cache_index(folio->swap); } EXPORT_SYMBOL_GPL(__folio_swap_cache_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 438 203 194 189 279 47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/audit_arch.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #include <uapi/linux/fanotify.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct kern_ipc_perm; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_SETELEM_RESET, AUDIT_NFT_OP_RULE_RESET, AUDIT_NFT_OP_INVALID, }; extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_uring_entry(u8 op); extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_uring_entry(u8 op) { /* * We intentionally check audit_context() before audit_enabled as most * Linux systems (as of ~2021) rely on systemd which forces audit to * be enabled regardless of the user's audit configuration. */ if (unlikely(audit_context() && audit_enabled)) __audit_uring_entry(op); } static inline void audit_uring_exit(int success, long code) { if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_openat2_how(struct open_how *how) { if (unlikely(!audit_dummy_context())) __audit_openat2_how(how); } static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { if (!audit_dummy_context()) __audit_fanotify(response, friar); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_uring_entry(u8 op) { } static inline void audit_uring_exit(int success, long code) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_openat2_how(struct open_how *how) { } static inline void audit_log_kern_module(char *name) { } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 | // SPDX-License-Identifier: GPL-2.0-only /* * VXLAN: Virtual eXtensible Local Area Network * * Copyright (c) 2012-2013 Vyatta Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/udp.h> #include <linux/igmp.h> #include <linux/if_ether.h> #include <linux/ethtool.h> #include <net/arp.h> #include <net/ndisc.h> #include <net/gro.h> #include <net/ipv6_stubs.h> #include <net/ip.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/tun_proto.h> #include <net/vxlan.h> #include <net/nexthop.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> #endif #include "vxlan_private.h" #define VXLAN_VERSION "0.1" #define FDB_AGE_DEFAULT 300 /* 5 min */ #define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */ /* UDP port for VXLAN traffic. * The IANA assigned port is 4789, but the Linux default is 8472 * for compatibility with early adopters. */ static unsigned short vxlan_port __read_mostly = 8472; module_param_named(udp_port, vxlan_port, ushort, 0444); MODULE_PARM_DESC(udp_port, "Destination UDP port"); static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); unsigned int vxlan_net_id; const u8 all_zeros_mac[ETH_ALEN + 2]; static struct rtnl_link_ops vxlan_link_ops; static int vxlan_sock_add(struct vxlan_dev *vxlan); static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); /* salt for hash table */ static u32 vxlan_salt __read_mostly; static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) { return vs->flags & VXLAN_F_COLLECT_METADATA || ip_tunnel_collect_metadata(); } /* Find VXLAN socket based on network namespace, address family, UDP port, * enabled unshareable flags and socket device binding (see l3mdev with * non-default VRF). */ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, __be16 port, u32 flags, int ifindex) { struct vxlan_sock *vs; flags &= VXLAN_F_RCV_FLAGS; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { if (inet_sk(vs->sock->sk)->inet_sport == port && vxlan_get_sk_family(vs) == family && vs->flags == flags && vs->sock->sk->sk_bound_dev_if == ifindex) return vs; } return NULL; } static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, int ifindex, __be32 vni, struct vxlan_vni_node **vninode) { struct vxlan_vni_node *vnode; struct vxlan_dev_node *node; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA && !(vs->flags & VXLAN_F_VNIFILTER)) vni = 0; hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) { if (!node->vxlan) continue; vnode = NULL; if (node->vxlan->cfg.flags & VXLAN_F_VNIFILTER) { vnode = vxlan_vnifilter_lookup(node->vxlan, vni); if (!vnode) continue; } else if (node->vxlan->default_dst.remote_vni != vni) { continue; } if (IS_ENABLED(CONFIG_IPV6)) { const struct vxlan_config *cfg = &node->vxlan->cfg; if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) && cfg->remote_ifindex != ifindex) continue; } if (vninode) *vninode = vnode; return node->vxlan; } return NULL; } /* Look up VNI in a per net namespace table */ static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex, __be32 vni, sa_family_t family, __be16 port, u32 flags) { struct vxlan_sock *vs; vs = vxlan_find_sock(net, family, port, flags, ifindex); if (!vs) return NULL; return vxlan_vs_find_vni(vs, ifindex, vni, NULL); } /* Fill in neighbour message in skbuff. */ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, u32 portid, u32 seq, int type, unsigned int flags, const struct vxlan_rdst *rdst) { unsigned long now = jiffies; struct nda_cacheinfo ci; bool send_ip, send_eth; struct nlmsghdr *nlh; struct nexthop *nh; struct ndmsg *ndm; int nh_family; u32 nh_id; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); memset(ndm, 0, sizeof(*ndm)); send_eth = send_ip = true; rcu_read_lock(); nh = rcu_dereference(fdb->nh); if (nh) { nh_family = nexthop_get_family(nh); nh_id = nh->id; } rcu_read_unlock(); if (type == RTM_GETNEIGH) { if (rdst) { send_ip = !vxlan_addr_any(&rdst->remote_ip); ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else if (nh) { ndm->ndm_family = nh_family; } send_eth = !is_zero_ether_addr(fdb->eth_addr); } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; ndm->ndm_ifindex = vxlan->dev->ifindex; ndm->ndm_flags = fdb->flags; if (rdst && rdst->offloaded) ndm->ndm_flags |= NTF_OFFLOADED; ndm->ndm_type = RTN_UNICAST; if (!net_eq(dev_net(vxlan->dev), vxlan->net) && nla_put_s32(skb, NDA_LINK_NETNSID, peernet2id(dev_net(vxlan->dev), vxlan->net))) goto nla_put_failure; if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr)) goto nla_put_failure; if (nh) { if (nla_put_u32(skb, NDA_NH_ID, nh_id)) goto nla_put_failure; } else if (rdst) { if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) goto nla_put_failure; if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port && nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) goto nla_put_failure; } if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && nla_put_u32(skb, NDA_SRC_VNI, be32_to_cpu(fdb->vni))) goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t vxlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */ + nla_total_size(sizeof(__be16)) /* NDA_PORT */ + nla_total_size(sizeof(__be32)) /* NDA_VNI */ + nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */ + nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */ + nla_total_size(sizeof(struct nda_cacheinfo)); } static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd); if (err < 0) { /* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, const struct vxlan_rdst *rd, struct netlink_ext_ack *extack, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { fdb_info->info.dev = vxlan->dev; fdb_info->info.extack = extack; fdb_info->remote_ip = rd->remote_ip; fdb_info->remote_port = rd->remote_port; fdb_info->remote_vni = rd->remote_vni; fdb_info->remote_ifindex = rd->remote_ifindex; memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN); fdb_info->vni = fdb->vni; fdb_info->offloaded = rd->offloaded; fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER; } static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, bool adding, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info info; enum switchdev_notifier_type notifier_type; int ret; if (WARN_ON(!rd)) return 0; notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); ret = call_switchdev_notifiers(notifier_type, vxlan->dev, &info.info, extack); return notifier_to_errno(ret); } static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type, bool swdev_notify, struct netlink_ext_ack *extack) { int err; if (swdev_notify && rd) { switch (type) { case RTM_NEWNEIGH: err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, true, extack); if (err) return err; break; case RTM_DELNEIGH: vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, false, extack); break; } } __vxlan_fdb_notify(vxlan, fdb, rd, type); return 0; } static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { .remote_ip = *ipa, /* goes to NDA_DST */ .remote_vni = cpu_to_be32(VXLAN_N_VID), }; vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) { struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { }; memcpy(f.eth_addr, eth_addr, ETH_ALEN); vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } /* Hash Ethernet address */ static u32 eth_hash(const unsigned char *addr) { u64 value = get_unaligned((u64 *)addr); /* only want 6 bytes */ #ifdef __BIG_ENDIAN value >>= 16; #else value <<= 16; #endif return hash_64(value, FDB_HASH_BITS); } u32 eth_vni_hash(const unsigned char *addr, __be32 vni) { /* use 1 byte of OUI and 3 bytes of NIC */ u32 key = get_unaligned((u32 *)(addr + 2)); return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1); } u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) return eth_vni_hash(mac, vni); else return eth_hash(mac); } /* Hash chain to use given mac address */ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)]; } /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni); struct vxlan_fdb *f; hlist_for_each_entry_rcu(f, head, hlist) { if (ether_addr_equal(mac, f->eth_addr)) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (vni == f->vni) return f; } else { return f; } } } return NULL; } static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, vni); if (f && f->used != jiffies) f->used = jiffies; return f; } /* caller should hold vxlan->hash_lock */ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex) { struct vxlan_rdst *rd; list_for_each_entry(rd, &f->remotes, list) { if (vxlan_addr_equal(&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex) return rd; } return NULL; } int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); u8 eth_addr[ETH_ALEN + 2] = { 0 }; struct vxlan_rdst *rdst; struct vxlan_fdb *f; int rc = 0; if (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)) return -EINVAL; ether_addr_copy(eth_addr, mac); rcu_read_lock(); f = __vxlan_find_mac(vxlan, eth_addr, vni); if (!f) { rc = -ENOENT; goto out; } rdst = first_remote_rcu(f); vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info); out: rcu_read_unlock(); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc); static int vxlan_fdb_notify_one(struct notifier_block *nb, const struct vxlan_dev *vxlan, const struct vxlan_fdb *f, const struct vxlan_rdst *rdst, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info fdb_info; int rc; vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info); rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, &fdb_info); return notifier_to_errno(rc); } int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; int rc = 0; if (!netif_is_vxlan(dev)) return -EINVAL; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) { if (f->vni == vni) { list_for_each_entry(rdst, &f->remotes, list) { rc = vxlan_fdb_notify_one(nb, vxlan, f, rdst, extack); if (rc) goto unlock; } } } spin_unlock_bh(&vxlan->hash_lock[h]); } return 0; unlock: spin_unlock_bh(&vxlan->hash_lock[h]); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_replay); void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; if (!netif_is_vxlan(dev)) return; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) if (f->vni == vni) list_for_each_entry(rdst, &f->remotes, list) rdst->offloaded = false; spin_unlock_bh(&vxlan->hash_lock[h]); } } EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload); /* Replace destination of unicast mac */ static int vxlan_fdb_replace(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst *oldrd) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); if (!rd) return 0; *oldrd = *rd; dst_cache_reset(&rd->dst_cache); rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; rd->offloaded = false; return 1; } /* Add/update destinations for multicast */ static int vxlan_fdb_append(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst **rdp) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOMEM; if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { kfree(rd); return -ENOMEM; } rd->remote_ip = *ip; rd->remote_port = port; rd->offloaded = false; rd->remote_vni = vni; rd->remote_ifindex = ifindex; list_add_tail_rcu(&rd->list, &f->remotes); *rdp = rd; return 1; } static bool vxlan_parse_gpe_proto(struct vxlanhdr *hdr, __be16 *protocol) { struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)hdr; /* Need to have Next Protocol set for interfaces in GPE mode. */ if (!gpe->np_applied) return false; /* "The initial version is 0. If a receiver does not support the * version indicated it MUST drop the packet. */ if (gpe->version != 0) return false; /* "When the O bit is set to 1, the packet is an OAM packet and OAM * processing MUST occur." However, we don't implement OAM * processing, thus drop the packet. */ if (gpe->oam_flag) return false; *protocol = tun_p_to_eth_p(gpe->next_protocol); if (!*protocol) return false; return true; } static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, __be32 vni_field, struct gro_remcsum *grc, bool nopartial) { size_t start, offset; if (skb->remcsum_offload) return vh; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; start = vxlan_rco_start(vni_field); offset = start + vxlan_rco_offset(vni_field); vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen, start, offset, grc, nopartial); skb->remcsum_offload = 1; return vh; } static struct vxlanhdr *vxlan_gro_prepare_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb, struct gro_remcsum *grc) { struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk); __be32 flags; skb_gro_remcsum_init(grc); off_vx = skb_gro_offset(skb); hlen = off_vx + sizeof(*vh); vh = skb_gro_header(skb, hlen, off_vx); if (unlikely(!vh)) return NULL; skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); flags = vh->vx_flags; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), vh->vx_vni, grc, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) return NULL; } skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; vh2 = (struct vxlanhdr *)(p->data + off_vx); if (vh->vx_flags != vh2->vx_flags || vh->vx_vni != vh2->vx_vni) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } return vh; } static struct sk_buff *vxlan_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct gro_remcsum grc; int flush = 1; if (vxlan_gro_prepare_receive(sk, head, skb, &grc)) { pp = call_gro_receive(eth_gro_receive, head, skb); flush = 0; } skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static struct sk_buff *vxlan_gpe_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; struct sk_buff *pp = NULL; struct gro_remcsum grc; struct vxlanhdr *vh; __be16 protocol; int flush = 1; vh = vxlan_gro_prepare_receive(sk, head, skb, &grc); if (vh) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto out; ptype = gro_find_receive_by_type(protocol); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; } out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { /* Sets 'skb->inner_mac_header' since we are always called with * 'skb->encapsulation' set. */ return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } static int vxlan_gpe_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct vxlanhdr *vh = (struct vxlanhdr *)(skb->data + nhoff); const struct packet_offload *ptype; int err = -ENOSYS; __be16 protocol; if (!vxlan_parse_gpe_proto(vh, &protocol)) return err; ptype = gro_find_complete_by_type(protocol); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); return err; } static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac, __u16 state, __be32 src_vni, __u16 ndm_flags) { struct vxlan_fdb *f; f = kmalloc(sizeof(*f), GFP_ATOMIC); if (!f) return NULL; f->state = state; f->flags = ndm_flags; f->updated = f->used = jiffies; f->vni = src_vni; f->nh = NULL; RCU_INIT_POINTER(f->vdev, vxlan); INIT_LIST_HEAD(&f->nh_list); INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); return f; } static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac, __be32 src_vni, struct vxlan_fdb *f) { ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, vxlan_fdb_head(vxlan, mac, src_vni)); } static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, u32 nhid, struct netlink_ext_ack *extack) { struct nexthop *old_nh = rtnl_dereference(fdb->nh); struct nexthop *nh; int err = -EINVAL; if (old_nh && old_nh->id == nhid) return 0; nh = nexthop_find_by_id(vxlan->net, nhid); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto err_inval; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); nh = NULL; goto err_inval; } if (!nexthop_is_fdb(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop"); goto err_inval; } if (!nexthop_is_multipath(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group"); goto err_inval; } /* check nexthop group family */ switch (vxlan->default_dst.remote_ip.sa.sa_family) { case AF_INET: if (!nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } break; case AF_INET6: if (nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } } if (old_nh) { list_del_rcu(&fdb->nh_list); nexthop_put(old_nh); } rcu_assign_pointer(fdb->nh, nh); list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list); return 1; err_inval: if (nh) nexthop_put(nh); return err; } int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, struct vxlan_fdb **fdb, struct netlink_ext_ack *extack) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int rc; if (vxlan->cfg.addrmax && vxlan->addrcnt >= vxlan->cfg.addrmax) return -ENOSPC; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); if (!f) return -ENOMEM; if (nhid) rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); else rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) goto errout; *fdb = f; return 0; errout: kfree(f); return rc; } static void __vxlan_fdb_free(struct vxlan_fdb *f) { struct vxlan_rdst *rd, *nd; struct nexthop *nh; nh = rcu_dereference_raw(f->nh); if (nh) { rcu_assign_pointer(f->nh, NULL); rcu_assign_pointer(f->vdev, NULL); nexthop_put(nh); } list_for_each_entry_safe(rd, nd, &f->remotes, list) { dst_cache_destroy(&rd->dst_cache); kfree(rd); } kfree(f); } static void vxlan_fdb_free(struct rcu_head *head) { struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); __vxlan_fdb_free(f); } static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, bool do_notify, bool swdev_notify) { struct vxlan_rdst *rd; netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; if (do_notify) { if (rcu_access_pointer(f->nh)) vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH, swdev_notify, NULL); else list_for_each_entry(rd, &f->remotes, list) vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); } hlist_del_rcu(&f->hlist); list_del_rcu(&f->nh_list); call_rcu(&f->rcu, vxlan_fdb_free); } static void vxlan_dst_free(struct rcu_head *head) { struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); dst_cache_destroy(&rd->dst_cache); kfree(rd); } static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 vni, __u32 ifindex, __u16 ndm_flags, struct vxlan_fdb *f, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_rdst *rd = NULL; struct vxlan_rdst oldrd; int notify = 0; int rc = 0; int err; if (nhid && !rcu_access_pointer(f->nh)) { NL_SET_ERR_MSG(extack, "Cannot replace an existing non nexthop fdb with a nexthop"); return -EOPNOTSUPP; } if (nhid && (flags & NLM_F_APPEND)) { NL_SET_ERR_MSG(extack, "Cannot append to a nexthop fdb"); return -EOPNOTSUPP; } /* Do not allow an externally learned entry to take over an entry added * by the user. */ if (!(fdb_flags & NTF_EXT_LEARNED) || !(f->flags & NTF_VXLAN_ADDED_BY_USER)) { if (f->state != state) { f->state = state; f->updated = jiffies; notify = 1; } if (f->flags != fdb_flags) { f->flags = fdb_flags; f->updated = jiffies; notify = 1; } } if ((flags & NLM_F_REPLACE)) { /* Only change unicasts */ if (!(is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { if (nhid) { rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); if (rc < 0) return rc; } else { rc = vxlan_fdb_replace(f, ip, port, vni, ifindex, &oldrd); } notify |= rc; } else { NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries"); return -EOPNOTSUPP; } } if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; notify |= rc; } if (ndm_flags & NTF_USE) f->used = jiffies; if (notify) { if (rd == NULL) rd = first_remote_rtnl(f); err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, swdev_notify, extack); if (err) goto err_notify; } return 0; err_notify: if (nhid) return err; if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; else if ((flags & NLM_F_APPEND) && rc) { list_del_rcu(&rd->list); call_rcu(&rd->rcu, vxlan_dst_free); } return err; } static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_fdb *f; int rc; /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, vni, ifindex, fdb_flags, nhid, &f, extack); if (rc < 0) return rc; vxlan_fdb_insert(vxlan, mac, src_vni, f); rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, swdev_notify, extack); if (rc) goto err_notify; return 0; err_notify: vxlan_fdb_destroy(vxlan, f, false, false); return rc; } /* Add new entry to forwarding table -- assumes lock held */ int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, src_vni); if (f) { if (flags & NLM_F_EXCL) { netdev_dbg(vxlan->dev, "lost race to create %pM\n", mac); return -EEXIST; } return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, vni, ifindex, ndm_flags, f, nhid, swdev_notify, extack); } else { if (!(flags & NLM_F_CREATE)) return -ENOENT; return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, port, src_vni, vni, ifindex, ndm_flags, nhid, swdev_notify, extack); } } static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { list_del_rcu(&rd->list); vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); call_rcu(&rd->rcu, vxlan_dst_free); } static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, union vxlan_addr *ip, __be16 *port, __be32 *src_vni, __be32 *vni, u32 *ifindex, u32 *nhid, struct netlink_ext_ack *extack) { struct net *net = dev_net(vxlan->dev); int err; if (tb[NDA_NH_ID] && (tb[NDA_DST] || tb[NDA_VNI] || tb[NDA_IFINDEX] || tb[NDA_PORT])) { NL_SET_ERR_MSG(extack, "DST, VNI, ifindex and port are mutually exclusive with NH_ID"); return -EINVAL; } if (tb[NDA_DST]) { err = vxlan_nla_get_addr(ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG(extack, "Unsupported address family"); return err; } } else { union vxlan_addr *remote = &vxlan->default_dst.remote_ip; if (remote->sa.sa_family == AF_INET) { ip->sin.sin_addr.s_addr = htonl(INADDR_ANY); ip->sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { ip->sin6.sin6_addr = in6addr_any; ip->sa.sa_family = AF_INET6; #endif } } if (tb[NDA_PORT]) { if (nla_len(tb[NDA_PORT]) != sizeof(__be16)) { NL_SET_ERR_MSG(extack, "Invalid vxlan port"); return -EINVAL; } *port = nla_get_be16(tb[NDA_PORT]); } else { *port = vxlan->cfg.dst_port; } if (tb[NDA_VNI]) { if (nla_len(tb[NDA_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid vni"); return -EINVAL; } *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); } else { *vni = vxlan->default_dst.remote_vni; } if (tb[NDA_SRC_VNI]) { if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid src vni"); return -EINVAL; } *src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); } else { *src_vni = vxlan->default_dst.remote_vni; } if (tb[NDA_IFINDEX]) { struct net_device *tdev; if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid ifindex"); return -EINVAL; } *ifindex = nla_get_u32(tb[NDA_IFINDEX]); tdev = __dev_get_by_index(net, *ifindex); if (!tdev) { NL_SET_ERR_MSG(extack, "Device not found"); return -EADDRNOTAVAIL; } } else { *ifindex = 0; } *nhid = nla_get_u32_default(tb[NDA_NH_ID], 0); return 0; } /* Add static entry (via netlink) */ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); /* struct net *net = dev_net(vxlan->dev); */ union vxlan_addr ip; __be16 port; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; int err; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { pr_info("RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID])) return -EINVAL; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, nhid, true, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } int __vxlan_fdb_delete(struct vxlan_dev *vxlan, const unsigned char *addr, union vxlan_addr ip, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int err = -ENOENT; f = vxlan_find_mac(vxlan, addr, src_vni); if (!f) return err; if (!vxlan_addr_any(&ip)) { rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); if (!rd) goto out; } /* remove a destination if it's not the only one on the list, * otherwise destroy the fdb entry */ if (rd && !list_is_singular(&f->remotes)) { vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify); goto out; } vxlan_fdb_destroy(vxlan, f, true, swdev_notify); out: return 0; } /* Delete entry (via netlink) */ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); union vxlan_addr ip; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; __be16 port; int err; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } /* Dump forwarding table */ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; int err = 0; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; if (rcu_access_pointer(f->nh)) { if (*idx < cb->args[2]) goto skip_nh; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); if (err < 0) { rcu_read_unlock(); goto out; } skip_nh: *idx += 1; continue; } list_for_each_entry_rcu(rd, &f->remotes, list) { if (*idx < cb->args[2]) goto skip; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); if (err < 0) { rcu_read_unlock(); goto out; } skip: *idx += 1; } } rcu_read_unlock(); } out: return err; } static int vxlan_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; __be32 vni; int err; if (tb[NDA_VNI]) vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); else vni = vxlan->default_dst.remote_vni; rcu_read_lock(); f = __vxlan_find_mac(vxlan, addr, vni); if (!f) { NL_SET_ERR_MSG(extack, "Fdb entry not found"); err = -ENOENT; goto errout; } err = vxlan_fdb_info(skb, vxlan, f, portid, seq, RTM_NEWNEIGH, 0, first_remote_rcu(f)); errout: rcu_read_unlock(); return err; } /* Watch incoming packets to learn mapping between Ethernet address * and Tunnel endpoint. */ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, union vxlan_addr *src_ip, const u8 *src_mac, u32 src_ifindex, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 ifindex = 0; /* Ignore packets from invalid src-address */ if (!is_valid_ether_addr(src_mac)) return SKB_DROP_REASON_MAC_INVALID_SOURCE; #if IS_ENABLED(CONFIG_IPV6) if (src_ip->sa.sa_family == AF_INET6 && (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) ifindex = src_ifindex; #endif f = vxlan_find_mac(vxlan, src_mac, vni); if (likely(f)) { struct vxlan_rdst *rdst = first_remote_rcu(f); if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) && rdst->remote_ifindex == ifindex)) return SKB_NOT_DROPPED_YET; /* Don't migrate static entries, drop packets */ if (f->state & (NUD_PERMANENT | NUD_NOARP)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; /* Don't override an fdb with nexthop with a learnt entry */ if (rcu_access_pointer(f->nh)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pIS to %pIS\n", src_mac, &rdst->remote_ip.sa, &src_ip->sa); rdst->remote_ip = *src_ip; f->updated = jiffies; vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { u32 hash_index = fdb_head_index(vxlan, src_mac, vni); /* learned new entry */ spin_lock(&vxlan->hash_lock[hash_index]); /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, vni, vxlan->default_dst.remote_vni, ifindex, NTF_SELF, 0, true, NULL); spin_unlock(&vxlan->hash_lock[hash_index]); } return SKB_NOT_DROPPED_YET; } static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) { struct vxlan_net *vn; if (!vs) return false; if (!refcount_dec_and_test(&vs->refcnt)) return false; vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_rcu(&vs->hlist); udp_tunnel_notify_del_rx_port(vs->sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); return true; } static void vxlan_sock_release(struct vxlan_dev *vxlan) { struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); RCU_INIT_POINTER(vxlan->vn6_sock, NULL); #endif RCU_INIT_POINTER(vxlan->vn4_sock, NULL); synchronize_net(); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vs_del_vnigrp(vxlan); else vxlan_vs_del_dev(vxlan); if (__vxlan_sock_release_prep(sock4)) { udp_tunnel_sock_release(sock4->sock); kfree(sock4); } #if IS_ENABLED(CONFIG_IPV6) if (__vxlan_sock_release_prep(sock6)) { udp_tunnel_sock_release(sock6->sock); kfree(sock6); } #endif } static enum skb_drop_reason vxlan_remcsum(struct vxlanhdr *unparsed, struct sk_buff *skb, u32 vxflags) { enum skb_drop_reason reason; size_t start, offset; if (!(unparsed->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) goto out; start = vxlan_rco_start(unparsed->vx_vni); offset = start + vxlan_rco_offset(unparsed->vx_vni); reason = pskb_may_pull_reason(skb, offset + sizeof(u16)); if (reason) return reason; skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset, !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL)); out: unparsed->vx_flags &= ~VXLAN_HF_RCO; unparsed->vx_vni &= VXLAN_VNI_MASK; return SKB_NOT_DROPPED_YET; } static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, struct sk_buff *skb, u32 vxflags, struct vxlan_metadata *md) { struct vxlanhdr_gbp *gbp = (struct vxlanhdr_gbp *)unparsed; struct metadata_dst *tun_dst; if (!(unparsed->vx_flags & VXLAN_HF_GBP)) goto out; md->gbp = ntohs(gbp->policy_id); tun_dst = (struct metadata_dst *)skb_dst(skb); if (tun_dst) { __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_dst->u.tun_info.key.tun_flags); tun_dst->u.tun_info.options_len = sizeof(*md); } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; if (gbp->policy_applied) md->gbp |= VXLAN_GBP_POLICY_APPLIED; /* In flow-based mode, GBP is carried in dst_metadata */ if (!(vxflags & VXLAN_F_COLLECT_METADATA)) skb->mark = md->gbp; out: unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS; } static enum skb_drop_reason vxlan_set_mac(struct vxlan_dev *vxlan, struct vxlan_sock *vs, struct sk_buff *skb, __be32 vni) { union vxlan_addr saddr; u32 ifindex = skb->dev->ifindex; skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, vxlan->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) return SKB_DROP_REASON_LOCAL_MAC; /* Get address from the outer IP header */ if (vxlan_get_sk_family(vs) == AF_INET) { saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET6; #endif } if (!(vxlan->cfg.flags & VXLAN_F_LEARN)) return SKB_NOT_DROPPED_YET; return vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, ifindex, vni); } static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph, struct sk_buff *skb) { int err = 0; if (vxlan_get_sk_family(vs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err) && log_ecn_error) { if (vxlan_get_sk_family(vs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } return err <= 1; } /* Callback from net/ipv4/udp.c to receive packets */ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) { struct vxlan_vni_node *vninode = NULL; struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlanhdr unparsed; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 protocol = htons(ETH_P_TEB); enum skb_drop_reason reason; bool raw_proto = false; void *oiph; __be32 vni = 0; int nh; /* Need UDP and VXLAN header to be present */ reason = pskb_may_pull_reason(skb, VXLAN_HLEN); if (reason) goto drop; unparsed = *vxlan_hdr(skb); /* VNI flag always required to be set */ if (!(unparsed.vx_flags & VXLAN_HF_VNI)) { netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", ntohl(vxlan_hdr(skb)->vx_flags), ntohl(vxlan_hdr(skb)->vx_vni)); reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; /* Return non vxlan pkt */ goto drop; } unparsed.vx_flags &= ~VXLAN_HF_VNI; unparsed.vx_vni &= ~VXLAN_VNI_MASK; vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; vni = vxlan_vni(vxlan_hdr(skb)->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, &vninode); if (!vxlan) { reason = SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND; goto drop; } /* For backwards compatibility, only allow reserved fields to be * used by VXLAN extensions if explicitly requested. */ if (vs->flags & VXLAN_F_GPE) { if (!vxlan_parse_gpe_proto(&unparsed, &protocol)) goto drop; unparsed.vx_flags &= ~VXLAN_GPE_USED_BITS; raw_proto = true; } if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto, !net_eq(vxlan->net, dev_net(vxlan->dev)))) { reason = SKB_DROP_REASON_NOMEM; goto drop; } if (vs->flags & VXLAN_F_REMCSUM_RX) { reason = vxlan_remcsum(&unparsed, skb, vs->flags); if (unlikely(reason)) goto drop; } if (vxlan_collect_metadata(vs)) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst; __set_bit(IP_TUNNEL_KEY_BIT, flags); tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), flags, key32_to_tunnel_id(vni), sizeof(*md)); if (!tun_dst) { reason = SKB_DROP_REASON_NOMEM; goto drop; } md = ip_tunnel_info_opts(&tun_dst->u.tun_info); skb_dst_set(skb, (struct dst_entry *)tun_dst); } else { memset(md, 0, sizeof(*md)); } if (vs->flags & VXLAN_F_GBP) vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md); /* Note that GBP and GPE can never be active together. This is * ensured in vxlan_dev_configure. */ if (unparsed.vx_flags || unparsed.vx_vni) { /* If there are any unprocessed flags remaining treat * this as a malformed packet. This behavior diverges from * VXLAN RFC (RFC7348) which stipulates that bits in reserved * in reserved fields are to be ignored. The approach here * maintains compatibility with previous stack code, and also * is more robust and provides a little more security in * adding extensions to VXLAN. */ reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; goto drop; } if (!raw_proto) { reason = vxlan_set_mac(vxlan, vs, skb, vni); if (reason) goto drop; } else { skb_reset_mac_header(skb); skb->dev = vxlan->dev; skb->pkt_type = PACKET_HOST; } /* 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_reset_network_header(skb); reason = pskb_inet_may_pull_reason(skb); if (reason) { DEV_STATS_INC(vxlan->dev, rx_length_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { reason = SKB_DROP_REASON_IP_TUNNEL_ECN; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } rcu_read_lock(); if (unlikely(!(vxlan->dev->flags & IFF_UP))) { rcu_read_unlock(); dev_core_stats_rx_dropped_inc(vxlan->dev); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_DROPS, 0); reason = SKB_DROP_REASON_DEV_READY; goto drop; } dev_sw_netstats_rx_add(vxlan->dev, skb->len); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX, skb->len); gro_cells_receive(&vxlan->gro_cells, skb); rcu_read_unlock(); return 0; drop: reason = reason ?: SKB_DROP_REASON_NOT_SPECIFIED; /* Consume bad packet */ kfree_skb_reason(skb, reason); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a VNI for errors */ static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb) { struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlanhdr *hdr; __be32 vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN)) return -EINVAL; hdr = vxlan_hdr(skb); if (!(hdr->vx_flags & VXLAN_HF_VNI)) return -EINVAL; vs = rcu_dereference_sk_user_data(sk); if (!vs) return -ENOENT; vni = vxlan_vni(hdr->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, NULL); if (!vxlan) return -ENOENT; return 0; } static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct arphdr *parp; u8 *arpptr, *sha; __be32 sip, tip; struct neighbour *n; if (dev->flags & IFF_NOARP) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); goto out; } parp = arp_hdr(skb); if ((parp->ar_hrd != htons(ARPHRD_ETHER) && parp->ar_hrd != htons(ARPHRD_IEEE802)) || parp->ar_pro != htons(ETH_P_IP) || parp->ar_op != htons(ARPOP_REQUEST) || parp->ar_hln != dev->addr_len || parp->ar_pln != 4) goto out; arpptr = (u8 *)parp + sizeof(struct arphdr); sha = arpptr; arpptr += dev->addr_len; /* sha */ memcpy(&sip, arpptr, sizeof(sip)); arpptr += sizeof(sip); arpptr += dev->addr_len; /* tha */ memcpy(&tip, arpptr, sizeof(tip)); if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) goto out; n = neigh_lookup(&arp_tbl, &tip, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, n->ha, sha); neigh_release(n); if (reply == NULL) goto out; skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); } out: consume_skb(skb); return NETDEV_TX_OK; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *vxlan_na_create(struct sk_buff *request, struct neighbour *n, bool isrouter) { struct net_device *dev = request->dev; struct sk_buff *reply; struct nd_msg *ns, *na; struct ipv6hdr *pip6; u8 *daddr; int na_olen = 8; /* opt hdr + ETH_ALEN for target */ int ns_olen; int i, len; if (dev == NULL || !pskb_may_pull(request, request->len)) return NULL; len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + sizeof(*na) + na_olen + dev->needed_tailroom; reply = alloc_skb(len, GFP_ATOMIC); if (reply == NULL) return NULL; reply->protocol = htons(ETH_P_IPV6); reply->dev = dev; skb_reserve(reply, LL_RESERVED_SPACE(request->dev)); skb_push(reply, sizeof(struct ethhdr)); skb_reset_mac_header(reply); ns = (struct nd_msg *)(ipv6_hdr(request) + 1); daddr = eth_hdr(request)->h_source; ns_olen = request->len - skb_network_offset(request) - sizeof(struct ipv6hdr) - sizeof(*ns); for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { if (!ns->opt[i + 1]) { kfree_skb(reply); return NULL; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } /* Ethernet header */ ether_addr_copy(eth_hdr(reply)->h_dest, daddr); ether_addr_copy(eth_hdr(reply)->h_source, n->ha); eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); reply->protocol = htons(ETH_P_IPV6); skb_pull(reply, sizeof(struct ethhdr)); skb_reset_network_header(reply); skb_put(reply, sizeof(struct ipv6hdr)); /* IPv6 header */ pip6 = ipv6_hdr(reply); memset(pip6, 0, sizeof(struct ipv6hdr)); pip6->version = 6; pip6->priority = ipv6_hdr(request)->priority; pip6->nexthdr = IPPROTO_ICMPV6; pip6->hop_limit = 255; pip6->daddr = ipv6_hdr(request)->saddr; pip6->saddr = *(struct in6_addr *)n->primary_key; skb_pull(reply, sizeof(struct ipv6hdr)); skb_reset_transport_header(reply); /* Neighbor Advertisement */ na = skb_put_zero(reply, sizeof(*na) + na_olen); na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; na->icmph.icmp6_router = isrouter; na->icmph.icmp6_override = 1; na->icmph.icmp6_solicited = 1; na->target = ns->target; ether_addr_copy(&na->opt[2], n->ha); na->opt[0] = ND_OPT_TARGET_LL_ADDR; na->opt[1] = na_olen >> 3; na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6, csum_partial(na, sizeof(*na)+na_olen, 0)); pip6->payload_len = htons(sizeof(*na)+na_olen); skb_push(reply, sizeof(struct ipv6hdr)); reply->ip_summed = CHECKSUM_UNNECESSARY; return reply; } static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); const struct in6_addr *daddr; const struct ipv6hdr *iphdr; struct inet6_dev *in6_dev; struct neighbour *n; struct nd_msg *msg; rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) goto out; iphdr = ipv6_hdr(skb); daddr = &iphdr->daddr; msg = (struct nd_msg *)(iphdr + 1); if (ipv6_addr_loopback(daddr) || ipv6_addr_is_multicast(&msg->target)) goto out; n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = vxlan_na_create(skb, n, !!(f ? f->flags & NTF_ROUTER : 0)); neigh_release(n); if (reply == NULL) goto out; if (netif_rx(reply) == NET_RX_DROP) { dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); } out: rcu_read_unlock(); consume_skb(skb); return NETDEV_TX_OK; } #endif static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct neighbour *n; if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) return false; n = NULL; switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: { struct iphdr *pip; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: { struct ipv6hdr *pip6; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #endif default: return false; } if (n) { bool diff; diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha); if (diff) { memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, dev->addr_len); memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len); } neigh_release(n); return diff; } return false; } static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol) { struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh; gpe->np_applied = 1; gpe->next_protocol = tun_p_from_eth_p(protocol); if (!gpe->next_protocol) return -EPFNOSUPPORT; return 0; } static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, int iphdr_len, __be32 vni, struct vxlan_metadata *md, u32 vxflags, bool udp_sum) { struct vxlanhdr *vxh; int min_headroom; int err; int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 inner_protocol = htons(ETH_P_TEB); if ((vxflags & VXLAN_F_REMCSUM_TX) && skb->ip_summed == CHECKSUM_PARTIAL) { int csum_start = skb_checksum_start_offset(skb); if (csum_start <= VXLAN_MAX_REMCSUM_START && !(csum_start & VXLAN_RCO_SHIFT_MASK) && (skb->csum_offset == offsetof(struct udphdr, check) || skb->csum_offset == offsetof(struct tcphdr, check))) type |= SKB_GSO_TUNNEL_REMCSUM; } min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + VXLAN_HLEN + iphdr_len; /* Need space for new headers (invalidates iph ptr) */ err = skb_cow_head(skb, min_headroom); if (unlikely(err)) return err; err = iptunnel_handle_offloads(skb, type); if (err) return err; vxh = __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(vni); if (type & SKB_GSO_TUNNEL_REMCSUM) { unsigned int start; start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr); vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset); vxh->vx_flags |= VXLAN_HF_RCO; if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; skb->encapsulation = 0; } } if (vxflags & VXLAN_F_GBP) vxlan_build_gbp_hdr(vxh, md); if (vxflags & VXLAN_F_GPE) { err = vxlan_build_gpe_hdr(vxh, skb->protocol); if (err < 0) return err; inner_protocol = skb->protocol; } skb_set_inner_protocol(skb, inner_protocol); return 0; } /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, bool snoop) { union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; struct net_device *dev; int len = skb->len; skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; __skb_pull(skb, skb_network_offset(skb)); if (remote_ip->sa.sa_family == AF_INET) { loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK); loopback.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { loopback.sin6.sin6_addr = in6addr_loopback; loopback.sa.sa_family = AF_INET6; #endif } rcu_read_lock(); dev = skb->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY); goto drop; } if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); dev_sw_netstats_tx_add(src_vxlan->dev, 1, len); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { dev_sw_netstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { drop: dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *vxlan, int addr_family, __be16 dst_port, int dst_ifindex, __be32 vni, struct dst_entry *dst, u32 rt_flags) { #if IS_ENABLED(CONFIG_IPV6) /* IPv6 rt-flags are checked against RTF_LOCAL, but the value of * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry. */ BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL); #endif /* Bypass encapsulation if the destination is local */ if (rt_flags & RTCF_LOCAL && !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && vxlan->cfg.flags & VXLAN_F_LOCALBYPASS) { struct vxlan_dev *dst_vxlan; dst_release(dst); dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni, addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND); return -ENOENT; } vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni, true); return 1; } return 0; } void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc) { struct dst_cache *dst_cache; struct ip_tunnel_info *info; struct ip_tunnel_key *pkey; struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; struct dst_entry *ndst = NULL; int addr_family; __u8 tos, ttl; int ifindex; int err; u32 flags = vxlan->cfg.flags; bool use_cache; bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); enum skb_drop_reason reason; bool no_eth_encap; __be32 vni = 0; no_eth_encap = flags & VXLAN_F_GPE && skb->protocol != htons(ETH_P_TEB); reason = skb_vlan_inet_prepare(skb, no_eth_encap); if (reason) goto drop; reason = SKB_DROP_REASON_NOT_SPECIFIED; old_iph = ip_hdr(skb); info = skb_tunnel_info(skb); use_cache = ip_tunnel_dst_cache_usable(skb, info); if (rdst) { memset(&key, 0, sizeof(key)); pkey = &key; if (vxlan_addr_any(&rdst->remote_ip)) { if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan, default_vni, true); return; } goto drop; } addr_family = vxlan->cfg.saddr.sa.sa_family; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = (rdst->remote_vni) ? : default_vni; ifindex = rdst->remote_ifindex; if (addr_family == AF_INET) { key.u.ipv4.src = vxlan->cfg.saddr.sin.sin_addr.s_addr; key.u.ipv4.dst = rdst->remote_ip.sin.sin_addr.s_addr; } else { key.u.ipv6.src = vxlan->cfg.saddr.sin6.sin6_addr; key.u.ipv6.dst = rdst->remote_ip.sin6.sin6_addr; } dst_cache = &rdst->dst_cache; md->gbp = skb->mark; if (flags & VXLAN_F_TTL_INHERIT) { ttl = ip_tunnel_get_ttl(old_iph, skb); } else { ttl = vxlan->cfg.ttl; if (!ttl && vxlan_addr_multicast(&rdst->remote_ip)) ttl = 1; } tos = vxlan->cfg.tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); if (tos && !info) use_cache = false; if (addr_family == AF_INET) udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); else udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); #if IS_ENABLED(CONFIG_IPV6) switch (vxlan->cfg.label_policy) { case VXLAN_LABEL_FIXED: key.label = vxlan->cfg.label; break; case VXLAN_LABEL_INHERIT: key.label = ip_tunnel_get_flowlabel(old_iph, skb); break; default: DEBUG_NET_WARN_ON_ONCE(1); goto drop; } #endif } else { if (!info) { WARN_ONCE(1, "%s: Missing encapsulation instructions\n", dev->name); goto drop; } pkey = &info->key; addr_family = ip_tunnel_info_af(info); dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } ttl = info->key.ttl; tos = info->key.tos; udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); rcu_read_lock(); if (addr_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; __be16 df = 0; __be32 saddr; if (!ifindex) ifindex = sock4->sock->sk->sk_bound_dev_if; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(rt)) { err = PTR_ERR(rt); reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { /* Bypass encapsulation if the destination is local */ err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, dst_port, ifindex, vni, &rt->dst, rt->rt_flags); if (err) goto out_unlock; if (vxlan->cfg.df == VXLAN_DF_SET) { df = htons(IP_DF); } else if (vxlan->cfg.df == VXLAN_DF_INHERIT) { struct ethhdr *eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6 || (ntohs(eth->h_proto) == ETH_P_IP && old_iph->frag_off & htons(IP_DF))) df = htons(IP_DF); } } else if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) { df = htons(IP_DF); } ndst = &rt->dst; err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom(flags & VXLAN_F_GPE), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv4.src = pkey->u.ipv4.dst; unclone->key.u.ipv4.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr, pkey->u.ipv4.dst, tos, ttl, df, src_port, dst_port, xnet, !udp_sum); #if IS_ENABLED(CONFIG_IPV6) } else { struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct in6_addr saddr; if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); ndst = NULL; reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags; err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6, dst_port, ifindex, vni, ndst, rt6i_flags); if (err) goto out_unlock; } err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom((flags & VXLAN_F_GPE) | VXLAN_F_IPV6), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv6.src = pkey->u.ipv6.dst; unclone->key.u.ipv6.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, &saddr, &pkey->u.ipv6.dst, tos, ttl, pkey->label, src_port, dst_port, !udp_sum); #endif } vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); out_unlock: rcu_read_unlock(); return; drop: dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, reason); return; tx_error: rcu_read_unlock(); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); dst_release(ndst); DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, reason); } static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, struct vxlan_fdb *f, __be32 vni, bool did_rsc) { struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = rcu_dereference(f->nh); if (!nh) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc); else goto drop; return; drop: dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); } static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, u32 nhid, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = nexthop_find_by_id(dev_net(dev), nhid); if (unlikely(!nh || !nexthop_is_fdb(nh) || !nexthop_is_multipath(nh))) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (vxlan->cfg.saddr.sa.sa_family != nh_rdst.remote_ip.sa.sa_family) goto drop; if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, false); else goto drop; return NETDEV_TX_OK; drop: dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); return NETDEV_TX_OK; } /* Transmit local packets over Vxlan * * Outer IP header inherits ECN and DF from inner header. * Outer UDP destination is the VXLAN assigned port. * source port is based on hash of flow */ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; u32 nhid = 0; bool did_rsc; info = skb_tunnel_info(skb); skb_reset_mac_header(skb); if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && info->mode & IP_TUNNEL_INFO_TX) { vni = tunnel_id_to_key32(info->key.tun_id); nhid = info->key.nhid; } else { if (info && info->mode & IP_TUNNEL_INFO_TX) vxlan_xmit_one(skb, dev, vni, NULL, false); else kfree_skb_reason(skb, SKB_DROP_REASON_TUNNEL_TXINFO); return NETDEV_TX_OK; } } if (vxlan->cfg.flags & VXLAN_F_PROXY) { eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); if (m->icmph.icmp6_code == 0 && m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb, vni); } #endif } if (nhid) return vxlan_xmit_nhid(skb, dev, nhid, vni); if (vxlan->cfg.flags & VXLAN_F_MDB) { struct vxlan_mdb_entry *mdb_entry; rcu_read_lock(); mdb_entry = vxlan_mdb_entry_skb_get(vxlan, skb, vni); if (mdb_entry) { netdev_tx_t ret; ret = vxlan_mdb_xmit(vxlan, mdb_entry, skb); rcu_read_unlock(); return ret; } rcu_read_unlock(); } eth = eth_hdr(skb); f = vxlan_find_mac(vxlan, eth->h_dest, vni); did_rsc = false; if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) && (ntohs(eth->h_proto) == ETH_P_IP || ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); if (did_rsc) f = vxlan_find_mac(vxlan, eth->h_dest, vni); } if (f == NULL) { f = vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f == NULL) { if ((vxlan->cfg.flags & VXLAN_F_L2MISS) && !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); return NETDEV_TX_OK; } } if (rcu_access_pointer(f->nh)) { vxlan_xmit_nh(skb, dev, f, (vni ? : vxlan->default_dst.remote_vni), did_rsc); } else { list_for_each_entry_rcu(rdst, &f->remotes, list) { struct sk_buff *skb1; if (!fdst) { fdst = rdst; continue; } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); } if (fdst) vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); else kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); } return NETDEV_TX_OK; } /* Walk the forwarding table and purge stale entries */ static void vxlan_cleanup(struct timer_list *t) { struct vxlan_dev *vxlan = from_timer(vxlan, t, age_timer); unsigned long next_timer = jiffies + FDB_AGE_INTERVAL; unsigned int h; if (!netif_running(vxlan->dev)) return; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); unsigned long timeout; if (f->state & (NUD_PERMANENT | NUD_NOARP)) continue; if (f->flags & NTF_EXT_LEARNED) continue; timeout = f->used + vxlan->cfg.age_interval * HZ; if (time_before_eq(timeout, jiffies)) { netdev_dbg(vxlan->dev, "garbage collect %pM\n", f->eth_addr); f->state = NUD_STALE; vxlan_fdb_destroy(vxlan, f, true, true); } else if (time_before(timeout, next_timer)) next_timer = timeout; } spin_unlock(&vxlan->hash_lock[h]); } mod_timer(&vxlan->age_timer, next_timer); } static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_init_rcu(&vxlan->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&vxlan->hlist6.hlist); #endif spin_unlock(&vn->sock_lock); } static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, struct vxlan_dev_node *node) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __be32 vni = vxlan->default_dst.remote_vni; node->vxlan = vxlan; spin_lock(&vn->sock_lock); hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); spin_unlock(&vn->sock_lock); } /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int err; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_init(vxlan); err = gro_cells_init(&vxlan->gro_cells, dev); if (err) goto err_vnigroup_uninit; err = vxlan_mdb_init(vxlan); if (err) goto err_gro_cells_destroy; netdev_lockdep_set_classes(dev); return 0; err_gro_cells_destroy: gro_cells_destroy(&vxlan->gro_cells); err_vnigroup_uninit: if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); return err; } static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) { struct vxlan_fdb *f; u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) vxlan_fdb_destroy(vxlan, f, true, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); vxlan_mdb_fini(vxlan); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); gro_cells_destroy(&vxlan->gro_cells); vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); } /* Start ageing timer and join group when device is brought up */ static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int ret; ret = vxlan_sock_add(vxlan); if (ret < 0) return ret; ret = vxlan_multicast_join(vxlan); if (ret) { vxlan_sock_release(vxlan); return ret; } if (vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); return ret; } struct vxlan_fdb_flush_desc { bool ignore_default_entry; unsigned long state; unsigned long state_mask; unsigned long flags; unsigned long flags_mask; __be32 src_vni; u32 nhid; __be32 vni; __be16 port; union vxlan_addr dst_ip; }; static bool vxlan_fdb_is_default_entry(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan) { return is_zero_ether_addr(f->eth_addr) && f->vni == vxlan->cfg.vni; } static bool vxlan_fdb_nhid_matches(const struct vxlan_fdb *f, u32 nhid) { struct nexthop *nh = rtnl_dereference(f->nh); return nh && nh->id == nhid; } static bool vxlan_fdb_flush_matches(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { if (desc->state_mask && (f->state & desc->state_mask) != desc->state) return false; if (desc->flags_mask && (f->flags & desc->flags_mask) != desc->flags) return false; if (desc->ignore_default_entry && vxlan_fdb_is_default_entry(f, vxlan)) return false; if (desc->src_vni && f->vni != desc->src_vni) return false; if (desc->nhid && !vxlan_fdb_nhid_matches(f, desc->nhid)) return false; return true; } static bool vxlan_fdb_flush_should_match_remotes(const struct vxlan_fdb_flush_desc *desc) { return desc->vni || desc->port || desc->dst_ip.sa.sa_family; } static bool vxlan_fdb_flush_remote_matches(const struct vxlan_fdb_flush_desc *desc, const struct vxlan_rdst *rd) { if (desc->vni && rd->remote_vni != desc->vni) return false; if (desc->port && rd->remote_port != desc->port) return false; if (desc->dst_ip.sa.sa_family && !vxlan_addr_equal(&rd->remote_ip, &desc->dst_ip)) return false; return true; } static void vxlan_fdb_flush_match_remotes(struct vxlan_fdb *f, struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc, bool *p_destroy_fdb) { bool remotes_flushed = false; struct vxlan_rdst *rd, *tmp; list_for_each_entry_safe(rd, tmp, &f->remotes, list) { if (!vxlan_fdb_flush_remote_matches(desc, rd)) continue; vxlan_fdb_dst_destroy(vxlan, f, rd, true); remotes_flushed = true; } *p_destroy_fdb = remotes_flushed && list_empty(&f->remotes); } /* Purge the forwarding table */ static void vxlan_flush(struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { bool match_remotes = vxlan_fdb_flush_should_match_remotes(desc); unsigned int h; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); if (!vxlan_fdb_flush_matches(f, vxlan, desc)) continue; if (match_remotes) { bool destroy_fdb = false; vxlan_fdb_flush_match_remotes(f, vxlan, desc, &destroy_fdb); if (!destroy_fdb) continue; } vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock_bh(&vxlan->hash_lock[h]); } } static const struct nla_policy vxlan_del_bulk_policy[NDA_MAX + 1] = { [NDA_SRC_VNI] = { .type = NLA_U32 }, [NDA_NH_ID] = { .type = NLA_U32 }, [NDA_VNI] = { .type = NLA_U32 }, [NDA_PORT] = { .type = NLA_U16 }, [NDA_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [NDA_NDM_STATE_MASK] = { .type = NLA_U16 }, [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 }, }; #define VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS (NTF_MASTER | NTF_SELF) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES (NUD_PERMANENT | NUD_NOARP) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS (NTF_EXT_LEARNED | NTF_OFFLOADED | \ NTF_ROUTER) static int vxlan_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = {}; struct ndmsg *ndm = nlmsg_data(nlh); struct nlattr *tb[NDA_MAX + 1]; u8 ndm_flags; int err; ndm_flags = ndm->ndm_flags & ~VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, vxlan_del_bulk_policy, extack); if (err) return err; if (ndm_flags & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm flag bits set"); return -EINVAL; } if (ndm->ndm_state & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm state bits set"); return -EINVAL; } desc.state = ndm->ndm_state; desc.flags = ndm_flags; if (tb[NDA_NDM_STATE_MASK]) desc.state_mask = nla_get_u16(tb[NDA_NDM_STATE_MASK]); if (tb[NDA_NDM_FLAGS_MASK]) desc.flags_mask = nla_get_u8(tb[NDA_NDM_FLAGS_MASK]); if (tb[NDA_SRC_VNI]) desc.src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); if (tb[NDA_NH_ID]) desc.nhid = nla_get_u32(tb[NDA_NH_ID]); if (tb[NDA_VNI]) desc.vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); if (tb[NDA_PORT]) desc.port = nla_get_be16(tb[NDA_PORT]); if (tb[NDA_DST]) { union vxlan_addr ip; err = vxlan_nla_get_addr(&ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG_ATTR(extack, tb[NDA_DST], "Unsupported address family"); return err; } desc.dst_ip = ip; } vxlan_flush(vxlan, &desc); return 0; } /* Cleanup timer and forwarding table on shutdown */ static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, .state = 0, .state_mask = NUD_PERMANENT | NUD_NOARP, }; vxlan_multicast_leave(vxlan); del_timer_sync(&vxlan->age_timer); vxlan_flush(vxlan, &desc); vxlan_sock_release(vxlan); return 0; } /* Stub, nothing needs to be done. */ static void vxlan_set_multicast_list(struct net_device *dev) { } static int vxlan_change_mtu(struct net_device *dev, int new_mtu) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); /* This check is different than dev->max_mtu, because it looks at * the lowerdev->mtu, rather than the static dev->max_mtu */ if (lowerdev) { int max_mtu = lowerdev->mtu - vxlan_headroom(vxlan->cfg.flags); if (new_mtu > max_mtu) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct ip_tunnel_info *info = skb_tunnel_info(skb); __be16 sport, dport; sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); dport = info->key.tp_dst ? : vxlan->cfg.dst_port; if (ip_tunnel_info_af(info) == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; if (!sock4) return -EIO; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, 0, &info->key.u.ipv4.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); } else { #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct dst_entry *ndst; if (!sock6) return -EIO; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, 0, &info->key.u.ipv6.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); #else /* !CONFIG_IPV6 */ return -EPFNOSUPPORT; #endif } info->key.tp_src = sport; info->key.tp_dst = dport; return 0; } static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_set_rx_mode = vxlan_set_multicast_list, .ndo_change_mtu = vxlan_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fdb_add = vxlan_fdb_add, .ndo_fdb_del = vxlan_fdb_delete, .ndo_fdb_del_bulk = vxlan_fdb_delete_bulk, .ndo_fdb_dump = vxlan_fdb_dump, .ndo_fdb_get = vxlan_fdb_get, .ndo_mdb_add = vxlan_mdb_add, .ndo_mdb_del = vxlan_mdb_del, .ndo_mdb_del_bulk = vxlan_mdb_del_bulk, .ndo_mdb_dump = vxlan_mdb_dump, .ndo_mdb_get = vxlan_mdb_get, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; static const struct net_device_ops vxlan_netdev_raw_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_change_mtu = vxlan_change_mtu, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type vxlan_type = { .name = "vxlan", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening VXLAN udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void vxlan_offload_rx_ports(struct net_device *dev, bool push) { struct vxlan_sock *vs; struct net *net = dev_net(dev); struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int i; spin_lock(&vn->sock_lock); for (i = 0; i < PORT_HASH_SIZE; ++i) { hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { unsigned short type; if (vs->flags & VXLAN_F_GPE) type = UDP_TUNNEL_TYPE_VXLAN_GPE; else type = UDP_TUNNEL_TYPE_VXLAN; if (push) udp_tunnel_push_rx_port(dev, vs->sock, type); else udp_tunnel_drop_rx_port(dev, vs->sock, type); } } spin_unlock(&vn->sock_lock); } /* Initialize the device structure. */ static void vxlan_setup(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; eth_hw_addr_random(dev); ether_setup(dev); dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &vxlan_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->vlan_features = dev->features; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->change_proto_down = true; dev->lltx = true; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; INIT_LIST_HEAD(&vxlan->next); timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); vxlan->dev = dev; for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_init(&vxlan->hash_lock[h]); INIT_HLIST_HEAD(&vxlan->fdb_head[h]); } } static void vxlan_ether_setup(struct net_device *dev) { dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->netdev_ops = &vxlan_netdev_ether_ops; } static void vxlan_raw_setup(struct net_device *dev) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->netdev_ops = &vxlan_netdev_raw_ops; } static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, [IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, [IFLA_VXLAN_LABEL] = { .type = NLA_U32 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, [IFLA_VXLAN_PORT_RANGE] = { .len = sizeof(struct ifla_vxlan_port_range) }, [IFLA_VXLAN_PROXY] = { .type = NLA_U8 }, [IFLA_VXLAN_RSC] = { .type = NLA_U8 }, [IFLA_VXLAN_L2MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_L3MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_COLLECT_METADATA] = { .type = NLA_U8 }, [IFLA_VXLAN_PORT] = { .type = NLA_U16 }, [IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, }, [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, [IFLA_VXLAN_DF] = { .type = NLA_U8 }, [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu < ETH_MIN_MTU || mtu > ETH_MAX_MTU) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "MTU must be between 68 and 65535"); return -EINVAL; } } if (!data) { NL_SET_ERR_MSG(extack, "Required attributes not provided to perform the operation"); return -EINVAL; } if (data[IFLA_VXLAN_ID]) { u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); if (id >= VXLAN_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID], "VXLAN ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_VXLAN_PORT_RANGE]) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE], "Invalid source port range"); return -EINVAL; } } if (data[IFLA_VXLAN_DF]) { enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]); if (df < 0 || df > VXLAN_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static void vxlan_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, VXLAN_VERSION, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "vxlan", sizeof(drvinfo->driver)); } static int vxlan_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); if (!lowerdev) { cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; return 0; } return __ethtool_get_link_ksettings(lowerdev, cmd); } static const struct ethtool_ops vxlan_ethtool_ops = { .get_drvinfo = vxlan_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = vxlan_get_link_ksettings, }; static struct socket *vxlan_create_sock(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.use_udp6_rx_checksums = !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX); udp_conf.ipv6_v6only = 1; } else { udp_conf.family = AF_INET; } udp_conf.local_udp_port = port; udp_conf.bind_ifindex = ifindex; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } /* Create new listen socket if needed */ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; struct socket *sock; unsigned int h; struct udp_tunnel_sock_cfg tunnel_cfg; vs = kzalloc(sizeof(*vs), GFP_KERNEL); if (!vs) return ERR_PTR(-ENOMEM); for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vs->vni_list[h]); sock = vxlan_create_sock(net, ipv6, port, flags, ifindex); if (IS_ERR(sock)) { kfree(vs); return ERR_CAST(sock); } vs->sock = sock; refcount_set(&vs->refcnt, 1); vs->flags = (flags & VXLAN_F_RCV_FLAGS); spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); udp_tunnel_notify_add_rx_port(sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); /* Mark socket as an encapsulation socket. */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = vs; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = vxlan_rcv; tunnel_cfg.encap_err_lookup = vxlan_err_lookup; tunnel_cfg.encap_destroy = NULL; if (vs->flags & VXLAN_F_GPE) { tunnel_cfg.gro_receive = vxlan_gpe_gro_receive; tunnel_cfg.gro_complete = vxlan_gpe_gro_complete; } else { tunnel_cfg.gro_receive = vxlan_gro_receive; tunnel_cfg.gro_complete = vxlan_gro_complete; } setup_udp_tunnel_sock(net, sock, &tunnel_cfg); return vs; } static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; struct vxlan_sock *vs = NULL; struct vxlan_dev_node *node; int l3mdev_index = 0; if (vxlan->cfg.remote_ifindex) l3mdev_index = l3mdev_master_upper_ifindex_by_index( vxlan->net, vxlan->cfg.remote_ifindex); if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (vs && !refcount_inc_not_zero(&vs->refcnt)) { spin_unlock(&vn->sock_lock); return -EBUSY; } spin_unlock(&vn->sock_lock); } if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (IS_ERR(vs)) return PTR_ERR(vs); #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(vxlan->vn6_sock, vs); node = &vxlan->hlist6; } else #endif { rcu_assign_pointer(vxlan->vn4_sock, vs); node = &vxlan->hlist4; } if (metadata && (vxlan->cfg.flags & VXLAN_F_VNIFILTER)) vxlan_vs_add_vnigrp(vxlan, vs, ipv6); else vxlan_vs_add_dev(vs, vxlan, node); return 0; } static int vxlan_sock_add(struct vxlan_dev *vxlan) { bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; bool ipv6 = vxlan->cfg.flags & VXLAN_F_IPV6 || metadata; bool ipv4 = !ipv6 || metadata; int ret = 0; RCU_INIT_POINTER(vxlan->vn4_sock, NULL); #if IS_ENABLED(CONFIG_IPV6) RCU_INIT_POINTER(vxlan->vn6_sock, NULL); if (ipv6) { ret = __vxlan_sock_add(vxlan, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = __vxlan_sock_add(vxlan, false); if (ret < 0) vxlan_sock_release(vxlan); return ret; } int vxlan_vni_in_use(struct net *src_net, struct vxlan_dev *vxlan, struct vxlan_config *conf, __be32 vni) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *tmp; list_for_each_entry(tmp, &vn->vxlan_list, next) { if (tmp == vxlan) continue; if (tmp->cfg.flags & VXLAN_F_VNIFILTER) { if (!vxlan_vnifilter_lookup(tmp, vni)) continue; } else if (tmp->cfg.vni != vni) { continue; } if (tmp->cfg.dst_port != conf->dst_port) continue; if ((tmp->cfg.flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6)) != (conf->flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6))) continue; if ((conf->flags & VXLAN_F_IPV6_LINKLOCAL) && tmp->cfg.remote_ifindex != conf->remote_ifindex) continue; return -EEXIST; } return 0; } static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, struct net_device **lower, struct vxlan_dev *old, struct netlink_ext_ack *extack) { bool use_ipv6 = false; if (conf->flags & VXLAN_F_GPE) { /* For now, allow GPE only together with * COLLECT_METADATA. This can be relaxed later; in such * case, the other side of the PtP link will have to be * provided. */ if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) || !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG(extack, "VXLAN GPE does not support this combination of attributes"); return -EINVAL; } } if (!conf->remote_ip.sa.sa_family && !conf->saddr.sa.sa_family) { /* Unless IPv6 is explicitly requested, assume IPv4 */ conf->remote_ip.sa.sa_family = AF_INET; conf->saddr.sa.sa_family = AF_INET; } else if (!conf->remote_ip.sa.sa_family) { conf->remote_ip.sa.sa_family = conf->saddr.sa.sa_family; } else if (!conf->saddr.sa.sa_family) { conf->saddr.sa.sa_family = conf->remote_ip.sa.sa_family; } if (conf->saddr.sa.sa_family != conf->remote_ip.sa.sa_family) { NL_SET_ERR_MSG(extack, "Local and remote address must be from the same family"); return -EINVAL; } if (vxlan_addr_multicast(&conf->saddr)) { NL_SET_ERR_MSG(extack, "Local address cannot be multicast"); return -EINVAL; } if (conf->saddr.sa.sa_family == AF_INET6) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } use_ipv6 = true; conf->flags |= VXLAN_F_IPV6; if (!(conf->flags & VXLAN_F_COLLECT_METADATA)) { int local_type = ipv6_addr_type(&conf->saddr.sin6.sin6_addr); int remote_type = ipv6_addr_type(&conf->remote_ip.sin6.sin6_addr); if (local_type & IPV6_ADDR_LINKLOCAL) { if (!(remote_type & IPV6_ADDR_LINKLOCAL) && (remote_type != IPV6_ADDR_ANY)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags |= VXLAN_F_IPV6_LINKLOCAL; } else { if (remote_type == (IPV6_ADDR_UNICAST | IPV6_ADDR_LINKLOCAL)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags &= ~VXLAN_F_IPV6_LINKLOCAL; } } } if (conf->label && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label attribute only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->label_policy && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label policy only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->remote_ifindex) { struct net_device *lowerdev; lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); if (!lowerdev) { NL_SET_ERR_MSG(extack, "Invalid local interface, device not found"); return -ENODEV; } #if IS_ENABLED(CONFIG_IPV6) if (use_ipv6) { struct inet6_dev *idev = __in6_dev_get(lowerdev); if (idev && idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 support disabled by administrator"); return -EPERM; } } #endif *lower = lowerdev; } else { if (vxlan_addr_multicast(&conf->remote_ip)) { NL_SET_ERR_MSG(extack, "Local interface required for multicast remote destination"); return -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) if (conf->flags & VXLAN_F_IPV6_LINKLOCAL) { NL_SET_ERR_MSG(extack, "Local interface required for link-local local/remote addresses"); return -EINVAL; } #endif *lower = NULL; } if (!conf->dst_port) { if (conf->flags & VXLAN_F_GPE) conf->dst_port = htons(IANA_VXLAN_GPE_UDP_PORT); else conf->dst_port = htons(vxlan_port); } if (!conf->age_interval) conf->age_interval = FDB_AGE_DEFAULT; if (vxlan_vni_in_use(src_net, old, conf, conf->vni)) { NL_SET_ERR_MSG(extack, "A VXLAN device with the specified VNI already exists"); return -EEXIST; } return 0; } static void vxlan_config_apply(struct net_device *dev, struct vxlan_config *conf, struct net_device *lowerdev, struct net *src_net, bool changelink) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; int max_mtu = ETH_MAX_MTU; u32 flags = conf->flags; if (!changelink) { if (flags & VXLAN_F_GPE) vxlan_raw_setup(dev); else vxlan_ether_setup(dev); if (conf->mtu) dev->mtu = conf->mtu; vxlan->net = src_net; } dst->remote_vni = conf->vni; memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip)); if (lowerdev) { dst->remote_ifindex = conf->remote_ifindex; netif_inherit_tso_max(dev, lowerdev); needed_headroom = lowerdev->hard_header_len; needed_headroom += lowerdev->needed_headroom; dev->needed_tailroom = lowerdev->needed_tailroom; max_mtu = lowerdev->mtu - vxlan_headroom(flags); if (max_mtu < ETH_MIN_MTU) max_mtu = ETH_MIN_MTU; if (!changelink && !conf->mtu) dev->mtu = max_mtu; } if (dev->mtu > max_mtu) dev->mtu = max_mtu; if (flags & VXLAN_F_COLLECT_METADATA) flags |= VXLAN_F_IPV6; needed_headroom += vxlan_headroom(flags); dev->needed_headroom = needed_headroom; memcpy(&vxlan->cfg, conf, sizeof(*conf)); } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; int ret; ret = vxlan_config_validate(src_net, conf, &lowerdev, vxlan, extack); if (ret) return ret; vxlan_config_apply(dev, conf, lowerdev, src_net, changelink); return 0; } static int __vxlan_dev_create(struct net *net, struct net_device *dev, struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *remote_dev = NULL; struct vxlan_fdb *f = NULL; bool unregister = false; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_dev_configure(net, dev, conf, false, extack); if (err) return err; dev->ethtool_ops = &vxlan_ethtool_ops; /* create an fdb entry for a valid default destination */ if (!vxlan_addr_any(&dst->remote_ip)) { err = vxlan_fdb_create(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, NTF_SELF, 0, &f, extack); if (err) return err; } err = register_netdevice(dev); if (err) goto errout; unregister = true; if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); if (!remote_dev) { err = -ENODEV; goto errout; } err = netdev_upper_dev_link(remote_dev, dev, extack); if (err) goto errout; } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto unlink; if (f) { vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f); /* notify default fdb entry */ err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, true, extack); if (err) { vxlan_fdb_destroy(vxlan, f, false, false); if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); goto unregister; } } list_add(&vxlan->next, &vn->vxlan_list); if (remote_dev) dst->remote_dev = remote_dev; return 0; unlink: if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); errout: /* unregister_netdevice() destroys the default FDB entry with deletion * notification. But the addition notification was not sent yet, so * destroy the entry by hand here. */ if (f) __vxlan_fdb_free(f); unregister: if (unregister) unregister_netdevice(dev); return err; } /* Set/clear flags based on attribute */ static int vxlan_nl2flag(struct vxlan_config *conf, struct nlattr *tb[], int attrtype, unsigned long mask, bool changelink, bool changelink_supported, struct netlink_ext_ack *extack) { unsigned long flags; if (!tb[attrtype]) return 0; if (changelink && !changelink_supported) { vxlan_flag_attr_error(attrtype, extack); return -EOPNOTSUPP; } if (vxlan_policy[attrtype].type == NLA_FLAG) flags = conf->flags | mask; else if (nla_get_u8(tb[attrtype])) flags = conf->flags | mask; else flags = conf->flags & ~mask; conf->flags = flags; return 0; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); int err = 0; memset(conf, 0, sizeof(*conf)); /* if changelink operation, start with old existing cfg */ if (changelink) memcpy(conf, &vxlan->cfg, sizeof(*conf)); if (data[IFLA_VXLAN_ID]) { __be32 vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); if (changelink && (vni != conf->vni)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], "Cannot change VNI"); return -EOPNOTSUPP; } conf->vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); } if (data[IFLA_VXLAN_GROUP]) { if (changelink && (conf->remote_ip.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); conf->remote_ip.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_GROUP6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->remote_ip.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); conf->remote_ip.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LOCAL]) { if (changelink && (conf->saddr.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL], "New local address family does not match old"); return -EOPNOTSUPP; } conf->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); conf->saddr.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_LOCAL6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->saddr.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "New local address family does not match old"); return -EOPNOTSUPP; } /* TODO: respect scope id */ conf->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); conf->saddr.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LINK]) conf->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]); if (data[IFLA_VXLAN_TOS]) conf->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); if (data[IFLA_VXLAN_TTL]) conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); if (data[IFLA_VXLAN_TTL_INHERIT]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_TTL_INHERIT, VXLAN_F_TTL_INHERIT, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LABEL]) conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & IPV6_FLOWLABEL_MASK; if (data[IFLA_VXLAN_LABEL_POLICY]) conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]); if (data[IFLA_VXLAN_LEARNING]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING, VXLAN_F_LEARN, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to learn on a new device */ conf->flags |= VXLAN_F_LEARN; } if (data[IFLA_VXLAN_AGEING]) conf->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); if (data[IFLA_VXLAN_PROXY]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_PROXY, VXLAN_F_PROXY, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_RSC]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_RSC, VXLAN_F_RSC, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L2MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L2MISS, VXLAN_F_L2MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L3MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L3MISS, VXLAN_F_L3MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LIMIT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LIMIT], "Cannot change limit"); return -EOPNOTSUPP; } conf->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); } if (data[IFLA_VXLAN_COLLECT_METADATA]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_COLLECT_METADATA, VXLAN_F_COLLECT_METADATA, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_PORT_RANGE]) { if (!changelink) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); conf->port_min = ntohs(p->low); conf->port_max = ntohs(p->high); } else { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE], "Cannot change port range"); return -EOPNOTSUPP; } } if (data[IFLA_VXLAN_PORT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT], "Cannot change port"); return -EOPNOTSUPP; } conf->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); } if (data[IFLA_VXLAN_UDP_CSUM]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_UDP_CSUM], "Cannot change UDP_CSUM flag"); return -EOPNOTSUPP; } if (!nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) conf->flags |= VXLAN_F_UDP_ZERO_CSUM_TX; } if (data[IFLA_VXLAN_LOCALBYPASS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LOCALBYPASS, VXLAN_F_LOCALBYPASS, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to local bypass on a new device */ conf->flags |= VXLAN_F_LOCALBYPASS; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, VXLAN_F_UDP_ZERO_CSUM6_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, VXLAN_F_UDP_ZERO_CSUM6_RX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_TX, VXLAN_F_REMCSUM_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_RX, VXLAN_F_REMCSUM_RX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_GBP]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GBP, VXLAN_F_GBP, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_GPE]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GPE, VXLAN_F_GPE, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL, VXLAN_F_REMCSUM_NOPARTIAL, changelink, false, extack); if (err) return err; } if (tb[IFLA_MTU]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "Cannot change mtu"); return -EOPNOTSUPP; } conf->mtu = nla_get_u32(tb[IFLA_MTU]); } if (data[IFLA_VXLAN_DF]) conf->df = nla_get_u8(data[IFLA_VXLAN_DF]); if (data[IFLA_VXLAN_VNIFILTER]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_VNIFILTER, VXLAN_F_VNIFILTER, changelink, false, extack); if (err) return err; if ((conf->flags & VXLAN_F_VNIFILTER) && !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_VNIFILTER], "vxlan vnifilter only valid in collect metadata mode"); return -EINVAL; } } return 0; } static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_config conf; int err; err = vxlan_nl2conf(tb, data, dev, &conf, false, extack); if (err) return err; return __vxlan_dev_create(src_net, dev, &conf, extack); } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; struct vxlan_config conf; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) return err; err = vxlan_config_validate(vxlan->net, &conf, &lowerdev, vxlan, extack); if (err) return err; if (dst->remote_dev == lowerdev) lowerdev = NULL; err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, extack); if (err) return err; /* handle default dst entry */ if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!vxlan_addr_any(&conf.remote_ip)) { err = vxlan_fdb_update(vxlan, all_zeros_mac, &conf.remote_ip, NUD_REACHABLE | NUD_PERMANENT, NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, conf.vni, conf.vni, conf.remote_ifindex, NTF_SELF, 0, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } if (!vxlan_addr_any(&dst->remote_ip)) __vxlan_fdb_delete(vxlan, all_zeros_mac, dst->remote_ip, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); /* If vni filtering device, also update fdb entries of * all vnis that were using default remote ip */ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { err = vxlan_vnilist_update_group(vxlan, &dst->remote_ip, &conf.remote_ip, extack); if (err) { netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } } if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); if (lowerdev && lowerdev != dst->remote_dev) dst->remote_dev = lowerdev; vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); return 0; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, }; vxlan_flush(vxlan, &desc); list_del(&vxlan->next); unregister_netdevice_queue(dev, head); if (vxlan->default_dst.remote_dev) netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); } static size_t vxlan_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LABEL_POLICY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L2MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L3MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_COLLECT_METADATA */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */ nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ /* IFLA_VXLAN_PORT_RANGE */ nla_total_size(sizeof(struct ifla_vxlan_port_range)) + nla_total_size(0) + /* IFLA_VXLAN_GBP */ nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ 0; } static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { const struct vxlan_dev *vxlan = netdev_priv(dev); const struct vxlan_rdst *dst = &vxlan->default_dst; struct ifla_vxlan_port_range ports = { .low = htons(vxlan->cfg.port_min), .high = htons(vxlan->cfg.port_max), }; if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni))) goto nla_put_failure; if (!vxlan_addr_any(&dst->remote_ip)) { if (dst->remote_ip.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_GROUP, dst->remote_ip.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_GROUP6, &dst->remote_ip.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) goto nla_put_failure; if (!vxlan_addr_any(&vxlan->cfg.saddr)) { if (vxlan->cfg.saddr.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL, vxlan->cfg.saddr.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6, &vxlan->cfg.saddr.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, !!(vxlan->cfg.flags & VXLAN_F_PROXY)) || nla_put_u8(skb, IFLA_VXLAN_RSC, !!(vxlan->cfg.flags & VXLAN_F_RSC)) || nla_put_u8(skb, IFLA_VXLAN_L2MISS, !!(vxlan->cfg.flags & VXLAN_F_L2MISS)) || nla_put_u8(skb, IFLA_VXLAN_L3MISS, !!(vxlan->cfg.flags & VXLAN_F_L3MISS)) || nla_put_u8(skb, IFLA_VXLAN_COLLECT_METADATA, !!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) || nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, !(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX)) || nla_put_u8(skb, IFLA_VXLAN_LOCALBYPASS, !!(vxlan->cfg.flags & VXLAN_F_LOCALBYPASS))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GPE && nla_put_flag(skb, IFLA_VXLAN_GPE)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_REMCSUM_NOPARTIAL && nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER && nla_put_u8(skb, IFLA_VXLAN_VNIFILTER, !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *vxlan_get_link_net(const struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); return READ_ONCE(vxlan->net); } static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .kind = "vxlan", .maxtype = IFLA_VXLAN_MAX, .policy = vxlan_policy, .priv_size = sizeof(struct vxlan_dev), .setup = vxlan_setup, .validate = vxlan_validate, .newlink = vxlan_newlink, .changelink = vxlan_changelink, .dellink = vxlan_dellink, .get_size = vxlan_get_size, .fill_info = vxlan_fill_info, .get_link_net = vxlan_get_link_net, }; struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &vxlan_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; err = __vxlan_dev_create(net, dev, conf, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) { LIST_HEAD(list_kill); vxlan_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } return dev; } EXPORT_SYMBOL_GPL(vxlan_dev_create); static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, struct net_device *dev) { struct vxlan_dev *vxlan, *next; LIST_HEAD(list_kill); list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) { struct vxlan_rdst *dst = &vxlan->default_dst; /* In case we created vxlan device with carrier * and we loose the carrier due to module unload * we also need to remove vxlan device. In other * cases, it's not necessary and remote_ifindex * is 0 here, so no matches. */ if (dst->remote_ifindex == dev->ifindex) vxlan_dellink(vxlan->dev, &list_kill); } unregister_netdevice_many(&list_kill); } static int vxlan_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); if (event == NETDEV_UNREGISTER) vxlan_handle_lowerdev_unregister(vn, dev); else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) vxlan_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) vxlan_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block vxlan_notifier_block __read_mostly = { .notifier_call = vxlan_netdevice_event, }; static void vxlan_fdb_offloaded_set(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst; struct vxlan_fdb *f; u32 hash_index; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) goto out; rdst = vxlan_fdb_find_rdst(f, &fdb_info->remote_ip, fdb_info->remote_port, fdb_info->remote_vni, fdb_info->remote_ifindex); if (!rdst) goto out; rdst->offloaded = fdb_info->offloaded; out: spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static int vxlan_fdb_external_learn_add(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct netlink_ext_ack *extack; u32 hash_index; int err; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); extack = switchdev_notifier_info_to_extack(&fdb_info->info); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, NUD_REACHABLE, NLM_F_CREATE | NLM_F_REPLACE, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, 0, false, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_fdb_external_learn_del(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 hash_index; int err = 0; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) err = -ENOENT; else if (f->flags & NTF_EXT_LEARNED) err = __vxlan_fdb_delete(vxlan, fdb_info->eth_addr, fdb_info->remote_ip, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_vxlan_fdb_info *fdb_info; int err = 0; switch (event) { case SWITCHDEV_VXLAN_FDB_OFFLOADED: vxlan_fdb_offloaded_set(dev, ptr); break; case SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_add(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = true; vxlan_fdb_offloaded_set(dev, fdb_info); break; case SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_del(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = false; vxlan_fdb_offloaded_set(dev, fdb_info); break; } return err; } static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = { .notifier_call = vxlan_switchdev_event, }; static void vxlan_fdb_nh_flush(struct nexthop *nh) { struct vxlan_fdb *fdb; struct vxlan_dev *vxlan; u32 hash_index; rcu_read_lock(); list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) { vxlan = rcu_dereference(fdb->vdev); WARN_ON(!vxlan); hash_index = fdb_head_index(vxlan, fdb->eth_addr, vxlan->default_dst.remote_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!hlist_unhashed(&fdb->hlist)) vxlan_fdb_destroy(vxlan, fdb, false, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } rcu_read_unlock(); } static int vxlan_nexthop_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct nh_notifier_info *info = ptr; struct nexthop *nh; if (event != NEXTHOP_EVENT_DEL) return NOTIFY_DONE; nh = nexthop_find_by_id(info->net, info->id); if (!nh) return NOTIFY_DONE; vxlan_fdb_nh_flush(nh); return NOTIFY_DONE; } static __net_init int vxlan_init_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; INIT_LIST_HEAD(&vn->vxlan_list); spin_lock_init(&vn->sock_lock); vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; for (h = 0; h < PORT_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vn->sock_list[h]); return register_nexthop_notifier(net, &vn->nexthop_notifier_block, NULL); } static void __net_exit vxlan_destroy_tunnels(struct vxlan_net *vn, struct list_head *dev_to_kill) { struct vxlan_dev *vxlan, *next; list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) vxlan_dellink(vxlan->dev, dev_to_kill); } static void __net_exit vxlan_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); __unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); vxlan_destroy_tunnels(vn, dev_to_kill); } } static void __net_exit vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; for (h = 0; h < PORT_HASH_SIZE; ++h) WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); } static struct pernet_operations vxlan_net_ops = { .init = vxlan_init_net, .exit_batch_rtnl = vxlan_exit_batch_rtnl, .exit = vxlan_exit_net, .id = &vxlan_net_id, .size = sizeof(struct vxlan_net), }; static int __init vxlan_init_module(void) { int rc; get_random_bytes(&vxlan_salt, sizeof(vxlan_salt)); rc = register_pernet_subsys(&vxlan_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&vxlan_notifier_block); if (rc) goto out2; rc = register_switchdev_notifier(&vxlan_switchdev_notifier_block); if (rc) goto out3; rc = rtnl_link_register(&vxlan_link_ops); if (rc) goto out4; rc = vxlan_vnifilter_init(); if (rc) goto out5; return 0; out5: rtnl_link_unregister(&vxlan_link_ops); out4: unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); out3: unregister_netdevice_notifier(&vxlan_notifier_block); out2: unregister_pernet_subsys(&vxlan_net_ops); out1: return rc; } late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { vxlan_vnifilter_uninit(); rtnl_link_unregister(&vxlan_link_ops); unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); unregister_netdevice_notifier(&vxlan_notifier_block); unregister_pernet_subsys(&vxlan_net_ops); /* rcu_barrier() is called by netns */ } module_exit(vxlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(VXLAN_VERSION); MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>"); MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("vxlan"); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | /* * Copyright (c) 2015, Mellanox Technologies 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 "core_priv.h" #include <linux/in.h> #include <linux/in6.h> /* For in6_dev_get/in6_dev_put */ #include <net/addrconf.h> #include <net/bonding.h> #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> static struct workqueue_struct *gid_cache_wq; enum gid_op_type { GID_DEL = 0, GID_ADD }; struct update_gid_event_work { struct work_struct work; union ib_gid gid; struct ib_gid_attr gid_attr; enum gid_op_type gid_op; }; #define ROCE_NETDEV_CALLBACK_SZ 3 struct netdev_event_work_cmd { roce_netdev_callback cb; roce_netdev_filter filter; struct net_device *ndev; struct net_device *filter_ndev; }; struct netdev_event_work { struct work_struct work; struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ]; }; static const struct { bool (*is_supported)(const struct ib_device *device, u32 port_num); enum ib_gid_type gid_type; } PORT_CAP_TO_GID_TYPE[] = { {rdma_protocol_roce_eth_encap, IB_GID_TYPE_ROCE}, {rdma_protocol_roce_udp_encap, IB_GID_TYPE_ROCE_UDP_ENCAP}, }; #define CAP_TO_GID_TABLE_SIZE ARRAY_SIZE(PORT_CAP_TO_GID_TYPE) unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u32 port) { int i; unsigned int ret_flags = 0; if (!rdma_protocol_roce(ib_dev, port)) return 1UL << IB_GID_TYPE_IB; for (i = 0; i < CAP_TO_GID_TABLE_SIZE; i++) if (PORT_CAP_TO_GID_TYPE[i].is_supported(ib_dev, port)) ret_flags |= 1UL << PORT_CAP_TO_GID_TYPE[i].gid_type; return ret_flags; } EXPORT_SYMBOL(roce_gid_type_mask_support); static void update_gid(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *gid_attr) { int i; unsigned long gid_type_mask = roce_gid_type_mask_support(ib_dev, port); for (i = 0; i < IB_GID_TYPE_SIZE; i++) { if ((1UL << i) & gid_type_mask) { gid_attr->gid_type = i; switch (gid_op) { case GID_ADD: ib_cache_gid_add(ib_dev, port, gid, gid_attr); break; case GID_DEL: ib_cache_gid_del(ib_dev, port, gid, gid_attr); break; } } } } enum bonding_slave_state { BONDING_SLAVE_STATE_ACTIVE = 1UL << 0, BONDING_SLAVE_STATE_INACTIVE = 1UL << 1, /* No primary slave or the device isn't a slave in bonding */ BONDING_SLAVE_STATE_NA = 1UL << 2, }; static enum bonding_slave_state is_eth_active_slave_of_bonding_rcu(struct net_device *dev, struct net_device *upper) { if (upper && netif_is_bond_master(upper)) { struct net_device *pdev = bond_option_active_slave_get_rcu(netdev_priv(upper)); if (pdev) return dev == pdev ? BONDING_SLAVE_STATE_ACTIVE : BONDING_SLAVE_STATE_INACTIVE; } return BONDING_SLAVE_STATE_NA; } #define REQUIRED_BOND_STATES (BONDING_SLAVE_STATE_ACTIVE | \ BONDING_SLAVE_STATE_NA) static bool is_eth_port_of_netdev_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *real_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); real_dev = rdma_vlan_dev_real_dev(cookie); if (!real_dev) real_dev = cookie; res = ((rdma_is_upper_dev_rcu(rdma_ndev, cookie) && (is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) & REQUIRED_BOND_STATES)) || real_dev == rdma_ndev); rcu_read_unlock(); return res; } static bool is_eth_port_inactive_slave_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); master_dev = netdev_master_upper_dev_get_rcu(rdma_ndev); res = is_eth_active_slave_of_bonding_rcu(rdma_ndev, master_dev) == BONDING_SLAVE_STATE_INACTIVE; rcu_read_unlock(); return res; } /** * is_ndev_for_default_gid_filter - Check if a given netdevice * can be considered for default GIDs or not. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: rdma netdevice pointer * @cookie: Netdevice to consider to form a default GID * * is_ndev_for_default_gid_filter() returns true if a given netdevice can be * considered for deriving default RoCE GID, returns false otherwise. */ static bool is_ndev_for_default_gid_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool res; if (!rdma_ndev) return false; rcu_read_lock(); /* * When rdma netdevice is used in bonding, bonding master netdevice * should be considered for default GIDs. Therefore, ignore slave rdma * netdevices when bonding is considered. * Additionally when event(cookie) netdevice is bond master device, * make sure that it the upper netdevice of rdma netdevice. */ res = ((cookie_ndev == rdma_ndev && !netif_is_bond_slave(rdma_ndev)) || (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev))); rcu_read_unlock(); return res; } static bool pass_all_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { return true; } static bool upper_device_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { bool res; if (!rdma_ndev) return false; if (rdma_ndev == cookie) return true; rcu_read_lock(); res = rdma_is_upper_dev_rcu(rdma_ndev, cookie); rcu_read_unlock(); return res; } /** * is_upper_ndev_bond_master_filter - Check if a given netdevice * is bond master device of netdevice of the RDMA device of port. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: Pointer to rdma netdevice * @cookie: Netdevice to consider to form a default GID * * is_upper_ndev_bond_master_filter() returns true if a cookie_netdev * is bond master device and rdma_ndev is its lower netdevice. It might * not have been established as slave device yet. */ static bool is_upper_ndev_bond_master_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool match = false; if (!rdma_ndev) return false; rcu_read_lock(); if (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev)) match = true; rcu_read_unlock(); return match; } static void update_gid_ip(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, struct net_device *ndev, struct sockaddr *addr) { union ib_gid gid; struct ib_gid_attr gid_attr; rdma_ip2gid(addr, &gid); memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; update_gid(gid_op, ib_dev, port, &gid, &gid_attr); } static void bond_delete_netdev_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, struct net_device *event_ndev) { struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev); unsigned long gid_type_mask; if (!rdma_ndev) return; if (!real_dev) real_dev = event_ndev; rcu_read_lock(); if (((rdma_ndev != event_ndev && !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) || is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) == BONDING_SLAVE_STATE_INACTIVE)) { rcu_read_unlock(); return; } rcu_read_unlock(); gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void enum_netdev_ipv4_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { const struct in_ifaddr *ifa; struct in_device *in_dev; struct sin_list { struct list_head list; struct sockaddr_in ip; }; struct sin_list *sin_iter; struct sin_list *sin_temp; LIST_HEAD(sin_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; rcu_read_lock(); in_dev = __in_dev_get_rcu(ndev); if (!in_dev) { rcu_read_unlock(); return; } in_dev_for_each_ifa_rcu(ifa, in_dev) { struct sin_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->ip.sin_family = AF_INET; entry->ip.sin_addr.s_addr = ifa->ifa_address; list_add_tail(&entry->list, &sin_list); } rcu_read_unlock(); list_for_each_entry_safe(sin_iter, sin_temp, &sin_list, list) { update_gid_ip(GID_ADD, ib_dev, port, ndev, (struct sockaddr *)&sin_iter->ip); list_del(&sin_iter->list); kfree(sin_iter); } } static void enum_netdev_ipv6_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { struct inet6_ifaddr *ifp; struct inet6_dev *in6_dev; struct sin6_list { struct list_head list; struct sockaddr_in6 sin6; }; struct sin6_list *sin6_iter; struct sin6_list *sin6_temp; struct ib_gid_attr gid_attr = {.ndev = ndev}; LIST_HEAD(sin6_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; in6_dev = in6_dev_get(ndev); if (!in6_dev) return; read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { struct sin6_list *entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) continue; entry->sin6.sin6_family = AF_INET6; entry->sin6.sin6_addr = ifp->addr; list_add_tail(&entry->list, &sin6_list); } read_unlock_bh(&in6_dev->lock); in6_dev_put(in6_dev); list_for_each_entry_safe(sin6_iter, sin6_temp, &sin6_list, list) { union ib_gid gid; rdma_ip2gid((struct sockaddr *)&sin6_iter->sin6, &gid); update_gid(GID_ADD, ib_dev, port, &gid, &gid_attr); list_del(&sin6_iter->list); kfree(sin6_iter); } } static void _add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { enum_netdev_ipv4_ips(ib_dev, port, ndev); if (IS_ENABLED(CONFIG_IPV6)) enum_netdev_ipv6_ips(ib_dev, port, ndev); } static void add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { _add_netdev_ips(ib_dev, port, cookie); } static void del_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, cookie); } /** * del_default_gids - Delete default GIDs of the event/cookie netdevice * @ib_dev: RDMA device pointer * @port: Port of the RDMA device whose GID table to consider * @rdma_ndev: Unused rdma netdevice * @cookie: Pointer to event netdevice * * del_default_gids() deletes the default GIDs of the event/cookie netdevice. */ static void del_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, cookie_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void add_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *event_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, event_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_SET); } static void enum_all_gids_of_dev_cb(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net *net; struct net_device *ndev; /* Lock the rtnl to make sure the netdevs does not move under * our feet */ rtnl_lock(); down_read(&net_rwsem); for_each_net(net) for_each_netdev(net, ndev) { /* * Filter and add default GIDs of the primary netdevice * when not in bonding mode, or add default GIDs * of bond master device, when in bonding mode. */ if (is_ndev_for_default_gid_filter(ib_dev, port, rdma_ndev, ndev)) add_default_gids(ib_dev, port, rdma_ndev, ndev); if (is_eth_port_of_netdev_filter(ib_dev, port, rdma_ndev, ndev)) _add_netdev_ips(ib_dev, port, ndev); } up_read(&net_rwsem); rtnl_unlock(); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @ib_dev: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ib_dev) { ib_enum_roce_netdev(ib_dev, pass_all_filter, NULL, enum_all_gids_of_dev_cb, NULL); } EXPORT_SYMBOL(rdma_roce_rescan_device); /** * rdma_roce_rescan_port - Rescan all of the network devices in the system * and add their gids if relevant to the port of the RoCE device. * * @ib_dev: IB device * @port: Port number */ void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port) { struct net_device *ndev = NULL; if (rdma_protocol_roce(ib_dev, port)) { ndev = ib_device_get_netdev(ib_dev, port); if (!ndev) return; enum_all_gids_of_dev_cb(ib_dev, port, ndev, ndev); dev_put(ndev); } } EXPORT_SYMBOL(rdma_roce_rescan_port); static void callback_for_addr_gid_device_scan(struct ib_device *device, u32 port, struct net_device *rdma_ndev, void *cookie) { struct update_gid_event_work *parsed = cookie; return update_gid(parsed->gid_op, device, port, &parsed->gid, &parsed->gid_attr); } struct upper_list { struct list_head list; struct net_device *upper; }; static int netdev_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); struct list_head *upper_list = (struct list_head *)priv->data; if (!entry) return 0; list_add_tail(&entry->list, upper_list); dev_hold(upper); entry->upper = upper; return 0; } static void handle_netdev_upper(struct ib_device *ib_dev, u32 port, void *cookie, void (*handle_netdev)(struct ib_device *ib_dev, u32 port, struct net_device *ndev)) { struct net_device *ndev = cookie; struct netdev_nested_priv priv; struct upper_list *upper_iter; struct upper_list *upper_temp; LIST_HEAD(upper_list); priv.data = &upper_list; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv); rcu_read_unlock(); handle_netdev(ib_dev, port, ndev); list_for_each_entry_safe(upper_iter, upper_temp, &upper_list, list) { handle_netdev(ib_dev, port, upper_iter->upper); dev_put(upper_iter->upper); list_del(&upper_iter->list); kfree(upper_iter); } } void roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, ndev); } EXPORT_SYMBOL(roce_del_all_netdev_gids); static void del_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, roce_del_all_netdev_gids); } static void add_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, _add_netdev_ips); } static void del_netdev_default_ips_join(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_ndev; rcu_read_lock(); master_ndev = netdev_master_upper_dev_get_rcu(rdma_ndev); dev_hold(master_ndev); rcu_read_unlock(); if (master_ndev) { bond_delete_netdev_default_gids(ib_dev, port, rdma_ndev, master_ndev); dev_put(master_ndev); } } /* The following functions operate on all IB devices. netdevice_event and * addr_event execute ib_enum_all_roce_netdevs through a work. * ib_enum_all_roce_netdevs iterates through all IB devices. */ static void netdevice_event_work_handler(struct work_struct *_work) { struct netdev_event_work *work = container_of(_work, struct netdev_event_work, work); unsigned int i; for (i = 0; i < ARRAY_SIZE(work->cmds) && work->cmds[i].cb; i++) { ib_enum_all_roce_netdevs(work->cmds[i].filter, work->cmds[i].filter_ndev, work->cmds[i].cb, work->cmds[i].ndev); dev_put(work->cmds[i].ndev); dev_put(work->cmds[i].filter_ndev); } kfree(work); } static int netdevice_queue_work(struct netdev_event_work_cmd *cmds, struct net_device *ndev) { unsigned int i; struct netdev_event_work *ndev_work = kmalloc(sizeof(*ndev_work), GFP_KERNEL); if (!ndev_work) return NOTIFY_DONE; memcpy(ndev_work->cmds, cmds, sizeof(ndev_work->cmds)); for (i = 0; i < ARRAY_SIZE(ndev_work->cmds) && ndev_work->cmds[i].cb; i++) { if (!ndev_work->cmds[i].ndev) ndev_work->cmds[i].ndev = ndev; if (!ndev_work->cmds[i].filter_ndev) ndev_work->cmds[i].filter_ndev = ndev; dev_hold(ndev_work->cmds[i].ndev); dev_hold(ndev_work->cmds[i].filter_ndev); } INIT_WORK(&ndev_work->work, netdevice_event_work_handler); queue_work(gid_cache_wq, &ndev_work->work); return NOTIFY_DONE; } static const struct netdev_event_work_cmd add_cmd = { .cb = add_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd add_cmd_upper_ips = { .cb = add_netdev_upper_ips, .filter = is_eth_port_of_netdev_filter }; static void ndev_event_unlink(struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd upper_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter }; cmds[0] = upper_ips_del_cmd; cmds[0].ndev = changeupper_info->upper_dev; cmds[1] = add_cmd; } static const struct netdev_event_work_cmd bonding_default_add_cmd = { .cb = add_default_gids, .filter = is_upper_ndev_bond_master_filter }; static void ndev_event_link(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd bonding_default_del_cmd = { .cb = del_default_gids, .filter = is_upper_ndev_bond_master_filter }; /* * When a lower netdev is linked to its upper bonding * netdev, delete lower slave netdev's default GIDs. */ cmds[0] = bonding_default_del_cmd; cmds[0].ndev = event_ndev; cmds[0].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device default GIDs */ cmds[1] = bonding_default_add_cmd; cmds[1].ndev = changeupper_info->upper_dev; cmds[1].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device IP based GIDs */ cmds[2] = add_cmd_upper_ips; cmds[2].ndev = changeupper_info->upper_dev; cmds[2].filter_ndev = changeupper_info->upper_dev; } static void netdevice_event_changeupper(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { if (changeupper_info->linking) ndev_event_link(event_ndev, changeupper_info, cmds); else ndev_event_unlink(changeupper_info, cmds); } static const struct netdev_event_work_cmd add_default_gid_cmd = { .cb = add_default_gids, .filter = is_ndev_for_default_gid_filter, }; static int netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { static const struct netdev_event_work_cmd del_cmd = { .cb = del_netdev_ips, .filter = pass_all_filter}; static const struct netdev_event_work_cmd bonding_default_del_cmd_join = { .cb = del_netdev_default_ips_join, .filter = is_eth_port_inactive_slave_filter }; static const struct netdev_event_work_cmd netdev_del_cmd = { .cb = del_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd bonding_event_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter}; struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ] = { {NULL} }; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_UP: cmds[0] = bonding_default_del_cmd_join; cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; break; case NETDEV_UNREGISTER: if (ndev->reg_state < NETREG_UNREGISTERED) cmds[0] = del_cmd; else return NOTIFY_DONE; break; case NETDEV_CHANGEADDR: cmds[0] = netdev_del_cmd; if (ndev->reg_state == NETREG_REGISTERED) { cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; } break; case NETDEV_CHANGEUPPER: netdevice_event_changeupper(ndev, container_of(ptr, struct netdev_notifier_changeupper_info, info), cmds); break; case NETDEV_BONDING_FAILOVER: cmds[0] = bonding_event_ips_del_cmd; /* Add default GIDs of the bond device */ cmds[1] = bonding_default_add_cmd; /* Add IP based GIDs of the bond device */ cmds[2] = add_cmd_upper_ips; break; default: return NOTIFY_DONE; } return netdevice_queue_work(cmds, ndev); } static void update_gid_event_work_handler(struct work_struct *_work) { struct update_gid_event_work *work = container_of(_work, struct update_gid_event_work, work); ib_enum_all_roce_netdevs(is_eth_port_of_netdev_filter, work->gid_attr.ndev, callback_for_addr_gid_device_scan, work); dev_put(work->gid_attr.ndev); kfree(work); } static int addr_event(struct notifier_block *this, unsigned long event, struct sockaddr *sa, struct net_device *ndev) { struct update_gid_event_work *work; enum gid_op_type gid_op; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_UP: gid_op = GID_ADD; break; case NETDEV_DOWN: gid_op = GID_DEL; break; default: return NOTIFY_DONE; } work = kmalloc(sizeof(*work), GFP_ATOMIC); if (!work) return NOTIFY_DONE; INIT_WORK(&work->work, update_gid_event_work_handler); rdma_ip2gid(sa, &work->gid); work->gid_op = gid_op; memset(&work->gid_attr, 0, sizeof(work->gid_attr)); dev_hold(ndev); work->gid_attr.ndev = ndev; queue_work(gid_cache_wq, &work->work); return NOTIFY_DONE; } static int inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in in; struct net_device *ndev; struct in_ifaddr *ifa = ptr; in.sin_family = AF_INET; in.sin_addr.s_addr = ifa->ifa_address; ndev = ifa->ifa_dev->dev; return addr_event(this, event, (struct sockaddr *)&in, ndev); } static int inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in6 in6; struct net_device *ndev; struct inet6_ifaddr *ifa6 = ptr; in6.sin6_family = AF_INET6; in6.sin6_addr = ifa6->addr; ndev = ifa6->idev->dev; return addr_event(this, event, (struct sockaddr *)&in6, ndev); } static struct notifier_block nb_netdevice = { .notifier_call = netdevice_event }; static struct notifier_block nb_inetaddr = { .notifier_call = inetaddr_event }; static struct notifier_block nb_inet6addr = { .notifier_call = inet6addr_event }; int __init roce_gid_mgmt_init(void) { gid_cache_wq = alloc_ordered_workqueue("gid-cache-wq", 0); if (!gid_cache_wq) return -ENOMEM; register_inetaddr_notifier(&nb_inetaddr); if (IS_ENABLED(CONFIG_IPV6)) register_inet6addr_notifier(&nb_inet6addr); /* We relay on the netdevice notifier to enumerate all * existing devices in the system. Register to this notifier * last to make sure we will not miss any IP add/del * callbacks. */ register_netdevice_notifier(&nb_netdevice); return 0; } void __exit roce_gid_mgmt_cleanup(void) { if (IS_ENABLED(CONFIG_IPV6)) unregister_inet6addr_notifier(&nb_inet6addr); unregister_inetaddr_notifier(&nb_inetaddr); unregister_netdevice_notifier(&nb_netdevice); /* Ensure all gid deletion tasks complete before we go down, * to avoid any reference to free'd memory. By the time * ib-core is removed, all physical devices have been removed, * so no issue with remaining hardware contexts. */ destroy_workqueue(gid_cache_wq); } |
| 662 662 609 624 625 624 626 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> #include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_PAGE_ORDER 10 #else #define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) # define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \ get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK)) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false # define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } /* * Check whether a migratetype can be merged with another migratetype. * * It is only mergeable when it can fall back to other migratetypes for * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. */ static inline bool migratetype_is_mergeable(int mt) { return mt < MIGRATE_PCPTYPES; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) #define folio_migratetype(folio) \ get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \ MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; struct pglist_data; #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_EVENT_ITEMS }; #else #define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, #ifdef CONFIG_UNACCEPTED_MEMORY NR_UNACCEPTED, #endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, #ifdef CONFIG_HUGETLB_PAGE NR_HUGETLB, #endif NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the item should be printed in THPs (/proc/vmstat * currently prints number of anon, file and shmem THPs. But the item * is charged in pages). */ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || item == NR_SHMEM_PMDMAPPED || item == NR_FILE_PMDMAPPED; } /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define WORKINGSET_ANON 0 #define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { /* * An lruvec has many dirty pages backed by a congested BDI: * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. * It can be cleared by cgroup reclaim or kswapd. * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. * It can only be cleared by kswapd. * * Essentially, kswapd can unthrottle an lruvec throttled by cgroup * reclaim, but not vice versa. This only applies to the root cgroup. * The goal is to prevent cgroup reclaim on the root cgroup (e.g. * memory.reclaim) to unthrottle an unbalanced node (that was throttled * by kswapd). */ LRUVEC_CGROUP_CONGESTED, LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ /* * Evictable pages are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while * a page is on one of lrugen->folios[]. Otherwise it stores 0. * * A page is added to the youngest generation on faulting. The aging needs to * check the accessed bit at least twice before handing this page over to the * eviction. The first check takes care of the accessed bit set on the initial * fault; the second check makes sure this page hasn't been used since then. * This process, AKA second chance, requires a minimum of two generations, * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive * LRU, e.g., /proc/vmstat, these two generations are considered active; the * rest of generations, if they exist, are considered inactive. See * lru_gen_is_active(). * * PG_active is always cleared while a page is on one of lrugen->folios[] so * that the aging needs not to worry about it. And it's set again when a page * considered active is isolated for non-reclaiming purposes, e.g., migration. * See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits * in folio->flags. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* * Each generation is divided into multiple tiers. A page accessed N times * through file descriptors is in tier order_base_2(N). A page in the first tier * (N=0,1) is marked by PG_referenced unless it was faulted in through page * tables or read ahead. A page in any other tier (N>1) is marked by * PG_referenced and PG_workingset. This implies a minimum of two tiers is * supported without using additional bits in folio->flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, * comparisons of refaulted/(evicted+protected) from the first tier and the * rest infer whether pages accessed multiple times through file descriptors * are statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in * folio->flags. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H struct lruvec; struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) #ifdef CONFIG_LRU_GEN enum { LRU_GEN_ANON, LRU_GEN_FILE, }; enum { LRU_GEN_CORE, LRU_GEN_MM_WALK, LRU_GEN_NONLEAF_YOUNG, NR_LRU_GEN_CAPS }; #define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) /* whether to keep historical stats from evicted generations */ #ifdef CONFIG_LRU_GEN_STATS #define NR_HIST_GENS MAX_NR_GENS #else #define NR_HIST_GENS 1U #endif /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are * stored in min_seq[] separately for anon and file types as clean file pages * can be evicted regardless of swap constraints. * * Normally anon and file min_seq are in sync. But if swapping is constrained, * e.g., out of swap space, file min_seq is allowed to advance and leave anon * min_seq behind. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; /* the first tier doesn't need protection, hence the minus one */ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; /* the memcg generation this lru_gen_folio belongs to */ u8 gen; /* the list segment this lru_gen_folio belongs to */ u8 seg; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_node list; }; enum { MM_LEAF_TOTAL, /* total leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS }; /* double-buffering Bloom filters */ #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; /* where the last iteration ended before */ struct list_head *tail; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; /* max_seq from lru_gen_folio: can be out of date */ unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* to batch the mm stats */ int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; bool can_swap; bool force_scan; }; /* * For each node, memcgs are divided into two generations: the old and the * young. For each generation, memcgs are randomly sharded into multiple bins * to improve scalability. For each bin, the hlist_nulls is virtually divided * into three segments: the head, the tail and the default. * * An onlining memcg is added to the tail of a random bin in the old generation. * The eviction starts at the head of a random bin in the old generation. The * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes * the old generation, is incremented when all its bins become empty. * * There are four operations: * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; * 3. The first attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_TAIL; * 4. The second attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * * Notes: * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing * of their max_seq counters ensures the eventual fairness to all eligible * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). * 2. There are only two valid generations: old (seq) and young (seq+1). * MEMCG_NR_GENS is set to three so that when reading the generation counter * locklessly, a stale value (seq-1) does not wraparound to young. */ #define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { /* the per-node memcg generation counter */ unsigned long seq; /* each memcg has one lru_gen_folio per node */ unsigned long nr_memcgs[MEMCG_NR_GENS]; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; /* protects the above */ spinlock_t lock; }; void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); #else /* !CONFIG_LRU_GEN */ static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) { } static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } #endif /* CONFIG_LRU_GEN */ struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_folio lrugen; #ifdef CONFIG_LRU_GEN_WALKS_MMU /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, WMARK_PROMO, NR_WMARK }; /* * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) /* * Flags used in pcp->flags field. * * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the * previous page freeing. To avoid to drain PCP for an accident * high-order page freeing. * * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before * draining PCP for consecutive high-order pages freeing without * allocation if data cache slice of CPU is large enough. To reduce * zone lock contention and keep cache-hot pages reusing. */ #define PCPF_PREV_FREE_HIGH_ORDER BIT(0) #define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int high_min; /* min high watermark */ int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ u8 flags; /* protected by pcp->lock */ u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA u8 expire; /* When 0, remote pagesets are drained */ #endif short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; } ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; s8 stat_threshold; #endif #ifdef CONFIG_NUMA /* * Low priority inaccurate counters that are only folded * on demand. Use a large type to avoid the overhead of * folding during refresh_cpu_vm_stats. */ unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Therefore, we do not allow * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and * faulted, they come from the right zone right away. However, it is * still possible that address space already has pages in * ZONE_MOVABLE at the time when pages are pinned (i.e. user has * touches that memory before pinning). In such case we migrate them * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. * 7. Memory-hotplug: when using memmap_on_memory and onlining the * memory to the MOVABLE zone, the vmemmap pages are also placed in * such zone. Such pages cannot be really moved around as they are * self-stored in the range, but they are treated as movable when * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pages __percpu *per_cpu_pageset; struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access */ int pageset_high_min; int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * present_early_pages is present pages existing within the zone * located on memory available since early boot, excluding hotplugged * memory. * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * cma pages is present pages that are assigned for CMA use * (MIGRATE_CMA). * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/done(). Any reader who can't tolerant drift of * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; #if defined(CONFIG_MEMORY_HOTPLUG) unsigned long present_early_pages; #endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[NR_PAGE_ORDERS]; #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; #endif /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long wmark_pages(const struct zone *z, enum zone_watermarks w) { return z->_watermark[w] + z->watermark_boost; } static inline unsigned long min_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_MIN); } static inline unsigned long low_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_LOW); } static inline unsigned long high_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_HIGH); } static inline unsigned long promo_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_PROMO); } static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_cma_pages(struct zone *zone) { #ifdef CONFIG_CMA return zone->cma_pages; #else return 0; #endif } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } #ifndef BUILD_VDSO32_64 /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) #define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) #define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } static inline enum zone_type folio_zonenum(const struct folio *folio) { return page_zonenum(&folio->page); } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different * pgmaps. Otherwise getting the pgmap of a given segment is not possible * without scanning the entire segment. This helper returns true either if * both pages are not zone device pages or both pages are zone device pages * with the same pgmap. */ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { if (is_zone_device_page(a) != is_zone_device_page(b)) return false; if (!is_zone_device_page(a)) return true; return a->pgmap == b->pgmap; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { return true; } #endif static inline bool folio_is_zone_device(const struct folio *folio) { return is_zone_device_page(&folio->page); } static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } static inline bool folio_is_zone_movable(const struct folio *folio) { return folio_zonenum(folio) == ZONE_MOVABLE; } #endif /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; /* * The array of struct pages for flatmem. * It must be declared for SPARSEMEM as well because there are configurations * that rely on that. */ extern struct page *mem_map; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. */ struct memory_failure_stats { /* * Number of raw pages poisoned. * Cases not accounted: memory outside kernel control, offline page, * arch-specific memory_failure (SGX), hwpoison_filter() filtered * error events, and unpoison actions from hwpoison_unpoison. */ unsigned long total; /* * Recovery results of poisoned raw pages handled by memory_failure, * in sync with mf_result. * total = ignored + failed + delayed + recovered. * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. */ unsigned long ignored; unsigned long failed; unsigned long delayed; unsigned long recovered; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; /* workqueues for throttling reclaim for different reasons. */ wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ #ifdef CONFIG_MEMORY_HOTPLUG struct mutex kswapd_lock; #endif struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; /* promote threshold in ms */ unsigned int nbp_threshold; /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif #ifdef CONFIG_MEMORY_FAILURE struct memory_failure_stats mf_stats; #endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE static inline bool zone_is_zone_device(struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else static inline bool zone_is_zone_device(struct zone *zone) { return false; } #endif /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } #else /* CONFIG_NUMA */ #include <asm/mmzone.h> #endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z: The cursor used as a starting point for the search * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. * * Return: the next zone at or below highest_zoneidx within the allowed * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist: The zonelist to search for a suitable zone * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. * * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone: The current zone in the iterator * @z: The current pointer within zonelist->_zonerefs being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone: The current zone in the iterator * @z: The current pointer within zonelist->zones being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!zonelist_zone(z)) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available on all architectures. * However, we can exceed 6 bits on some other architectures except * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available * with the worst case of 64K pages on arm64) if we make sure the * exceeded bit is not applicable to powerpc. */ enum { SECTION_MARKED_PRESENT_BIT, SECTION_HAS_MEM_MAP_BIT, SECTION_IS_ONLINE_BIT, SECTION_IS_EARLY_BIT, #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif SECTION_MAP_LAST_BIT, }; #define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) #define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) #define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) #define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else static inline int online_device_section(struct mem_section *section) { return 0; } #endif static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN * @pfn: the page frame number to check * * Check if there is a valid memory map entry aka struct page for the @pfn. * Note, that availability of the memory map entry does not imply that * there is actual usable memory at that @pfn. The struct page may * represent a hole or an unusable page frame. * * Return: 1 for PFNs that have memory map entries and 0 otherwise */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the * pfn. Else it might lead to false positives when * some of the upper bits are set, but the lower bits * match a valid pfn. */ if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) return 0; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 98 |